system

Abstract

We provide the system. [Solution] A means of analyzing electronic communications and scoring their degree of negativity based on criteria entered by the user, A means for evaluating and hiding communications that users find offensive, based on the aforementioned scoring, A means of determining whether a communication contains constructive opinions and, if necessary, allowing the user to display them, 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 persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 SNS and other online communication platforms, users often feel mental stress against unpleasant comments or aggressive remarks. In an environment where such unpleasant comments exist, there is a problem that it is difficult to comfortably and safely utilize online services. Also, since constructive opinions are mixed with unpleasant comments, there is also a problem that users cannot easily find valuable feedback.

Means for Solving the Problems

[0005] This invention makes it possible to efficiently hide offensive comments by using a means to analyze electronic communications and score their negativity based on user-defined criteria. Furthermore, by automatically analyzing the results and identifying and displaying comments containing constructive opinions as needed, it prevents users from missing out on valuable feedback. In addition, by utilizing machine learning algorithms based on natural language processing and user feedback, the accuracy of the scoring is improved, enabling filtering that is more tailored to individual users.

[0006] "User-defined criteria" refers to pre-set evaluation scales and conditions used to classify comments that users find offensive or opinions they perceive as constructive.

[0007] "Electronic communication" refers to the act of transmitting information such as messages, comments, and posts via electronic devices.

[0008] "Methods for scoring negativity" refer to methods of analyzing communication content and quantifying its negative nature and impact for evaluation.

[0009] "Means of evaluating whether to hide" refers to the process of preventing communications that are deemed not worth displaying to the user, based on their negativeness score, from being displayed on the system.

[0010] "Determining whether it contains constructive opinions" refers to the act of evaluating whether the content of a communication provides useful information or suggestions to the user or the recipient.

[0011] "Natural language processing" refers to computer technology that analyzes, understands, and generates text written in human language.

[0012] A "machine learning algorithm" refers to a computer process or method that learns patterns and rules from data and uses that knowledge to analyze and predict new data. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] 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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

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

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

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

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

[0019] In the following embodiments, the 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).

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

[0021] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0034] This invention provides a system that allows users to reduce the mental burden caused by offensive comments on social networking services (SNS) and other online platforms. This system operates around the user, the terminal, and the server, each playing a specific role.

[0035] 1. User settings

[0036] Users first install the application and connect it to their online account. Here, they can customize settings to distinguish between offensive and constructive comments. These settings include specifying keywords and criteria for comment tone.

[0037] 2. Collection and analysis of comments

[0038] The device collects comments related to the user on social media and sends them to a server. The server uses natural language processing technology to analyze these comments and score their degree of negativity. This scoring depends on the tone and context of the words used in the text.

[0039] 3. Filtering and display

[0040] Based on the scoring results, the server sends instructions to the device to hide comments whose level of discomfort exceeds the user-defined threshold. On the other hand, if a comment is deemed constructive, its content is displayed to the user by the device.

[0041] 4. Improving the user experience

[0042] Users can provide feedback on their satisfaction with the filtering results and suggest areas for improvement through the feedback function. This feedback is processed on the server and used to improve the accuracy of scoring and judgments through machine learning models.

[0043] Specific example

[0044] For example, if a user sets their preferences to "I accept criticism, but I want to avoid offensive language," the server will consider a comment like "This product has room for improvement" to be constructive and display it. However, a comment like "You are incompetent" will be deemed offensive and hidden. This allows users to have a more pleasant online experience.

[0045] In this way, the present invention specifically implements means to provide an environment in which users can use social networking services with peace of mind.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] Users install the application and link their social media accounts to it. They then set custom criteria to distinguish between "offensive comments" and "constructive comments." These criteria may include specific keywords or attributes.

[0049] Step 2:

[0050] The device monitors new comments related to users on social media and collects comment data as soon as it is detected. The collected comments are sent to a server for analysis.

[0051] Step 3:

[0052] The server analyzes received comments using a natural language processing engine. This analysis evaluates the text within the comments contextually and scores their degree of negativity.

[0053] Step 4:

[0054] Based on the scoring results, the server evaluates the comments using a threshold set by the user. Comments that exceed the threshold for offensiveness are deemed offensive and are instructed to be hidden.

[0055] Step 5:

[0056] The server further determines whether a comment is constructive. This is determined by whether the comment contains suggestions for improvement or raises issues. If it is deemed constructive, it will not be hidden and will be displayed to the user.

[0057] Step 6:

[0058] The device automatically applies filtering results according to instructions from the server. Comments deemed offensive will not be displayed on the user's screen, and only comments recognized as constructive will be shown.

[0059] Step 7:

[0060] Users can provide feedback on filtering through the app. This feedback is sent to the server.

[0061] Step 8:

[0062] The server uses the received feedback to improve the AI ​​model, enhancing the accuracy of scoring and judgments. This continuously improves the user experience for each individual user.

[0063] (Example 1)

[0064] 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."

[0065] Unpleasant information encountered by users online is a factor that increases their mental burden. However, current systems lack effective means of filtering this information, hindering users' comfortable browsing experience. Furthermore, methods for accurately determining whether information is useful are still immature and require improvement.

[0066] 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.

[0067] In this invention, the server includes means for analyzing information transmission and generating evaluation values ​​based on criteria entered by the user; means for evaluating information transmission that the user finds unpleasant based on the evaluation values ​​so as to hide it; and means for determining whether information transmission contains useful opinions and, if necessary, permitting the user to display them. This allows the user to effectively filter out unpleasant information transmission, enabling a comfortable user experience.

[0068] "User" refers to an individual or legal entity that uses the system to manage the transmission of offensive information.

[0069] "Information transmission" refers to forms of communication, such as comments and messages, that occur on online platforms.

[0070] "Analysis" refers to the process of using a computer to analyze the content of information transmission and evaluate its emotions and tone.

[0071] "Evaluation value" refers to a numerical value or indicator that shows the degree of negativity or constructiveness generated in response to the content of the information being conveyed.

[0072] "Filtering" refers to the process of hiding information that users find offensive.

[0073] "Useful opinions" refer to opinions that are beneficial in the context of information dissemination and contain constructive or helpful content for the user.

[0074] "Making something invisible" refers to the action of visually eliminating or hiding information that the user deems offensive.

[0075] A "server" refers to a central processing unit that analyzes information transmission and controls filtering and display.

[0076] This invention provides a system aimed at helping users avoid unpleasant online experiences through the analysis and filtering of information transmission. The system consists of a user's terminal, interfaces to various online platforms, and a server that performs information processing.

[0077] Users first install a dedicated application on their device and link it to their online account. Within this application, users enter custom filtering criteria, such as "avoid offensive language." This allows the device to collect relevant information in real time and send the data to a server.

[0078] The server analyzes the collected information transmission using Python and various natural language processing libraries (e.g., NLTK and spaCy). During this process, evaluation values ​​are generated and compared to thresholds set by the user. Based on these analysis results, the server returns filtering instructions to the terminal.

[0079] The terminal adjusts the information displayed to the user based on instructions from the server. Specifically, constructive information is displayed to the user, while information deemed offensive is hidden or displayed with a warning. Criteria for determining usefulness are also processed based on pre-set parameters.

[0080] Furthermore, users can provide feedback on filtering, which updates the generated AI model on the server, improving the accuracy of the analysis. For example, if a user sets the system to "show only constructive criticism," comments such as "there is room for improvement" will be displayed, while personal attacks such as "incompetent" will not be displayed.

[0081] An example of a prompt for a generative AI model would be: "Explain how the system should handle communication when the user is tolerant of criticism but wants to avoid offensive language."

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

[0083] Step 1:

[0084] The user installs the application on their device and links it to their online account. The user then enters filtering criteria into the app. These criteria include keywords and tones to avoid, forming the basis for the program to identify offensive information. This configuration information is sent from the device to the server.

[0085] Step 2:

[0086] The device collects information transmission in real time via an online platform API. The input consists of comments and message content. This data, including the type of information, sender, and posting timestamp, is ready to be sent to the server. The specific operation here involves data access and collection using the API.

[0087] Step 3:

[0088] The terminal sends the collected information transmission data to the server. The server receives it and starts analysis using a natural language processing library (e.g., NLTK, spaCy). The input is the information transmission data, and the output is an evaluation value indicating its degree of negativity. The specific operations are text analysis and tone evaluation scoring.

[0089] Step 4:

[0090] The server compares the generated evaluation value to a threshold set by the user. The inputs here are the evaluation value and user settings, and the output is a filtering instruction. The specific operation involves comparing the score value with the threshold. Based on this result, it is determined which information is displayed.

[0091] Step 5:

[0092] The server sends the filtering results as instructions to the terminal. Based on these instructions, the terminal decides whether to display or hide the information to the user. The input is the filtering instructions from the server, and the output is the updated information display status. The specific operations are information display control and screen updating.

[0093] Step 6:

[0094] The user provides feedback on the accuracy of the filtered information. The terminal collects this feedback and sends it to the server. The input is the feedback content, and the output is the transmitted data. The specific operation involves the user inputting their opinion and sending the data.

[0095] Step 7:

[0096] The server updates the generated AI model based on the received feedback, improving the accuracy of the analysis. The input in this process is the feedback data, and the output is the new model parameters. The specific operations are feedback analysis and model training.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] In physical stores, there is a challenge in that it is difficult for service providers to evaluate the quality of feedback they receive directly from customers in real time and to respond quickly and accurately based on that feedback. In particular, it is a significant burden to properly recognize negative feedback and identify what should be taken as constructive opinions.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for analyzing voice information and scoring its degree of negativity based on criteria entered by the user; means for evaluating, based on the scoring, whether to display information that the service provider finds unpleasant as a warning on a display device; and means for determining whether the voice information contains constructive opinions and, if necessary, permitting the service provider to display them. This enables the service provider to efficiently manage customer feedback and improve the quality of customer service.

[0102] "Auditory information" refers to information acquired as sound, and includes the speaker's intentions and content.

[0103] "Negativeness" is an indicator that shows how negative or critical the feedback is.

[0104] A "service provider" refers to an individual or organization that provides goods or services to a customer.

[0105] A "display device" is a device used to visually display information, and in this context, it includes glasses-type devices worn by service providers.

[0106] "Speech recognition technology" is a technology that converts speech into text and is used to extract context and content from audio information.

[0107] A "machine learning algorithm" is a mathematical method that uses large amounts of data to learn patterns and trends in that data, and then uses that learning for subsequent analysis and prediction.

[0108] The system realizing this invention has the function of analyzing customer feedback in physical stores in real time using speech recognition technology and natural language processing technology. When the server receives voice information, it scores the degree of negativity based on criteria set by the user. The software used in this process is a speech recognition library and a text analysis library. Specifically, the Python speech_recognition library is used to convert voice to text, and the TextBlob library is used to analyze the tone and content of the feedback.

[0109] Based on the analysis results, the server instructs the service provider to display warnings on display devices such as smart glasses if they perceive the information as highly negative. Conversely, information deemed constructive is notified to the service provider as needed. This process allows the service provider to quickly adjust customer responses and improve the customer experience.

[0110] For example, if a service provider receives real-time customer feedback such as "the selection of this product is not very good," the system scores the feedback. If it determines that the feedback is negative, "Negative Feedback Detected" will be displayed on the smart glasses, prompting service improvement. In this way, the quality of store operations can be enhanced.

[0111] An example of a prompt for a generative AI model is: "Create a program that performs real-time feedback analysis based on voice feedback from customers. If the feedback is negative, it should display a warning."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The device acquires voice feedback from customers using a microphone. The input is the voice spoken by the customer, which is processed by the device's built-in speech recognition function. The speech recognition technology converts the voice into text to obtain the output. Specifically, the process involves converting the voice to text using the Python `speech_recognition` library.

[0115] Step 2:

[0116] The terminal sends the converted text to the server. The server receives this text as input and analyzes the feedback content using natural language processing. The data processing performed here involves tone analysis using the TextBlob library, and a negativity score is generated as output. Specifically, the process involves analyzing the words and context of the text and then scoring them.

[0117] Step 3:

[0118] The server determines which feedback to display as a warning to the service provider based on the analyzed negativity score. The input is the negativity score obtained in step 2, a comparison operation is performed, and the result is output. Specifically, it compares the result to a predetermined threshold, and if it is determined to be negative, it generates a display command.

[0119] Step 4:

[0120] The server sends a display command to the terminal, and the terminal presents a warning to the service provider via a display device. The input is the display command sent from the server, and the output is a visual warning to the service provider. A specific operation involves a process that displays a message such as "Negative Feedback Detected" on a display device such as smart glasses.

[0121] 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.

[0122] This invention provides a negative comment filtering system that incorporates an emotion engine that recognizes the user's emotional state. The system aims to prevent the display of offensive comments on social networking services (SNS) and online platforms. The embodiments of this system are described in detail below.

[0123] 1. User settings and emotion recognition

[0124] Users install the application and connect their social media accounts. Users set criteria for comments they find offensive, which forms the basis for filtering. The device also has an emotion engine that recognizes the user's emotions in real time. The emotion engine determines the user's emotional state from their voice tone, facial expressions, and interactions during input.

[0125] 2. Comment Collection and Analysis

[0126] The device detects new comments related to the user on social media and sends them to the server. The server processes the comments using a natural language processing engine to analyze their context and keywords. Based on the analysis results, it scores the negativity of the comments.

[0127] 3. Dynamic threshold adjustment and filtering

[0128] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. A milder threshold is applied when the user is in a good mood, while a stricter threshold is applied when the user is feeling stressed or burdened. This filtering criterion is used to select which comments are displayed to the user.

[0129] 4. Display and feedback to the user

[0130] Only comments that have been filtered will be displayed on the device. Users can review the displayed comments and provide feedback. This feedback is processed on the server and used to improve the accuracy of the sentiment engine and filtering criteria.

[0131] Specific example

[0132] For example, if the emotion engine detects that a user is feeling down, the server sets a higher threshold, deeming even minor negative elements offensive and hiding them. On another day, if the user is perceived as feeling good, the threshold is lowered, and even slightly critical comments are displayed. In this way, the present invention achieves flexible comment filtering tailored to the emotions of individual users.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] Users install the application and link their social media accounts to it. Within the app, users can set criteria for what constitutes an offensive or constructive comment.

[0136] Step 2:

[0137] The device captures voice tone, facial expressions, input patterns, and other data to recognize the user's emotional state in real time. This allows the emotion engine to determine the user's psychological state.

[0138] Step 3:

[0139] The device detects comments related to the user on social media and sends that data to the server each time a new comment is posted.

[0140] Step 4:

[0141] The server analyzes received comments using natural language processing techniques and scores their degree of negativity. This analysis utilizes the context of the comment and the keywords it contains.

[0142] Step 5:

[0143] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. It lowers the threshold when the user is feeling down and raises it when they are feeling positive.

[0144] Step 6:

[0145] The server decides whether to hide comments deemed negative based on adjusted thresholds. Comments deemed constructive remain visible.

[0146] Step 7:

[0147] The terminal receives instructions from the server, filters the target comments, and displays them on the user screen. Hidden comments are kept invisible to the user.

[0148] Step 8:

[0149] Users can provide feedback on the displayed comments, including their thoughts and opinions, and this feedback is sent to the server.

[0150] Step 9:

[0151] The server uses feedback to improve its sentiment engine and filtering algorithms, which will then be used for future comment analysis. This will enable the delivery of a more personalized user experience.

[0152] (Example 2)

[0153] 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".

[0154] There is a need to efficiently filter comments that users find offensive on social media and online platforms, while flexibly adjusting the criteria for selecting comments according to the user's emotional state. Furthermore, utilizing user feedback on filtered comments to further improve the accuracy of the filtering process is a crucial challenge.

[0155] 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.

[0156] In this invention, the server includes means for analyzing electronic communications and scoring the degree of negativity based on criteria entered by the user, means for recognizing the user's emotional state in real time and dynamically adjusting the threshold for negativity according to that emotional state, and means for providing a machine learning algorithm that improves the accuracy of negativity scoring based on user feedback. This enables flexible filtering optimized for each user and continuous improvement of accuracy.

[0157] "Electronic communication" refers to information such as text, images, audio, and video that is sent and received via the internet or communication networks.

[0158] "Negativeness" refers to the degree to which a comment or piece of information is evaluated as negative or critical, expressed as a numerical value or score.

[0159] "Real-time recognition" means processing data instantly and making instantaneous judgments about the current situation and state.

[0160] A "threshold" refers to a numerical value or range that serves as a standard for determining whether a particular condition is exceeded.

[0161] "Feedback" refers to the opinions and reactions that users provide regarding the results and behavior of a system.

[0162] A "machine learning algorithm" is a computational method for making predictions and decisions by learning from data and analyzing patterns and rules.

[0163] This invention is a system for filtering comments received by users from social networking services (SNS) and online platforms. The system recognizes the user's emotional state in real time and dynamically adjusts the filtering criteria based on that information to select which comments to display to the user.

[0164] Users install the application on devices such as smartphones and computers, and connect to their social networking service (SNS) accounts through this application. The application has a function that allows users to set criteria for comments they find offensive, and these criteria form the basis of the filtering process.

[0165] The device is equipped with an emotion engine that analyzes voice tone, facial expressions, typing patterns, and other factors. This emotion engine can determine the user's emotional state in real time and classify it into categories such as "positive," "neutral," and "negative." Based on the user's emotional state, the server adjusts the threshold for negativity and performs comment filtering.

[0166] The server processes received comments through a natural language processing engine. This engine analyzes the context and keywords of the communication and scores the negativity of the comments based on the information obtained. Based on the threshold set as the filtering criterion, it decides whether to hide comments with a high negativity score.

[0167] Users can provide feedback on filtered comments. The server then collects this feedback and applies machine learning algorithms to improve the accuracy of the filtering. By repeating this process, the system's adaptability is enhanced, and the user experience is improved.

[0168] For example, if the emotion engine detects that a user is feeling down, the threshold will be set higher, and more comments will be filtered out. On the other hand, if the user is perceived as feeling good, the threshold will be lowered, and critical comments may also be displayed.

[0169] An example of a prompt to input into a generative AI model is: "Please describe a system that filters comments a user receives from social media. In particular, please describe in detail how the sentiment engine works and how the filtering criteria are dynamically adjusted."

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The user installs the application on their device and connects their social media account. The user sets filtering criteria. This requires the user's authentication information and filtering criteria as input. The application saves the settings information as output, which is then used in subsequent processes.

[0173] Step 2:

[0174] The device uses an emotion engine to recognize the user's emotional state in real time. For example, it receives sensor data that detects voice tone, facial expressions, and input speed as input, and analyzes the emotional state. The output is a classification of the emotional state as either "positive," "neutral," or "negative."

[0175] Step 3:

[0176] The device periodically detects new comments on social media. This involves obtaining the comment's text data and the date and time it was posted as input. This data is then converted into data packets for transmission to the server and output.

[0177] Step 4:

[0178] The server analyzes the received comment data using a natural language processing engine. The input consists of the comment text data and associated metadata. Using this, the server extracts the context and keywords of the comments and scores their negativity. The output is the negativity score for each comment.

[0179] Step 5:

[0180] The server dynamically adjusts the negativity threshold based on the emotional state received from the terminal. The input is the classified emotional state and the negativity score. The server sets a more lenient threshold for "positive" emotional states and a stricter threshold for "negative" states. The output is the adjusted threshold.

[0181] Step 6:

[0182] The server filters comments according to a threshold and sends the selected comments to the terminal. The input is the adjusted threshold and the negativity score of the comments. The output is a list of comments that should be displayed to the user.

[0183] Step 7:

[0184] Users provide feedback on the displayed comments. The device sends this feedback as input to the server. The output is the user's feedback data. This feedback allows the server to use machine learning algorithms to improve the accuracy of filtering.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] The vast amount of information users receive online sometimes includes communications that are unpleasant for them. Furthermore, there is a lack of systems that dynamically display appropriate information based on each user's emotional state. Therefore, there is a need to create an environment where users can use online services more comfortably without experiencing stress.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes means for analyzing electronic communications and scoring their negativity based on user-defined criteria and real-time recognized emotional states; means for disclosing communications that the user finds unpleasant by dynamically adjusting thresholds based on the scoring and emotional states; and means for determining whether communications contain constructive opinions and relevant information according to the user's emotional state, and for allowing display or selecting appropriate information as necessary. This enables filtering and selection of information that matches the user's emotional state.

[0190] "User-defined criteria" are indicators used by users to determine the degree of negativity, based on their own preferences and comfort levels.

[0191] "Real-time recognized emotional state" refers to a state in which the user's current emotions are analyzed and identified in real time using emotion recognition technology.

[0192] "Electronic communication" is a general term for messages and posts delivered to users via the internet, and includes formats such as text, audio, and video.

[0193] "Scoring the degree of negativity" means evaluating the context and content of a received communication and assigning a score to the degree of negative elements contained within it.

[0194] "Dynamic threshold adjustment based on emotional state" is a process that flexibly changes the threshold for the negativity score according to the user's emotional state.

[0195] "Hide evaluation" refers to the act of deciding not to display specific communications to users based on the scoring results.

[0196] "Determining whether a communication contains constructive opinions" means analyzing whether the communication provides useful and valuable information to the user.

[0197] "Identifying relevant information based on emotional state" is the process of selecting the information most relevant to the user's current emotions.

[0198] "Selecting the right information" means choosing the most appropriate content to provide information that matches the user's emotional state and needs.

[0199] To implement this invention, it is necessary to construct a negative comment filtering system that utilizes emotion recognition technology. The system primarily operates via the user's terminal and a server.

[0200] The user's device will be equipped with a face-tracking camera and microphone to recognize emotions in real time. An emotion engine will analyze the user's facial expressions and voice tone to identify their emotional state in real time. The AI ​​model used for emotion recognition could be, for example, the "Emotion API."

[0201] The server analyzes electronic communications based on user-defined criteria and the user's emotional state as perceived in real time. It scores the negativity of communications using natural language processing technology (e.g., Google Cloud Natural Language) and applies dynamic thresholds based on the user's emotional state. This allows the server to select content to display and evaluate whether to hide offensive communications.

[0202] Users can improve the system's accuracy by providing feedback. The server uses machine learning algorithms to improve filtering accuracy based on user feedback and changes in emotional state.

[0203] For example, if the emotion engine detects that a user is feeling down, the server will set a higher threshold and hide even minor negative elements. Additionally, advertisements for relaxation-related products will be prioritized for users experiencing stress.

[0204] An example of a prompt statement to input to a generative AI model is written as follows:

[0205] "Analyze the user's voice tone and facial expressions to identify their emotional state today. If they need to relax, suggest advertisements for the most suitable relaxation products."

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The server receives voice tone and facial expression data transmitted in real time from the user's device. The input data includes an emotion score obtained through an emotion recognition API. The server analyzes this data to determine the user's emotional state.

[0209] Step 2:

[0210] The user sets criteria for negativity through the application. Based on this, the server determines a dynamic threshold for scoring the negativity of the communication. The user's set criteria are input into the scoring engine, and an appropriate threshold is output.

[0211] Step 3:

[0212] The device sends electronic communication data obtained from social networking services (SNS) and online platforms to the server. The input data consists of comments and messages in text format. The server uses a natural language processing engine to analyze the context and keywords of the comments and score their degree of negativity.

[0213] Step 4:

[0214] The server compares the scoring results with the user's real-time emotional state to decide whether to display or hide the communication. The inputs are the scoring results and the emotional state, and the output is returned to the user's terminal as whether or not the communication should be displayed.

[0215] Step 5:

[0216] Users review filtered communications and provide feedback as needed. The server inputs this feedback into a machine learning algorithm to improve filtering accuracy. The output represents the algorithm's learning results and will be reflected in future filtering.

[0217] Step 6:

[0218] The server selects the most appropriate ads and relevant information based on the user's emotional state. Based on the sentiment score, it selects content that meets the user's needs and outputs it to the ad display management platform. This ensures that users receive information that resonates with their emotions.

[0219] Step 7:

[0220] The AI ​​model receives prompts that inform it of changes in the user's emotional state and provide optimal information. These prompts are generated based on an emotional state scoring result and input into the AI ​​model. The output is an optimized suggestion of the information the user is seeking.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention provides a system that allows users to reduce the mental burden caused by offensive comments on social networking services (SNS) and other online platforms. This system operates around the user, the terminal, and the server, each playing a specific role.

[0238] 1. User settings

[0239] Users first install the application and connect it to their online account. Here, they can customize settings to distinguish between offensive and constructive comments. These settings include specifying keywords and criteria for comment tone.

[0240] 2. Collection and analysis of comments

[0241] The device collects comments related to the user on social media and sends them to a server. The server uses natural language processing technology to analyze these comments and score their degree of negativity. This scoring depends on the tone and context of the words used in the text.

[0242] 3. Filtering and display

[0243] Based on the scoring results, the server sends instructions to the device to hide comments whose level of discomfort exceeds the user-defined threshold. On the other hand, if a comment is deemed constructive, its content is displayed to the user by the device.

[0244] 4. Improving the user experience

[0245] Users can provide feedback on their satisfaction with the filtering results and suggest areas for improvement through the feedback function. This feedback is processed on the server and used to improve the accuracy of scoring and judgments through machine learning models.

[0246] Specific example

[0247] For example, if a user sets their preferences to "I accept criticism, but I want to avoid offensive language," the server will consider a comment like "This product has room for improvement" to be constructive and display it. However, a comment like "You are incompetent" will be deemed offensive and hidden. This allows users to have a more pleasant online experience.

[0248] In this way, the present invention specifically implements means to provide an environment in which users can use social networking services with peace of mind.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] Users install the application and link their social media accounts to it. They then set custom criteria to distinguish between "offensive comments" and "constructive comments." These criteria may include specific keywords or attributes.

[0252] Step 2:

[0253] The device monitors new comments related to users on social media and collects comment data as soon as it is detected. The collected comments are sent to a server for analysis.

[0254] Step 3:

[0255] The server analyzes received comments using a natural language processing engine. This analysis evaluates the text within the comments contextually and scores their degree of negativity.

[0256] Step 4:

[0257] Based on the scoring results, the server evaluates the comments using a threshold set by the user. Comments that exceed the threshold for offensiveness are deemed offensive and are instructed to be hidden.

[0258] Step 5:

[0259] The server further determines whether a comment is constructive. This is determined by whether the comment contains suggestions for improvement or raises issues. If it is deemed constructive, it will not be hidden and will be displayed to the user.

[0260] Step 6:

[0261] The device automatically applies filtering results according to instructions from the server. Comments deemed offensive will not be displayed on the user's screen, and only comments recognized as constructive will be shown.

[0262] Step 7:

[0263] Users can provide feedback on filtering through the app. This feedback is sent to the server.

[0264] Step 8:

[0265] The server uses the received feedback to improve the AI ​​model, enhancing the accuracy of scoring and judgments. This continuously improves the user experience for each individual user.

[0266] (Example 1)

[0267] 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."

[0268] Unpleasant information encountered by users online is a factor that increases their mental burden. However, current systems lack effective means of filtering this information, hindering users' comfortable browsing experience. Furthermore, methods for accurately determining whether information is useful are still immature and require improvement.

[0269] 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.

[0270] In this invention, the server includes means for analyzing information transmission and generating evaluation values ​​based on criteria entered by the user; means for evaluating information transmission that the user finds unpleasant based on the evaluation values ​​so as to hide it; and means for determining whether information transmission contains useful opinions and, if necessary, permitting the user to display them. This allows the user to effectively filter out unpleasant information transmission, enabling a comfortable user experience.

[0271] "User" refers to an individual or legal entity that uses the system to manage the transmission of offensive information.

[0272] "Information transmission" refers to forms of communication, such as comments and messages, that occur on online platforms.

[0273] "Analysis" refers to the process of using a computer to analyze the content of information transmission and evaluate its emotions and tone.

[0274] "Evaluation value" refers to a numerical value or indicator that shows the degree of negativity or constructiveness generated in response to the content of the information being conveyed.

[0275] "Filtering" refers to the process of hiding information that users find offensive.

[0276] "Useful opinions" refer to opinions that are beneficial in the context of information dissemination and contain constructive or helpful content for the user.

[0277] "Making something invisible" refers to the action of visually eliminating or hiding information that the user deems offensive.

[0278] A "server" refers to a central processing unit that analyzes information transmission and controls filtering and display.

[0279] This invention provides a system aimed at enabling users to avoid unpleasant online experiences through the analysis and filtering of information transmission. The system consists of a user's terminal, an interface with various online platforms, and a server for information processing.

[0280] First, the user installs a dedicated application on the terminal and links the online account. On this application, the user inputs filtering criteria such as "avoid aggressive expressions" as custom settings. Thereby, the terminal collects relevant information transmissions in real time and sends the data to the server.

[0281] The server analyzes the collected information transmissions using Python and various natural language processing libraries (e.g., NLTK and spaCy). In this process, an evaluation value is generated and compared with the threshold set by the user. Based on this analysis result, the server returns a filtering instruction to the terminal.

[0282] The terminal adjusts the information transmissions visible to the user based on the server's instructions. That is, constructive information transmissions are displayed to the user, and information transmissions judged to be unpleasant are either not displayed or displayed with a warning. The criteria for judging usefulness are also processed based on pre-set parameters.

[0283] Furthermore, the user can provide feedback regarding filtering, thereby updating the generated AI model on the server and improving the analysis accuracy. As a specific example, when the user sets "display only constructive criticism", comments like "there is room for improvement" are displayed, while personal attack comments like "you are incompetent" are processed as not displayed.

[0284] Examples of prompt texts for the generated AI model include "When the user is tolerant of criticism but wants to avoid aggressive words, please explain how the system should process information transmissions."

[0285] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0286] Step 1:

[0287] The user installs an application on the terminal and links it to their online account. The user inputs filtering criteria into the application. The input here is based on keywords or tone criteria to be avoided, thereby forming a basis for the program to identify unpleasant information transmission. This setting information is sent from the terminal to the server.

[0288] Step 2:

[0289] The terminal collects information transmission in real time via the online platform API. The input is the content of comments or messages. This data includes the type of information, the sender, and the posting timestamp, and is ready to be sent to the server. The specific operation here is data access and collection using the API.

[0290] Step 3:

[0291] The terminal sends the collected information transmission data to the server. The server receives it and starts analysis using a natural language processing library (e.g., NLTK, spaCy). The input is the information transmission data, and the output is an evaluation value indicating its negativity. The specific operation is text analysis and tone evaluation scoring.

[0292] Step 4:

[0293] The server compares the generated evaluation value with the threshold set by the user. The input here is the evaluation value and the user setting, and the output is a filtering instruction. The specific operation is a comparison operation between the score value and the threshold. Based on this result, it is determined which information will be displayed.

[0294] Step 5:

[0295] The server sends the filtering results as instructions to the terminal. Based on these instructions, the terminal decides whether to display or hide the information to the user. The input is the filtering instructions from the server, and the output is the updated information display status. The specific operations are information display control and screen updating.

[0296] Step 6:

[0297] The user provides feedback on the accuracy of the filtered information. The terminal collects this feedback and sends it to the server. The input is the feedback content, and the output is the transmitted data. The specific operation involves the user inputting their opinion and sending the data.

[0298] Step 7:

[0299] The server updates the generated AI model based on the received feedback, improving the accuracy of the analysis. The input in this process is the feedback data, and the output is the new model parameters. The specific operations are feedback analysis and model training.

[0300] (Application Example 1)

[0301] 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."

[0302] In physical stores, there is a challenge in that it is difficult for service providers to evaluate the quality of feedback they receive directly from customers in real time and to respond quickly and accurately based on that feedback. In particular, it is a significant burden to properly recognize negative feedback and identify what should be taken as constructive opinions.

[0303] 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.

[0304] In this invention, the server includes means for analyzing voice information and scoring the degree of negativity based on the criteria input by the user, means for evaluating, based on the scoring, to display information that the service provider feels uncomfortable about on the display device as a warning, and means for determining whether the voice information contains constructive opinions and permitting the display to the service provider as necessary. Thereby, it becomes possible for the service provider to efficiently manage customer feedback and improve the quality of customer service.

[0305] "Voice information" refers to information obtained as voice and includes the intentions and contents of the speaker.

[0306] "Degree of negativity" is an index indicating how negative or critical the feedback content is.

[0307] "Service provider" refers to an individual or group that provides goods or services to customers.

[0308] "Display device" is a device for visually displaying information, and here it includes the glasses-type device worn by the service provider.

[0309] "Voice recognition technology" is a technology for converting voice into text and is used to extract context and content from voice information.

[0310] "Machine learning algorithm" is a mathematical method that learns the patterns and trends of a large amount of data based on those data and is used for subsequent analysis and prediction.

[0311] The system realizing this invention has the function of analyzing customer feedback in physical stores in real time using speech recognition technology and natural language processing technology. When the server receives voice information, it scores the degree of negativity based on criteria set by the user. The software used in this process is a speech recognition library and a text analysis library. Specifically, the Python speech_recognition library is used to convert voice to text, and the TextBlob library is used to analyze the tone and content of the feedback.

[0312] Based on the analysis results, the server instructs the service provider to display warnings on display devices such as smart glasses if they perceive the information as highly negative. Conversely, information deemed constructive is notified to the service provider as needed. This process allows the service provider to quickly adjust customer responses and improve the customer experience.

[0313] For example, if a service provider receives real-time customer feedback such as "the selection of this product is not very good," the system scores the feedback. If it determines that the feedback is negative, "Negative Feedback Detected" will be displayed on the smart glasses, prompting service improvement. In this way, the quality of store operations can be enhanced.

[0314] An example of a prompt for a generative AI model is: "Create a program that performs real-time feedback analysis based on voice feedback from customers. If the feedback is negative, it should display a warning."

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The device acquires voice feedback from customers using a microphone. The input is the voice spoken by the customer, which is processed by the device's built-in speech recognition function. The speech recognition technology converts the voice into text to obtain the output. Specifically, the process involves converting the voice to text using the Python `speech_recognition` library.

[0318] Step 2:

[0319] The terminal sends the converted text to the server. The server receives this text as input and analyzes the feedback content using natural language processing. The data processing performed here involves tone analysis using the TextBlob library, and a negativity score is generated as output. Specifically, the process involves analyzing the words and context of the text and then scoring them.

[0320] Step 3:

[0321] The server determines which feedback to display as a warning to the service provider based on the analyzed negativity score. The input is the negativity score obtained in step 2, a comparison operation is performed, and the result is output. Specifically, it compares the result to a predetermined threshold, and if it is determined to be negative, it generates a display command.

[0322] Step 4:

[0323] The server sends a display command to the terminal, and the terminal presents a warning to the service provider via a display device. The input is the display command sent from the server, and the output is a visual warning to the service provider. A specific operation involves a process that displays a message such as "Negative Feedback Detected" on a display device such as smart glasses.

[0324] 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.

[0325] This invention provides a negative comment filtering system that incorporates an emotion engine that recognizes the user's emotional state. The system aims to prevent the display of offensive comments on social networking services (SNS) and online platforms. The embodiments of this system are described in detail below.

[0326] 1. User settings and emotion recognition

[0327] Users install the application and connect their social media accounts. Users set criteria for comments they find offensive, which forms the basis for filtering. The device also has an emotion engine that recognizes the user's emotions in real time. The emotion engine determines the user's emotional state from their voice tone, facial expressions, and interactions during input.

[0328] 2. Comment Collection and Analysis

[0329] The device detects new comments related to the user on social media and sends them to the server. The server processes the comments using a natural language processing engine to analyze their context and keywords. Based on the analysis results, it scores the negativity of the comments.

[0330] 3. Dynamic threshold adjustment and filtering

[0331] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. A milder threshold is applied when the user is in a good mood, while a stricter threshold is applied when the user is feeling stressed or burdened. This filtering criterion is used to select which comments are displayed to the user.

[0332] 4. Display and feedback to the user

[0333] Only comments that have been filtered will be displayed on the device. Users can review the displayed comments and provide feedback. This feedback is processed on the server and used to improve the accuracy of the sentiment engine and filtering criteria.

[0334] Specific example

[0335] For example, if the emotion engine detects that a user is feeling down, the server sets a higher threshold, deeming even minor negative elements offensive and hiding them. On another day, if the user is perceived as feeling good, the threshold is lowered, and even slightly critical comments are displayed. In this way, the present invention achieves flexible comment filtering tailored to the emotions of individual users.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] Users install the application and link their social media accounts to it. Within the app, users can set criteria for what constitutes an offensive or constructive comment.

[0339] Step 2:

[0340] The device captures voice tone, facial expressions, input patterns, and other data to recognize the user's emotional state in real time. This allows the emotion engine to determine the user's psychological state.

[0341] Step 3:

[0342] The device detects comments related to the user on social media and sends that data to the server each time a new comment is posted.

[0343] Step 4:

[0344] The server analyzes received comments using natural language processing techniques and scores their degree of negativity. This analysis utilizes the context of the comment and the keywords it contains.

[0345] Step 5:

[0346] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. It lowers the threshold when the user is feeling down and raises it when they are feeling positive.

[0347] Step 6:

[0348] The server decides whether to hide comments deemed negative based on adjusted thresholds. Comments deemed constructive remain visible.

[0349] Step 7:

[0350] The terminal receives instructions from the server, filters the target comments, and displays them on the user screen. Hidden comments are kept invisible to the user.

[0351] Step 8:

[0352] Users can provide feedback on the displayed comments, including their thoughts and opinions, and this feedback is sent to the server.

[0353] Step 9:

[0354] The server uses feedback to improve its sentiment engine and filtering algorithms, which will then be used for future comment analysis. This will enable the delivery of a more personalized user experience.

[0355] (Example 2)

[0356] 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".

[0357] There is a need to efficiently filter comments that users find offensive on social media and online platforms, while flexibly adjusting the criteria for selecting comments according to the user's emotional state. Furthermore, utilizing user feedback on filtered comments to further improve the accuracy of the filtering process is a crucial challenge.

[0358] 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.

[0359] In this invention, the server includes means for analyzing electronic communications and scoring the degree of negativity based on criteria entered by the user, means for recognizing the user's emotional state in real time and dynamically adjusting the threshold for negativity according to that emotional state, and means for providing a machine learning algorithm that improves the accuracy of negativity scoring based on user feedback. This enables flexible filtering optimized for each user and continuous improvement of accuracy.

[0360] "Electronic communication" refers to information such as text, images, audio, and video that is sent and received via the internet or communication networks.

[0361] "Negativeness" refers to the degree to which a comment or piece of information is evaluated as negative or critical, expressed as a numerical value or score.

[0362] "Real-time recognition" means processing data instantly and making instantaneous judgments about the current situation and state.

[0363] A "threshold" refers to a numerical value or range that serves as a standard for determining whether a particular condition is exceeded.

[0364] "Feedback" refers to the opinions and reactions that users provide regarding the results and behavior of a system.

[0365] A "machine learning algorithm" is a computational method for making predictions and decisions by learning from data and analyzing patterns and rules.

[0366] This invention is a system for filtering comments received by users from social networking services (SNS) and online platforms. The system recognizes the user's emotional state in real time and dynamically adjusts the filtering criteria based on that information to select which comments to display to the user.

[0367] Users install the application on devices such as smartphones and computers, and connect to their social networking service (SNS) accounts through this application. The application has a function that allows users to set criteria for comments they find offensive, and these criteria form the basis of the filtering process.

[0368] The device is equipped with an emotion engine that analyzes voice tone, facial expressions, typing patterns, and other factors. This emotion engine can determine the user's emotional state in real time and classify it into categories such as "positive," "neutral," and "negative." Based on the user's emotional state, the server adjusts the threshold for negativity and performs comment filtering.

[0369] The server processes received comments through a natural language processing engine. This engine analyzes the context and keywords of the communication and scores the negativity of the comments based on the information obtained. Based on the threshold set as the filtering criterion, it decides whether to hide comments with a high negativity score.

[0370] Users can provide feedback on filtered comments. The server then collects this feedback and applies machine learning algorithms to improve the accuracy of the filtering. By repeating this process, the system's adaptability is enhanced, and the user experience is improved.

[0371] For example, if the emotion engine detects that a user is feeling down, the threshold will be set higher, and more comments will be filtered out. On the other hand, if the user is perceived as feeling good, the threshold will be lowered, and critical comments may also be displayed.

[0372] An example of a prompt to input into a generative AI model is: "Please describe a system that filters comments a user receives from social media. In particular, please describe in detail how the sentiment engine works and how the filtering criteria are dynamically adjusted."

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The user installs the application on their device and connects their social media account. The user sets filtering criteria. This requires the user's authentication information and filtering criteria as input. The application saves the settings information as output, which is then used in subsequent processes.

[0376] Step 2:

[0377] The device uses an emotion engine to recognize the user's emotional state in real time. For example, it receives sensor data that detects voice tone, facial expressions, and input speed as input, and analyzes the emotional state. The output is a classification of the emotional state as either "positive," "neutral," or "negative."

[0378] Step 3:

[0379] The device periodically detects new comments on social media. This involves obtaining the comment's text data and the date and time it was posted as input. This data is then converted into data packets for transmission to the server and output.

[0380] Step 4:

[0381] The server analyzes the received comment data using a natural language processing engine. The input consists of the comment text data and associated metadata. Using this, the server extracts the context and keywords of the comments and scores their negativity. The output is the negativity score for each comment.

[0382] Step 5:

[0383] The server dynamically adjusts the negativity threshold based on the emotional state received from the terminal. The input is the classified emotional state and the negativity score. The server sets a more lenient threshold for "positive" emotional states and a stricter threshold for "negative" states. The output is the adjusted threshold.

[0384] Step 6:

[0385] The server filters comments according to a threshold and sends the selected comments to the terminal. The input is the adjusted threshold and the negativity score of the comments. The output is a list of comments that should be displayed to the user.

[0386] Step 7:

[0387] Users provide feedback on the displayed comments. The device sends this feedback as input to the server. The output is the user's feedback data. This feedback allows the server to use machine learning algorithms to improve the accuracy of filtering.

[0388] (Application Example 2)

[0389] 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."

[0390] The vast amount of information users receive online sometimes includes communications that are unpleasant for them. Furthermore, there is a lack of systems that dynamically display appropriate information based on each user's emotional state. Therefore, there is a need to create an environment where users can use online services more comfortably without experiencing stress.

[0391] 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.

[0392] In this invention, the server includes means for analyzing electronic communications and scoring their negativity based on user-defined criteria and real-time recognized emotional states; means for disclosing communications that the user finds unpleasant by dynamically adjusting thresholds based on the scoring and emotional states; and means for determining whether communications contain constructive opinions and relevant information according to the user's emotional state, and for allowing display or selecting appropriate information as necessary. This enables filtering and selection of information that matches the user's emotional state.

[0393] "User-defined criteria" are indicators used by users to determine the degree of negativity, based on their own preferences and comfort levels.

[0394] "Real-time recognized emotional state" refers to a state in which the user's current emotions are analyzed and identified in real time using emotion recognition technology.

[0395] "Electronic communication" is a general term for messages and posts delivered to users via the internet, and includes formats such as text, audio, and video.

[0396] "Scoring the degree of negativity" means evaluating the context and content of a received communication and assigning a score to the degree of negative elements contained within it.

[0397] "Dynamic threshold adjustment based on emotional state" is a process that flexibly changes the threshold for the negativity score according to the user's emotional state.

[0398] "Hide evaluation" refers to the act of deciding not to display specific communications to users based on the scoring results.

[0399] "Determining whether a communication contains constructive opinions" means analyzing whether the communication provides useful and valuable information to the user.

[0400] "Identifying relevant information based on emotional state" is the process of selecting the information most relevant to the user's current emotions.

[0401] "Selecting the right information" means choosing the most appropriate content to provide information that matches the user's emotional state and needs.

[0402] To implement this invention, it is necessary to construct a negative comment filtering system that utilizes emotion recognition technology. The system primarily operates via the user's terminal and a server.

[0403] The user's device will be equipped with a face-tracking camera and microphone to recognize emotions in real time. An emotion engine will analyze the user's facial expressions and voice tone to identify their emotional state in real time. The AI ​​model used for emotion recognition could be, for example, the "Emotion API."

[0404] The server analyzes electronic communications based on user-defined criteria and the user's emotional state as perceived in real time. It scores the negativity of communications using natural language processing techniques (e.g., Google Cloud Natural Language) and applies dynamic thresholds based on the user's emotional state. This allows the server to select content to display and evaluate whether to hide offensive communications.

[0405] Users can improve the system's accuracy by providing feedback. The server uses machine learning algorithms to improve filtering accuracy based on user feedback and changes in emotional state.

[0406] For example, if the emotion engine detects that a user is feeling down, the server will set a higher threshold and hide even minor negative elements. Additionally, advertisements for relaxation-related products will be prioritized for users experiencing stress.

[0407] An example of a prompt statement to input to a generative AI model is written as follows:

[0408] "Analyze the user's voice tone and facial expressions to identify their emotional state today. If they need to relax, suggest advertisements for the most suitable relaxation products."

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The server receives voice tone and facial expression data transmitted in real time from the user's device. The input data includes an emotion score obtained through an emotion recognition API. The server analyzes this data to determine the user's emotional state.

[0412] Step 2:

[0413] The user sets criteria for negativity through the application. Based on this, the server determines a dynamic threshold for scoring the negativity of the communication. The user's set criteria are input into the scoring engine, and an appropriate threshold is output.

[0414] Step 3:

[0415] The device sends electronic communication data obtained from social networking services (SNS) and online platforms to the server. The input data consists of comments and messages in text format. The server uses a natural language processing engine to analyze the context and keywords of the comments and score their degree of negativity.

[0416] Step 4:

[0417] The server compares the scoring results with the user's real-time emotional state to decide whether to display or hide the communication. The inputs are the scoring results and the emotional state, and the output is returned to the user's terminal as whether or not the communication should be displayed.

[0418] Step 5:

[0419] Users review filtered communications and provide feedback as needed. The server inputs this feedback into a machine learning algorithm to improve filtering accuracy. The output represents the algorithm's learning results and will be reflected in future filtering.

[0420] Step 6:

[0421] The server selects the most appropriate ads and relevant information based on the user's emotional state. Based on the sentiment score, it selects content that meets the user's needs and outputs it to the ad display management platform. This ensures that users receive information that resonates with their emotions.

[0422] Step 7:

[0423] The AI ​​model receives prompts that inform it of changes in the user's emotional state and provide optimal information. These prompts are generated based on an emotional state scoring result and input into the AI ​​model. The output is an optimized suggestion of the information the user is seeking.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention provides a system that allows users to reduce the mental burden caused by offensive comments on social networking services (SNS) and other online platforms. This system operates around the user, the terminal, and the server, each playing a specific role.

[0441] 1. User settings

[0442] Users first install the application and connect it to their online account. Here, they can customize settings to distinguish between offensive and constructive comments. These settings include specifying keywords and criteria for comment tone.

[0443] 2. Collection and analysis of comments

[0444] The device collects comments related to the user on social media and sends them to a server. The server uses natural language processing technology to analyze these comments and score their degree of negativity. This scoring depends on the tone and context of the words used in the text.

[0445] 3. Filtering and display

[0446] Based on the scoring results, the server sends instructions to the device to hide comments whose level of discomfort exceeds the user-defined threshold. On the other hand, if a comment is deemed constructive, its content is displayed to the user by the device.

[0447] 4. Improving the user experience

[0448] Users can provide feedback on their satisfaction with the filtering results and suggest areas for improvement through the feedback function. This feedback is processed on the server and used to improve the accuracy of scoring and judgments through machine learning models.

[0449] Specific example

[0450] For example, if a user sets their preferences to "I accept criticism, but I want to avoid offensive language," the server will consider a comment like "This product has room for improvement" to be constructive and display it. However, a comment like "You are incompetent" will be deemed offensive and hidden. This allows users to have a more pleasant online experience.

[0451] In this way, the present invention specifically implements means to provide an environment in which users can use social networking services with peace of mind.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] Users install the application and link their social media accounts to it. They then set custom criteria to distinguish between "offensive comments" and "constructive comments." These criteria may include specific keywords or attributes.

[0455] Step 2:

[0456] The device monitors new comments related to users on social media and collects comment data as soon as it is detected. The collected comments are sent to a server for analysis.

[0457] Step 3:

[0458] The server analyzes received comments using a natural language processing engine. This analysis evaluates the text within the comments contextually and scores their degree of negativity.

[0459] Step 4:

[0460] Based on the scoring results, the server evaluates the comments using a threshold set by the user. Comments that exceed the threshold for offensiveness are deemed offensive and are instructed to be hidden.

[0461] Step 5:

[0462] The server further determines whether a comment is constructive. This is determined by whether the comment contains suggestions for improvement or raises issues. If it is deemed constructive, it will not be hidden and will be displayed to the user.

[0463] Step 6:

[0464] The device automatically applies filtering results according to instructions from the server. Comments deemed offensive will not be displayed on the user's screen, and only comments recognized as constructive will be shown.

[0465] Step 7:

[0466] Users can provide feedback on filtering through the app. This feedback is sent to the server.

[0467] Step 8:

[0468] The server uses the received feedback to improve the AI ​​model, enhancing the accuracy of scoring and judgments. This continuously improves the user experience for each individual user.

[0469] (Example 1)

[0470] 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."

[0471] Unpleasant information encountered by users online is a factor that increases their mental burden. However, current systems lack effective means of filtering this information, hindering users' comfortable browsing experience. Furthermore, methods for accurately determining whether information is useful are still immature and require improvement.

[0472] 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.

[0473] In this invention, the server includes means for analyzing information transmission and generating evaluation values ​​based on criteria entered by the user; means for evaluating information transmission that the user finds unpleasant based on the evaluation values ​​so as to hide it; and means for determining whether information transmission contains useful opinions and, if necessary, permitting the user to display them. This allows the user to effectively filter out unpleasant information transmission, enabling a comfortable user experience.

[0474] "User" refers to an individual or legal entity that uses the system to manage the transmission of offensive information.

[0475] "Information transmission" refers to forms of communication, such as comments and messages, that occur on online platforms.

[0476] "Analysis" refers to the process of using a computer to analyze the content of information transmission and evaluate its emotions and tone.

[0477] "Evaluation value" refers to a numerical value or indicator that shows the degree of negativity or constructiveness generated in response to the content of the information being conveyed.

[0478] "Filtering" refers to the process of hiding information that users find offensive.

[0479] "Useful opinions" refer to opinions that are beneficial in the context of information dissemination and contain constructive or helpful content for the user.

[0480] "Making something invisible" refers to the action of visually eliminating or hiding information that the user deems offensive.

[0481] A "server" refers to a central processing unit that analyzes information transmission and controls filtering and display.

[0482] This invention provides a system aimed at helping users avoid unpleasant online experiences through the analysis and filtering of information transmission. The system consists of a user's terminal, interfaces to various online platforms, and a server that performs information processing.

[0483] Users first install a dedicated application on their device and link it to their online account. Within this application, users enter custom filtering criteria, such as "avoid offensive language." This allows the device to collect relevant information in real time and send the data to a server.

[0484] The server analyzes the collected information transmission using Python and various natural language processing libraries (e.g., NLTK and spaCy). During this process, evaluation values ​​are generated and compared to thresholds set by the user. Based on these analysis results, the server returns filtering instructions to the terminal.

[0485] The terminal adjusts the information displayed to the user based on instructions from the server. Specifically, constructive information is displayed to the user, while information deemed offensive is hidden or displayed with a warning. Criteria for determining usefulness are also processed based on pre-set parameters.

[0486] Furthermore, users can provide feedback on filtering, which updates the generated AI model on the server, improving the accuracy of the analysis. For example, if a user sets the system to "show only constructive criticism," comments such as "there is room for improvement" will be displayed, while personal attacks such as "incompetent" will not be displayed.

[0487] An example of a prompt for a generative AI model would be: "Explain how the system should handle communication when the user is tolerant of criticism but wants to avoid offensive language."

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] The user installs the application on their device and links it to their online account. The user then enters filtering criteria into the app. These criteria include keywords and tones to avoid, forming the basis for the program to identify offensive information. This configuration information is sent from the device to the server.

[0491] Step 2:

[0492] The device collects information transmission in real time via an online platform API. The input consists of comments and message content. This data, including the type of information, sender, and posting timestamp, is ready to be sent to the server. The specific operation here involves data access and collection using the API.

[0493] Step 3:

[0494] The terminal sends the collected information transmission data to the server. The server receives it and starts analysis using a natural language processing library (e.g., NLTK, spaCy). The input is the information transmission data, and the output is an evaluation value indicating its degree of negativity. The specific operations are text analysis and tone evaluation scoring.

[0495] Step 4:

[0496] The server compares the generated evaluation value to a threshold set by the user. The inputs here are the evaluation value and user settings, and the output is a filtering instruction. The specific operation involves comparing the score value with the threshold. Based on this result, it is determined which information is displayed.

[0497] Step 5:

[0498] The server sends the filtering results as instructions to the terminal. Based on these instructions, the terminal decides whether to display or hide the information to the user. The input is the filtering instructions from the server, and the output is the updated information display status. The specific operations are information display control and screen updating.

[0499] Step 6:

[0500] The user provides feedback on the accuracy of the filtered information. The terminal collects this feedback and sends it to the server. The input is the feedback content, and the output is the transmitted data. The specific operation involves the user inputting their opinion and sending the data.

[0501] Step 7:

[0502] The server updates the generated AI model based on the received feedback, improving the accuracy of the analysis. The input in this process is the feedback data, and the output is the new model parameters. The specific operations are feedback analysis and model training.

[0503] (Application Example 1)

[0504] 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."

[0505] In physical stores, there is a challenge in that it is difficult for service providers to evaluate the quality of feedback they receive directly from customers in real time and to respond quickly and accurately based on that feedback. In particular, it is a significant burden to properly recognize negative feedback and identify what should be taken as constructive opinions.

[0506] 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.

[0507] In this invention, the server includes means for analyzing voice information and scoring its degree of negativity based on criteria entered by the user; means for evaluating, based on the scoring, whether to display information that the service provider finds unpleasant as a warning on a display device; and means for determining whether the voice information contains constructive opinions and, if necessary, permitting the service provider to display them. This enables the service provider to efficiently manage customer feedback and improve the quality of customer service.

[0508] "Auditory information" refers to information acquired as sound, and includes the speaker's intentions and content.

[0509] "Negativeness" is an indicator that shows how negative or critical the feedback is.

[0510] A "service provider" refers to an individual or organization that provides goods or services to a customer.

[0511] A "display device" is a device used to visually display information, and in this context, it includes glasses-type devices worn by service providers.

[0512] "Speech recognition technology" is a technology that converts speech into text and is used to extract context and content from audio information.

[0513] A "machine learning algorithm" is a mathematical method that uses large amounts of data to learn patterns and trends in that data, and then uses that learning for subsequent analysis and prediction.

[0514] The system realizing this invention has the function of analyzing customer feedback in physical stores in real time using speech recognition technology and natural language processing technology. When the server receives voice information, it scores the degree of negativity based on criteria set by the user. The software used in this process is a speech recognition library and a text analysis library. Specifically, the Python speech_recognition library is used to convert voice to text, and the TextBlob library is used to analyze the tone and content of the feedback.

[0515] Based on the analysis results, the server instructs the service provider to display warnings on display devices such as smart glasses if they perceive the information as highly negative. Conversely, information deemed constructive is notified to the service provider as needed. This process allows the service provider to quickly adjust customer responses and improve the customer experience.

[0516] For example, if a service provider receives real-time customer feedback such as "the selection of this product is not very good," the system scores the feedback. If it determines that the feedback is negative, "Negative Feedback Detected" will be displayed on the smart glasses, prompting service improvement. In this way, the quality of store operations can be enhanced.

[0517] An example of a prompt for a generative AI model is: "Create a program that performs real-time feedback analysis based on voice feedback from customers. If the feedback is negative, it should display a warning."

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The device acquires voice feedback from customers using a microphone. The input is the voice spoken by the customer, which is processed by the device's built-in speech recognition function. The speech recognition technology converts the voice into text to obtain the output. Specifically, the process involves converting the voice to text using the Python `speech_recognition` library.

[0521] Step 2:

[0522] The terminal sends the converted text to the server. The server receives this text as input and analyzes the feedback content using natural language processing. The data processing performed here involves tone analysis using the TextBlob library, and a negativity score is generated as output. Specifically, the process involves analyzing the words and context of the text and then scoring them.

[0523] Step 3:

[0524] The server determines which feedback to display as a warning to the service provider based on the analyzed negativity score. The input is the negativity score obtained in step 2, a comparison operation is performed, and the result is output. Specifically, it compares the result to a predetermined threshold, and if it is determined to be negative, it generates a display command.

[0525] Step 4:

[0526] The server sends a display command to the terminal, and the terminal presents a warning to the service provider via a display device. The input is the display command sent from the server, and the output is a visual warning to the service provider. A specific operation involves a process that displays a message such as "Negative Feedback Detected" on a display device such as smart glasses.

[0527] 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.

[0528] This invention provides a negative comment filtering system that incorporates an emotion engine that recognizes the user's emotional state. The system aims to prevent the display of offensive comments on social networking services (SNS) and online platforms. The embodiments of this system are described in detail below.

[0529] 1. User settings and emotion recognition

[0530] Users install the application and connect their social media accounts. Users set criteria for comments they find offensive, which forms the basis for filtering. The device also has an emotion engine that recognizes the user's emotions in real time. The emotion engine determines the user's emotional state from their voice tone, facial expressions, and interactions during input.

[0531] 2. Comment Collection and Analysis

[0532] The device detects new comments related to the user on social media and sends them to the server. The server processes the comments using a natural language processing engine to analyze their context and keywords. Based on the analysis results, it scores the negativity of the comments.

[0533] 3. Dynamic threshold adjustment and filtering

[0534] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. A milder threshold is applied when the user is in a good mood, while a stricter threshold is applied when the user is feeling stressed or burdened. This filtering criterion is used to select which comments are displayed to the user.

[0535] 4. Display and feedback to the user

[0536] Only comments that have been filtered will be displayed on the device. Users can review the displayed comments and provide feedback. This feedback is processed on the server and used to improve the accuracy of the sentiment engine and filtering criteria.

[0537] Specific example

[0538] For example, if the emotion engine detects that a user is feeling down, the server sets a higher threshold, deeming even minor negative elements offensive and hiding them. On another day, if the user is perceived as feeling good, the threshold is lowered, and even slightly critical comments are displayed. In this way, the present invention achieves flexible comment filtering tailored to the emotions of individual users.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] Users install the application and link their social media accounts to it. Within the app, users can set criteria for what constitutes an offensive or constructive comment.

[0542] Step 2:

[0543] The device captures voice tone, facial expressions, input patterns, and other data to recognize the user's emotional state in real time. This allows the emotion engine to determine the user's psychological state.

[0544] Step 3:

[0545] The device detects comments related to the user on social media and sends that data to the server each time a new comment is posted.

[0546] Step 4:

[0547] The server analyzes received comments using natural language processing techniques and scores their degree of negativity. This analysis utilizes the context of the comment and the keywords it contains.

[0548] Step 5:

[0549] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. It lowers the threshold when the user is feeling down and raises it when they are feeling positive.

[0550] Step 6:

[0551] The server decides whether to hide comments deemed negative based on adjusted thresholds. Comments deemed constructive remain visible.

[0552] Step 7:

[0553] The terminal receives instructions from the server, filters the target comments, and displays them on the user screen. Hidden comments are kept invisible to the user.

[0554] Step 8:

[0555] Users can provide feedback on the displayed comments, including their thoughts and opinions, and this feedback is sent to the server.

[0556] Step 9:

[0557] The server uses feedback to improve its sentiment engine and filtering algorithms, which will then be used for future comment analysis. This will enable the delivery of a more personalized user experience.

[0558] (Example 2)

[0559] 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."

[0560] There is a need to efficiently filter comments that users find offensive on social media and online platforms, while flexibly adjusting the criteria for selecting comments according to the user's emotional state. Furthermore, utilizing user feedback on filtered comments to further improve the accuracy of the filtering process is a crucial challenge.

[0561] 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.

[0562] In this invention, the server includes means for analyzing electronic communications and scoring the degree of negativity based on criteria entered by the user, means for recognizing the user's emotional state in real time and dynamically adjusting the threshold for negativity according to that emotional state, and means for providing a machine learning algorithm that improves the accuracy of negativity scoring based on user feedback. This enables flexible filtering optimized for each user and continuous improvement of accuracy.

[0563] "Electronic communication" refers to information such as text, images, audio, and video that is sent and received via the internet or communication networks.

[0564] "Negativeness" refers to the degree to which a comment or piece of information is evaluated as negative or critical, expressed as a numerical value or score.

[0565] "Real-time recognition" means processing data instantly and making instantaneous judgments about the current situation and state.

[0566] A "threshold" refers to a numerical value or range that serves as a standard for determining whether a particular condition is exceeded.

[0567] "Feedback" refers to the opinions and reactions that users provide regarding the results and behavior of a system.

[0568] A "machine learning algorithm" is a computational method for making predictions and decisions by learning from data and analyzing patterns and rules.

[0569] This invention is a system for filtering comments received by users from social networking services (SNS) and online platforms. The system recognizes the user's emotional state in real time and dynamically adjusts the filtering criteria based on that information to select which comments to display to the user.

[0570] Users install the application on devices such as smartphones and computers, and connect to their social networking service (SNS) accounts through this application. The application has a function that allows users to set criteria for comments they find offensive, and these criteria form the basis of the filtering process.

[0571] The device is equipped with an emotion engine that analyzes voice tone, facial expressions, typing patterns, and other factors. This emotion engine can determine the user's emotional state in real time and classify it into categories such as "positive," "neutral," and "negative." Based on the user's emotional state, the server adjusts the threshold for negativity and performs comment filtering.

[0572] The server processes received comments through a natural language processing engine. This engine analyzes the context and keywords of the communication and scores the negativity of the comments based on the information obtained. Based on the threshold set as the filtering criterion, it decides whether to hide comments with a high negativity score.

[0573] Users can provide feedback on filtered comments. The server then collects this feedback and applies machine learning algorithms to improve the accuracy of the filtering. By repeating this process, the system's adaptability is enhanced, and the user experience is improved.

[0574] For example, if the emotion engine detects that a user is feeling down, the threshold will be set higher, and more comments will be filtered out. On the other hand, if the user is perceived as feeling good, the threshold will be lowered, and critical comments may also be displayed.

[0575] An example of a prompt to input into a generative AI model is: "Please describe a system that filters comments a user receives from social media. In particular, please describe in detail how the sentiment engine works and how the filtering criteria are dynamically adjusted."

[0576] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0577] Step 1:

[0578] The user installs the application on their device and connects their social media account. The user sets filtering criteria. This requires the user's authentication information and filtering criteria as input. The application saves the settings information as output, which is then used in subsequent processes.

[0579] Step 2:

[0580] The device uses an emotion engine to recognize the user's emotional state in real time. For example, it receives sensor data that detects voice tone, facial expressions, and input speed as input, and analyzes the emotional state. The output is a classification of the emotional state as either "positive," "neutral," or "negative."

[0581] Step 3:

[0582] The device periodically detects new comments on social media. This involves obtaining the comment's text data and the date and time it was posted as input. This data is then converted into data packets for transmission to the server and output.

[0583] Step 4:

[0584] The server analyzes the received comment data using a natural language processing engine. The input consists of the comment text data and associated metadata. Using this, the server extracts the context and keywords of the comments and scores their negativity. The output is the negativity score for each comment.

[0585] Step 5:

[0586] The server dynamically adjusts the negativity threshold based on the emotional state received from the terminal. The input is the classified emotional state and the negativity score. The server sets a more lenient threshold for "positive" emotional states and a stricter threshold for "negative" states. The output is the adjusted threshold.

[0587] Step 6:

[0588] The server filters comments according to a threshold and sends the selected comments to the terminal. The input is the adjusted threshold and the negativity score of the comments. The output is a list of comments that should be displayed to the user.

[0589] Step 7:

[0590] Users provide feedback on the displayed comments. The device sends this feedback as input to the server. The output is the user's feedback data. This feedback allows the server to use machine learning algorithms to improve the accuracy of filtering.

[0591] (Application Example 2)

[0592] 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."

[0593] The vast amount of information users receive online sometimes includes communications that are unpleasant for them. Furthermore, there is a lack of systems that dynamically display appropriate information based on each user's emotional state. Therefore, there is a need to create an environment where users can use online services more comfortably without experiencing stress.

[0594] 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.

[0595] In this invention, the server includes means for analyzing electronic communications and scoring their negativity based on user-defined criteria and real-time recognized emotional states; means for disclosing communications that the user finds unpleasant by dynamically adjusting thresholds based on the scoring and emotional states; and means for determining whether communications contain constructive opinions and relevant information according to the user's emotional state, and for allowing display or selecting appropriate information as necessary. This enables filtering and selection of information that matches the user's emotional state.

[0596] "User-defined criteria" are indicators used by users to determine the degree of negativity, based on their own preferences and comfort levels.

[0597] "Real-time recognized emotional state" refers to a state in which the user's current emotions are analyzed and identified in real time using emotion recognition technology.

[0598] "Electronic communication" is a general term for messages and posts delivered to users via the internet, and includes formats such as text, audio, and video.

[0599] "Scoring the degree of negativity" means evaluating the context and content of a received communication and assigning a score to the degree of negative elements contained within it.

[0600] "Dynamic threshold adjustment based on emotional state" is a process that flexibly changes the threshold for the negativity score according to the user's emotional state.

[0601] "Hide evaluation" refers to the act of deciding not to display specific communications to users based on the scoring results.

[0602] "Determining whether a communication contains constructive opinions" means analyzing whether the communication provides useful and valuable information to the user.

[0603] "Identifying relevant information based on emotional state" is the process of selecting the information most relevant to the user's current emotions.

[0604] "Selecting the right information" means choosing the most appropriate content to provide information that matches the user's emotional state and needs.

[0605] To implement this invention, it is necessary to construct a negative comment filtering system that utilizes emotion recognition technology. The system primarily operates via the user's terminal and a server.

[0606] The user's device will be equipped with a face-tracking camera and microphone to recognize emotions in real time. An emotion engine will analyze the user's facial expressions and voice tone to identify their emotional state in real time. The AI ​​model used for emotion recognition could be, for example, the "Emotion API."

[0607] The server analyzes electronic communications based on user-defined criteria and the user's emotional state as perceived in real time. It scores the negativity of communications using natural language processing techniques (e.g., Google Cloud Natural Language) and applies dynamic thresholds based on the user's emotional state. This allows the server to select content to display and evaluate whether to hide offensive communications.

[0608] Users can improve the system's accuracy by providing feedback. The server uses machine learning algorithms to improve filtering accuracy based on user feedback and changes in emotional state.

[0609] For example, if the emotion engine detects that a user is feeling down, the server will set a higher threshold and hide even minor negative elements. Additionally, advertisements for relaxation-related products will be prioritized for users experiencing stress.

[0610] An example of a prompt statement to input to a generative AI model is written as follows:

[0611] "Analyze the user's voice tone and facial expressions to identify their emotional state today. If they need to relax, suggest advertisements for the most suitable relaxation products."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server receives voice tone and facial expression data transmitted in real time from the user's device. The input data includes an emotion score obtained through an emotion recognition API. The server analyzes this data to determine the user's emotional state.

[0615] Step 2:

[0616] The user sets criteria for negativity through the application. Based on this, the server determines a dynamic threshold for scoring the negativity of the communication. The user's set criteria are input into the scoring engine, and an appropriate threshold is output.

[0617] Step 3:

[0618] The device sends electronic communication data obtained from social networking services (SNS) and online platforms to the server. The input data consists of comments and messages in text format. The server uses a natural language processing engine to analyze the context and keywords of the comments and score their degree of negativity.

[0619] Step 4:

[0620] The server compares the scoring results with the user's real-time emotional state to decide whether to display or hide the communication. The inputs are the scoring results and the emotional state, and the output is returned to the user's terminal as whether or not the communication should be displayed.

[0621] Step 5:

[0622] Users review filtered communications and provide feedback as needed. The server inputs this feedback into a machine learning algorithm to improve filtering accuracy. The output represents the algorithm's learning results and will be reflected in future filtering.

[0623] Step 6:

[0624] The server selects the most appropriate ads and relevant information based on the user's emotional state. Based on the sentiment score, it selects content that meets the user's needs and outputs it to the ad display management platform. This ensures that users receive information that resonates with their emotions.

[0625] Step 7:

[0626] The AI ​​model receives prompts that inform it of changes in the user's emotional state and provide optimal information. These prompts are generated based on an emotional state scoring result and input into the AI ​​model. The output is an optimized suggestion of the information the user is seeking.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] [Fourth Embodiment]

[0631] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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".

[0644] This invention provides a system that allows users to reduce the mental burden caused by offensive comments on social networking services (SNS) and other online platforms. This system operates around the user, the terminal, and the server, each playing a specific role.

[0645] 1. User settings

[0646] Users first install the application and connect it to their online account. Here, they can customize settings to distinguish between offensive and constructive comments. These settings include specifying keywords and criteria for comment tone.

[0647] 2. Collection and analysis of comments

[0648] The device collects comments related to the user on social media and sends them to a server. The server uses natural language processing technology to analyze these comments and score their degree of negativity. This scoring depends on the tone and context of the words used in the text.

[0649] 3. Filtering and display

[0650] Based on the scoring results, the server sends instructions to the device to hide comments whose level of discomfort exceeds the user-defined threshold. On the other hand, if a comment is deemed constructive, its content is displayed to the user by the device.

[0651] 4. Improving the user experience

[0652] Users can provide feedback on their satisfaction with the filtering results and suggest areas for improvement through the feedback function. This feedback is processed on the server and used to improve the accuracy of scoring and judgments through machine learning models.

[0653] Specific example

[0654] For example, if a user sets their preferences to "I accept criticism, but I want to avoid offensive language," the server will consider a comment like "This product has room for improvement" to be constructive and display it. However, a comment like "You are incompetent" will be deemed offensive and hidden. This allows users to have a more pleasant online experience.

[0655] In this way, the present invention specifically implements means to provide an environment in which users can use social networking services with peace of mind.

[0656] The following describes the processing flow.

[0657] Step 1:

[0658] Users install the application and link their social media accounts to it. They then set custom criteria to distinguish between "offensive comments" and "constructive comments." These criteria may include specific keywords or attributes.

[0659] Step 2:

[0660] The device monitors new comments related to users on social media and collects comment data as soon as it is detected. The collected comments are sent to a server for analysis.

[0661] Step 3:

[0662] The server analyzes received comments using a natural language processing engine. This analysis evaluates the text within the comments contextually and scores their degree of negativity.

[0663] Step 4:

[0664] Based on the scoring results, the server evaluates the comments using a threshold set by the user. Comments that exceed the threshold for offensiveness are deemed offensive and are instructed to be hidden.

[0665] Step 5:

[0666] The server further determines whether a comment is constructive. This is determined by whether the comment contains suggestions for improvement or raises issues. If it is deemed constructive, it will not be hidden and will be displayed to the user.

[0667] Step 6:

[0668] The device automatically applies filtering results according to instructions from the server. Comments deemed offensive will not be displayed on the user's screen, and only comments recognized as constructive will be shown.

[0669] Step 7:

[0670] Users can provide feedback on filtering through the app. This feedback is sent to the server.

[0671] Step 8:

[0672] The server uses the received feedback to improve the AI ​​model, enhancing the accuracy of scoring and judgments. This continuously improves the user experience for each individual user.

[0673] (Example 1)

[0674] 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".

[0675] Unpleasant information encountered by users online is a factor that increases their mental burden. However, current systems lack effective means of filtering this information, hindering users' comfortable browsing experience. Furthermore, methods for accurately determining whether information is useful are still immature and require improvement.

[0676] 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.

[0677] In this invention, the server includes means for analyzing information transmission and generating evaluation values ​​based on criteria entered by the user; means for evaluating information transmission that the user finds unpleasant based on the evaluation values ​​so as to hide it; and means for determining whether information transmission contains useful opinions and, if necessary, permitting the user to display them. This allows the user to effectively filter out unpleasant information transmission, enabling a comfortable user experience.

[0678] "User" refers to an individual or legal entity that uses the system to manage the transmission of offensive information.

[0679] "Information transmission" refers to forms of communication, such as comments and messages, that occur on online platforms.

[0680] "Analysis" refers to the process of using a computer to analyze the content of information transmission and evaluate its emotions and tone.

[0681] "Evaluation value" refers to a numerical value or indicator that shows the degree of negativity or constructiveness generated in response to the content of the information being conveyed.

[0682] "Filtering" refers to the process of hiding information that users find offensive.

[0683] "Useful opinions" refer to opinions that are beneficial in the context of information dissemination and contain constructive or helpful content for the user.

[0684] "Making something invisible" refers to the action of visually eliminating or hiding information that the user deems offensive.

[0685] A "server" refers to a central processing unit that analyzes information transmission and controls filtering and display.

[0686] This invention provides a system aimed at helping users avoid unpleasant online experiences through the analysis and filtering of information transmission. The system consists of a user's terminal, interfaces to various online platforms, and a server that performs information processing.

[0687] Users first install a dedicated application on their device and link it to their online account. Within this application, users enter custom filtering criteria, such as "avoid offensive language." This allows the device to collect relevant information in real time and send the data to a server.

[0688] The server analyzes the collected information transmission using Python and various natural language processing libraries (e.g., NLTK and spaCy). During this process, evaluation values ​​are generated and compared to thresholds set by the user. Based on these analysis results, the server returns filtering instructions to the terminal.

[0689] The terminal adjusts the information displayed to the user based on instructions from the server. Specifically, constructive information is displayed to the user, while information deemed offensive is hidden or displayed with a warning. Criteria for determining usefulness are also processed based on pre-set parameters.

[0690] Furthermore, users can provide feedback on filtering, which updates the generated AI model on the server, improving the accuracy of the analysis. For example, if a user sets the system to "show only constructive criticism," comments such as "there is room for improvement" will be displayed, while personal attacks such as "incompetent" will not be displayed.

[0691] An example of a prompt for a generative AI model would be: "Explain how the system should handle communication when the user is tolerant of criticism but wants to avoid offensive language."

[0692] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0693] Step 1:

[0694] The user installs the application on their device and links it to their online account. The user then enters filtering criteria into the app. These criteria include keywords and tones to avoid, forming the basis for the program to identify offensive information. This configuration information is sent from the device to the server.

[0695] Step 2:

[0696] The device collects information transmission in real time via an online platform API. The input consists of comments and message content. This data, including the type of information, sender, and posting timestamp, is ready to be sent to the server. The specific operation here involves data access and collection using the API.

[0697] Step 3:

[0698] The terminal sends the collected information transmission data to the server. The server receives it and starts analysis using a natural language processing library (e.g., NLTK, spaCy). The input is the information transmission data, and the output is an evaluation value indicating its degree of negativity. The specific operations are text analysis and tone evaluation scoring.

[0699] Step 4:

[0700] The server compares the generated evaluation value to a threshold set by the user. The inputs here are the evaluation value and user settings, and the output is a filtering instruction. The specific operation involves comparing the score value with the threshold. Based on this result, it is determined which information is displayed.

[0701] Step 5:

[0702] The server sends the filtering results as instructions to the terminal. Based on these instructions, the terminal decides whether to display or hide the information to the user. The input is the filtering instructions from the server, and the output is the updated information display status. The specific operations are information display control and screen updating.

[0703] Step 6:

[0704] The user provides feedback on the accuracy of the filtered information. The terminal collects this feedback and sends it to the server. The input is the feedback content, and the output is the transmitted data. The specific operation involves the user inputting their opinion and sending the data.

[0705] Step 7:

[0706] The server updates the generated AI model based on the received feedback, improving the accuracy of the analysis. The input in this process is the feedback data, and the output is the new model parameters. The specific operations are feedback analysis and model training.

[0707] (Application Example 1)

[0708] 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".

[0709] In physical stores, there is a challenge in that it is difficult for service providers to evaluate the quality of feedback they receive directly from customers in real time and to respond quickly and accurately based on that feedback. In particular, it is a significant burden to properly recognize negative feedback and identify what should be taken as constructive opinions.

[0710] 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.

[0711] In this invention, the server includes means for analyzing voice information and scoring its degree of negativity based on criteria entered by the user; means for evaluating, based on the scoring, whether to display information that the service provider finds unpleasant as a warning on a display device; and means for determining whether the voice information contains constructive opinions and, if necessary, permitting the service provider to display them. This enables the service provider to efficiently manage customer feedback and improve the quality of customer service.

[0712] "Auditory information" refers to information acquired as sound, and includes the speaker's intentions and content.

[0713] "Negativeness" is an indicator that shows how negative or critical the feedback is.

[0714] A "service provider" refers to an individual or organization that provides goods or services to a customer.

[0715] A "display device" is a device used to visually display information, and in this context, it includes glasses-type devices worn by service providers.

[0716] "Speech recognition technology" is a technology that converts speech into text and is used to extract context and content from audio information.

[0717] A "machine learning algorithm" is a mathematical method that uses large amounts of data to learn patterns and trends in that data, and then uses that learning for subsequent analysis and prediction.

[0718] The system realizing this invention has the function of analyzing customer feedback in physical stores in real time using speech recognition technology and natural language processing technology. When the server receives voice information, it scores the degree of negativity based on criteria set by the user. The software used in this process is a speech recognition library and a text analysis library. Specifically, the Python speech_recognition library is used to convert voice to text, and the TextBlob library is used to analyze the tone and content of the feedback.

[0719] Based on the analysis results, the server instructs the service provider to display warnings on display devices such as smart glasses if they perceive the information as highly negative. Conversely, information deemed constructive is notified to the service provider as needed. This process allows the service provider to quickly adjust customer responses and improve the customer experience.

[0720] For example, if a service provider receives real-time customer feedback such as "the selection of this product is not very good," the system scores the feedback. If it determines that the feedback is negative, "Negative Feedback Detected" will be displayed on the smart glasses, prompting service improvement. In this way, the quality of store operations can be enhanced.

[0721] An example of a prompt for a generative AI model is: "Create a program that performs real-time feedback analysis based on voice feedback from customers. If the feedback is negative, it should display a warning."

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] The device acquires voice feedback from customers using a microphone. The input is the voice spoken by the customer, which is processed by the device's built-in speech recognition function. The speech recognition technology converts the voice into text to obtain the output. Specifically, the process involves converting the voice to text using the Python `speech_recognition` library.

[0725] Step 2:

[0726] The terminal sends the converted text to the server. The server receives this text as input and analyzes the feedback content using natural language processing. The data processing performed here involves tone analysis using the TextBlob library, and a negativity score is generated as output. Specifically, the process involves analyzing the words and context of the text and then scoring them.

[0727] Step 3:

[0728] The server determines which feedback to display as a warning to the service provider based on the analyzed negativity score. The input is the negativity score obtained in step 2, a comparison operation is performed, and the result is output. Specifically, it compares the result to a predetermined threshold, and if it is determined to be negative, it generates a display command.

[0729] Step 4:

[0730] The server sends a display command to the terminal, and the terminal presents a warning to the service provider via a display device. The input is the display command sent from the server, and the output is a visual warning to the service provider. A specific operation involves a process that displays a message such as "Negative Feedback Detected" on a display device such as smart glasses.

[0731] 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.

[0732] This invention provides a negative comment filtering system that incorporates an emotion engine that recognizes the user's emotional state. The system aims to prevent the display of offensive comments on social networking services (SNS) and online platforms. The embodiments of this system are described in detail below.

[0733] 1. User settings and emotion recognition

[0734] Users install the application and connect their social media accounts. Users set criteria for comments they find offensive, which forms the basis for filtering. The device also has an emotion engine that recognizes the user's emotions in real time. The emotion engine determines the user's emotional state from their voice tone, facial expressions, and interactions during input.

[0735] 2. Comment Collection and Analysis

[0736] The device detects new comments related to the user on social media and sends them to the server. The server processes the comments using a natural language processing engine to analyze their context and keywords. Based on the analysis results, it scores the negativity of the comments.

[0737] 3. Dynamic threshold adjustment and filtering

[0738] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. A milder threshold is applied when the user is in a good mood, while a stricter threshold is applied when the user is feeling stressed or burdened. This filtering criterion is used to select which comments are displayed to the user.

[0739] 4. Display and feedback to the user

[0740] Only comments that have been filtered will be displayed on the device. Users can review the displayed comments and provide feedback. This feedback is processed on the server and used to improve the accuracy of the sentiment engine and filtering criteria.

[0741] Specific example

[0742] For example, if the emotion engine detects that a user is feeling down, the server sets a higher threshold, deeming even minor negative elements offensive and hiding them. On another day, if the user is perceived as feeling good, the threshold is lowered, and even slightly critical comments are displayed. In this way, the present invention achieves flexible comment filtering tailored to the emotions of individual users.

[0743] The following describes the processing flow.

[0744] Step 1:

[0745] Users install the application and link their social media accounts to it. Within the app, users can set criteria for what constitutes an offensive or constructive comment.

[0746] Step 2:

[0747] The device captures voice tone, facial expressions, input patterns, and other data to recognize the user's emotional state in real time. This allows the emotion engine to determine the user's psychological state.

[0748] Step 3:

[0749] The device detects comments related to the user on social media and sends that data to the server each time a new comment is posted.

[0750] Step 4:

[0751] The server analyzes received comments using natural language processing techniques and scores their degree of negativity. This analysis utilizes the context of the comment and the keywords it contains.

[0752] Step 5:

[0753] The server dynamically adjusts the negativity threshold based on the user's emotional state as recognized by the emotion engine. It lowers the threshold when the user is feeling down and raises it when they are feeling positive.

[0754] Step 6:

[0755] The server decides whether to hide comments deemed negative based on adjusted thresholds. Comments deemed constructive remain visible.

[0756] Step 7:

[0757] The terminal receives instructions from the server, filters the target comments, and displays them on the user screen. Hidden comments are kept invisible to the user.

[0758] Step 8:

[0759] Users can provide feedback on the displayed comments, including their thoughts and opinions, and this feedback is sent to the server.

[0760] Step 9:

[0761] The server uses feedback to improve its sentiment engine and filtering algorithms, which will then be used for future comment analysis. This will enable the delivery of a more personalized user experience.

[0762] (Example 2)

[0763] 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".

[0764] There is a need to efficiently filter comments that users find offensive on social media and online platforms, while flexibly adjusting the criteria for selecting comments according to the user's emotional state. Furthermore, utilizing user feedback on filtered comments to further improve the accuracy of the filtering process is a crucial challenge.

[0765] 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.

[0766] In this invention, the server includes means for analyzing electronic communications and scoring the degree of negativity based on criteria entered by the user, means for recognizing the user's emotional state in real time and dynamically adjusting the threshold for negativity according to that emotional state, and means for providing a machine learning algorithm that improves the accuracy of negativity scoring based on user feedback. This enables flexible filtering optimized for each user and continuous improvement of accuracy.

[0767] "Electronic communication" refers to information such as text, images, audio, and video that is sent and received via the internet or communication networks.

[0768] "Negativeness" refers to the degree to which a comment or piece of information is evaluated as negative or critical, expressed as a numerical value or score.

[0769] "Real-time recognition" means processing data instantly and making instantaneous judgments about the current situation and state.

[0770] A "threshold" refers to a numerical value or range that serves as a standard for determining whether a particular condition is exceeded.

[0771] "Feedback" refers to the opinions and reactions that users provide regarding the results and behavior of a system.

[0772] A "machine learning algorithm" is a computational method for making predictions and decisions by learning from data and analyzing patterns and rules.

[0773] This invention is a system for filtering comments received by users from social networking services (SNS) and online platforms. The system recognizes the user's emotional state in real time and dynamically adjusts the filtering criteria based on that information to select which comments to display to the user.

[0774] Users install the application on devices such as smartphones and computers, and connect to their social networking service (SNS) accounts through this application. The application has a function that allows users to set criteria for comments they find offensive, and these criteria form the basis of the filtering process.

[0775] The device is equipped with an emotion engine that analyzes voice tone, facial expressions, typing patterns, and other factors. This emotion engine can determine the user's emotional state in real time and classify it into categories such as "positive," "neutral," and "negative." Based on the user's emotional state, the server adjusts the threshold for negativity and performs comment filtering.

[0776] The server processes received comments through a natural language processing engine. This engine analyzes the context and keywords of the communication and scores the negativity of the comments based on the information obtained. Based on the threshold set as the filtering criterion, it decides whether to hide comments with a high negativity score.

[0777] Users can provide feedback on filtered comments. The server then collects this feedback and applies machine learning algorithms to improve the accuracy of the filtering. By repeating this process, the system's adaptability is enhanced, and the user experience is improved.

[0778] For example, if the emotion engine detects that a user is feeling down, the threshold will be set higher, and more comments will be filtered out. On the other hand, if the user is perceived as feeling good, the threshold will be lowered, and critical comments may also be displayed.

[0779] An example of a prompt to input into a generative AI model is: "Please describe a system that filters comments a user receives from social media. In particular, please describe in detail how the sentiment engine works and how the filtering criteria are dynamically adjusted."

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] The user installs the application on their device and connects their social media account. The user sets filtering criteria. This requires the user's authentication information and filtering criteria as input. The application saves the settings information as output, which is then used in subsequent processes.

[0783] Step 2:

[0784] The device uses an emotion engine to recognize the user's emotional state in real time. For example, it receives sensor data that detects voice tone, facial expressions, and input speed as input, and analyzes the emotional state. The output is a classification of the emotional state as either "positive," "neutral," or "negative."

[0785] Step 3:

[0786] The device periodically detects new comments on social media. This involves obtaining the comment's text data and the date and time it was posted as input. This data is then converted into data packets for transmission to the server and output.

[0787] Step 4:

[0788] The server analyzes the received comment data using a natural language processing engine. The input consists of the comment text data and associated metadata. Using this, the server extracts the context and keywords of the comments and scores their negativity. The output is the negativity score for each comment.

[0789] Step 5:

[0790] The server dynamically adjusts the negativity threshold based on the emotional state received from the terminal. The input is the classified emotional state and the negativity score. The server sets a more lenient threshold for "positive" emotional states and a stricter threshold for "negative" states. The output is the adjusted threshold.

[0791] Step 6:

[0792] The server filters comments according to a threshold and sends the selected comments to the terminal. The input is the adjusted threshold and the negativity score of the comments. The output is a list of comments that should be displayed to the user.

[0793] Step 7:

[0794] Users provide feedback on the displayed comments. The device sends this feedback as input to the server. The output is the user's feedback data. This feedback allows the server to use machine learning algorithms to improve the accuracy of filtering.

[0795] (Application Example 2)

[0796] 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".

[0797] The vast amount of information users receive online sometimes includes communications that are unpleasant for them. Furthermore, there is a lack of systems that dynamically display appropriate information based on each user's emotional state. Therefore, there is a need to create an environment where users can use online services more comfortably without experiencing stress.

[0798] 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.

[0799] In this invention, the server includes means for analyzing electronic communications and scoring their negativity based on user-defined criteria and real-time recognized emotional states; means for disclosing communications that the user finds unpleasant by dynamically adjusting thresholds based on the scoring and emotional states; and means for determining whether communications contain constructive opinions and relevant information according to the user's emotional state, and for allowing display or selecting appropriate information as necessary. This enables filtering and selection of information that matches the user's emotional state.

[0800] "User-defined criteria" are indicators used by users to determine the degree of negativity, based on their own preferences and comfort levels.

[0801] "Real-time recognized emotional state" refers to a state in which the user's current emotions are analyzed and identified in real time using emotion recognition technology.

[0802] "Electronic communication" is a general term for messages and posts delivered to users via the internet, and includes formats such as text, audio, and video.

[0803] "Scoring the degree of negativity" means evaluating the context and content of a received communication and assigning a score to the degree of negative elements contained within it.

[0804] "Dynamic threshold adjustment based on emotional state" is a process that flexibly changes the threshold for the negativity score according to the user's emotional state.

[0805] "Hide evaluation" refers to the act of deciding not to display specific communications to users based on the scoring results.

[0806] "Determining whether a communication contains constructive opinions" means analyzing whether the communication provides useful and valuable information to the user.

[0807] "Identifying relevant information based on emotional state" is the process of selecting the information most relevant to the user's current emotions.

[0808] "Selecting the right information" means choosing the most appropriate content to provide information that matches the user's emotional state and needs.

[0809] To implement this invention, it is necessary to construct a negative comment filtering system that utilizes emotion recognition technology. The system primarily operates via the user's terminal and a server.

[0810] The user's device will be equipped with a face-tracking camera and microphone to recognize emotions in real time. An emotion engine will analyze the user's facial expressions and voice tone to identify their emotional state in real time. The AI ​​model used for emotion recognition could be, for example, the "Emotion API."

[0811] The server analyzes electronic communications based on user-defined criteria and the user's emotional state as perceived in real time. It scores the negativity of communications using natural language processing techniques (e.g., Google Cloud Natural Language) and applies dynamic thresholds based on the user's emotional state. This allows the server to select content to display and evaluate whether to hide offensive communications.

[0812] Users can improve the system's accuracy by providing feedback. The server uses machine learning algorithms to improve filtering accuracy based on user feedback and changes in emotional state.

[0813] For example, if the emotion engine detects that a user is feeling down, the server will set a higher threshold and hide even minor negative elements. Additionally, advertisements for relaxation-related products will be prioritized for users experiencing stress.

[0814] An example of a prompt statement to input to a generative AI model is written as follows:

[0815] "Analyze the user's voice tone and facial expressions to identify their emotional state today. If they need to relax, suggest advertisements for the most suitable relaxation products."

[0816] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0817] Step 1:

[0818] The server receives voice tone and facial expression data transmitted in real time from the user's device. The input data includes an emotion score obtained through an emotion recognition API. The server analyzes this data to determine the user's emotional state.

[0819] Step 2:

[0820] The user sets criteria for negativity through the application. Based on this, the server determines a dynamic threshold for scoring the negativity of the communication. The user's set criteria are input into the scoring engine, and an appropriate threshold is output.

[0821] Step 3:

[0822] The device sends electronic communication data obtained from social networking services (SNS) and online platforms to the server. The input data consists of comments and messages in text format. The server uses a natural language processing engine to analyze the context and keywords of the comments and score their degree of negativity.

[0823] Step 4:

[0824] The server compares the scoring results with the user's real-time emotional state to decide whether to display or hide the communication. The inputs are the scoring results and the emotional state, and the output is returned to the user's terminal as whether or not the communication should be displayed.

[0825] Step 5:

[0826] Users review filtered communications and provide feedback as needed. The server inputs this feedback into a machine learning algorithm to improve filtering accuracy. The output represents the algorithm's learning results and will be reflected in future filtering.

[0827] Step 6:

[0828] The server selects the most appropriate ads and relevant information based on the user's emotional state. Based on the sentiment score, it selects content that meets the user's needs and outputs it to the ad display management platform. This ensures that users receive information that resonates with their emotions.

[0829] Step 7:

[0830] The AI ​​model receives prompts that inform it of changes in the user's emotional state and provide optimal information. These prompts are generated based on an emotional state scoring result and input into the AI ​​model. The output is an optimized suggestion of the information the user is seeking.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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."

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0852] The following is further disclosed regarding the embodiments described above.

[0853] (Claim 1)

[0854] A means of analyzing electronic communications and scoring their degree of negativity based on criteria entered by the user,

[0855] A means for evaluating and hiding communications that users find offensive, based on the aforementioned scoring,

[0856] A means of determining whether a communication contains constructive opinions and, if necessary, allowing the user to display them,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, which uses natural language processing to analyze the context and keywords of a communication.

[0860] (Claim 3)

[0861] The system according to claim 1, comprising a machine learning algorithm that improves the accuracy of negativeness scoring based on user feedback.

[0862] "Example 1"

[0863] (Claim 1)

[0864] A means for analyzing information transmission and generating evaluation values ​​based on criteria entered by the user,

[0865] A means for evaluating how to make information transmission that users find unpleasant invisible, based on the aforementioned evaluation values,

[0866] A means of determining whether information transmission contains useful opinions and, if necessary, permitting the user to display them,

[0867] A means of collecting information using the user's terminal and transmitting it to an analysis device,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which processes information using a computer language and analyzes the context of information transmission and important words.

[0871] (Claim 3)

[0872] The system according to claim 1, comprising a data processing algorithm that improves the accuracy of generating evaluation values ​​based on user feedback.

[0873] "Application Example 1"

[0874] (Claim 1)

[0875] A means of analyzing voice information based on criteria entered by the user and scoring the degree of negativity,

[0876] A means for evaluating whether to display information that the service provider finds offensive as a warning on a display device, based on the aforementioned scoring,

[0877] A means of determining whether audio information contains constructive opinions and, if necessary, allowing the service provider to display them,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, which uses speech recognition technology to analyze the context and keywords of speech information.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising a machine learning algorithm that improves the accuracy of negativeness scoring based on feedback from service providers.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] A means of analyzing electronic communications and scoring their degree of negativity based on criteria entered by the user,

[0886] A means for evaluating and hiding communications that users find offensive, based on the aforementioned scoring,

[0887] A means for recognizing the user's emotional state in real time and dynamically adjusting the threshold for negativity according to that emotional state,

[0888] A means of determining whether a communication contains constructive opinions and, if necessary, allowing the user to display them,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, which uses natural language processing to analyze the context and keywords of a communication.

[0892] (Claim 3)

[0893] The system according to claim 1, comprising a machine learning algorithm that improves the accuracy of negativeness scoring based on user feedback.

[0894] "Application example 2 when combining with an emotional engine"

[0895] (Claim 1)

[0896] A means for analyzing electronic communications and scoring the degree of negativity based on user-defined criteria and emotional states recognized in real time,

[0897] A means for disclosing and evaluating communications that the user finds unpleasant, based on the aforementioned scoring and dynamic threshold adjustments based on emotional state,

[0898] Means for determining whether a communication contains constructive opinions and relevant information in accordance with the user's emotional state, and for allowing display or selecting appropriate information as necessary,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, which uses natural language processing and emotion recognition technology to analyze the context and keywords of a communication, and further selects information based on the emotional state.

[0902] (Claim 3)

[0903] The system according to claim 1, comprising a machine learning algorithm that improves the accuracy of negativity scoring and information presentation based on user feedback and changes in emotional state. [Explanation of symbols]

[0904] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing electronic communications and scoring their degree of negativity based on criteria entered by the user, A means for evaluating and hiding communications that users find offensive, based on the aforementioned scoring, A means of determining whether a communication contains constructive opinions and, if necessary, allowing the user to display them, A system that includes this.

2. The system according to claim 1, which uses natural language processing to analyze the context and keywords of a communication.

3. The system according to claim 1, comprising a machine learning algorithm that improves the accuracy of negativeness scoring based on user feedback.

Images