system

Abstract

We provide the system. [Solution] A means for an information processing device to analyze input information received from a user and to evaluate potential risks from legal, ethical, and social perspectives, A means for automatically generating correction suggestions for the user based on the aforementioned evaluation, A means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold, A means by which the information processing device automatically generates an apology expression when the threshold is exceeded, A means of presenting the aforementioned user with the aforementioned apology and countermeasures, A means for analyzing multiple responses to the aforementioned post, classifying the sentiment of the text, and providing the user with the analysis results, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In an information sharing platform using the Internet, the risk that a user's post violates laws, is unethical, or gives a socially inappropriate impression is increasing. Such risks may lead to a loss of credibility or economic losses for users or organizations, so means for detecting and dealing with this in advance are required. In addition, when an excessive negative reaction from outside, so-called "going viral", occurs for the posted content, the situation may deteriorate because an immediate and appropriate response cannot be made. It is necessary to effectively solve such problems.

Means for Solving the Problems

[0005] This invention provides a system in which an information processing device that receives posted content uses machine learning models and external databases to pre-evaluate the potential risks contained in the post and automatically generates correction suggestions. Furthermore, it has a function to monitor external reactions in real time, automatically generate and present apologies to users if there is a possibility of a backlash, and further solves these problems by performing sentiment analysis of reactions to the post and providing users with detailed feedback.

[0006] An "information processing device" refers to a system that receives posted information, analyzes the data using various algorithms, and provides suggestions and feedback to users.

[0007] "Users" refers to individuals or groups who provide information through information processing devices and engage in posting activities via social networking services (SNS).

[0008] "Potential risks" refer to the potential problems or troubles that publicly available information may cause, which should be considered from a legal, ethical, or social standpoint.

[0009] "Correction suggestions" refer to solutions or improvements that information processing devices automatically provide to users to enhance the security of posted content.

[0010] A "threshold" refers to a specific numerical value or condition that an information processing device sets as a criterion for determining whether a post has become a "flame war" based on the reactions to that post.

[0011] "Apology statements" refer to texts that information processing devices automatically generate during online controversies, which users then use to appropriately apologize or resolve misunderstandings.

[0012] "Sentiment analysis" refers to the process of using natural language processing technology to determine whether the expressions in posts and comments are positive, negative, or neutral.

[0013] "Feedback" refers to information and advice provided by an information processing device to users based on analysis results, aimed at improving and optimizing their posting activities. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The system of the present invention comprises a server, a terminal, and a user. This system evaluates potential risks from the perspectives of legal compliance, ethics, and safety regarding content posted by users on social networking services (SNS), and automatically suggests revisions to the posts as needed. Upon receiving a user's post, the server utilizes its built-in machine learning model and an external database to comprehensively evaluate the risks contained in the post. Specifically, the server analyzes language and phrases using natural language processing technology to detect potential legal violations and socially inappropriate expressions. Furthermore, based on the risks discovered, the server can suggest revisions to the user. For example, if ambiguous expressions may lead to misunderstandings, specific revision suggestions will be provided.

[0036] Furthermore, the server monitors external reactions to posts in real time, and if negative reactions exceeding a certain threshold are detected, it determines that the post has become a "flame war." Once a flame war is detected, the server provides an automatically generated apology and presents it to the user as a swift countermeasure. Here, appropriate apology expressions based on past data are used, ensuring a quick and accurate response. For example, if a misunderstanding arises regarding a product, an apology is generated along with information to resolve the misunderstanding.

[0037] The server also collects numerous comments accompanying posts and uses sentiment analysis technology to classify each comment as positive, negative, or neutral. Based on this analysis, the server provides users with feedback. This feedback allows users to consider areas for improvement and strategies in their social media activities. For example, if a user collects reviews of a new product, the server incorporates that feedback to help identify ways to improve the product.

[0038] In this way, this system, through a series of automated processes, mitigates potential risks in social media activities and supports users in creating posts that increase their influence safely and effectively.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users create content to post on social media using their devices and send it to the system. This content can range from simple text input to images and links.

[0042] Step 2:

[0043] The device receives the user's submission and sends it to the server. The server receives this information as data for analysis.

[0044] Step 3:

[0045] The server inputs the received posts into a machine learning model for language analysis. Through natural language processing, it evaluates whether the content complies with laws and regulations and does not contain ethical issues. For example, it extracts specific keywords from the text and compares them with a legal database.

[0046] Step 4:

[0047] Once the server identifies potential risks, it automatically generates suggested fixes for the user based on those risks. The suggestions are clarified by including specific improvements to address ambiguous or potentially misleading language.

[0048] Step 5:

[0049] The information is sent again from the server to the terminal, and the user reviews the proposed revisions. Based on this information, the user can optionally modify or approve the posted content.

[0050] Step 6:

[0051] The user completes the revisions or approves the post, then sends it back to the server from their device for final confirmation, which is then stored in the system.

[0052] Step 7:

[0053] For published posts, the server monitors external comments and reactions in real time. It analyzes the emotional reactions to the post and detects a "flame war" if a large number of negative reactions exceed a threshold.

[0054] Step 8:

[0055] If a social media firestorm is detected, the server automatically generates an apology. Based on past cases and data, it creates content that is appropriate for the situation.

[0056] Step 9:

[0057] The server sends a generated apology letter along with information suggesting countermeasures to the terminal, urging the user to take prompt action. The user can then take appropriate action based on the suggestions.

[0058] Step 10:

[0059] As additional feedback, the server compiles sentiment analysis results for posts and related comments and provides this information to the user via their device. The user can then use this feedback to optimize their future posts.

[0060] (Example 1)

[0061] 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."

[0062] In today's rapidly information-driven world, content posted on social media can cause problems from a legal and ethical standpoint, leading to social trouble and online firestorms. This increases the risk of individuals and organizations losing credibility and suffering financial losses. Furthermore, there is a growing need for swift and appropriate responses to problems that arise after posting, necessitating new technological tools to address these challenges.

[0063] 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.

[0064] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold. This allows for proactive risk reduction in SNS activities and enables a rapid response in the event of a problem.

[0065] An "information processing device" is a core component of a system that receives, analyzes, and processes data, and it enables a variety of functions based on user input.

[0066] "User" refers to any entity that inputs information and receives feedback through this system, and includes individuals or corporations.

[0067] "Input information" refers to all information, including text data and media files, that users provide for posting on social media or other platforms.

[0068] "Potential risks" refer to elements that predict and analyze what problems the posted content may cause in relation to laws, ethics, and social standards.

[0069] "Suggested revisions" refer to specific changes and advice automatically generated to improve user-submitted content.

[0070] "External reactions" refer to feedback, comments, and ratings received from users of social media and other platforms regarding the content of a post.

[0071] "Real-time monitoring" refers to the process of instantly tracking continuously changing information and immediately detecting changes or anomalies.

[0072] A "threshold" is a numerical value or standard set as a decision criterion for triggering a specific action; exceeding this level results in special processing.

[0073] "Apology expressions" refer to the automatically generated text that provides appropriate phrasing for users to apologize for problems caused by their posts.

[0074] "Classifying emotions" refers to the process of analyzing text data and categorizing it into different emotional categories such as positive, negative, and neutral.

[0075] A "machine learning model" refers to a computer system that uses algorithms to learn specific patterns and knowledge from large amounts of data, and then uses this knowledge to perform inferences and predictions on new data.

[0076] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes text analysis, translation, and automated conversation generation.

[0077] A "generative AI model" refers to artificial intelligence technology that automatically generates new text and data based on input information.

[0078] This invention is an information processing system that supports users in ensuring that the content they post on social media does not cause social problems. The system consists mainly of a server, a terminal, and a user, and evaluates the posted content from the perspectives of laws, ethics, and safety, and automatically generates revision suggestions and apologies as needed.

[0079] The server functions as the core of this system. The server receives text data sent from the user's terminal and analyzes the data in detail using built-in natural language processing technology. Specifically, it detects legally or socially inappropriate expressions through keyword matching and uses machine learning models to comprehensively assess risks. This process also includes sentiment analysis technology, classifying external reactions to posts as positive, negative, or neutral.

[0080] Using a generative AI model, the server can automatically generate correction suggestions. For example, if ambiguous wording could lead to misunderstandings, it can present specific correction suggestions to the user. In addition, it monitors external reactions and, if negative feedback exceeding a certain threshold is collected, it has the function to promptly generate and provide an apology to the user. The generated apology can be flexibly customized to suit the situation by referring to past datasets.

[0081] As a concrete example of this system, when a user posts a product review, they can send a prompt message to the server such as, "Please evaluate whether this post is legally problematic," and the server will immediately evaluate the post and suggest corrections. The server can also generate an appropriate apology in response to a prompt such as, "Please generate this apology," enabling a swift response.

[0082] Thus, the present invention provides users with valuable support for safely and effectively engaging in activities on social networking services (SNS). The entire system features rapid real-time processing, contributing to the prevention and resolution of problems.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user enters text to post to the social networking service via their device. The entered text is then prepared for transmission to the server. The content submitted by the user is sent to the server and provided as input for data analysis.

[0086] Step 2:

[0087] The server passes the received text data to a natural language processing engine. Here, morphological and semantic analysis is performed to analyze the linguistic elements that make up the text. This analysis determines whether the posted content may violate laws or contain socially inappropriate expressions. A list of potential risks is generated as output.

[0088] Step 3:

[0089] The server uses a machine learning model to assess risk based on the analysis results. This process involves comparing the current post with past database data to comprehensively determine its risk level. The input is the analysis results, and the output is the assessed risk level. Specifically, it refers to similar past cases and generates a warning if the risk is high.

[0090] Step 4:

[0091] The server uses a generative AI model to automatically create correction suggestions for the user. The input is the result of a risk assessment, and the output is a specific correction suggestion. For example, if ambiguous language is detected, it will suggest a clearer way to phrase it.

[0092] Step 5:

[0093] The server monitors external reactions in real time even after a post has been published on social media. It uses the social media platform's API to collect the returned comments and ratings. The input is feedback data after publication, and the output is an aggregate of the reactions. If a specific negative reaction exceeds a threshold, the server proceeds to the next step.

[0094] Step 6:

[0095] The server uses a generative AI model to quickly create appropriate apology letters. The input is the aggregated results of external reactions, and the output is a customized apology letter. This includes specific actions such as referencing historical datasets to generate apology letters tailored to individual situations.

[0096] Step 7:

[0097] The server performs sentiment analysis on numerous comments on posts, classifying each comment as positive, negative, or neutral. The input is collected comment data, and the output is the classified sentiment information. Based on this analysis, the server provides users with specific feedback and suggests ways to improve their posting activities.

[0098] (Application Example 1)

[0099] 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."

[0100] In modern society, while information dissemination via social media and the internet is widespread, the risk of users unintentionally violating laws or disseminating socially inappropriate content is increasing. Furthermore, particularly in advertising, if content is misleading or perceived as inappropriate by the general public, it can not only damage a company's reputation but also lead to economic losses. There is a need to mitigate these risks and provide an environment where users can confidently disseminate information.

[0101] 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.

[0102] In this invention, the server includes means for analyzing input data received from users by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for analyzing advertising data to identify legal and ethical risks and generate proposed revisions; and means for performing a risk assessment before posting advertising content and presenting the assessment results to the user. This enables users to effectively disseminate information while maintaining legal compliance by evaluating the risks associated with advertisements and content on social media in advance and making appropriate revisions.

[0103] An "information processing device" is a device that has the ability to analyze specific information and make decisions based on data received from users.

[0104] "Input data" refers to any form of data provided to the information processing device by the user, and it forms the basis for analysis.

[0105] "Legal, ethical, and social considerations" refer to the legal standards, ethical norms, and general societal values ​​that are taken into account when determining the appropriateness of information.

[0106] "Assessing potential risks" is the process of identifying potential problems that information may contain and using that information to draw attention to them or propose corrective actions.

[0107] "Generating revised proposals" means creating specific suggestions for improving the content of the information based on the assessed risks.

[0108] "Advertising data" refers to a set of information used for marketing purposes of products and services, and is the subject of analysis.

[0109] "Risk assessment" is the process of detecting potential legal and ethical risks associated with advertising and informational content and determining their impact.

[0110] "Presenting evaluation results to users" means providing the analysis and suggestions obtained as a result of information processing in a format that users can review and understand.

[0111] This invention relates to a system for information processing, primarily configured with a server at its core. The server receives data input from a user via a specific terminal and analyzes it from legal, ethical, and social perspectives. The server utilizes machine learning models to assess potential risks. Based on these assessment results, the server presents specific corrective action plans to the user.

[0112] The server also acquires advertising data via the internet and evaluates its content legally and ethically before posting. The evaluation results are provided to users as needed, allowing them to make adjustments before posting content. After posting, the server performs sentiment analysis on the collected real-time feedback data. This allows the server to provide users with information that helps them review and optimize their advertising strategies.

[0113] The hardware used is a server computer, and the software includes the natural language processing library spaCy, and the machine learning libraries TENSORFLOW® and PyTorch. By combining these, data language processing, evaluation, and analysis are performed.

[0114] A concrete example is the process by which, when posting an advertisement for a new product on social media, the server identifies risks such as "This advertisement may violate certain laws" and provides the user with a clear suggestion to remove the content. An example of such a prompt would be: "Please assess the legal or ethical risks contained in the content of your new product post."

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

[0116] Step 1:

[0117] The server receives advertising content data entered from the terminal. This data includes ad text and image information and is subject to analysis. The server collects this input data and prepares it for analysis.

[0118] Step 2:

[0119] The server applies natural language processing techniques to the received content data. Specifically, it uses the spaCy library to break down the text into tokens and analyze its grammatical structure. The input is text data, and the output is grammatical analysis results. Based on these results, important keywords and sentences within the content are extracted.

[0120] Step 3:

[0121] The server utilizes machine learning models to evaluate extracted text data. This process uses TensorFlow and PyTorch to detect legal and ethical risks. The input is the text analysis result, and the output is the risk assessment result. This identifies potential risks hidden within advertisements.

[0122] Step 4:

[0123] The server generates proposed revisions based on the evaluation results. At this stage, it uses a generative AI model to suggest specific revisions. For example, it might output something like, "This expression is legally dangerous, so please remove it." The input is the risk assessment result, and the output is a suggestion for the user.

[0124] Step 5:

[0125] The server sends the generated evaluation results and suggested revisions to the terminal and presents them to the user. The user receives this and makes revisions to the advertising content. The input is suggested data from the server, and the output is information that leads to user action.

[0126] Step 6:

[0127] After a user posts an ad, the server collects feedback data in real time. This data shows the reaction to the ad and is used for sentiment analysis. The input is real-time data after posting, and the output is the collected feedback information as is.

[0128] Step 7:

[0129] The server performs sentiment analysis on the collected feedback data. It classifies it as positive, negative, or neutral and suggests improvements to the advertising strategy. The input is real-time feedback data, and the output is the sentiment analysis result. Based on this result, it provides information to devise the next strategy.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] The system of the present invention comprises a server, a terminal, and a user. In particular, it has the feature of recognizing the user's emotions and reflecting them in the posted content by incorporating an emotion engine. The user creates content to post to SNS using their own terminal. This content may include text, images, videos, etc. The created post is first sent from the terminal to the server.

[0132] The server uses various algorithms, legal databases, and an emotion engine within its information processing unit to analyze the content of received posts. The emotion engine recognizes the user's emotional state based on the user's input information. Based on the emotional results obtained from this recognition, the server comprehensively evaluates whether the posted content poses any potential risks. For example, if the user indicates negative emotions, the server points out that certain expressions may cause misunderstanding or offense and proposes ways to improve them.

[0133] Furthermore, the server uses the user's sentiment recognition results to generate individually customized modification suggestions. These suggestions take into account risks from multiple perspectives, including legal compliance, aesthetics, and emotional impact. The server then sends this information back to the terminal, where the user reviews and responds.

[0134] After a post is published, the server continuously monitors external comments and reactions in real time. The server uses a sentiment engine to determine whether the reactions are positive or negative. If the sentiment analysis reveals that negative reactions exceed a certain threshold, the server automatically generates an apology based on that information and suggests appropriate countermeasures to the user. For example, if a user receives numerous critical comments about a new product, the server will immediately provide additional information to clarify the misunderstandings along with an apology to calm the situation.

[0135] Furthermore, the emotion engine suggests highlighting positive elements to maximize the effectiveness of posts when the user's emotions are positive. As described above, this system evaluates the user's emotions and provides flexible feedback accordingly, enabling safer and more effective use of social media.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] Users use their devices to create and input content to post on social media. This content may include information such as text, images, and links.

[0139] Step 2:

[0140] The terminal receives the user's post and sends it to the server for further processing.

[0141] Step 3:

[0142] The server prepares to analyze the received posts. During this process, evaluation criteria are established within the information processing unit, taking into account legal, ethical, and social aspects.

[0143] Step 4:

[0144] The server uses an emotion engine to recognize the user's emotions from the content of their posts. Specifically, it classifies emotions as positive, negative, or neutral based on expressions in the text and selected emojis.

[0145] Step 5:

[0146] The server assesses potential risks in a way that reflects the user's emotions. If the user has negative emotions, it identifies the potential for increased risk associated with the content.

[0147] Step 6:

[0148] The server automatically generates correction suggestions for the user based on risk assessments. Specifically, these include improving ambiguous wording and recommending more specific expressions to avoid misunderstandings.

[0149] Step 7:

[0150] The server sends revision suggestions to the terminal and notifies the user of the suggestions. The user reviews the suggestions and adjusts the post as needed.

[0151] Step 8:

[0152] The user submits the final revised or approved post from their device to the server. The server accepts this final version of the post.

[0153] Step 9:

[0154] For published posts, the server monitors comments and other reactions in real time. It collects many reactions and uses sentiment analysis to determine whether they are positive or negative.

[0155] Step 10:

[0156] The server detects negative reactions exceeding a set threshold and determines that a situation has escalated into a "flame war." In response, the server provides the user with an automatically generated apology and appropriate countermeasures.

[0157] Step 11:

[0158] Based on all the sentiment data collected by the server, users are provided with detailed feedback. Users can use this feedback to more effectively manage their future posts.

[0159] (Example 2)

[0160] 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".

[0161] In modern society, advancements in communication technology have made it easy for individuals to disseminate information, but this has also increased the risk of inappropriate content and misleading expressions spreading. Therefore, there is a need for means to detect potential dangers and inappropriate expressions in user-generated information in advance and to correct them appropriately. Furthermore, rapid feedback and responses to external reactions after information has been published are also crucial. Conventional systems have struggled to efficiently address these challenges.

[0162] 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.

[0163] In this invention, the server includes an input device for receiving communication information generated by a user, an information processing device for analyzing the communication information, means for identifying the user's emotional state using emotion analysis technology, means for evaluating the potential risks of the communication information using legal information, means for automatically generating correction suggestions for the user based on the evaluated and identified emotional state, means for immediately monitoring external reactions to the communication information and recognizing reactions that exceed a pre-set standard, means for the information processing device to automatically generate an expression of apology when the standard is exceeded, means for presenting the user with a response along with the expression of apology, means for analyzing multiple reactions to the communication information, classifying emotions using natural language processing technology and providing results to the user, and means for providing a method that includes correction suggestions that emphasize positive elements using a generative AI model. This makes it possible to evaluate and correct the potential risks of information transmitted by users in advance and to respond quickly and appropriately to reactions after publication.

[0164] "User" refers to an individual or organization that generates and transmits communication information using an information processing system.

[0165] "Communication information" refers to information that includes all data formats transmitted by users through information processing systems, such as text, images, and videos.

[0166] An "input device" refers to hardware or software used to transmit communication information generated by a user to the network of an information processing system.

[0167] An "information processing device" refers to a computer system that analyzes received communication information and automatically generates correction suggestions and countermeasures for external feedback as needed.

[0168] "Emotional analysis technology" refers to technology that analyzes the emotional nuances contained in communication information in order to identify the emotional state of the user.

[0169] "Legal information" refers to database information based on laws, norms, and social standards, and is used to evaluate the appropriateness of communication information.

[0170] A "revision proposal" refers to suggestions for improvement presented to users in order to eliminate potential risks or inappropriate expressions in communication information.

[0171] "External reactions" refer to comments, feedback, evaluations, and other responses from third parties when communication information is made public.

[0172] "Pre-set criteria" refer to the minimum conditions under which countermeasures are automatically taken when external reactions meet certain criteria.

[0173] "Expression of apology" refers to a message that includes an automatically generated apology to correct misunderstandings when a user has posted misleading information.

[0174] "Natural language processing technology" refers to the technology used to process human language using computers and understand its meaning.

[0175] A "generative AI model" refers to a model that uses artificial intelligence technology to automatically construct revised proposals that emphasize positive elements.

[0176] This system is centered around users, terminals, and servers. Users generate communication information using their terminals and send it to the server. Terminals act as input devices, sending various data formats such as text, images, and videos to the server. Dedicated applications are installed on the terminals, providing a user-friendly operating environment through a user interface.

[0177] The server is equipped with an information processing device, and upon receiving communication information, it first uses sentiment analysis technology to identify the user's emotional state. This incorporates an algorithm that utilizes natural language processing technology to decipher emotional nuances from text. The server also works in conjunction with a legal information database to evaluate whether the posted content is safe in light of laws and social standards.

[0178] If risks are identified during the evaluation process, the server utilizes a generative AI model to automatically generate corrective suggestions for the user. These suggestions are personalized based on sentiment analysis results and can also emphasize positive elements. The suggestions are then presented to the user again via the device.

[0179] For example, when a user posts a review of a new product, the system can analyze the content to detect negative sentiments and suggest rephrasing potentially misleading expressions in a positive light. Furthermore, if numerous negative comments are received after publication, the server can automatically generate an apology and provide the user with a plan to reassure themselves.

[0180] An example of a prompt message is shown, illustrating a process where, when a user posts a review of a new product, sentiment ratings are used to identify negative expressions and suggest changing them to more favorable language. Furthermore, if critical comments increase after publication, a template for an apology is generated, providing the user with instructions on how to address the issue. This creates an environment where users can confidently share information.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The user generates communication information for posting to social networking services (SNS) using their device. This information may include text, images, and videos. This data is registered as input on the device, and the formatted data is prepared for output and transmission to the server. Specifically, the user edits and formats the post content using the interface of a dedicated application.

[0184] Step 2:

[0185] The terminal sends prepared communication information to the server. It receives pre-formatted data as input, structures it into data packets, and outputs them to the server via the network. During this process, data formatting checks and encoding are performed.

[0186] Step 3:

[0187] The server begins analyzing the received communication information. It takes data sent from the terminal as input and performs sentiment analysis using natural language processing techniques. This yields an output that identifies the user's emotional state. Specifically, it analyzes keywords and sentence structure within the communication information and calculates a positive or negative sentiment score.

[0188] Step 4:

[0189] The server evaluates the potential risks of communication information by referring to a legal information database based on the results of sentiment analysis. It takes the sentiment analysis results and communication information as input and outputs an evaluation by comparing them with the legal information database. Specifically, it checks whether any legal keywords are included and determines the level of safety.

[0190] Step 5:

[0191] The server generates revision suggestions using a generative AI model based on evaluation results and emotional states. It takes evaluation results as input and outputs specific revision suggestions for the user. This includes things like turning negative phrasing into positive phrasing and emphasizing statements. Specifically, it documents the generated suggestions according to a template.

[0192] Step 6:

[0193] The server sends the generated correction suggestions back to the terminal. The correction suggestions are the input, and they are returned to the terminal as output for presentation to the user. Specifically, the correction suggestions are presented to the user via notification or pop-up.

[0194] Step 7:

[0195] The user reviews the suggested content on their device and modifies the communication information as needed. The input is the suggested modifications, and the output is the modified communication information. Specifically, the user accepts or partially adopts the proposed modifications to finalize the posted content.

[0196] Step 8:

[0197] After a post is published, the server monitors external reactions to the communication information in real time. Based on the published communication information as input, it analyzes the acquired reactions and generates an output that performs an emotional classification. Specifically, if negative reactions exceed a certain threshold, it generates an expression of apology and countermeasures based on pre-set criteria.

[0198] (Application Example 2)

[0199] 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".

[0200] Conventional information processing systems analyzed posted content without adequately considering users' emotions or social backgrounds, potentially overlooking potential risks. Furthermore, in customer service, there was a lack of mechanisms to provide real-time feedback reflecting customer emotions, making appropriate customer service difficult. This resulted in the challenge of improving customer satisfaction.

[0201] 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.

[0202] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for analyzing customer input information based on emotional state and providing feedback for optimizing customer service. This enables a comprehensive evaluation of potential risks in posted content and flexible customer service responses based on customer emotions.

[0203] An "information processing device" is a device that analyzes data entered by users and evaluates potential risks from a legal and ethical standpoint.

[0204] "Analysis" is the act of breaking down input information to understand its meaning and trends.

[0205] "Laws and regulations" refer to rules and norms that are established and must be observed within a nation or local community.

[0206] A "potential risk" is a danger that is not immediately apparent but could potentially cause problems later on.

[0207] A "revision suggestion" is an automated suggestion that offers improvements to content posted by users.

[0208] "External reactions" refer to feedback such as comments and ratings that others give to the content of a post.

[0209] "Real-time monitoring" means instantly checking and analyzing data as it is being processed.

[0210] A "threshold" is a limit that, when exceeded, triggers a specific action.

[0211] An "expression of apology" is a way of expressing one's acknowledgment of a mistake and showing remorse to the other party.

[0212] "Countermeasures" refer to specific solutions or action plans taken in response to a problem or issue.

[0213] "Emotional state" refers to the user's psychological condition and emotional tendencies.

[0214] "Feedback" refers to the reactions or opinions that recipients express regarding a service or information.

[0215] To implement this invention, an information processing device is required. This device analyzes data entered by the user via a server, uses an emotion engine to recognize the user's emotional state in real time, and assesses potential risks. The system is built with a backend using Python and Flask, accepting data input from smartphones and other devices, and performing data analysis. In addition, it can utilize cloud infrastructure such as AWS® to scale up resources.

[0216] The server receives user-submitted content, including text, images, and videos, and passes it to the sentiment engine for analysis. The sentiment engine infers the user's emotional state from the input data and extracts positive or negative responses. Based on the evaluation results, feedback and correction suggestions are generated and presented to the user. In this process, the suggestions are customized by referring to previously collected datasets. For example, the optimal solution may be suggested based on past successful countermeasures and already resolved trouble cases.

[0217] When the user's device receives feedback from the server, it reviews the suggestions and implements countermeasures as necessary. The results of these actions are then sent back to the server and stored as evaluation and training data.

[0218] As a concrete example, if a user receives negative feedback about a new product, the server immediately uses the emotion engine to generate an apology and instructions for the salesperson. This not only quickly resolves customer dissatisfaction but also provides specific countermeasures for the salesperson. An example of input to the generating AI model is a prompt such as, "Analyze this review based on the emotion engine and suggest further purchase promotion measures if the customer's emotion is positive, or immediate follow-up methods if it is negative."

[0219] This system makes it possible to provide services that reflect user feedback in a timely and accurate manner in all business scenarios.

[0220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0221] Step 1:

[0222] Users create content using their own devices and send it to the server. Input can include text, images, and videos. This allows the user's created content to be delivered to the server.

[0223] Step 2:

[0224] The server runs an emotion engine to analyze the content of the posts it receives. The input is user-submitted data, and the output is an evaluation result indicating the emotional state. Specifically, the emotion analysis algorithm classifies the emotional tendencies of the posts and categorizes them as positive, negative, or neutral.

[0225] Step 3:

[0226] The server assesses potential risks based on evaluation results obtained from the emotion engine. It uses emotional state data as input and generates risk assessment results as output. Specifically, it focuses on identifying risk items when particularly negative emotions are detected and considers corrective action suggestions based on their content.

[0227] Step 4:

[0228] The server automatically generates correction suggestions based on the evaluation results. The input is the risk assessment result, and the output is the correction suggestions. Specifically, it refers to legal databases and historical datasets to generate appropriate improvement suggestions for user submissions.

[0229] Step 5:

[0230] The server monitors external feedback in real time. The input is reaction data collected from social media and other sources. It determines whether the reaction exceeds a threshold, and if it does, it generates an apology as output. Specifically, it re-analyzes the feedback data using an emotion engine to determine if the reaction is negative.

[0231] Step 6:

[0232] The server presents the user with a generated apology and proposed solutions. The input is the generated apology and solutions, and the output is a notification to the user. Specifically, the apology and details of the solutions are sent as a text message.

[0233] Step 7:

[0234] The user's device reviews the feedback received from the server and implements corrective actions as needed. This input is a notification from the server, and the output is the result of the implemented actions, which is then sent back to the server. Specifically, the user acts in accordance with the suggested corrections, and this is logged by the server.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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".

[0251] The system of the present invention comprises a server, a terminal, and a user. This system evaluates potential risks from the perspectives of legal compliance, ethics, and safety regarding content posted by users on social networking services (SNS), and automatically suggests revisions to the posts as needed. Upon receiving a user's post, the server utilizes its built-in machine learning model and an external database to comprehensively evaluate the risks contained in the post. Specifically, the server analyzes language and phrases using natural language processing technology to detect potential legal violations and socially inappropriate expressions. Furthermore, based on the risks discovered, the server can suggest revisions to the user. For example, if ambiguous expressions may lead to misunderstandings, specific revision suggestions will be provided.

[0252] Furthermore, the server monitors external reactions to posts in real time, and if negative reactions exceeding a certain threshold are detected, it determines that the post has become a "flame war." Once a flame war is detected, the server provides an automatically generated apology and presents it to the user as a swift countermeasure. Here, appropriate apology expressions based on past data are used, ensuring a quick and accurate response. For example, if a misunderstanding arises regarding a product, an apology is generated along with information to resolve the misunderstanding.

[0253] The server also collects numerous comments accompanying posts and uses sentiment analysis technology to classify each comment as positive, negative, or neutral. Based on this analysis, the server provides users with feedback. This feedback allows users to consider areas for improvement and strategies in their social media activities. For example, if a user collects reviews of a new product, the server incorporates that feedback to help identify ways to improve the product.

[0254] In this way, this system, through a series of automated processes, mitigates potential risks in social media activities and supports users in creating posts that increase their influence safely and effectively.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] Users create content to post on social media using their devices and send it to the system. This content can range from simple text input to images and links.

[0258] Step 2:

[0259] The device receives the user's submission and sends it to the server. The server receives this information as data for analysis.

[0260] Step 3:

[0261] The server inputs the received posts into a machine learning model for language analysis. Through natural language processing, it evaluates whether the content complies with laws and regulations and does not contain ethical issues. For example, it extracts specific keywords from the text and compares them with a legal database.

[0262] Step 4:

[0263] Once the server identifies potential risks, it automatically generates suggested fixes for the user based on those risks. The suggestions are clarified by including specific improvements to address ambiguous or potentially misleading language.

[0264] Step 5:

[0265] The information is sent again from the server to the terminal, and the user reviews the proposed revisions. Based on this information, the user can optionally modify or approve the posted content.

[0266] Step 6:

[0267] The user completes the revisions or approves the post, then sends it back to the server from their device for final confirmation, which is then stored in the system.

[0268] Step 7:

[0269] For published posts, the server monitors external comments and reactions in real time. It analyzes the emotional reactions to the post and detects a "flame war" if a large number of negative reactions exceed a threshold.

[0270] Step 8:

[0271] If a social media firestorm is detected, the server automatically generates an apology. Based on past cases and data, it creates content that is appropriate for the situation.

[0272] Step 9:

[0273] The server sends a generated apology letter along with information suggesting countermeasures to the terminal, urging the user to take prompt action. The user can then take appropriate action based on the suggestions.

[0274] Step 10:

[0275] As additional feedback, the server compiles sentiment analysis results for posts and related comments and provides this information to the user via their device. The user can then use this feedback to optimize their future posts.

[0276] (Example 1)

[0277] 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."

[0278] In today's rapidly information-driven world, content posted on social media can cause problems from a legal and ethical standpoint, leading to social trouble and online firestorms. This increases the risk of individuals and organizations losing credibility and suffering financial losses. Furthermore, there is a growing need for swift and appropriate responses to problems that arise after posting, necessitating new technological tools to address these challenges.

[0279] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in the first embodiment is realized by the following respective means.

[0280] In this invention, the server includes means for analyzing input information received by an information processing apparatus from a user and evaluating potential risks from the perspectives of laws, ethics, and society, means for automatically generating a correction proposal to the user based on the evaluation, and means for monitoring external reactions to posted content in real time and detecting reactions that exceed a preset threshold value. Thereby, risks in SNS activities can be reduced in advance, and prompt response can be made in case of a problem.

[0281] An "information processing apparatus" is a core component of a system that receives, analyzes, and processes data, and realizes various functions based on user input.

[0282] A "user" refers to a subject that inputs information and obtains feedback through this system, including individuals or corporations.

[0283] "Input information" means all information including text data and media files provided by a user for posting on SNS or other platforms.

[0284] "Potential risk" refers to an element for predicting and analyzing what problems the posted content may cause with respect to legal, ethical, and social standards.

[0285] "Correction proposal" means specific change plans or advice automatically generated to improve the user's posted content.

[0286] "External reaction" refers to feedback, comments, evaluations, etc. sent by SNS or other platform users with respect to the posted content.

[0287] "Real-time monitoring" refers to the process of instantly tracking continuously changing information and immediately detecting changes or anomalies.

[0288] A "threshold" is a numerical value or standard set as a decision criterion for triggering a specific action; exceeding this level results in special processing.

[0289] "Apology expressions" refer to the automatically generated text that provides appropriate phrasing for users to apologize for problems caused by their posts.

[0290] "Classifying emotions" refers to the process of analyzing text data and categorizing it into different emotional categories such as positive, negative, and neutral.

[0291] A "machine learning model" refers to a computer system that uses algorithms to learn specific patterns and knowledge from large amounts of data, and then uses this knowledge to perform inferences and predictions on new data.

[0292] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes text analysis, translation, and automated conversation generation.

[0293] A "generative AI model" refers to artificial intelligence technology that automatically generates new text and data based on input information.

[0294] This invention is an information processing system that supports users in ensuring that the content they post on social media does not cause social problems. The system consists mainly of a server, a terminal, and a user, and evaluates the posted content from the perspectives of laws, ethics, and safety, and automatically generates revision suggestions and apologies as needed.

[0295] The server functions as the core of this system. The server receives text data sent from the user's terminal and analyzes the data in detail using built-in natural language processing technology. Specifically, it detects legally or socially inappropriate expressions through keyword matching and uses machine learning models to comprehensively assess risks. This process also includes sentiment analysis technology, classifying external reactions to posts as positive, negative, or neutral.

[0296] Using a generative AI model, the server can automatically generate correction suggestions. For example, if ambiguous wording could lead to misunderstandings, it can present specific correction suggestions to the user. In addition, it monitors external reactions and, if negative feedback exceeding a certain threshold is collected, it has the function to promptly generate and provide an apology to the user. The generated apology can be flexibly customized to suit the situation by referring to past datasets.

[0297] As a concrete example of this system, when a user posts a product review, they can send a prompt message to the server such as, "Please evaluate whether this post is legally problematic," and the server will immediately evaluate the post and suggest corrections. The server can also generate an appropriate apology in response to a prompt such as, "Please generate this apology," enabling a swift response.

[0298] Thus, the present invention provides users with valuable support for safely and effectively engaging in activities on social networking services (SNS). The entire system features rapid real-time processing, contributing to the prevention and resolution of problems.

[0299] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0300] Step 1:

[0301] The user inputs the text to be posted on the SNS through the terminal. The input text is prepared for transmission to the server. The posted content submitted by the user is sent to the server, providing input for data analysis.

[0302] Step 2:

[0303] The server passes the received text data to the natural language processing engine. Here, morphological analysis and semantic analysis are performed, and the language elements constituting the sentence are analyzed. Through this analysis, the possibility of legal violations and socially inappropriate expressions in the posted content are determined. As output, a list of possible risks is generated.

[0304] Step 3:

[0305] Based on the analysis results, the server uses a machine learning model to evaluate the risks. In this process, it is compared with the past database to comprehensively judge the risk level of the current post. The input is the analysis result, and the output is the degree of the evaluated risk. As a specific operation, past similar cases are referred to, and a warning is generated if the risk is high.

[0306] Step 4:

[0307] The server automatically creates a correction proposal for the user using the generative AI model. The input is the result of the risk assessment, and the output is a specific amendment. For example, if an ambiguous expression is detected, a clear way of saying it is proposed.

[0308] Step 5:

[0309] Even after the post is published on the SNS, the server monitors the external reactions in real-time. Using the API of the SNS platform, the returned comments and evaluations are collected. The input is the feedback data after publication, and the output is the aggregated result of the reactions. If a specific negative reaction exceeds the threshold, proceed to the next step.

[0310] Step 6:

[0311] The server uses a generative AI model to quickly create appropriate apology letters. The input is the aggregated results of external reactions, and the output is a customized apology letter. This includes specific actions such as referencing historical datasets to generate apology letters tailored to individual situations.

[0312] Step 7:

[0313] The server performs sentiment analysis on numerous comments on posts, classifying each comment as positive, negative, or neutral. The input is collected comment data, and the output is the classified sentiment information. Based on this analysis, the server provides users with specific feedback and suggests ways to improve their posting activities.

[0314] (Application Example 1)

[0315] 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."

[0316] In modern society, while information dissemination via social media and the internet is widespread, the risk of users unintentionally violating laws or disseminating socially inappropriate content is increasing. Furthermore, particularly in advertising, if content is misleading or perceived as inappropriate by the general public, it can not only damage a company's reputation but also lead to economic losses. There is a need to mitigate these risks and provide an environment where users can confidently disseminate information.

[0317] 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.

[0318] In this invention, the server includes means for analyzing input data received from users by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for analyzing advertising data to identify legal and ethical risks and generate proposed revisions; and means for performing a risk assessment before posting advertising content and presenting the assessment results to the user. This enables users to effectively disseminate information while maintaining legal compliance by evaluating the risks associated with advertisements and content on social media in advance and making appropriate revisions.

[0319] An "information processing device" is a device that has the ability to analyze specific information and make decisions based on data received from users.

[0320] "Input data" refers to any form of data provided to the information processing device by the user, and it forms the basis for analysis.

[0321] "Legal, ethical, and social considerations" refer to the legal standards, ethical norms, and general societal values ​​that are taken into account when determining the appropriateness of information.

[0322] "Assessing potential risks" is the process of identifying potential problems that information may contain and using that information to draw attention to them or propose corrective actions.

[0323] "Generating revised proposals" means creating specific suggestions for improving the content of the information based on the assessed risks.

[0324] "Advertising data" refers to a set of information used for marketing purposes of products and services, and is the subject of analysis.

[0325] "Risk assessment" is the process of detecting potential legal and ethical risks associated with advertising and informational content and determining their impact.

[0326] "Presenting evaluation results to users" means providing the analysis and suggestions obtained as a result of information processing in a format that users can review and understand.

[0327] This invention relates to a system for information processing, primarily configured with a server at its core. The server receives data input from a user via a specific terminal and analyzes it from legal, ethical, and social perspectives. The server utilizes machine learning models to assess potential risks. Based on these assessment results, the server presents specific corrective action plans to the user.

[0328] The server also acquires advertising data via the internet and evaluates its content legally and ethically before posting. The evaluation results are provided to users as needed, allowing them to make adjustments before posting content. After posting, the server performs sentiment analysis on the collected real-time feedback data. This allows the server to provide users with information that helps them review and optimize their advertising strategies.

[0329] The hardware used is a server computer, and the software includes the natural language processing library spaCy and the machine learning libraries TensorFlow and PyTorch. By combining these, data language processing, evaluation, and analysis are performed.

[0330] A concrete example is the process by which, when posting an advertisement for a new product on social media, the server identifies risks such as "This advertisement may violate certain laws" and provides the user with a clear suggestion to remove the content. An example of such a prompt would be: "Please assess the legal or ethical risks contained in the content of your new product post."

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The server receives advertising content data entered from the terminal. This data includes ad text and image information and is subject to analysis. The server collects this input data and prepares it for analysis.

[0334] Step 2:

[0335] The server applies natural language processing techniques to the received content data. Specifically, it uses the spaCy library to break down the text into tokens and analyze its grammatical structure. The input is text data, and the output is grammatical analysis results. Based on these results, important keywords and sentences within the content are extracted.

[0336] Step 3:

[0337] The server utilizes machine learning models to evaluate extracted text data. This process uses TensorFlow and PyTorch to detect legal and ethical risks. The input is the text analysis result, and the output is the risk assessment result. This identifies potential risks hidden within advertisements.

[0338] Step 4:

[0339] The server generates proposed revisions based on the evaluation results. At this stage, it uses a generative AI model to suggest specific revisions. For example, it might output something like, "This expression is legally dangerous, so please remove it." The input is the risk assessment result, and the output is a suggestion for the user.

[0340] Step 5:

[0341] The server sends the generated evaluation results and suggested revisions to the terminal and presents them to the user. The user receives this and makes revisions to the advertising content. The input is suggested data from the server, and the output is information that leads to user action.

[0342] Step 6:

[0343] After a user posts an ad, the server collects feedback data in real time. This data shows the reaction to the ad and is used for sentiment analysis. The input is real-time data after posting, and the output is the collected feedback information as is.

[0344] Step 7:

[0345] The server performs sentiment analysis on the collected feedback data. It classifies it as positive, negative, or neutral and suggests improvements to the advertising strategy. The input is real-time feedback data, and the output is the sentiment analysis result. Based on this result, it provides information to devise the next strategy.

[0346] 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.

[0347] The system of the present invention comprises a server, a terminal, and a user. In particular, it has the feature of recognizing the user's emotions and reflecting them in the posted content by incorporating an emotion engine. The user creates content to post to SNS using their own terminal. This content may include text, images, videos, etc. The created post is first sent from the terminal to the server.

[0348] The server uses various algorithms, legal databases, and an emotion engine within its information processing unit to analyze the content of received posts. The emotion engine recognizes the user's emotional state based on the user's input information. Based on the emotional results obtained from this recognition, the server comprehensively evaluates whether the posted content poses any potential risks. For example, if the user indicates negative emotions, the server points out that certain expressions may cause misunderstanding or offense and proposes ways to improve them.

[0349] Furthermore, the server uses the user's sentiment recognition results to generate individually customized modification suggestions. These suggestions take into account risks from multiple perspectives, including legal compliance, aesthetics, and emotional impact. The server then sends this information back to the terminal, where the user reviews and responds.

[0350] After a post is published, the server continuously monitors external comments and reactions in real time. The server uses a sentiment engine to determine whether the reactions are positive or negative. If the sentiment analysis reveals that negative reactions exceed a certain threshold, the server automatically generates an apology based on that information and suggests appropriate countermeasures to the user. For example, if a user receives numerous critical comments about a new product, the server will immediately provide additional information to clarify the misunderstandings along with an apology to calm the situation.

[0351] Furthermore, the emotion engine suggests highlighting positive elements to maximize the effectiveness of posts when the user's emotions are positive. As described above, this system evaluates the user's emotions and provides flexible feedback accordingly, enabling safer and more effective use of social media.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] Users use their devices to create and input content to post on social media. This content may include information such as text, images, and links.

[0355] Step 2:

[0356] The terminal receives the user's post and sends it to the server for further processing.

[0357] Step 3:

[0358] The server prepares to analyze the received posts. During this process, evaluation criteria are established within the information processing unit, taking into account legal, ethical, and social aspects.

[0359] Step 4:

[0360] The server uses an emotion engine to recognize the user's emotions from the content of their posts. Specifically, it classifies emotions as positive, negative, or neutral based on expressions in the text and selected emojis.

[0361] Step 5:

[0362] The server assesses potential risks in a way that reflects the user's emotions. If the user has negative emotions, it identifies the potential for increased risk associated with the content.

[0363] Step 6:

[0364] The server automatically generates correction suggestions for the user based on risk assessments. Specifically, these include improving ambiguous wording and recommending more specific expressions to avoid misunderstandings.

[0365] Step 7:

[0366] The server sends revision suggestions to the terminal and notifies the user of the suggestions. The user reviews the suggestions and adjusts the post as needed.

[0367] Step 8:

[0368] The user submits the final revised or approved post from their device to the server. The server accepts this final version of the post.

[0369] Step 9:

[0370] For published posts, the server monitors comments and other reactions in real time. It collects many reactions and uses sentiment analysis to determine whether they are positive or negative.

[0371] Step 10:

[0372] The server detects negative reactions exceeding a set threshold and determines that a situation has escalated into a "flame war." In response, the server provides the user with an automatically generated apology and appropriate countermeasures.

[0373] Step 11:

[0374] Based on all the sentiment data collected by the server, users are provided with detailed feedback. Users can use this feedback to more effectively manage their future posts.

[0375] (Example 2)

[0376] 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".

[0377] In modern society, advancements in communication technology have made it easy for individuals to disseminate information, but this has also increased the risk of inappropriate content and misleading expressions spreading. Therefore, there is a need for means to detect potential dangers and inappropriate expressions in user-generated information in advance and to correct them appropriately. Furthermore, rapid feedback and responses to external reactions after information has been published are also crucial. Conventional systems have struggled to efficiently address these challenges.

[0378] 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.

[0379] In this invention, the server includes an input device for receiving communication information generated by a user, an information processing device for analyzing the communication information, means for identifying the user's emotional state using emotion analysis technology, means for evaluating the potential risks of the communication information using legal information, means for automatically generating correction suggestions for the user based on the evaluated and identified emotional state, means for immediately monitoring external reactions to the communication information and recognizing reactions that exceed a pre-set standard, means for the information processing device to automatically generate an expression of apology when the standard is exceeded, means for presenting the user with a response along with the expression of apology, means for analyzing multiple reactions to the communication information, classifying emotions using natural language processing technology and providing results to the user, and means for providing a method that includes correction suggestions that emphasize positive elements using a generative AI model. This makes it possible to evaluate and correct the potential risks of information transmitted by users in advance and to respond quickly and appropriately to reactions after publication.

[0380] "User" refers to an individual or organization that generates and transmits communication information using an information processing system.

[0381] "Communication information" refers to information that includes all data formats transmitted by users through information processing systems, such as text, images, and videos.

[0382] An "input device" refers to hardware or software used to transmit communication information generated by a user to the network of an information processing system.

[0383] An "information processing device" refers to a computer system that analyzes received communication information and automatically generates correction suggestions and countermeasures for external feedback as needed.

[0384] "Emotional analysis technology" refers to technology that analyzes the emotional nuances contained in communication information in order to identify the emotional state of the user.

[0385] "Legal information" refers to database information based on laws, norms, and social standards, and is used to evaluate the appropriateness of communication information.

[0386] A "revision proposal" refers to suggestions for improvement presented to users in order to eliminate potential risks or inappropriate expressions in communication information.

[0387] "External reactions" refer to comments, feedback, evaluations, and other responses from third parties when communication information is made public.

[0388] "Pre-set criteria" refer to the minimum conditions under which countermeasures are automatically taken when external reactions meet certain criteria.

[0389] "Expression of apology" refers to a message that includes an automatically generated apology to correct misunderstandings when a user has posted misleading information.

[0390] "Natural language processing technology" refers to the technology used to process human language using computers and understand its meaning.

[0391] A "generative AI model" refers to a model that uses artificial intelligence technology to automatically construct revised proposals that emphasize positive elements.

[0392] This system is centered around users, terminals, and servers. Users generate communication information using their terminals and send it to the server. Terminals act as input devices, sending various data formats such as text, images, and videos to the server. Dedicated applications are installed on the terminals, providing a user-friendly operating environment through a user interface.

[0393] The server is equipped with an information processing device, and upon receiving communication information, it first uses sentiment analysis technology to identify the user's emotional state. This incorporates an algorithm that utilizes natural language processing technology to decipher emotional nuances from text. The server also works in conjunction with a legal information database to evaluate whether the posted content is safe in light of laws and social standards.

[0394] If risks are identified during the evaluation process, the server utilizes a generative AI model to automatically generate corrective suggestions for the user. These suggestions are personalized based on sentiment analysis results and can also emphasize positive elements. The suggestions are then presented to the user again via the device.

[0395] For example, when a user posts a review of a new product, the system can analyze the content to detect negative sentiments and suggest rephrasing potentially misleading expressions in a positive light. Furthermore, if numerous negative comments are received after publication, the server can automatically generate an apology and provide the user with a plan to reassure themselves.

[0396] An example of a prompt message is shown, illustrating a process where, when a user posts a review of a new product, sentiment ratings are used to identify negative expressions and suggest changing them to more favorable language. Furthermore, if critical comments increase after publication, a template for an apology is generated, providing the user with instructions on how to address the issue. This creates an environment where users can confidently share information.

[0397] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0398] Step 1:

[0399] The user generates communication information for posting to social networking services (SNS) using their device. This information may include text, images, and videos. This data is registered as input on the device, and the formatted data is prepared for output and transmission to the server. Specifically, the user edits and formats the post content using the interface of a dedicated application.

[0400] Step 2:

[0401] The terminal sends prepared communication information to the server. It receives pre-formatted data as input, structures it into data packets, and outputs them to the server via the network. During this process, data formatting checks and encoding are performed.

[0402] Step 3:

[0403] The server begins analyzing the received communication information. It takes data sent from the terminal as input and performs sentiment analysis using natural language processing techniques. This yields an output that identifies the user's emotional state. Specifically, it analyzes keywords and sentence structure within the communication information and calculates a positive or negative sentiment score.

[0404] Step 4:

[0405] The server evaluates the potential risks of communication information by referring to a legal information database based on the results of sentiment analysis. It takes the sentiment analysis results and communication information as input and outputs an evaluation by comparing them with the legal information database. Specifically, it checks whether any legal keywords are included and determines the level of safety.

[0406] Step 5:

[0407] The server generates revision suggestions using a generative AI model based on evaluation results and emotional states. It takes evaluation results as input and outputs specific revision suggestions for the user. This includes things like turning negative phrasing into positive phrasing and emphasizing statements. Specifically, it documents the generated suggestions according to a template.

[0408] Step 6:

[0409] The server sends the generated correction suggestions back to the terminal. The correction suggestions are the input, and they are returned to the terminal as output for presentation to the user. Specifically, the correction suggestions are presented to the user via notification or pop-up.

[0410] Step 7:

[0411] The user reviews the suggested content on their device and modifies the communication information as needed. The input is the suggested modifications, and the output is the modified communication information. Specifically, the user accepts or partially adopts the proposed modifications to finalize the posted content.

[0412] Step 8:

[0413] After a post is published, the server monitors external reactions to the communication information in real time. Based on the published communication information as input, it analyzes the acquired reactions and generates an output that performs an emotional classification. Specifically, if negative reactions exceed a certain threshold, it generates an expression of apology and countermeasures based on pre-set criteria.

[0414] (Application Example 2)

[0415] 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."

[0416] Conventional information processing systems analyzed posted content without adequately considering users' emotions or social backgrounds, potentially overlooking potential risks. Furthermore, in customer service, there was a lack of mechanisms to provide real-time feedback reflecting customer emotions, making appropriate customer service difficult. This resulted in the challenge of improving customer satisfaction.

[0417] 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.

[0418] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for analyzing customer input information based on emotional state and providing feedback for optimizing customer service. This enables a comprehensive evaluation of potential risks in posted content and flexible customer service responses based on customer emotions.

[0419] An "information processing device" is a device that analyzes data entered by users and evaluates potential risks from a legal and ethical standpoint.

[0420] "Analysis" is the act of breaking down input information to understand its meaning and trends.

[0421] "Laws and regulations" refer to rules and norms that are established and must be observed within a nation or local community.

[0422] A "potential risk" is a danger that is not immediately apparent but could potentially cause problems later on.

[0423] A "revision suggestion" is an automated suggestion that offers improvements to content posted by users.

[0424] "External reactions" refer to feedback such as comments and ratings that others give to the content of a post.

[0425] "Real-time monitoring" means instantly checking and analyzing data as it is being processed.

[0426] A "threshold" is a limit that, when exceeded, triggers a specific action.

[0427] An "expression of apology" is a way of expressing one's acknowledgment of a mistake and showing remorse to the other party.

[0428] "Countermeasures" refer to specific solutions or action plans taken in response to a problem or issue.

[0429] "Emotional state" refers to the user's psychological condition and emotional tendencies.

[0430] "Feedback" refers to the reactions or opinions that recipients express regarding a service or information.

[0431] To implement this invention, an information processing device is required. This device analyzes data entered by the user via a server, uses an emotion engine to recognize the user's emotional state in real time, and assesses potential risks. The system is built with a backend using Python and Flask, accepting data input from smartphones and other devices, and performing data analysis. In addition, it can utilize cloud infrastructure such as AWS to scale up resources.

[0432] The server receives user-submitted content, including text, images, and videos, and passes it to the sentiment engine for analysis. The sentiment engine infers the user's emotional state from the input data and extracts positive or negative responses. Based on the evaluation results, feedback and correction suggestions are generated and presented to the user. In this process, the suggestions are customized by referring to previously collected datasets. For example, the optimal solution may be suggested based on past successful countermeasures and already resolved trouble cases.

[0433] When the user's device receives feedback from the server, it reviews the suggestions and implements countermeasures as necessary. The results of these actions are then sent back to the server and stored as evaluation and training data.

[0434] As a concrete example, if a user receives negative feedback about a new product, the server immediately uses the emotion engine to generate an apology and instructions for the salesperson. This not only quickly resolves customer dissatisfaction but also provides specific countermeasures for the salesperson. An example of input to the generating AI model is a prompt such as, "Analyze this review based on the emotion engine and suggest further purchase promotion measures if the customer's emotion is positive, or immediate follow-up methods if it is negative."

[0435] This system makes it possible to provide services that reflect user feedback in a timely and accurate manner in all business scenarios.

[0436] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0437] Step 1:

[0438] Users create content using their own devices and send it to the server. Input can include text, images, and videos. This allows the user's created content to be delivered to the server.

[0439] Step 2:

[0440] The server runs an emotion engine to analyze the content of the posts it receives. The input is user-submitted data, and the output is an evaluation result indicating the emotional state. Specifically, the emotion analysis algorithm classifies the emotional tendencies of the posts and categorizes them as positive, negative, or neutral.

[0441] Step 3:

[0442] The server assesses potential risks based on evaluation results obtained from the emotion engine. It uses emotional state data as input and generates risk assessment results as output. Specifically, it focuses on identifying risk items when particularly negative emotions are detected and considers corrective action suggestions based on their content.

[0443] Step 4:

[0444] The server automatically generates correction suggestions based on the evaluation results. The input is the risk assessment result, and the output is the correction suggestions. Specifically, it refers to legal databases and historical datasets to generate appropriate improvement suggestions for user submissions.

[0445] Step 5:

[0446] The server monitors external feedback in real time. The input is reaction data collected from social media and other sources. It determines whether the reaction exceeds a threshold, and if it does, it generates an apology as output. Specifically, it re-analyzes the feedback data using an emotion engine to determine if the reaction is negative.

[0447] Step 6:

[0448] The server presents the user with a generated apology and proposed solutions. The input is the generated apology and solutions, and the output is a notification to the user. Specifically, the apology and details of the solutions are sent as a text message.

[0449] Step 7:

[0450] The user's device reviews the feedback received from the server and implements corrective actions as needed. This input is a notification from the server, and the output is the result of the implemented actions, which is then sent back to the server. Specifically, the user acts in accordance with the suggested corrections, and this is logged by the server.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] [Third Embodiment]

[0455] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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".

[0467] The system of the present invention comprises a server, a terminal, and a user. This system evaluates potential risks from the perspectives of legal compliance, ethics, and safety regarding content posted by users on social networking services (SNS), and automatically suggests revisions to the posts as needed. Upon receiving a user's post, the server utilizes its built-in machine learning model and an external database to comprehensively evaluate the risks contained in the post. Specifically, the server analyzes language and phrases using natural language processing technology to detect potential legal violations and socially inappropriate expressions. Furthermore, based on the risks discovered, the server can suggest revisions to the user. For example, if ambiguous expressions may lead to misunderstandings, specific revision suggestions will be provided.

[0468] Furthermore, the server monitors external reactions to posts in real time, and if negative reactions exceeding a certain threshold are detected, it determines that the post has become a "flame war." Once a flame war is detected, the server provides an automatically generated apology and presents it to the user as a swift countermeasure. Here, appropriate apology expressions based on past data are used, ensuring a quick and accurate response. For example, if a misunderstanding arises regarding a product, an apology is generated along with information to resolve the misunderstanding.

[0469] The server also collects numerous comments accompanying posts and uses sentiment analysis technology to classify each comment as positive, negative, or neutral. Based on this analysis, the server provides users with feedback. This feedback allows users to consider areas for improvement and strategies in their social media activities. For example, if a user collects reviews of a new product, the server incorporates that feedback to help identify ways to improve the product.

[0470] In this way, this system, through a series of automated processes, mitigates potential risks in social media activities and supports users in creating posts that increase their influence safely and effectively.

[0471] The following describes the processing flow.

[0472] Step 1:

[0473] Users create content to post on social media using their devices and send it to the system. This content can range from simple text input to images and links.

[0474] Step 2:

[0475] The device receives the user's submission and sends it to the server. The server receives this information as data for analysis.

[0476] Step 3:

[0477] The server inputs the received posts into a machine learning model for language analysis. Through natural language processing, it evaluates whether the content complies with laws and regulations and does not contain ethical issues. For example, it extracts specific keywords from the text and compares them with a legal database.

[0478] Step 4:

[0479] Once the server identifies potential risks, it automatically generates suggested fixes for the user based on those risks. The suggestions are clarified by including specific improvements to address ambiguous or potentially misleading language.

[0480] Step 5:

[0481] The information is sent again from the server to the terminal, and the user reviews the proposed revisions. Based on this information, the user can optionally modify or approve the posted content.

[0482] Step 6:

[0483] The user completes the revisions or approves the post, then sends it back to the server from their device for final confirmation, which is then stored in the system.

[0484] Step 7:

[0485] For published posts, the server monitors external comments and reactions in real time. It analyzes the emotional reactions to the post and detects a "flame war" if a large number of negative reactions exceed a threshold.

[0486] Step 8:

[0487] If a social media firestorm is detected, the server automatically generates an apology. Based on past cases and data, it creates content that is appropriate for the situation.

[0488] Step 9:

[0489] The server sends a generated apology letter along with information suggesting countermeasures to the terminal, urging the user to take prompt action. The user can then take appropriate action based on the suggestions.

[0490] Step 10:

[0491] As additional feedback, the server compiles sentiment analysis results for posts and related comments and provides this information to the user via their device. The user can then use this feedback to optimize their future posts.

[0492] (Example 1)

[0493] 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."

[0494] In today's rapidly information-driven world, content posted on social media can cause problems from a legal and ethical standpoint, leading to social trouble and online firestorms. This increases the risk of individuals and organizations losing credibility and suffering financial losses. Furthermore, there is a growing need for swift and appropriate responses to problems that arise after posting, necessitating new technological tools to address these challenges.

[0495] 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.

[0496] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold. This allows for proactive risk reduction in SNS activities and enables a rapid response in the event of a problem.

[0497] An "information processing device" is a core component of a system that receives, analyzes, and processes data, and it enables a variety of functions based on user input.

[0498] "User" refers to any entity that inputs information and receives feedback through this system, and includes individuals or corporations.

[0499] "Input information" refers to all information, including text data and media files, that users provide for posting on social media or other platforms.

[0500] "Potential risks" refer to elements that predict and analyze what problems the posted content may cause in relation to laws, ethics, and social standards.

[0501] "Suggested revisions" refer to specific changes and advice automatically generated to improve user-submitted content.

[0502] "External reactions" refer to feedback, comments, and ratings received from users of social media and other platforms regarding the content of a post.

[0503] "Real-time monitoring" refers to the process of instantly tracking continuously changing information and immediately detecting changes or anomalies.

[0504] A "threshold" is a numerical value or standard set as a decision criterion for triggering a specific action; exceeding this level results in special processing.

[0505] "Apology expressions" refer to the automatically generated text that provides appropriate phrasing for users to apologize for problems caused by their posts.

[0506] "Classifying emotions" refers to the process of analyzing text data and categorizing it into different emotional categories such as positive, negative, and neutral.

[0507] A "machine learning model" refers to a computer system that uses algorithms to learn specific patterns and knowledge from large amounts of data, and then uses this knowledge to perform inferences and predictions on new data.

[0508] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes text analysis, translation, and automated conversation generation.

[0509] A "generative AI model" refers to artificial intelligence technology that automatically generates new text and data based on input information.

[0510] This invention is an information processing system that supports users in ensuring that the content they post on social media does not cause social problems. The system consists mainly of a server, a terminal, and a user, and evaluates the posted content from the perspectives of laws, ethics, and safety, and automatically generates revision suggestions and apologies as needed.

[0511] The server functions as the core of this system. The server receives text data sent from the user's terminal and analyzes the data in detail using built-in natural language processing technology. Specifically, it detects legally or socially inappropriate expressions through keyword matching and uses machine learning models to comprehensively assess risks. This process also includes sentiment analysis technology, classifying external reactions to posts as positive, negative, or neutral.

[0512] Using a generative AI model, the server can automatically generate correction suggestions. For example, if ambiguous wording could lead to misunderstandings, it can present specific correction suggestions to the user. In addition, it monitors external reactions and, if negative feedback exceeding a certain threshold is collected, it has the function to promptly generate and provide an apology to the user. The generated apology can be flexibly customized to suit the situation by referring to past datasets.

[0513] As a concrete example of this system, when a user posts a product review, they can send a prompt message to the server such as, "Please evaluate whether this post is legally problematic," and the server will immediately evaluate the post and suggest corrections. The server can also generate an appropriate apology in response to a prompt such as, "Please generate this apology," enabling a swift response.

[0514] Thus, the present invention provides users with valuable support for safely and effectively engaging in activities on social networking services (SNS). The entire system features rapid real-time processing, contributing to the prevention and resolution of problems.

[0515] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0516] Step 1:

[0517] The user enters text to post to the social networking service via their device. The entered text is then prepared for transmission to the server. The content submitted by the user is sent to the server and provided as input for data analysis.

[0518] Step 2:

[0519] The server passes the received text data to a natural language processing engine. Here, morphological and semantic analysis is performed to analyze the linguistic elements that make up the text. This analysis determines whether the posted content may violate laws or contain socially inappropriate expressions. A list of potential risks is generated as output.

[0520] Step 3:

[0521] The server uses a machine learning model to assess risk based on the analysis results. This process involves comparing the current post with past database data to comprehensively determine its risk level. The input is the analysis results, and the output is the assessed risk level. Specifically, it refers to similar past cases and generates a warning if the risk is high.

[0522] Step 4:

[0523] The server uses a generative AI model to automatically create correction suggestions for the user. The input is the result of a risk assessment, and the output is a specific correction suggestion. For example, if ambiguous language is detected, it will suggest a clearer way to phrase it.

[0524] Step 5:

[0525] The server monitors external reactions in real time even after a post has been published on social media. It uses the social media platform's API to collect the returned comments and ratings. The input is feedback data after publication, and the output is an aggregate of the reactions. If a specific negative reaction exceeds a threshold, the server proceeds to the next step.

[0526] Step 6:

[0527] The server uses a generative AI model to quickly create appropriate apology letters. The input is the aggregated results of external reactions, and the output is a customized apology letter. This includes specific actions such as referencing historical datasets to generate apology letters tailored to individual situations.

[0528] Step 7:

[0529] The server performs sentiment analysis on numerous comments on posts, classifying each comment as positive, negative, or neutral. The input is collected comment data, and the output is the classified sentiment information. Based on this analysis, the server provides users with specific feedback and suggests ways to improve their posting activities.

[0530] (Application Example 1)

[0531] 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."

[0532] In modern society, while information dissemination via social media and the internet is widespread, the risk of users unintentionally violating laws or disseminating socially inappropriate content is increasing. Furthermore, particularly in advertising, if content is misleading or perceived as inappropriate by the general public, it can not only damage a company's reputation but also lead to economic losses. There is a need to mitigate these risks and provide an environment where users can confidently disseminate information.

[0533] 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.

[0534] In this invention, the server includes means for analyzing input data received from users by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for analyzing advertising data to identify legal and ethical risks and generate proposed revisions; and means for performing a risk assessment before posting advertising content and presenting the assessment results to the user. This enables users to effectively disseminate information while maintaining legal compliance by evaluating the risks associated with advertisements and content on social media in advance and making appropriate revisions.

[0535] An "information processing device" is a device that has the ability to analyze specific information and make decisions based on data received from users.

[0536] "Input data" refers to any form of data provided to the information processing device by the user, and it forms the basis for analysis.

[0537] "Legal, ethical, and social considerations" refer to the legal standards, ethical norms, and general societal values ​​that are taken into account when determining the appropriateness of information.

[0538] "Assessing potential risks" is the process of identifying potential problems that information may contain and using that information to draw attention to them or propose corrective actions.

[0539] "Generating revised proposals" means creating specific suggestions for improving the content of the information based on the assessed risks.

[0540] "Advertising data" refers to a set of information used for marketing purposes of products and services, and is the subject of analysis.

[0541] "Risk assessment" is the process of detecting potential legal and ethical risks associated with advertising and informational content and determining their impact.

[0542] "Presenting evaluation results to users" means providing the analysis and suggestions obtained as a result of information processing in a format that users can review and understand.

[0543] This invention relates to a system for information processing, primarily configured with a server at its core. The server receives data input from a user via a specific terminal and analyzes it from legal, ethical, and social perspectives. The server utilizes machine learning models to assess potential risks. Based on these assessment results, the server presents specific corrective action plans to the user.

[0544] The server also acquires advertising data via the internet and evaluates its content legally and ethically before posting. The evaluation results are provided to users as needed, allowing them to make adjustments before posting content. After posting, the server performs sentiment analysis on the collected real-time feedback data. This allows the server to provide users with information that helps them review and optimize their advertising strategies.

[0545] The hardware used is a server computer, and the software includes the natural language processing library spaCy and the machine learning libraries TensorFlow and PyTorch. By combining these, data language processing, evaluation, and analysis are performed.

[0546] A concrete example is the process by which, when posting an advertisement for a new product on social media, the server identifies risks such as "This advertisement may violate certain laws" and provides the user with a clear suggestion to remove the content. An example of such a prompt would be: "Please assess the legal or ethical risks contained in the content of your new product post."

[0547] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0548] Step 1:

[0549] The server receives advertising content data entered from the terminal. This data includes ad text and image information and is subject to analysis. The server collects this input data and prepares it for analysis.

[0550] Step 2:

[0551] The server applies natural language processing techniques to the received content data. Specifically, it uses the spaCy library to break down the text into tokens and analyze its grammatical structure. The input is text data, and the output is grammatical analysis results. Based on these results, important keywords and sentences within the content are extracted.

[0552] Step 3:

[0553] The server utilizes machine learning models to evaluate extracted text data. This process uses TensorFlow and PyTorch to detect legal and ethical risks. The input is the text analysis result, and the output is the risk assessment result. This identifies potential risks hidden within advertisements.

[0554] Step 4:

[0555] The server generates proposed revisions based on the evaluation results. At this stage, it uses a generative AI model to suggest specific revisions. For example, it might output something like, "This expression is legally dangerous, so please remove it." The input is the risk assessment result, and the output is a suggestion for the user.

[0556] Step 5:

[0557] The server sends the generated evaluation results and suggested revisions to the terminal and presents them to the user. The user receives this and makes revisions to the advertising content. The input is suggested data from the server, and the output is information that leads to user action.

[0558] Step 6:

[0559] After a user posts an ad, the server collects feedback data in real time. This data shows the reaction to the ad and is used for sentiment analysis. The input is real-time data after posting, and the output is the collected feedback information as is.

[0560] Step 7:

[0561] The server performs sentiment analysis on the collected feedback data. It classifies it as positive, negative, or neutral and suggests improvements to the advertising strategy. The input is real-time feedback data, and the output is the sentiment analysis result. Based on this result, it provides information to devise the next strategy.

[0562] 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.

[0563] The system of the present invention comprises a server, a terminal, and a user. In particular, it has the feature of recognizing the user's emotions and reflecting them in the posted content by incorporating an emotion engine. The user creates content to post to SNS using their own terminal. This content may include text, images, videos, etc. The created post is first sent from the terminal to the server.

[0564] The server uses various algorithms, legal databases, and an emotion engine within its information processing unit to analyze the content of received posts. The emotion engine recognizes the user's emotional state based on the user's input information. Based on the emotional results obtained from this recognition, the server comprehensively evaluates whether the posted content poses any potential risks. For example, if the user indicates negative emotions, the server points out that certain expressions may cause misunderstanding or offense and proposes ways to improve them.

[0565] Furthermore, the server uses the user's sentiment recognition results to generate individually customized modification suggestions. These suggestions take into account risks from multiple perspectives, including legal compliance, aesthetics, and emotional impact. The server then sends this information back to the terminal, where the user reviews and responds.

[0566] After a post is published, the server continuously monitors external comments and reactions in real time. The server uses a sentiment engine to determine whether the reactions are positive or negative. If the sentiment analysis reveals that negative reactions exceed a certain threshold, the server automatically generates an apology based on that information and suggests appropriate countermeasures to the user. For example, if a user receives numerous critical comments about a new product, the server will immediately provide additional information to clarify the misunderstandings along with an apology to calm the situation.

[0567] Furthermore, the emotion engine suggests highlighting positive elements to maximize the effectiveness of posts when the user's emotions are positive. As described above, this system evaluates the user's emotions and provides flexible feedback accordingly, enabling safer and more effective use of social media.

[0568] The following describes the processing flow.

[0569] Step 1:

[0570] Users use their devices to create and input content to post on social media. This content may include information such as text, images, and links.

[0571] Step 2:

[0572] The terminal receives the user's post and sends it to the server for further processing.

[0573] Step 3:

[0574] The server prepares to analyze the received posts. During this process, evaluation criteria are established within the information processing unit, taking into account legal, ethical, and social aspects.

[0575] Step 4:

[0576] The server uses an emotion engine to recognize the user's emotions from the content of their posts. Specifically, it classifies emotions as positive, negative, or neutral based on expressions in the text and selected emojis.

[0577] Step 5:

[0578] The server assesses potential risks in a way that reflects the user's emotions. If the user has negative emotions, it identifies the potential for increased risk associated with the content.

[0579] Step 6:

[0580] The server automatically generates correction suggestions for the user based on risk assessments. Specifically, these include improving ambiguous wording and recommending more specific expressions to avoid misunderstandings.

[0581] Step 7:

[0582] The server sends revision suggestions to the terminal and notifies the user of the suggestions. The user reviews the suggestions and adjusts the post as needed.

[0583] Step 8:

[0584] The user submits the final revised or approved post from their device to the server. The server accepts this final version of the post.

[0585] Step 9:

[0586] For published posts, the server monitors comments and other reactions in real time. It collects many reactions and uses sentiment analysis to determine whether they are positive or negative.

[0587] Step 10:

[0588] The server detects negative reactions exceeding a set threshold and determines that a situation has escalated into a "flame war." In response, the server provides the user with an automatically generated apology and appropriate countermeasures.

[0589] Step 11:

[0590] Based on all the sentiment data collected by the server, users are provided with detailed feedback. Users can use this feedback to more effectively manage their future posts.

[0591] (Example 2)

[0592] 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."

[0593] In modern society, advancements in communication technology have made it easy for individuals to disseminate information, but this has also increased the risk of inappropriate content and misleading expressions spreading. Therefore, there is a need for means to detect potential dangers and inappropriate expressions in user-generated information in advance and to correct them appropriately. Furthermore, rapid feedback and responses to external reactions after information has been published are also crucial. Conventional systems have struggled to efficiently address these challenges.

[0594] 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.

[0595] In this invention, the server includes an input device for receiving communication information generated by a user, an information processing device for analyzing the communication information, means for identifying the user's emotional state using emotion analysis technology, means for evaluating the potential risks of the communication information using legal information, means for automatically generating correction suggestions for the user based on the evaluated and identified emotional state, means for immediately monitoring external reactions to the communication information and recognizing reactions that exceed a pre-set standard, means for the information processing device to automatically generate an expression of apology when the standard is exceeded, means for presenting the user with a response along with the expression of apology, means for analyzing multiple reactions to the communication information, classifying emotions using natural language processing technology and providing results to the user, and means for providing a method that includes correction suggestions that emphasize positive elements using a generative AI model. This makes it possible to evaluate and correct the potential risks of information transmitted by users in advance and to respond quickly and appropriately to reactions after publication.

[0596] "User" refers to an individual or organization that generates and transmits communication information using an information processing system.

[0597] "Communication information" refers to information that includes all data formats transmitted by users through information processing systems, such as text, images, and videos.

[0598] An "input device" refers to hardware or software used to transmit communication information generated by a user to the network of an information processing system.

[0599] An "information processing device" refers to a computer system that analyzes received communication information and automatically generates correction suggestions and countermeasures for external feedback as needed.

[0600] "Emotional analysis technology" refers to technology that analyzes the emotional nuances contained in communication information in order to identify the emotional state of the user.

[0601] "Legal information" refers to database information based on laws, norms, and social standards, and is used to evaluate the appropriateness of communication information.

[0602] A "revision proposal" refers to suggestions for improvement presented to users in order to eliminate potential risks or inappropriate expressions in communication information.

[0603] "External reactions" refer to comments, feedback, evaluations, and other responses from third parties when communication information is made public.

[0604] "Pre-set criteria" refer to the minimum conditions under which countermeasures are automatically taken when external reactions meet certain criteria.

[0605] "Expression of apology" refers to a message that includes an automatically generated apology to correct misunderstandings when a user has posted misleading information.

[0606] "Natural language processing technology" refers to the technology used to process human language using computers and understand its meaning.

[0607] A "generative AI model" refers to a model that uses artificial intelligence technology to automatically construct revised proposals that emphasize positive elements.

[0608] This system is centered around users, terminals, and servers. Users generate communication information using their terminals and send it to the server. Terminals act as input devices, sending various data formats such as text, images, and videos to the server. Dedicated applications are installed on the terminals, providing a user-friendly operating environment through a user interface.

[0609] The server is equipped with an information processing device, and upon receiving communication information, it first uses sentiment analysis technology to identify the user's emotional state. This incorporates an algorithm that utilizes natural language processing technology to decipher emotional nuances from text. The server also works in conjunction with a legal information database to evaluate whether the posted content is safe in light of laws and social standards.

[0610] If risks are identified during the evaluation process, the server utilizes a generative AI model to automatically generate corrective suggestions for the user. These suggestions are personalized based on sentiment analysis results and can also emphasize positive elements. The suggestions are then presented to the user again via the device.

[0611] For example, when a user posts a review of a new product, the system can analyze the content to detect negative sentiments and suggest rephrasing potentially misleading expressions in a positive light. Furthermore, if numerous negative comments are received after publication, the server can automatically generate an apology and provide the user with a plan to reassure themselves.

[0612] An example of a prompt message is shown, illustrating a process where, when a user posts a review of a new product, sentiment ratings are used to identify negative expressions and suggest changing them to more favorable language. Furthermore, if critical comments increase after publication, a template for an apology is generated, providing the user with instructions on how to address the issue. This creates an environment where users can confidently share information.

[0613] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0614] Step 1:

[0615] The user generates communication information for posting to social networking services (SNS) using their device. This information may include text, images, and videos. This data is registered as input on the device, and the formatted data is prepared for output and transmission to the server. Specifically, the user edits and formats the post content using the interface of a dedicated application.

[0616] Step 2:

[0617] The terminal sends prepared communication information to the server. It receives pre-formatted data as input, structures it into data packets, and outputs them to the server via the network. During this process, data formatting checks and encoding are performed.

[0618] Step 3:

[0619] The server begins analyzing the received communication information. It takes data sent from the terminal as input and performs sentiment analysis using natural language processing techniques. This yields an output that identifies the user's emotional state. Specifically, it analyzes keywords and sentence structure within the communication information and calculates a positive or negative sentiment score.

[0620] Step 4:

[0621] The server evaluates the potential risks of communication information by referring to a legal information database based on the results of sentiment analysis. It takes the sentiment analysis results and communication information as input and outputs an evaluation by comparing them with the legal information database. Specifically, it checks whether any legal keywords are included and determines the level of safety.

[0622] Step 5:

[0623] The server generates revision suggestions using a generative AI model based on evaluation results and emotional states. It takes evaluation results as input and outputs specific revision suggestions for the user. This includes things like turning negative phrasing into positive phrasing and emphasizing statements. Specifically, it documents the generated suggestions according to a template.

[0624] Step 6:

[0625] The server sends the generated correction suggestions back to the terminal. The correction suggestions are the input, and they are returned to the terminal as output for presentation to the user. Specifically, the correction suggestions are presented to the user via notification or pop-up.

[0626] Step 7:

[0627] The user reviews the suggested content on their device and modifies the communication information as needed. The input is the suggested modifications, and the output is the modified communication information. Specifically, the user accepts or partially adopts the proposed modifications to finalize the posted content.

[0628] Step 8:

[0629] After a post is published, the server monitors external reactions to the communication information in real time. Based on the published communication information as input, it analyzes the acquired reactions and generates an output that performs an emotional classification. Specifically, if negative reactions exceed a certain threshold, it generates an expression of apology and countermeasures based on pre-set criteria.

[0630] (Application Example 2)

[0631] 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."

[0632] Conventional information processing systems analyzed posted content without adequately considering users' emotions or social backgrounds, potentially overlooking potential risks. Furthermore, in customer service, there was a lack of mechanisms to provide real-time feedback reflecting customer emotions, making appropriate customer service difficult. This resulted in the challenge of improving customer satisfaction.

[0633] 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.

[0634] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for analyzing customer input information based on emotional state and providing feedback for optimizing customer service. This enables a comprehensive evaluation of potential risks in posted content and flexible customer service responses based on customer emotions.

[0635] An "information processing device" is a device that analyzes data entered by users and evaluates potential risks from a legal and ethical standpoint.

[0636] "Analysis" is the act of breaking down input information to understand its meaning and trends.

[0637] "Laws and regulations" refer to rules and norms that are established and must be observed within a nation or local community.

[0638] A "potential risk" is a danger that is not immediately apparent but could potentially cause problems later on.

[0639] A "revision suggestion" is an automated suggestion that offers improvements to content posted by users.

[0640] "External reactions" refer to feedback such as comments and ratings that others give to the content of a post.

[0641] "Real-time monitoring" means instantly checking and analyzing data as it is being processed.

[0642] A "threshold" is a limit that, when exceeded, triggers a specific action.

[0643] An "expression of apology" is a way of expressing one's acknowledgment of a mistake and showing remorse to the other party.

[0644] "Countermeasures" refer to specific solutions or action plans taken in response to a problem or issue.

[0645] "Emotional state" refers to the user's psychological condition and emotional tendencies.

[0646] "Feedback" refers to the reactions or opinions that recipients express regarding a service or information.

[0647] To implement this invention, an information processing device is required. This device analyzes data entered by the user via a server, uses an emotion engine to recognize the user's emotional state in real time, and assesses potential risks. The system is built with a backend using Python and Flask, accepting data input from smartphones and other devices, and performing data analysis. In addition, it can utilize cloud infrastructure such as AWS to scale up resources.

[0648] The server receives user-submitted content, including text, images, and videos, and passes it to the sentiment engine for analysis. The sentiment engine infers the user's emotional state from the input data and extracts positive or negative responses. Based on the evaluation results, feedback and correction suggestions are generated and presented to the user. In this process, the suggestions are customized by referring to previously collected datasets. For example, the optimal solution may be suggested based on past successful countermeasures and already resolved trouble cases.

[0649] When the user's device receives feedback from the server, it reviews the suggestions and implements countermeasures as necessary. The results of these actions are then sent back to the server and stored as evaluation and training data.

[0650] As a concrete example, if a user receives negative feedback about a new product, the server immediately uses the emotion engine to generate an apology and instructions for the salesperson. This not only quickly resolves customer dissatisfaction but also provides specific countermeasures for the salesperson. An example of input to the generating AI model is a prompt such as, "Analyze this review based on the emotion engine and suggest further purchase promotion measures if the customer's emotion is positive, or immediate follow-up methods if it is negative."

[0651] This system makes it possible to provide services that reflect user feedback in a timely and accurate manner in all business scenarios.

[0652] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0653] Step 1:

[0654] Users create content using their own devices and send it to the server. Input can include text, images, and videos. This allows the user's created content to be delivered to the server.

[0655] Step 2:

[0656] The server runs an emotion engine to analyze the content of the posts it receives. The input is user-submitted data, and the output is an evaluation result indicating the emotional state. Specifically, the emotion analysis algorithm classifies the emotional tendencies of the posts and categorizes them as positive, negative, or neutral.

[0657] Step 3:

[0658] The server assesses potential risks based on evaluation results obtained from the emotion engine. It uses emotional state data as input and generates risk assessment results as output. Specifically, it focuses on identifying risk items when particularly negative emotions are detected and considers corrective action suggestions based on their content.

[0659] Step 4:

[0660] The server automatically generates correction suggestions based on the evaluation results. The input is the risk assessment result, and the output is the correction suggestions. Specifically, it refers to legal databases and historical datasets to generate appropriate improvement suggestions for user submissions.

[0661] Step 5:

[0662] The server monitors external feedback in real time. The input is reaction data collected from social media and other sources. It determines whether the reaction exceeds a threshold, and if it does, it generates an apology as output. Specifically, it re-analyzes the feedback data using an emotion engine to determine if the reaction is negative.

[0663] Step 6:

[0664] The server presents the user with a generated apology and proposed solutions. The input is the generated apology and solutions, and the output is a notification to the user. Specifically, the apology and details of the solutions are sent as a text message.

[0665] Step 7:

[0666] The user's device reviews the feedback received from the server and implements corrective actions as needed. This input is a notification from the server, and the output is the result of the implemented actions, which is then sent back to the server. Specifically, the user acts in accordance with the suggested corrections, and this is logged by the server.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] [Fourth Embodiment]

[0671] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0672] 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.

[0673] 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).

[0674] 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.

[0675] 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.

[0676] 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).

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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".

[0684] The system of the present invention comprises a server, a terminal, and a user. This system evaluates potential risks from the perspectives of legal compliance, ethics, and safety regarding content posted by users on social networking services (SNS), and automatically suggests revisions to the posts as needed. Upon receiving a user's post, the server utilizes its built-in machine learning model and an external database to comprehensively evaluate the risks contained in the post. Specifically, the server analyzes language and phrases using natural language processing technology to detect potential legal violations and socially inappropriate expressions. Furthermore, based on the risks discovered, the server can suggest revisions to the user. For example, if ambiguous expressions may lead to misunderstandings, specific revision suggestions will be provided.

[0685] Furthermore, the server monitors external reactions to posts in real time, and if negative reactions exceeding a certain threshold are detected, it determines that the post has become a "flame war." Once a flame war is detected, the server provides an automatically generated apology and presents it to the user as a swift countermeasure. Here, appropriate apology expressions based on past data are used, ensuring a quick and accurate response. For example, if a misunderstanding arises regarding a product, an apology is generated along with information to resolve the misunderstanding.

[0686] The server also collects numerous comments accompanying posts and uses sentiment analysis technology to classify each comment as positive, negative, or neutral. Based on this analysis, the server provides users with feedback. This feedback allows users to consider areas for improvement and strategies in their social media activities. For example, if a user collects reviews of a new product, the server incorporates that feedback to help identify ways to improve the product.

[0687] In this way, this system, through a series of automated processes, mitigates potential risks in social media activities and supports users in creating posts that increase their influence safely and effectively.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] Users create content to post on social media using their devices and send it to the system. This content can range from simple text input to images and links.

[0691] Step 2:

[0692] The device receives the user's submission and sends it to the server. The server receives this information as data for analysis.

[0693] Step 3:

[0694] The server inputs the received posts into a machine learning model for language analysis. Through natural language processing, it evaluates whether the content complies with laws and regulations and does not contain ethical issues. For example, it extracts specific keywords from the text and compares them with a legal database.

[0695] Step 4:

[0696] Once the server identifies potential risks, it automatically generates suggested fixes for the user based on those risks. The suggestions are clarified by including specific improvements to address ambiguous or potentially misleading language.

[0697] Step 5:

[0698] The information is sent again from the server to the terminal, and the user reviews the proposed revisions. Based on this information, the user can optionally modify or approve the posted content.

[0699] Step 6:

[0700] The user completes the revisions or approves the post, then sends it back to the server from their device for final confirmation, which is then stored in the system.

[0701] Step 7:

[0702] For published posts, the server monitors external comments and reactions in real time. It analyzes the emotional reactions to the post and detects a "flame war" if a large number of negative reactions exceed a threshold.

[0703] Step 8:

[0704] If a social media firestorm is detected, the server automatically generates an apology. Based on past cases and data, it creates content that is appropriate for the situation.

[0705] Step 9:

[0706] The server sends a generated apology letter along with information suggesting countermeasures to the terminal, urging the user to take prompt action. The user can then take appropriate action based on the suggestions.

[0707] Step 10:

[0708] As additional feedback, the server compiles sentiment analysis results for posts and related comments and provides this information to the user via their device. The user can then use this feedback to optimize their future posts.

[0709] (Example 1)

[0710] 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".

[0711] In today's rapidly information-driven world, content posted on social media can cause problems from a legal and ethical standpoint, leading to social trouble and online firestorms. This increases the risk of individuals and organizations losing credibility and suffering financial losses. Furthermore, there is a growing need for swift and appropriate responses to problems that arise after posting, necessitating new technological tools to address these challenges.

[0712] 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.

[0713] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold. This allows for proactive risk reduction in SNS activities and enables a rapid response in the event of a problem.

[0714] An "information processing device" is a core component of a system that receives, analyzes, and processes data, and it enables a variety of functions based on user input.

[0715] "User" refers to any entity that inputs information and receives feedback through this system, and includes individuals or corporations.

[0716] "Input information" refers to all information, including text data and media files, that users provide for posting on social media or other platforms.

[0717] "Potential risks" refer to elements that predict and analyze what problems the posted content may cause in relation to laws, ethics, and social standards.

[0718] "Suggested revisions" refer to specific changes and advice automatically generated to improve user-submitted content.

[0719] "External reactions" refer to feedback, comments, and ratings received from users of social media and other platforms regarding the content of a post.

[0720] "Real-time monitoring" refers to the process of instantly tracking continuously changing information and immediately detecting changes or anomalies.

[0721] A "threshold" is a numerical value or standard set as a decision criterion for triggering a specific action; exceeding this level results in special processing.

[0722] "Apology expressions" refer to the automatically generated text that provides appropriate phrasing for users to apologize for problems caused by their posts.

[0723] "Classifying emotions" refers to the process of analyzing text data and categorizing it into different emotional categories such as positive, negative, and neutral.

[0724] A "machine learning model" refers to a computer system that uses algorithms to learn specific patterns and knowledge from large amounts of data, and then uses this knowledge to perform inferences and predictions on new data.

[0725] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes text analysis, translation, and automated conversation generation.

[0726] A "generative AI model" refers to artificial intelligence technology that automatically generates new text and data based on input information.

[0727] This invention is an information processing system that supports users in ensuring that the content they post on social media does not cause social problems. The system consists mainly of a server, a terminal, and a user, and evaluates the posted content from the perspectives of laws, ethics, and safety, and automatically generates revision suggestions and apologies as needed.

[0728] The server functions as the core of this system. The server receives text data sent from the user's terminal and analyzes the data in detail using built-in natural language processing technology. Specifically, it detects legally or socially inappropriate expressions through keyword matching and uses machine learning models to comprehensively assess risks. This process also includes sentiment analysis technology, classifying external reactions to posts as positive, negative, or neutral.

[0729] Using a generative AI model, the server can automatically generate correction suggestions. For example, if ambiguous wording could lead to misunderstandings, it can present specific correction suggestions to the user. In addition, it monitors external reactions and, if negative feedback exceeding a certain threshold is collected, it has the function to promptly generate and provide an apology to the user. The generated apology can be flexibly customized to suit the situation by referring to past datasets.

[0730] As a concrete example of this system, when a user posts a product review, they can send a prompt message to the server such as, "Please evaluate whether this post is legally problematic," and the server will immediately evaluate the post and suggest corrections. The server can also generate an appropriate apology in response to a prompt such as, "Please generate this apology," enabling a swift response.

[0731] Thus, the present invention provides users with valuable support for safely and effectively engaging in activities on social networking services (SNS). The entire system features rapid real-time processing, contributing to the prevention and resolution of problems.

[0732] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0733] Step 1:

[0734] The user enters text to post to the social networking service via their device. The entered text is then prepared for transmission to the server. The content submitted by the user is sent to the server and provided as input for data analysis.

[0735] Step 2:

[0736] The server passes the received text data to a natural language processing engine. Here, morphological and semantic analysis is performed to analyze the linguistic elements that make up the text. This analysis determines whether the posted content may violate laws or contain socially inappropriate expressions. A list of potential risks is generated as output.

[0737] Step 3:

[0738] The server uses a machine learning model to assess risk based on the analysis results. This process involves comparing the current post with past database data to comprehensively determine its risk level. The input is the analysis results, and the output is the assessed risk level. Specifically, it refers to similar past cases and generates a warning if the risk is high.

[0739] Step 4:

[0740] The server uses a generative AI model to automatically create correction suggestions for the user. The input is the result of a risk assessment, and the output is a specific correction suggestion. For example, if ambiguous language is detected, it will suggest a clearer way to phrase it.

[0741] Step 5:

[0742] The server monitors external reactions in real time even after a post has been published on social media. It uses the social media platform's API to collect the returned comments and ratings. The input is feedback data after publication, and the output is an aggregate of the reactions. If a specific negative reaction exceeds a threshold, the server proceeds to the next step.

[0743] Step 6:

[0744] The server uses a generative AI model to quickly create appropriate apology letters. The input is the aggregated results of external reactions, and the output is a customized apology letter. This includes specific actions such as referencing historical datasets to generate apology letters tailored to individual situations.

[0745] Step 7:

[0746] The server performs sentiment analysis on numerous comments on posts, classifying each comment as positive, negative, or neutral. The input is collected comment data, and the output is the classified sentiment information. Based on this analysis, the server provides users with specific feedback and suggests ways to improve their posting activities.

[0747] (Application Example 1)

[0748] 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".

[0749] In modern society, while information dissemination via social media and the internet is widespread, the risk of users unintentionally violating laws or disseminating socially inappropriate content is increasing. Furthermore, particularly in advertising, if content is misleading or perceived as inappropriate by the general public, it can not only damage a company's reputation but also lead to economic losses. There is a need to mitigate these risks and provide an environment where users can confidently disseminate information.

[0750] 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.

[0751] In this invention, the server includes means for analyzing input data received from users by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for analyzing advertising data to identify legal and ethical risks and generate proposed revisions; and means for performing a risk assessment before posting advertising content and presenting the assessment results to the user. This enables users to effectively disseminate information while maintaining legal compliance by evaluating the risks associated with advertisements and content on social media in advance and making appropriate revisions.

[0752] An "information processing device" is a device that has the ability to analyze specific information and make decisions based on data received from users.

[0753] "Input data" refers to any form of data provided to the information processing device by the user, and it forms the basis for analysis.

[0754] "Legal, ethical, and social considerations" refer to the legal standards, ethical norms, and general societal values ​​that are taken into account when determining the appropriateness of information.

[0755] "Assessing potential risks" is the process of identifying potential problems that information may contain and using that information to draw attention to them or propose corrective actions.

[0756] "Generating revised proposals" means creating specific suggestions for improving the content of the information based on the assessed risks.

[0757] "Advertising data" refers to a set of information used for marketing purposes of products and services, and is the subject of analysis.

[0758] "Risk assessment" is the process of detecting potential legal and ethical risks associated with advertising and informational content and determining their impact.

[0759] "Presenting evaluation results to users" means providing the analysis and suggestions obtained as a result of information processing in a format that users can review and understand.

[0760] This invention relates to a system for information processing, primarily configured with a server at its core. The server receives data input from a user via a specific terminal and analyzes it from legal, ethical, and social perspectives. The server utilizes machine learning models to assess potential risks. Based on these assessment results, the server presents specific corrective action plans to the user.

[0761] The server also acquires advertising data via the internet and evaluates its content legally and ethically before posting. The evaluation results are provided to users as needed, allowing them to make adjustments before posting content. After posting, the server performs sentiment analysis on the collected real-time feedback data. This allows the server to provide users with information that helps them review and optimize their advertising strategies.

[0762] The hardware used is a server computer, and the software includes the natural language processing library spaCy and the machine learning libraries TensorFlow and PyTorch. By combining these, data language processing, evaluation, and analysis are performed.

[0763] A concrete example is the process by which, when posting an advertisement for a new product on social media, the server identifies risks such as "This advertisement may violate certain laws" and provides the user with a clear suggestion to remove the content. An example of such a prompt would be: "Please assess the legal or ethical risks contained in the content of your new product post."

[0764] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0765] Step 1:

[0766] The server receives advertising content data entered from the terminal. This data includes ad text and image information and is subject to analysis. The server collects this input data and prepares it for analysis.

[0767] Step 2:

[0768] The server applies natural language processing techniques to the received content data. Specifically, it uses the spaCy library to break down the text into tokens and analyze its grammatical structure. The input is text data, and the output is grammatical analysis results. Based on these results, important keywords and sentences within the content are extracted.

[0769] Step 3:

[0770] The server utilizes machine learning models to evaluate extracted text data. This process uses TensorFlow and PyTorch to detect legal and ethical risks. The input is the text analysis result, and the output is the risk assessment result. This identifies potential risks hidden within advertisements.

[0771] Step 4:

[0772] The server generates proposed revisions based on the evaluation results. At this stage, it uses a generative AI model to suggest specific revisions. For example, it might output something like, "This expression is legally dangerous, so please remove it." The input is the risk assessment result, and the output is a suggestion for the user.

[0773] Step 5:

[0774] The server sends the generated evaluation results and suggested revisions to the terminal and presents them to the user. The user receives this and makes revisions to the advertising content. The input is suggested data from the server, and the output is information that leads to user action.

[0775] Step 6:

[0776] After a user posts an ad, the server collects feedback data in real time. This data shows the reaction to the ad and is used for sentiment analysis. The input is real-time data after posting, and the output is the collected feedback information as is.

[0777] Step 7:

[0778] The server performs sentiment analysis on the collected feedback data. It classifies it as positive, negative, or neutral and suggests improvements to the advertising strategy. The input is real-time feedback data, and the output is the sentiment analysis result. Based on this result, it provides information to devise the next strategy.

[0779] 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.

[0780] The system of the present invention comprises a server, a terminal, and a user. In particular, it has the feature of recognizing the user's emotions and reflecting them in the posted content by incorporating an emotion engine. The user creates content to post to SNS using their own terminal. This content may include text, images, videos, etc. The created post is first sent from the terminal to the server.

[0781] The server uses various algorithms, legal databases, and an emotion engine within its information processing unit to analyze the content of received posts. The emotion engine recognizes the user's emotional state based on the user's input information. Based on the emotional results obtained from this recognition, the server comprehensively evaluates whether the posted content poses any potential risks. For example, if the user indicates negative emotions, the server points out that certain expressions may cause misunderstanding or offense and proposes ways to improve them.

[0782] Furthermore, the server uses the user's sentiment recognition results to generate individually customized modification suggestions. These suggestions take into account risks from multiple perspectives, including legal compliance, aesthetics, and emotional impact. The server then sends this information back to the terminal, where the user reviews and responds.

[0783] After a post is published, the server continuously monitors external comments and reactions in real time. The server uses a sentiment engine to determine whether the reactions are positive or negative. If the sentiment analysis reveals that negative reactions exceed a certain threshold, the server automatically generates an apology based on that information and suggests appropriate countermeasures to the user. For example, if a user receives numerous critical comments about a new product, the server will immediately provide additional information to clarify the misunderstandings along with an apology to calm the situation.

[0784] Furthermore, the emotion engine suggests highlighting positive elements to maximize the effectiveness of posts when the user's emotions are positive. As described above, this system evaluates the user's emotions and provides flexible feedback accordingly, enabling safer and more effective use of social media.

[0785] The following describes the processing flow.

[0786] Step 1:

[0787] Users use their devices to create and input content to post on social media. This content may include information such as text, images, and links.

[0788] Step 2:

[0789] The terminal receives the user's post and sends it to the server for further processing.

[0790] Step 3:

[0791] The server prepares to analyze the received posts. During this process, evaluation criteria are established within the information processing unit, taking into account legal, ethical, and social aspects.

[0792] Step 4:

[0793] The server uses an emotion engine to recognize the user's emotions from the content of their posts. Specifically, it classifies emotions as positive, negative, or neutral based on expressions in the text and selected emojis.

[0794] Step 5:

[0795] The server assesses potential risks in a way that reflects the user's emotions. If the user has negative emotions, it identifies the potential for increased risk associated with the content.

[0796] Step 6:

[0797] The server automatically generates correction suggestions for the user based on risk assessments. Specifically, these include improving ambiguous wording and recommending more specific expressions to avoid misunderstandings.

[0798] Step 7:

[0799] The server sends revision suggestions to the terminal and notifies the user of the suggestions. The user reviews the suggestions and adjusts the post as needed.

[0800] Step 8:

[0801] The user submits the final revised or approved post from their device to the server. The server accepts this final version of the post.

[0802] Step 9:

[0803] For published posts, the server monitors comments and other reactions in real time. It collects many reactions and uses sentiment analysis to determine whether they are positive or negative.

[0804] Step 10:

[0805] The server detects negative reactions exceeding a set threshold and determines that a situation has escalated into a "flame war." In response, the server provides the user with an automatically generated apology and appropriate countermeasures.

[0806] Step 11:

[0807] Based on all the sentiment data collected by the server, users are provided with detailed feedback. Users can use this feedback to more effectively manage their future posts.

[0808] (Example 2)

[0809] 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".

[0810] In modern society, advancements in communication technology have made it easy for individuals to disseminate information, but this has also increased the risk of inappropriate content and misleading expressions spreading. Therefore, there is a need for means to detect potential dangers and inappropriate expressions in user-generated information in advance and to correct them appropriately. Furthermore, rapid feedback and responses to external reactions after information has been published are also crucial. Conventional systems have struggled to efficiently address these challenges.

[0811] 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.

[0812] In this invention, the server includes an input device for receiving communication information generated by a user, an information processing device for analyzing the communication information, means for identifying the user's emotional state using emotion analysis technology, means for evaluating the potential risks of the communication information using legal information, means for automatically generating correction suggestions for the user based on the evaluated and identified emotional state, means for immediately monitoring external reactions to the communication information and recognizing reactions that exceed a pre-set standard, means for the information processing device to automatically generate an expression of apology when the standard is exceeded, means for presenting the user with a response along with the expression of apology, means for analyzing multiple reactions to the communication information, classifying emotions using natural language processing technology and providing results to the user, and means for providing a method that includes correction suggestions that emphasize positive elements using a generative AI model. This makes it possible to evaluate and correct the potential risks of information transmitted by users in advance and to respond quickly and appropriately to reactions after publication.

[0813] "User" refers to an individual or organization that generates and transmits communication information using an information processing system.

[0814] "Communication information" refers to information that includes all data formats transmitted by users through information processing systems, such as text, images, and videos.

[0815] An "input device" refers to hardware or software used to transmit communication information generated by a user to the network of an information processing system.

[0816] An "information processing device" refers to a computer system that analyzes received communication information and automatically generates correction suggestions and countermeasures for external feedback as needed.

[0817] "Emotional analysis technology" refers to technology that analyzes the emotional nuances contained in communication information in order to identify the emotional state of the user.

[0818] "Legal information" refers to database information based on laws, norms, and social standards, and is used to evaluate the appropriateness of communication information.

[0819] A "revision proposal" refers to suggestions for improvement presented to users in order to eliminate potential risks or inappropriate expressions in communication information.

[0820] "External reactions" refer to comments, feedback, evaluations, and other responses from third parties when communication information is made public.

[0821] "Pre-set criteria" refer to the minimum conditions under which countermeasures are automatically taken when external reactions meet certain criteria.

[0822] "Expression of apology" refers to a message that includes an automatically generated apology to correct misunderstandings when a user has posted misleading information.

[0823] "Natural language processing technology" refers to the technology used to process human language using computers and understand its meaning.

[0824] A "generative AI model" refers to a model that uses artificial intelligence technology to automatically construct revised proposals that emphasize positive elements.

[0825] This system is centered around users, terminals, and servers. Users generate communication information using their terminals and send it to the server. Terminals act as input devices, sending various data formats such as text, images, and videos to the server. Dedicated applications are installed on the terminals, providing a user-friendly operating environment through a user interface.

[0826] The server is equipped with an information processing device, and upon receiving communication information, it first uses sentiment analysis technology to identify the user's emotional state. This incorporates an algorithm that utilizes natural language processing technology to decipher emotional nuances from text. The server also works in conjunction with a legal information database to evaluate whether the posted content is safe in light of laws and social standards.

[0827] If risks are identified during the evaluation process, the server utilizes a generative AI model to automatically generate corrective suggestions for the user. These suggestions are personalized based on sentiment analysis results and can also emphasize positive elements. The suggestions are then presented to the user again via the device.

[0828] For example, when a user posts a review of a new product, the system can analyze the content to detect negative sentiments and suggest rephrasing potentially misleading expressions in a positive light. Furthermore, if numerous negative comments are received after publication, the server can automatically generate an apology and provide the user with a plan to reassure themselves.

[0829] An example of a prompt message is shown, illustrating a process where, when a user posts a review of a new product, sentiment ratings are used to identify negative expressions and suggest changing them to more favorable language. Furthermore, if critical comments increase after publication, a template for an apology is generated, providing the user with instructions on how to address the issue. This creates an environment where users can confidently share information.

[0830] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0831] Step 1:

[0832] The user generates communication information for posting to social networking services (SNS) using their device. This information may include text, images, and videos. This data is registered as input on the device, and the formatted data is prepared for output and transmission to the server. Specifically, the user edits and formats the post content using the interface of a dedicated application.

[0833] Step 2:

[0834] The terminal sends prepared communication information to the server. It receives pre-formatted data as input, structures it into data packets, and outputs them to the server via the network. During this process, data formatting checks and encoding are performed.

[0835] Step 3:

[0836] The server begins analyzing the received communication information. It takes data sent from the terminal as input and performs sentiment analysis using natural language processing techniques. This yields an output that identifies the user's emotional state. Specifically, it analyzes keywords and sentence structure within the communication information and calculates a positive or negative sentiment score.

[0837] Step 4:

[0838] The server evaluates the potential risks of communication information by referring to a legal information database based on the results of sentiment analysis. It takes the sentiment analysis results and communication information as input and outputs an evaluation by comparing them with the legal information database. Specifically, it checks whether any legal keywords are included and determines the level of safety.

[0839] Step 5:

[0840] The server generates revision suggestions using a generative AI model based on evaluation results and emotional states. It takes evaluation results as input and outputs specific revision suggestions for the user. This includes things like turning negative phrasing into positive phrasing and emphasizing statements. Specifically, it documents the generated suggestions according to a template.

[0841] Step 6:

[0842] The server sends the generated correction suggestions back to the terminal. The correction suggestions are the input, and they are returned to the terminal as output for presentation to the user. Specifically, the correction suggestions are presented to the user via notification or pop-up.

[0843] Step 7:

[0844] The user reviews the suggested content on their device and modifies the communication information as needed. The input is the suggested modifications, and the output is the modified communication information. Specifically, the user accepts or partially adopts the proposed modifications to finalize the posted content.

[0845] Step 8:

[0846] After a post is published, the server monitors external reactions to the communication information in real time. Based on the published communication information as input, it analyzes the acquired reactions and generates an output that performs an emotional classification. Specifically, if negative reactions exceed a certain threshold, it generates an expression of apology and countermeasures based on pre-set criteria.

[0847] (Application Example 2)

[0848] 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".

[0849] Conventional information processing systems analyzed posted content without adequately considering users' emotions or social backgrounds, potentially overlooking potential risks. Furthermore, in customer service, there was a lack of mechanisms to provide real-time feedback reflecting customer emotions, making appropriate customer service difficult. This resulted in the challenge of improving customer satisfaction.

[0850] 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.

[0851] In this invention, the server includes means for analyzing input information received from a user by an information processing device and evaluating potential risks from legal, ethical, and social perspectives; means for automatically generating correction suggestions for the user based on the evaluation; and means for analyzing customer input information based on emotional state and providing feedback for optimizing customer service. This enables a comprehensive evaluation of potential risks in posted content and flexible customer service responses based on customer emotions.

[0852] An "information processing device" is a device that analyzes data entered by users and evaluates potential risks from a legal and ethical standpoint.

[0853] "Analysis" is the act of breaking down input information to understand its meaning and trends.

[0854] "Laws and regulations" refer to rules and norms that are established and must be observed within a nation or local community.

[0855] A "potential risk" is a danger that is not immediately apparent but could potentially cause problems later on.

[0856] A "revision suggestion" is an automated suggestion that offers improvements to content posted by users.

[0857] "External reactions" refer to feedback such as comments and ratings that others give to the content of a post.

[0858] "Real-time monitoring" means instantly checking and analyzing data as it is being processed.

[0859] A "threshold" is a limit that, when exceeded, triggers a specific action.

[0860] An "expression of apology" is a way of expressing one's acknowledgment of a mistake and showing remorse to the other party.

[0861] "Countermeasures" refer to specific solutions or action plans taken in response to a problem or issue.

[0862] "Emotional state" refers to the user's psychological condition and emotional tendencies.

[0863] "Feedback" refers to the reactions or opinions that recipients express regarding a service or information.

[0864] To implement this invention, an information processing device is required. This device analyzes data entered by the user via a server, uses an emotion engine to recognize the user's emotional state in real time, and assesses potential risks. The system is built with a backend using Python and Flask, accepting data input from smartphones and other devices, and performing data analysis. In addition, it can utilize cloud infrastructure such as AWS to scale up resources.

[0865] The server receives user-submitted content, including text, images, and videos, and passes it to the sentiment engine for analysis. The sentiment engine infers the user's emotional state from the input data and extracts positive or negative responses. Based on the evaluation results, feedback and correction suggestions are generated and presented to the user. In this process, the suggestions are customized by referring to previously collected datasets. For example, the optimal solution may be suggested based on past successful countermeasures and already resolved trouble cases.

[0866] When the user's device receives feedback from the server, it reviews the suggestions and implements countermeasures as necessary. The results of these actions are then sent back to the server and stored as evaluation and training data.

[0867] As a concrete example, if a user receives negative feedback about a new product, the server immediately uses the emotion engine to generate an apology and instructions for the salesperson. This not only quickly resolves customer dissatisfaction but also provides specific countermeasures for the salesperson. An example of input to the generating AI model is a prompt such as, "Analyze this review based on the emotion engine and suggest further purchase promotion measures if the customer's emotion is positive, or immediate follow-up methods if it is negative."

[0868] This system makes it possible to provide services that reflect user feedback in a timely and accurate manner in all business scenarios.

[0869] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0870] Step 1:

[0871] Users create content using their own devices and send it to the server. Input can include text, images, and videos. This allows the user's created content to be delivered to the server.

[0872] Step 2:

[0873] The server runs an emotion engine to analyze the content of the posts it receives. The input is user-submitted data, and the output is an evaluation result indicating the emotional state. Specifically, the emotion analysis algorithm classifies the emotional tendencies of the posts and categorizes them as positive, negative, or neutral.

[0874] Step 3:

[0875] The server assesses potential risks based on evaluation results obtained from the emotion engine. It uses emotional state data as input and generates risk assessment results as output. Specifically, it focuses on identifying risk items when particularly negative emotions are detected and considers corrective action suggestions based on their content.

[0876] Step 4:

[0877] The server automatically generates correction suggestions based on the evaluation results. The input is the risk assessment result, and the output is the correction suggestions. Specifically, it refers to legal databases and historical datasets to generate appropriate improvement suggestions for user submissions.

[0878] Step 5:

[0879] The server monitors external feedback in real time. The input is reaction data collected from social media and other sources. It determines whether the reaction exceeds a threshold, and if it does, it generates an apology as output. Specifically, it re-analyzes the feedback data using an emotion engine to determine if the reaction is negative.

[0880] Step 6:

[0881] The server presents the user with a generated apology and proposed solutions. The input is the generated apology and solutions, and the output is a notification to the user. Specifically, the apology and details of the solutions are sent as a text message.

[0882] Step 7:

[0883] The user's device reviews the feedback received from the server and implements corrective actions as needed. This input is a notification from the server, and the output is the result of the implemented actions, which is then sent back to the server. Specifically, the user acts in accordance with the suggested corrections, and this is logged by the server.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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."

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] The following is further disclosed regarding the embodiments described above.

[0906] (Claim 1)

[0907] A means for an information processing device to analyze input information received from a user and to evaluate potential risks from legal, ethical, and social perspectives,

[0908] A means for automatically generating correction suggestions for the user based on the aforementioned evaluation,

[0909] A means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold,

[0910] A means by which the information processing device automatically generates an apology expression when the threshold is exceeded,

[0911] A means of presenting the aforementioned user with the aforementioned apology and countermeasures,

[0912] A means for analyzing multiple responses to the aforementioned post, classifying the sentiment of the text, and providing the user with the analysis results,

[0913] A system that includes this.

[0914] (Claim 2)

[0915] The system according to claim 1, wherein the automatically generated apology expression is flexibly customized by referring to past datasets.

[0916] (Claim 3)

[0917] The system according to claim 1, wherein the proposed modifications provided by the information processing device are based on a legal database.

[0918] "Example 1"

[0919] (Claim 1)

[0920] A means for an information processing device to analyze input information received from a user and to evaluate potential risks from legal, ethical, and social perspectives,

[0921] A means for automatically generating correction suggestions for the user based on the aforementioned evaluation,

[0922] A means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold,

[0923] A means by which the information processing device automatically generates an apology expression when the threshold is exceeded,

[0924] A means of presenting the aforementioned user with the aforementioned apology and countermeasures,

[0925] A means for analyzing multiple responses to the aforementioned post, classifying the sentiment of the text, and providing the user with the analysis results,

[0926] The aforementioned information processing device includes means for evaluating the risks of posting from multiple perspectives using a machine learning model,

[0927] A means of analyzing legally and socially inappropriate expressions using natural language processing technology,

[0928] A method for automatically generating apology statements and correction suggestions using a generative AI model,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, wherein the automatically generated apology expression is flexibly customized by referring to past datasets.

[0932] (Claim 3)

[0933] The system according to claim 1, wherein the proposed modifications provided by the information processing device are based on a legal database.

[0934] "Application Example 1"

[0935] (Claim 1)

[0936] A means for an information processing device to analyze input data received from users and evaluate potential risks from legal, ethical, and social perspectives,

[0937] A means for automatically generating correction suggestions for the user based on the aforementioned evaluation,

[0938] A means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold,

[0939] A means by which the information processing device automatically generates an apology expression when the threshold is exceeded,

[0940] A means of presenting the aforementioned user with the aforementioned apology and countermeasures,

[0941] A means for analyzing multiple responses to the aforementioned post, classifying the sentiment of the text, and providing the user with the analysis results,

[0942] A means of analyzing advertising data to identify legal and ethical risks and generate proposed revisions,

[0943] A means of conducting a risk assessment before posting advertising content and presenting the assessment results to users,

[0944] A means of providing information for building an advertising strategy based on feedback analysis after posting,

[0945] A system that includes this.

[0946] (Claim 2)

[0947] The system according to claim 1, wherein the automatically generated apology expression is flexibly customized by referring to a past information set.

[0948] (Claim 3)

[0949] The system according to claim 1, wherein the proposed modifications provided by the information processing device are based on legal information sources.

[0950] "Example 2 of combining an emotion engine"

[0951] (Claim 1)

[0952] An input device that receives communication information generated by the user,

[0953] An information processing device for analyzing the aforementioned communication information,

[0954] A means for identifying the user's emotional state using emotion analysis technology,

[0955] A means for evaluating the potential risks of the aforementioned communication information using legal information,

[0956] A means for automatically generating modification suggestions for the user based on the aforementioned evaluation and identified emotional state,

[0957] A means for immediately monitoring external reactions to the aforementioned communication information and recognizing reactions that exceed a pre-set standard,

[0958] A means by which the information processing device automatically generates an expression of gratitude when the aforementioned criteria are exceeded,

[0959] A means of presenting the aforementioned user with the aforementioned expression of gratitude and countermeasures,

[0960] A means for analyzing multiple responses to the aforementioned communication information, classifying emotions using natural language processing technology, and providing results to the user,

[0961] A means to provide a method that includes a revised proposal that emphasizes positive elements using a generative AI model,

[0962] A system that includes this.

[0963] (Claim 2)

[0964] The system according to claim 1, wherein the automatically generated expression of gratitude is flexibly adjusted by referring to a past information set.

[0965] (Claim 3)

[0966] The system according to claim 1, wherein the modification suggestions provided by the information processing device are based on legal information.

[0967] "Application example 2 when combining with an emotional engine"

[0968] (Claim 1)

[0969] A means for an information processing device to analyze input information received from a user and to evaluate potential risks from legal, ethical, and social perspectives,

[0970] A means for automatically generating correction suggestions for the user based on the aforementioned evaluation,

[0971] A means of analyzing customer input information based on emotional state and providing feedback to optimize customer service operations,

[0972] A means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold,

[0973] A means by which the information processing device automatically generates an apology expression when the threshold is exceeded,

[0974] A means of presenting the aforementioned user with the aforementioned apology and countermeasures,

[0975] A means for analyzing multiple responses to the aforementioned post, classifying the sentiment of the text, and providing the user with the analysis results,

[0976] A system that includes this.

[0977] (Claim 2)

[0978] The system according to claim 1, wherein the automatically generated apology expression is flexibly customized by referring to past datasets.

[0979] (Claim 3)

[0980] The system according to claim 1, wherein the proposed modifications provided by the information processing device are based on a legal database. [Explanation of Symbols]

[0981] 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 for an information processing device to analyze input information received from a user and to evaluate potential risks from legal, ethical, and social perspectives, A means for automatically generating correction suggestions for the user based on the aforementioned evaluation, A means for monitoring external reactions to posted content in real time and detecting reactions that exceed a pre-set threshold, A means by which the information processing device automatically generates an apology expression when the threshold is exceeded, A means of presenting the aforementioned user with the aforementioned apology and countermeasures, A means for analyzing multiple responses to the aforementioned post, classifying the sentiment of the text, and providing the user with the analysis results, A system that includes this.

2. The system according to claim 1, wherein the automatically generated apology expression is flexibly customized by referring to past datasets.

3. The system according to claim 1, wherein the proposed modifications provided by the information processing device are based on a legal database.

Images