system

Abstract

We provide the system. [Solution] A method for analyzing information on social networking services using natural language processing, A means for extracting the characteristics of the aforementioned information and classifying commercial posts and general posts, Means for filtering the classified information according to conditions specified by the user, means for displaying the filtered information on a user interface, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 recent years, social network services have been widely used as an important platform for information collection. However, since commercial promotion posts and posts by general users are mixed, it is difficult to efficiently obtain reliable information. This problem increases the possibility that consumers make decisions based on incorrect information, which is a factor that impairs the user experience. Therefore, there is a need for a method to automatically classify these posts and preferentially access highly reliable information.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a means for analyzing posted information on social networking services using natural language processing. Specifically, it includes means for extracting the characteristics of posts from the analyzed information and classifying them into commercial posts and posts by general users. Furthermore, it is possible to filter the classification results based on conditions specified by the user. The filtered information is displayed on the user interface, allowing users to easily access the reliable information they are looking for. In addition, means for using sentiment analysis and means for utilizing user feedback are also included to improve the accuracy of the classification.

[0006] "Natural language processing" is the technology that enables computers to understand, generate, and analyze human language.

[0007] A "social networking service" is a platform on the internet for people to share information and interact with each other.

[0008] "Information" refers to text data and media content posted on social networking services.

[0009] "Features" refer to attributes and characteristics extracted from the posted information, such as sentiment scores and post length.

[0010] A "commercial post" is a post that contains promotional information intended to advertise a product or service.

[0011] "General submissions" are posts containing personal opinions and experiences, and are not for commercial purposes.

[0012] "User interface" refers to the screen display and means of operation that a user uses to interact with a computer.

[0013] "Sentiment analysis" is a technology that automatically determines the emotions and intentions behind text and speeches.

[0014] "Feedback" refers to information collected from users, such as their evaluations and opinions, to help improve the system. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention provides a system that automatically classifies posts on social networking services into promotional posts and posts from regular users, enabling users to efficiently access reliable information.

[0037] This system consists of servers, terminals, and users.

[0038] First, the server collects multiple posts from social networking services. This includes hashtags, keywords, or geographical information based on user-specified criteria. The collected data is then converted into a format that is easy to parse. This involves cleaning and tokenizing the text.

[0039] Next, the server analyzes the collected post data using natural language processing technology. In this analysis process, features are extracted, and attributes such as the sentiment score, post length, and presence of links for each post are evaluated. Based on these features, the AI ​​model classifies the posts as either promotional posts or posts from regular users.

[0040] After classification, the server filters posts based on the user's specified filtering criteria. For example, if a user wants to avoid promotional posts, the server will exclude data identified as promotional and send only posts from regular users to the device.

[0041] The terminal receives filtered information from the server and displays it on the user interface. The display can be customized by the user, for example, by highlighting information of particular interest to the user.

[0042] Users can verify whether the displayed information meets their needs and provide feedback to the server. This feedback is used to improve subsequent analysis models and forms the basis for providing highly accurate classification results.

[0043] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects posts with hashtags related to "electronic devices" and uses an AI model to categorize them into promotional posts and genuine reviews. The device then displays only reviews from actual purchasers, excluding promotional posts. This allows the user to confidently select a product.

[0044] Thus, this system provides an environment in which users can efficiently obtain reliable information on social networks and make informed decisions.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server collects post data that meets specified conditions (e.g., specific keywords or hashtags) through the API of social networking services. At the same time, it also retrieves metadata such as post content, poster information, and posting time.

[0048] Step 2:

[0049] The server cleans the acquired raw data. The cleaning process removes unnecessary HTML tags and special characters, making the text a plain format. This prepares the data for efficient natural language processing.

[0050] Step 3:

[0051] The server tokenizes the cleaned text data. Tokenization is the process of dividing the text into words and phrases. After this, stemming and lemmatization are performed to unify the base form of the words.

[0052] Step 4:

[0053] The server uses natural language processing technology to extract features from each post. These features include the length of the text, sentiment score (positive, negative, neutral), and whether or not there are links.

[0054] Step 5:

[0055] The server uses a pre-trained AI model to classify each post into promotional posts and regular posts based on the extracted features. This AI model takes feature vectors as input to determine the nature of the posts.

[0056] Step 6:

[0057] The server filters categorized posts based on user-specified criteria. Depending on user settings, it is possible to exclude promotional posts or select only posts with a specific sentiment.

[0058] Step 7:

[0059] The server sends filtered post data to the user's device. During transmission, the information is organized chronologically and by relevance to improve readability.

[0060] Step 8:

[0061] The device displays the received information on the user interface. The display reflects the user's customization settings, including highlighting of important information and hiding of promotional posts.

[0062] Step 9:

[0063] Users review the displayed information and provide feedback as needed. This feedback is sent to the server and used for the continuous improvement of the AI ​​model.

[0064] (Example 1)

[0065] 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."

[0066] The amount of information on social networking services is vast, making it difficult for users to efficiently access reliable information. In particular, the mix of commercial posts and posts from general users makes it difficult for users to quickly find the information they need. Furthermore, mechanisms for improving the accuracy of information classification are currently insufficient.

[0067] 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.

[0068] In this invention, the server includes means for analyzing data using natural language processing, means for extracting data characteristics and classifying them based on specific conditions, and means for selecting data classified based on conditions specified by the user. This enables users to efficiently access reliable information they need and utilize feedback to further improve classification accuracy.

[0069] "Natural language processing" is a technology that enables computers to understand and analyze human language, and is used to analyze the meaning and structure of text.

[0070] "Methods for extracting data characteristics" refer to the process of finding distinctive information from data, and include evaluating attributes such as text sentiment scores, post length, and the presence or absence of links.

[0071] "Means of classification based on specific conditions" refers to the process of dividing data into defined categories based on extracted characteristics, with the aim of distinguishing between commercial posts and posts from general users.

[0072] "Means of sorting based on user-specified conditions" refers to the process of extracting only the necessary information from pre-classified data according to the user's set requirements.

[0073] An "output device" is a device used to provide information to a user visually, and includes, but is not limited to, displays and monitors.

[0074] "Utilizing feedback" is the process of collecting evaluations and opinions from users and using them as a reference to improve the performance and accuracy of the system.

[0075] In this embodiment of the invention, three elements are primarily involved: a server, a terminal, and a user.

[0076] First, the server collects data from social networking services. This collection is based on hashtags, keywords, or geographical information specified by the user. The server then converts the collected data into a format that is easy to analyze using natural language processing tools. In this process, the server cleans and tokenizes the text data. Furthermore, it uses AI models to extract data features and classify posts into commercial posts and posts from general users.

[0077] The terminal's role is to display filtered data received from the server on the user interface. This makes it easier for users to effectively obtain information that interests them. The user interface allows users to customize the display according to their preferences. For example, it can help users make choices by clearly highlighting new product reviews.

[0078] Users can provide feedback on the accuracy and usefulness of the displayed information. This feedback is used by the server to improve the accuracy of the AI ​​model. As a concrete example, if a user is looking for reviews of a new electronic device, the server will filter relevant posts based on the prompt "electronic device reviews" and provide actual user reviews as a result. This allows users to easily find reliable information and make purchasing decisions more smoothly.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects posted data from social networking services. User-specified hashtags, keywords, or geographical information are used as input. The collected raw data includes the post text, poster information, and date. This data forms the basis for subsequent processing by the server.

[0082] Step 2:

[0083] The server preprocesses the collected data. Because the input data contains unnecessary noise and formatting, it undergoes cleaning and tokenization. Specifically, it removes special characters and HTML tags and converts the data into a more manageable format by separating it into words. The output of this process is text data suitable for analysis.

[0084] Step 3:

[0085] The server uses natural language processing techniques to extract features from pre-processed data. It analyzes features such as sentiment scores, post length, and the presence or absence of links, and prepares them as input for the AI ​​model. It calculates these attributes from the text data received as input and outputs them as feature vectors.

[0086] Step 4:

[0087] The server classifies posts using an AI model based on feature vectors. A generative AI model is used to distinguish between commercial posts and posts from regular users, based on the prompt text. This classification outputs which category each post belongs to.

[0088] Step 5:

[0089] The server selects posts categorized based on the filtering conditions specified by the user. The input consists of the classification results and the filtering conditions set by the user. The output is the selected post data that matches the conditions.

[0090] Step 6:

[0091] The terminal displays filtered posts sent from the server on the user interface. Information formatted for user readability is received as input and reflected on the terminal. The output is an information display in a format that the user can easily understand.

[0092] Step 7:

[0093] The user evaluates the quality of the information displayed on the device and provides feedback to the server. Based on the feedback, the server adjusts the AI ​​model to improve classification accuracy. The input is the user's feedback, and the output is in the form of fine-tuning the AI ​​model.

[0094] (Application Example 1)

[0095] 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."

[0096] Traditionally, the sheer volume of information on social networks makes it difficult to efficiently extract reliable information. This is especially true when commercial information is prevalent, making it challenging to find posts from ordinary users and requiring significant time and effort for users to sift through the information they need. Therefore, there is a need for a system that allows users to easily access reliable general information and use it to aid in decision-making.

[0097] 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.

[0098] In this invention, the server includes means for collecting multiple data from a social network, means for analyzing the data using natural language processing, means for classifying commercial information and general information based on the attributes of the data, means for selecting the classified information according to conditions specified by the user, and means for displaying the selected information on a user interface and highlighting information of interest to the user. This enables users to easily access reliable general information on social networks and make decisions efficiently.

[0099] A "social network" is an online service that allows people to share information or content over the internet.

[0100] "Data" refers to a collection of information gathered on social networks, including posts, comments, and links.

[0101] "Natural language processing" is a technology for processing and analyzing human language using computers.

[0102] "Analysis" is the process of examining data in detail to understand and classify its contents.

[0103] An "attribute" is a specific characteristic or feature of data, used as a criterion for classification.

[0104] "Commercial information" refers to information disseminated for the purpose of promoting the sale of goods or services.

[0105] "General information" refers to information that is not for commercial purposes and is based on personal experiences and opinions.

[0106] "Selection" is the process of choosing only the necessary elements based on specific criteria.

[0107] A "user interface" refers to the display screens and functions that enable interaction between a computer system and a user.

[0108] "Highlighting" is a technique that visually highlights specific information to attract the user's attention.

[0109] The system of this invention efficiently analyzes data on social networks, enabling users to obtain reliable information. The server first collects posted data from social networks via an internet connection. The collected data is then processed using natural language processing techniques, including text cleaning and tokenization, to convert it into a parseable format. A standard server computer is used as the hardware, and natural language processing libraries and frameworks (such as the Transformers library) are utilized as the software.

[0110] After analysis, the server uses an AI model to classify posts into commercial and general information based on their data attributes. This allows for the selection of reliable information and filtering of information according to conditions specified by individual users. The selected information is then sent to the terminal and displayed via the user interface. Users can review information of interest and provide feedback to the server, contributing to the improvement of the classification algorithm's accuracy.

[0111] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects and analyzes data tagged with "electronic device," and displays only reliable reviews from general users on the device, allowing the user to make product selections based on more accurate information.

[0112] Furthermore, the following prompt statements can be used as input to the generative AI model.

[0113] "I'm looking for smartphone reviews. Please prioritize posts from regular users."

[0114] This allows users to easily obtain the most relevant information.

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

[0116] Step 1:

[0117] The server uses the APIs of social networking services to collect posted data based on specified conditions. It receives user-specified hashtags and keywords as input and makes API requests. The output, including the post text, user information, and posting date and time, is returned to the server in JSON format. This data is then stored in internal storage.

[0118] Step 2:

[0119] The server converts the collected data into a format that is easy to analyze using natural language processing techniques. The input is the posted data obtained in step 1. Specifically, it performs text preprocessing (cleaning, normalization, tokenization) and extracts sentiment scores and keywords. The output is an analyzable text dataset.

[0120] Step 3:

[0121] The server inputs the results of natural language processing analysis into an AI model to classify posts into commercial and general information. The feature data obtained in step 2 is used as input. Specifically, the AI ​​model is used to determine the commercial potential of each post and perform the classification. The output is the classification result (data labeled as commercial information).

[0122] Step 4:

[0123] The server sorts the information according to the filtering conditions specified by the user. The input is the data sorted in step 3. Specifically, it removes unnecessary information based on the user's preferences and extracts only the useful information. The output is the sorted information after filtering.

[0124] Step 5:

[0125] The server sends the filtered information to the terminal. The input is the filtering result from step 4. Specifically, it sends the data to the terminal and organizes the information in a user-friendly format. The output is feed data for display on the terminal.

[0126] Step 6:

[0127] The terminal displays the received information on the user interface. The input is feed data sent from the server. Specifically, it displays the data via the user interface and highlights the information that the user is interested in. As output, it provides visual information for the user to view.

[0128] Step 7:

[0129] The user reviews the displayed information and provides feedback. The input is the user's subjective evaluation. Specifically, the user generates feedback by pressing an evaluation button for a particular piece of information and sends it to the server. The output is the evaluation data received by the server.

[0130] Step 8:

[0131] The server learns to improve the accuracy of its classification algorithm based on feedback received from the user. The input is user feedback. Specifically, it retrains the AI ​​model or adjusts its parameters to improve the accuracy of subsequent analyses. The output is the improved model or improved filtering accuracy.

[0132] 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.

[0133] This invention is a system that aims to efficiently and optimally provide users with the information they need by classifying posts on social networking services into promotional posts and posts by general users, and combining this with an emotion engine that recognizes the emotional state of users.

[0134] The system consists of a server, a terminal, and an emotion engine for recognizing user emotions.

[0135] First, the server collects post data via the API of social networking services. The collected data is analyzed using natural language processing techniques to extract features. In this analysis, the context and tone of the posts are evaluated, and an AI model is used to classify them into promotional posts and regular posts. At the same time, sentiment analysis is also performed to calculate the sentiment score of the posts.

[0136] Next, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine analyzes the user's emotions from user interaction data and biometric information (e.g., freely customized input) and extracts that state as a digital signal.

[0137] The device retrieves filtered post information from the server and further adjusts the display of information based on the user's emotional state, determined by the sentiment engine. This is to enhance the user experience by highlighting different information depending on the user's emotions. For example, if the user is in a positive emotional state, positive and affirmative content will be highlighted, while if they are in a negative emotional state, calm and soothing content will be recommended to alleviate that state.

[0138] As a concrete example, consider a scenario where a user is feeling stressed and is searching for reviews about a new hobby. The server collects relevant review posts and analyzes the user's emotions using an emotion engine. On the user's device, posts that are expected to alleviate the user's stress are highlighted, providing a safe and secure environment for the user to access information.

[0139] This system makes it easier for users to obtain information that is best suited to their emotional state at any given time, allowing them to enjoy a more fulfilling user experience.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server collects post data containing specific keywords and hashtags through the APIs of social networking services. The collected data includes metadata such as post content, images, links, and poster information.

[0143] Step 2:

[0144] The server cleans the collected data. This cleaning process converts the text data into a more easily processed format, removing special characters and HTML tags. It also tokenizes the text, converting it to its base word form, thereby improving the accuracy of natural language processing.

[0145] Step 3:

[0146] The server uses natural language processing techniques to analyze the posted data and extract features from each post. These features include text length, sentiment score, frequency of words used, and image analysis results.

[0147] Step 4:

[0148] The server uses an AI model to classify posts into promotional posts and regular user posts based on extracted features. The AI ​​model is pre-trained and can determine whether or not there is commercial intent.

[0149] Step 5:

[0150] The server filters posts based on user-defined criteria. This filtering process includes excluding promotional posts and prioritizing posts with specific sentiment scores.

[0151] Step 6:

[0152] The emotion engine analyzes user input data and interaction logs to recognize the user's emotional state. The engine identifies the user's emotions from this data and sends that information to the server.

[0153] Step 7:

[0154] The server analyzes the user's sentiment data received from the sentiment engine and evaluates its relevance to the filtered post data. Based on this evaluation, the server selects posts appropriate to the user's emotional state and sends them to the device.

[0155] Step 8:

[0156] The device displays received posts on the user interface. During display, it's possible to apply features such as highlighting content based on the user's emotional state and animation effects to make specific feeds stand out.

[0157] Step 9:

[0158] Users act based on the displayed information and provide feedback as needed. This feedback is sent to the server and used to improve the system and train the model.

[0159] (Example 2)

[0160] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0161] Conventional information delivery systems lack the ability to select and display information based on the user's emotional state, making it difficult to provide information optimized for the user's psychological condition. Furthermore, there is room for improvement in the accuracy of classifying advertising information from general information, so further efforts are needed to provide the best possible user experience.

[0162] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0163] In this invention, the server includes means for analyzing information on a digital communication network using natural language processing, means for extracting features of the information and classifying it into advertising information and general information, means for sentiment analysis to recognize the user's emotional state, and means for filtering the classified information based on conditions and emotional states specified by the user. This makes it possible to provide optimal information according to the user's emotional state.

[0164] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0165] A "digital communication network" is a network system used to transmit data between electronic devices.

[0166] "Extracting information features" is the process of identifying and extracting important attributes and patterns from data.

[0167] "Advertising information" refers to information intended to promote products or services.

[0168] "General information" refers to everyday and general information that does not have a specific commercial purpose.

[0169] "Sentiment analysis" is a technology that automatically identifies and evaluates emotions and emotional nuances from text and data.

[0170] "Filtering" is the process of selecting data according to specific criteria and extracting only the necessary information.

[0171] A "user interface" refers to the means and designed screen displays and input devices that allow a system and a user to interact with each other.

[0172] This invention is a system for providing information optimized for the emotional state of users over a digital communication network. Specifically, it consists of a server, a terminal, and an emotion analysis engine for recognizing the user's emotions.

[0173] The server collects post data using social network APIs. During this process, the server analyzes the text data of each post using natural language processing techniques. Specifically, it utilizes programming languages ​​such as Python and natural language processing libraries to extract context and keywords from the text. Then, it uses a generative AI model to classify the posts into promotional and general information. Furthermore, it uses sentiment analysis techniques to calculate a sentiment score for each post.

[0174] The emotion engine uses biosensors and interaction data to analyze data about the user's emotions. This allows it to extract the user's current emotional state as a digital signal and provide that information to the system when needed.

[0175] The device retrieves filtered information from the server and adjusts the information displayed based on the user's emotional state. This adjustment is performed using, for example, a web browser or mobile application. If the user is feeling positive, positive and encouraging information is prioritized; if they are feeling negative, calming content that provides a sense of security is prioritized.

[0176] As a concrete example, consider a situation where a user is feeling stressed while searching for information about a new hobby. The server collects review articles related to the hobby, and the emotion engine evaluates the user's emotional state. The device highlights content that helps reduce the user's stress, providing an environment where they can comfortably access information.

[0177] An example of a prompt message might be, "Suggest a way to provide the user with the most suitable hobby-related reviews based on their emotional state."

[0178] This system allows users to smoothly acquire information that matches their emotional state at the time, enabling them to have a more fulfilling experience.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server collects posted data using the APIs of social networking services.

[0182] The system receives text data of posts obtained from the API as input. This data is converted to the required format and stored in a temporary data store.

[0183] Step 2:

[0184] The server analyzes the collected post data using natural language processing techniques.

[0185] The text data obtained as input is used to analyze the context and keywords using libraries such as TextBlob and NLTK. This allows for the extraction of key features of the posts.

[0186] Step 3:

[0187] The server uses a generative AI model to classify posts into promotional information and general information.

[0188] The system receives pre-analyzed feature data as input, performs classification calculations using AI models such as BERT and GPT, and determines the class of each post. The classification results are stored in a database.

[0189] Step 4:

[0190] The server uses sentiment analysis technology to calculate a sentiment score for each post.

[0191] Using the category data of the posts obtained in the previous step as input, a sentiment analysis library is used to calculate the sentiment score. The score is expressed as a number ranging from positive to negative, based on common metrics.

[0192] Step 5:

[0193] The emotion engine uses biosensors and interaction data to recognize the user's emotional state.

[0194] It receives user interaction data as input and collects data from biometric information as needed. Based on this, it outputs the user's emotional state as a digital signal.

[0195] Step 6:

[0196] The device retrieves filtered information from the server and adjusts the display of information based on the user's emotional state.

[0197] The device receives filtered post information and digital signals of the user's emotional state as input. Using this information, the device controls the placement and highlighting of information on the screen via a display algorithm. Content that aligns with the user's emotional state is highlighted.

[0198] Step 7:

[0199] The user reviews the information provided on the device and selects the necessary action.

[0200] Users can view content or request additional information based on the information provided and the options displayed.

[0201] (Application Example 2)

[0202] 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".

[0203] In recent years, content distribution services have made it difficult for users to find the information they need from the vast amount of data available. Furthermore, information is often provided without considering the user's emotional state, leading to a diminished user experience. Therefore, there is a need to enhance user satisfaction and provide a high-quality experience through optimal information delivery.

[0204] 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.

[0205] In this invention, the server includes means for analyzing information on a social networking service using natural language processing, means for extracting features of the information and classifying commercial posts and general posts, and means for filtering the classified information according to conditions specified by the user. This enables the optimal display of information based on the user's emotional state.

[0206] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0207] A "social networking service" refers to an online platform on the internet where people share opinions and information.

[0208] "Commercial posts" refer to information posted on social networking services by companies or advertisers for the purpose of promoting products or providing services.

[0209] "General posts" refer to information that individual users post on social networking services to share their everyday opinions and information.

[0210] "Filtering" is the process of selecting data that meets specific criteria from a large amount of information.

[0211] "Emotional state" refers to information that indicates the user's current mental state and emotional tendencies.

[0212] "User experience" refers to the overall experience and satisfaction of users when using a product or service.

[0213] This invention is a system for improving the user experience in content distribution services. This system combines natural language processing and sentiment analysis technologies to provide users with the most relevant information. The overall system flow is shown below.

[0214] The server first collects post data via the APIs of social networking services. At this stage, content from various users is aggregated. Next, natural language processing tools (e.g., Google® Cloud Natural Language API) are used to analyze these posts. As a result of the analysis, features of the posts are extracted and classified into commercial posts and general posts based on these features.

[0215] Next, the server uses an emotion analysis engine (e.g., IBM Watson® Emotion Analysis) to diagnose the emotional state of users based on the collected posts and user data. This allows the server to understand the emotional state of users and filter information accordingly.

[0216] The device receives filtered information sent from the server. Here, the device considers the user's emotional state and performs real-time control to highlight appropriate information. For this purpose, a content management system (e.g., Contentful) is utilized.

[0217] For example, if a user is feeling stressed, the server collects relaxing content that can help reduce stress and sends it to the device. The device then presents appropriate videos and content for the user to watch, thus supporting stress reduction.

[0218] Specific examples of prompt messages include, "Suggest video content suitable for reducing user stress," and "Display content that users seeking relaxation and healing can enjoy." This enables a customized experience tailored to individual users.

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The server collects posting data through the APIs of social networking services. The input is raw data such as user posts and shared content. The output generates a list of posting data to be analyzed. This data collection is performed in real time, ensuring that the latest posts are readily available.

[0222] Step 2:

[0223] The server analyzes the collected post data using natural language processing tools. This processing step extracts features such as context, tone, and theme from each post. The input is the post data collected in step 1, and the output is a dataset containing the features of each post. The analyzed information is classified into commercial posts and general posts, forming the basis for predicting content that users will be interested in.

[0224] Step 3:

[0225] The server uses an emotion analysis engine to diagnose the emotional state from posts and user data. The input data consists of the output data from step 2 and the user's past interaction history and response data. The output of this step is a score or evaluation indicating the user's emotional state. A generative AI model is used here to perform a detailed analysis of the user's current emotions.

[0226] Step 4:

[0227] The terminal receives filtered information from the server. The input is filtered information from the server based on the user's emotional state. This filtered information is adjusted according to the user's emotional state, governing the display of diverse content. The output is an optimized content list displayed on the user interface. This allows the user to easily access information that matches their own emotions.

[0228] Step 5:

[0229] Users interact with the provided content and provide feedback. This feedback is collected to improve the accuracy of future content recommendations. The input information mainly consists of user impressions and ratings. Based on this information, the system is continuously improved and used for future content recommendations. The feedback data is processed through a generative AI model process, based on example prompt sentences, to correct classification accuracy.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] This invention provides a system that automatically classifies posts on social networking services into promotional posts and posts from regular users, enabling users to efficiently access reliable information.

[0247] This system consists of servers, terminals, and users.

[0248] First, the server collects multiple posts from social networking services. This includes hashtags, keywords, or geographical information based on user-specified criteria. The collected data is then converted into a format that is easy to parse. This involves cleaning and tokenizing the text.

[0249] Next, the server analyzes the collected post data using natural language processing technology. In this analysis process, features are extracted, and attributes such as the sentiment score, post length, and presence of links for each post are evaluated. Based on these features, the AI ​​model classifies the posts as either promotional posts or posts from regular users.

[0250] After classification, the server filters posts based on the user's specified filtering criteria. For example, if a user wants to avoid promotional posts, the server will exclude data identified as promotional and send only posts from regular users to the device.

[0251] The terminal receives filtered information from the server and displays it on the user interface. The display can be customized by the user, for example, by highlighting information of particular interest to the user.

[0252] Users can verify whether the displayed information meets their needs and provide feedback to the server. This feedback is used to improve subsequent analysis models and forms the basis for providing highly accurate classification results.

[0253] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects posts with hashtags related to "electronic devices" and uses an AI model to categorize them into promotional posts and genuine reviews. The device then displays only reviews from actual purchasers, excluding promotional posts. This allows the user to confidently select a product.

[0254] Thus, this system provides an environment in which users can efficiently obtain reliable information on social networks and make informed decisions.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server collects post data that meets specified conditions (e.g., specific keywords or hashtags) through the API of social networking services. At the same time, it also retrieves metadata such as post content, poster information, and posting time.

[0258] Step 2:

[0259] The server cleans the acquired raw data. The cleaning process removes unnecessary HTML tags and special characters, making the text a plain format. This prepares the data for efficient natural language processing.

[0260] Step 3:

[0261] The server tokenizes the cleaned text data. Tokenization is the process of dividing the text into words and phrases. After this, stemming and lemmatization are performed to unify the base form of the words.

[0262] Step 4:

[0263] The server uses natural language processing technology to extract features from each post. These features include the length of the text, sentiment score (positive, negative, neutral), and whether or not there are links.

[0264] Step 5:

[0265] The server uses a pre-trained AI model to classify each post into promotional posts and regular posts based on the extracted features. This AI model takes feature vectors as input to determine the nature of the posts.

[0266] Step 6:

[0267] The server filters categorized posts based on user-specified criteria. Depending on user settings, it is possible to exclude promotional posts or select only posts with a specific sentiment.

[0268] Step 7:

[0269] The server sends filtered post data to the user's device. During transmission, the information is organized chronologically and by relevance to improve readability.

[0270] Step 8:

[0271] The device displays the received information on the user interface. The display reflects the user's customization settings, including highlighting of important information and hiding of promotional posts.

[0272] Step 9:

[0273] Users review the displayed information and provide feedback as needed. This feedback is sent to the server and used for the continuous improvement of the AI ​​model.

[0274] (Example 1)

[0275] 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."

[0276] The amount of information on social networking services is vast, making it difficult for users to efficiently access reliable information. In particular, the mix of commercial posts and posts from general users makes it difficult for users to quickly find the information they need. Furthermore, mechanisms for improving the accuracy of information classification are currently insufficient.

[0277] 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.

[0278] In this invention, the server includes means for analyzing data using natural language processing, means for extracting data characteristics and classifying them based on specific conditions, and means for selecting data classified based on conditions specified by the user. This enables users to efficiently access reliable information they need and utilize feedback to further improve classification accuracy.

[0279] "Natural language processing" is a technology that enables computers to understand and analyze human language, and is used to analyze the meaning and structure of text.

[0280] "Methods for extracting data characteristics" refer to the process of finding distinctive information from data, and include evaluating attributes such as text sentiment scores, post length, and the presence or absence of links.

[0281] "Means of classification based on specific conditions" refers to the process of dividing data into defined categories based on extracted characteristics, with the aim of distinguishing between commercial posts and posts from general users.

[0282] "Means of sorting based on user-specified conditions" refers to the process of extracting only the necessary information from pre-classified data according to the user's set requirements.

[0283] The "output device" is a device for visually providing information to the user, including but not limited to displays and monitors.

[0284] "Using feedback" is a process of collecting evaluations and opinions from users and using them as a reference to improve the performance and accuracy of the system.

[0285] In the form of this invention, three elements, namely the server, the terminal, and the user, are mainly involved.

[0286] First, the server collects data on the social network service. This collection is carried out based on the hash tags, keywords, or geographical information specified by the user. The server then converts the collected data into a form that is easy to analyze using natural language processing tools. In this process, the server cleans the text data and performs tokenization. Furthermore, it utilizes an AI model to extract the features of the data and classify it into commercial posts and general user posts.

[0287] The terminal plays a role in displaying the filtered data received from the server on the user interface. This makes it easier for the user to effectively obtain the information they are interested in. The user interface enables the user to customize the display according to their preferences. For example, by prominently highlighting the posts of new product reviews, it supports the user's selection.

[0288] The user can provide feedback on the accuracy and usefulness of the displayed information. This feedback is utilized as data for the server to improve the accuracy of the AI model. As a specific example of the operation, when the user is searching for reviews on a new electronic device, the server filters the relevant posts based on the prompt text "electronic device review" and provides the actual user reviews obtained as a result. Thereby, the user can easily find reliable information and smoothly proceed with the purchase decision.

[0289] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0290] Step 1:

[0291] The server collects posted data from social networking services. User-specified hashtags, keywords, or geographical information are used as input. The collected raw data includes the post text, poster information, and date. This data forms the basis for subsequent processing by the server.

[0292] Step 2:

[0293] The server preprocesses the collected data. Because the input data contains unnecessary noise and formatting, it undergoes cleaning and tokenization. Specifically, it removes special characters and HTML tags and converts the data into a more manageable format by separating it into words. The output of this process is text data suitable for analysis.

[0294] Step 3:

[0295] The server uses natural language processing techniques to extract features from pre-processed data. It analyzes features such as sentiment scores, post length, and the presence or absence of links, and prepares them as input for the AI ​​model. It calculates these attributes from the text data received as input and outputs them as feature vectors.

[0296] Step 4:

[0297] The server classifies posts using an AI model based on feature vectors. A generative AI model is used to distinguish between commercial posts and posts from regular users, based on the prompt text. This classification outputs which category each post belongs to.

[0298] Step 5:

[0299] The server selects posts classified based on the filtering conditions specified by the user. As input, it uses the classification results and the filtering conditions set by the user. As output, post data that meets the conditions is selected.

[0300] Step 6:

[0301] The terminal displays the filtered posts sent from the server on the user interface. Information arranged in an easy-to-view format is received as input and reflected on the terminal. The output is the display of information in a form that the user can easily understand.

[0302] Step 7:

[0303] The user evaluates the quality of the information displayed on the terminal and provides feedback to the server. Based on the feedback, the server adjusts the AI model to improve the classification accuracy. The input is the content of the user's feedback, and the output is in the form of fine-tuning the AI model.

[0304] (Application Example 1)

[0305] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0306] Conventionally, there is a large amount of information on social networks, and it is difficult to efficiently obtain highly reliable information from it. Especially when there is a lot of commercial information, it is difficult to find the posts of ordinary users, and it takes time and effort to select the information required by the users. Therefore, there is a demand for a system that allows users to easily access highly reliable general information and use it for decision-making.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0308] In this invention, the server includes means for collecting multiple data from a social network, means for analyzing the data using natural language processing, means for classifying commercial information and general information based on the attributes of the data, means for selecting the classified information according to conditions specified by the user, and means for displaying the selected information on a user interface and highlighting information of interest to the user. This enables users to easily access reliable general information on social networks and make decisions efficiently.

[0309] A "social network" is an online service that allows people to share information or content over the internet.

[0310] "Data" refers to a collection of information gathered on social networks, including posts, comments, and links.

[0311] "Natural language processing" is a technology for processing and analyzing human language using computers.

[0312] "Analysis" is the process of examining data in detail to understand and classify its contents.

[0313] An "attribute" is a specific characteristic or feature of data, used as a criterion for classification.

[0314] "Commercial information" refers to information disseminated for the purpose of promoting the sale of goods or services.

[0315] "General information" refers to information that is not for commercial purposes and is based on personal experiences and opinions.

[0316] "Selection" is the process of choosing only the necessary elements based on specific criteria.

[0317] A "user interface" refers to the display screens and functions that enable interaction between a computer system and a user.

[0318] "Highlighting" is a technique that visually highlights specific information to attract the user's attention.

[0319] The system of this invention efficiently analyzes data on social networks, enabling users to obtain reliable information. The server first collects posted data from social networks via an internet connection. The collected data is then processed using natural language processing techniques, including text cleaning and tokenization, to convert it into a parseable format. A standard server computer is used as the hardware, and natural language processing libraries and frameworks (such as the Transformers library) are utilized as the software.

[0320] After analysis, the server uses an AI model to classify posts into commercial and general information based on their data attributes. This allows for the selection of reliable information and filtering of information according to conditions specified by individual users. The selected information is then sent to the terminal and displayed via the user interface. Users can review information of interest and provide feedback to the server, contributing to the improvement of the classification algorithm's accuracy.

[0321] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects and analyzes data tagged with "electronic device," and displays only reliable reviews from general users on the device, allowing the user to make product selections based on more accurate information.

[0322] Furthermore, the following prompt statements can be used as input to the generative AI model.

[0323] "I'm looking for smartphone reviews. Please prioritize posts from regular users."

[0324] This allows users to easily obtain the most relevant information.

[0325] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0326] Step 1:

[0327] The server uses the APIs of social networking services to collect posted data based on specified conditions. It receives user-specified hashtags and keywords as input and makes API requests. The output, including the post text, user information, and posting date and time, is returned to the server in JSON format. This data is then stored in internal storage.

[0328] Step 2:

[0329] The server converts the collected data into a format that is easy to analyze using natural language processing techniques. The input is the posted data obtained in step 1. Specifically, it performs text preprocessing (cleaning, normalization, tokenization) and extracts sentiment scores and keywords. The output is an analyzable text dataset.

[0330] Step 3:

[0331] The server inputs the results of natural language processing analysis into an AI model to classify posts into commercial and general information. The feature data obtained in step 2 is used as input. Specifically, the AI ​​model is used to determine the commercial potential of each post and perform the classification. The output is the classification result (data labeled as commercial information).

[0332] Step 4:

[0333] The server sorts the information according to the filtering conditions specified by the user. The input is the data sorted in step 3. Specifically, it removes unnecessary information based on the user's preferences and extracts only the useful information. The output is the sorted information after filtering.

[0334] Step 5:

[0335] The server sends the filtered information to the terminal. The input is the filtering result from step 4. Specifically, it sends the data to the terminal and organizes the information in a user-friendly format. The output is feed data for display on the terminal.

[0336] Step 6:

[0337] The terminal displays the received information on the user interface. The input is feed data sent from the server. Specifically, it displays the data via the user interface and highlights the information that the user is interested in. As output, it provides visual information for the user to view.

[0338] Step 7:

[0339] The user reviews the displayed information and provides feedback. The input is the user's subjective evaluation. Specifically, the user generates feedback by pressing an evaluation button for a particular piece of information and sends it to the server. The output is the evaluation data received by the server.

[0340] Step 8:

[0341] The server learns to improve the accuracy of its classification algorithm based on feedback received from the user. The input is user feedback. Specifically, it retrains the AI ​​model or adjusts its parameters to improve the accuracy of subsequent analyses. The output is the improved model or improved filtering accuracy.

[0342] 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.

[0343] This invention is a system that aims to efficiently and optimally provide users with the information they need by classifying posts on social networking services into promotional posts and posts by general users, and combining this with an emotion engine that recognizes the emotional state of users.

[0344] The system consists of a server, a terminal, and an emotion engine for recognizing user emotions.

[0345] First, the server collects post data via the API of social networking services. The collected data is analyzed using natural language processing techniques to extract features. In this analysis, the context and tone of the posts are evaluated, and an AI model is used to classify them into promotional posts and regular posts. At the same time, sentiment analysis is also performed to calculate the sentiment score of the posts.

[0346] Next, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine analyzes the user's emotions from user interaction data and biometric information (e.g., freely customized input) and extracts that state as a digital signal.

[0347] The device retrieves filtered post information from the server and further adjusts the display of information based on the user's emotional state, determined by the sentiment engine. This is to enhance the user experience by highlighting different information depending on the user's emotions. For example, if the user is in a positive emotional state, positive and affirmative content will be highlighted, while if they are in a negative emotional state, calm and soothing content will be recommended to alleviate that state.

[0348] As a concrete example, consider a scenario where a user is feeling stressed and is searching for reviews about a new hobby. The server collects relevant review posts and analyzes the user's emotions using an emotion engine. On the user's device, posts that are expected to alleviate the user's stress are highlighted, providing a safe and secure environment for the user to access information.

[0349] This system makes it easier for users to obtain information that is best suited to their emotional state at any given time, allowing them to enjoy a more fulfilling user experience.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The server collects post data containing specific keywords and hashtags through the APIs of social networking services. The collected data includes metadata such as post content, images, links, and poster information.

[0353] Step 2:

[0354] The server cleans the collected data. This cleaning process converts the text data into a more easily processed format, removing special characters and HTML tags. It also tokenizes the text, converting it to its base word form, thereby improving the accuracy of natural language processing.

[0355] Step 3:

[0356] The server uses natural language processing techniques to analyze the posted data and extract features from each post. These features include text length, sentiment score, frequency of words used, and image analysis results.

[0357] Step 4:

[0358] The server uses an AI model to classify posts into promotional posts and regular user posts based on extracted features. The AI ​​model is pre-trained and can determine whether or not there is commercial intent.

[0359] Step 5:

[0360] The server filters posts based on user-defined criteria. This filtering process includes excluding promotional posts and prioritizing posts with specific sentiment scores.

[0361] Step 6:

[0362] The emotion engine analyzes user input data and interaction logs to recognize the user's emotional state. The engine identifies the user's emotions from this data and sends that information to the server.

[0363] Step 7:

[0364] The server analyzes the user's sentiment data received from the sentiment engine and evaluates its relevance to the filtered post data. Based on this evaluation, the server selects posts appropriate to the user's emotional state and sends them to the device.

[0365] Step 8:

[0366] The device displays received posts on the user interface. During display, it's possible to apply features such as highlighting content based on the user's emotional state and animation effects to make specific feeds stand out.

[0367] Step 9:

[0368] Users act based on the displayed information and provide feedback as needed. This feedback is sent to the server and used to improve the system and train the model.

[0369] (Example 2)

[0370] 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".

[0371] Conventional information delivery systems lack the ability to select and display information based on the user's emotional state, making it difficult to provide information optimized for the user's psychological condition. Furthermore, there is room for improvement in the accuracy of classifying advertising information from general information, so further efforts are needed to provide the best possible user experience.

[0372] 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.

[0373] In this invention, the server includes means for analyzing information on a digital communication network using natural language processing, means for extracting features of the information and classifying it into advertising information and general information, means for sentiment analysis to recognize the user's emotional state, and means for filtering the classified information based on conditions and emotional states specified by the user. This makes it possible to provide optimal information according to the user's emotional state.

[0374] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0375] A "digital communication network" is a network system used to transmit data between electronic devices.

[0376] "Extracting information features" is the process of identifying and extracting important attributes and patterns from data.

[0377] "Advertising information" refers to information intended to promote products or services.

[0378] "General information" refers to everyday and general information that does not have a specific commercial purpose.

[0379] "Sentiment analysis" is a technology that automatically identifies and evaluates emotions and emotional nuances from text and data.

[0380] "Filtering" is the process of selecting data according to specific criteria and extracting only the necessary information.

[0381] A "user interface" refers to the means and designed screen displays and input devices that allow a system and a user to interact with each other.

[0382] This invention is a system for providing information optimized for the emotional state of users over a digital communication network. Specifically, it consists of a server, a terminal, and an emotion analysis engine for recognizing the user's emotions.

[0383] The server collects post data using social network APIs. During this process, the server analyzes the text data of each post using natural language processing techniques. Specifically, it utilizes programming languages ​​such as Python and natural language processing libraries to extract context and keywords from the text. Then, it uses a generative AI model to classify the posts into promotional and general information. Furthermore, it uses sentiment analysis techniques to calculate a sentiment score for each post.

[0384] The emotion engine uses biosensors and interaction data to analyze data about the user's emotions. This allows it to extract the user's current emotional state as a digital signal and provide that information to the system when needed.

[0385] The device retrieves filtered information from the server and adjusts the information displayed based on the user's emotional state. This adjustment is performed using, for example, a web browser or mobile application. If the user is feeling positive, positive and encouraging information is prioritized; if they are feeling negative, calming content that provides a sense of security is prioritized.

[0386] As a concrete example, consider a situation where a user is feeling stressed while searching for information about a new hobby. The server collects review articles related to the hobby, and the emotion engine evaluates the user's emotional state. The device highlights content that helps reduce the user's stress, providing an environment where they can comfortably access information.

[0387] An example of a prompt message might be, "Suggest a way to provide the user with the most suitable hobby-related reviews based on their emotional state."

[0388] This system allows users to smoothly acquire information that matches their emotional state at the time, enabling them to have a more fulfilling experience.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] The server collects posted data using the APIs of social networking services.

[0392] The system receives text data of posts obtained from the API as input. This data is converted to the required format and stored in a temporary data store.

[0393] Step 2:

[0394] The server analyzes the collected post data using natural language processing techniques.

[0395] The text data obtained as input is used to analyze the context and keywords using libraries such as TextBlob and NLTK. This allows for the extraction of key features of the posts.

[0396] Step 3:

[0397] The server uses a generative AI model to classify posts into promotional information and general information.

[0398] The system receives pre-analyzed feature data as input, performs classification calculations using AI models such as BERT and GPT, and determines the class of each post. The classification results are stored in a database.

[0399] Step 4:

[0400] The server uses sentiment analysis technology to calculate a sentiment score for each post.

[0401] Using the category data of the posts obtained in the previous step as input, a sentiment analysis library is used to calculate the sentiment score. The score is expressed as a number ranging from positive to negative, based on common metrics.

[0402] Step 5:

[0403] The emotion engine uses biosensors and interaction data to recognize the user's emotional state.

[0404] It receives user interaction data as input and collects data from biometric information as needed. Based on this, it outputs the user's emotional state as a digital signal.

[0405] Step 6:

[0406] The device retrieves filtered information from the server and adjusts the display of information based on the user's emotional state.

[0407] The device receives filtered post information and digital signals of the user's emotional state as input. Using this information, the device controls the placement and highlighting of information on the screen via a display algorithm. Content that aligns with the user's emotional state is highlighted.

[0408] Step 7:

[0409] The user reviews the information provided on the device and selects the necessary action.

[0410] Users can view content or request additional information based on the information provided and the options displayed.

[0411] (Application Example 2)

[0412] 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."

[0413] In recent years, content distribution services have made it difficult for users to find the information they need from the vast amount of data available. Furthermore, information is often provided without considering the user's emotional state, leading to a diminished user experience. Therefore, there is a need to enhance user satisfaction and provide a high-quality experience through optimal information delivery.

[0414] 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.

[0415] In this invention, the server includes means for analyzing information on a social networking service using natural language processing, means for extracting features of the information and classifying commercial posts and general posts, and means for filtering the classified information according to conditions specified by the user. This enables the optimal display of information based on the user's emotional state.

[0416] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0417] A "social networking service" refers to an online platform on the internet where people share opinions and information.

[0418] "Commercial posts" refer to information posted on social networking services by companies or advertisers for the purpose of promoting products or providing services.

[0419] "General posts" refer to information that individual users post on social networking services to share their everyday opinions and information.

[0420] "Filtering" is the process of selecting data that meets specific criteria from a large amount of information.

[0421] "Emotional state" refers to information that indicates the user's current mental state and emotional tendencies.

[0422] "User experience" refers to the overall experience and satisfaction of users when using a product or service.

[0423] This invention is a system for improving the user experience in content distribution services. This system combines natural language processing and sentiment analysis technologies to provide users with the most relevant information. The overall system flow is shown below.

[0424] The server first collects post data via the APIs of social networking services. At this stage, content from various users is aggregated. Next, natural language processing tools (e.g., Google Cloud Natural Language API) are used to analyze these posts. As a result of the analysis, the characteristics of the posts are extracted and classified into commercial posts and general posts based on these characteristics.

[0425] Next, the server uses an emotion analysis engine (e.g., IBM Watson Emotion Analysis) to diagnose the emotional state of users based on the collected posts and user data. This allows the server to understand the emotional state of users and filter information accordingly.

[0426] The device receives filtered information sent from the server. Here, the device considers the user's emotional state and performs real-time control to highlight appropriate information. For this purpose, a content management system (e.g., Contentful) is utilized.

[0427] For example, if a user is feeling stressed, the server collects relaxing content that can help reduce stress and sends it to the device. The device then presents appropriate videos and content for the user to watch, thus supporting stress reduction.

[0428] Specific examples of prompt messages include, "Suggest video content suitable for reducing user stress," and "Display content that users seeking relaxation and healing can enjoy." This enables a customized experience tailored to individual users.

[0429] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0430] Step 1:

[0431] The server collects posting data through the APIs of social networking services. The input is raw data such as user posts and shared content. The output generates a list of posting data to be analyzed. This data collection is performed in real time, ensuring that the latest posts are readily available.

[0432] Step 2:

[0433] The server analyzes the collected post data using natural language processing tools. This processing step extracts features such as context, tone, and theme from each post. The input is the post data collected in step 1, and the output is a dataset containing the features of each post. The analyzed information is classified into commercial posts and general posts, forming the basis for predicting content that users will be interested in.

[0434] Step 3:

[0435] The server uses an emotion analysis engine to diagnose the emotional state from posts and user data. The input data consists of the output data from step 2 and the user's past interaction history and response data. The output of this step is a score or evaluation indicating the user's emotional state. A generative AI model is used here to perform a detailed analysis of the user's current emotions.

[0436] Step 4:

[0437] The terminal receives filtered information from the server. The input is filtered information from the server based on the user's emotional state. This filtered information is adjusted according to the user's emotional state, governing the display of diverse content. The output is an optimized content list displayed on the user interface. This allows the user to easily access information that matches their own emotions.

[0438] Step 5:

[0439] Users interact with the provided content and provide feedback. This feedback is collected to improve the accuracy of future content recommendations. The input information mainly consists of user impressions and ratings. Based on this information, the system is continuously improved and used for future content recommendations. The feedback data is processed through a generative AI model process, based on example prompt sentences, to correct classification accuracy.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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".

[0456] This invention provides a system that automatically classifies posts on social networking services into promotional posts and posts from regular users, enabling users to efficiently access reliable information.

[0457] This system consists of servers, terminals, and users.

[0458] First, the server collects multiple posts from social networking services. This includes hashtags, keywords, or geographical information based on user-specified criteria. The collected data is then converted into a format that is easy to parse. This involves cleaning and tokenizing the text.

[0459] Next, the server analyzes the collected post data using natural language processing technology. In this analysis process, features are extracted, and attributes such as the sentiment score, post length, and presence of links for each post are evaluated. Based on these features, the AI ​​model classifies the posts as either promotional posts or posts from regular users.

[0460] After classification, the server filters posts based on the user's specified filtering criteria. For example, if a user wants to avoid promotional posts, the server will exclude data identified as promotional and send only posts from regular users to the device.

[0461] The terminal receives filtered information from the server and displays it on the user interface. The display can be customized by the user, for example, by highlighting information of particular interest to the user.

[0462] Users can verify whether the displayed information meets their needs and provide feedback to the server. This feedback is used to improve subsequent analysis models and forms the basis for providing highly accurate classification results.

[0463] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects posts with hashtags related to "electronic devices" and uses an AI model to categorize them into promotional posts and genuine reviews. The device then displays only reviews from actual purchasers, excluding promotional posts. This allows the user to confidently select a product.

[0464] Thus, this system provides an environment in which users can efficiently obtain reliable information on social networks and make informed decisions.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The server collects post data that meets specified conditions (e.g., specific keywords or hashtags) through the API of social networking services. At the same time, it also retrieves metadata such as post content, poster information, and posting time.

[0468] Step 2:

[0469] The server cleans the acquired raw data. The cleaning process removes unnecessary HTML tags and special characters, making the text a plain format. This prepares the data for efficient natural language processing.

[0470] Step 3:

[0471] The server tokenizes the cleaned text data. Tokenization is the process of dividing the text into words and phrases. After this, stemming and lemmatization are performed to unify the base form of the words.

[0472] Step 4:

[0473] The server uses natural language processing technology to extract features from each post. These features include the length of the text, sentiment score (positive, negative, neutral), and whether or not there are links.

[0474] Step 5:

[0475] The server uses a pre-trained AI model to classify each post into promotional posts and regular posts based on the extracted features. This AI model takes feature vectors as input to determine the nature of the posts.

[0476] Step 6:

[0477] The server filters categorized posts based on user-specified criteria. Depending on user settings, it is possible to exclude promotional posts or select only posts with a specific sentiment.

[0478] Step 7:

[0479] The server sends filtered post data to the user's device. During transmission, the information is organized chronologically and by relevance to improve readability.

[0480] Step 8:

[0481] The device displays the received information on the user interface. The display reflects the user's customization settings, including highlighting of important information and hiding of promotional posts.

[0482] Step 9:

[0483] Users review the displayed information and provide feedback as needed. This feedback is sent to the server and used for the continuous improvement of the AI ​​model.

[0484] (Example 1)

[0485] 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."

[0486] The amount of information on social networking services is vast, making it difficult for users to efficiently access reliable information. In particular, the mix of commercial posts and posts from general users makes it difficult for users to quickly find the information they need. Furthermore, mechanisms for improving the accuracy of information classification are currently insufficient.

[0487] 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.

[0488] In this invention, the server includes means for analyzing data using natural language processing, means for extracting data characteristics and classifying them based on specific conditions, and means for selecting data classified based on conditions specified by the user. This enables users to efficiently access reliable information they need and utilize feedback to further improve classification accuracy.

[0489] "Natural language processing" is a technology that enables computers to understand and analyze human language, and is used to analyze the meaning and structure of text.

[0490] "Methods for extracting data characteristics" refer to the process of finding distinctive information from data, and include evaluating attributes such as text sentiment scores, post length, and the presence or absence of links.

[0491] "Means of classification based on specific conditions" refers to the process of dividing data into defined categories based on extracted characteristics, with the aim of distinguishing between commercial posts and posts from general users.

[0492] "Means of sorting based on user-specified conditions" refers to the process of extracting only the necessary information from pre-classified data according to the user's set requirements.

[0493] An "output device" is a device used to provide information to a user visually, and includes, but is not limited to, displays and monitors.

[0494] "Utilizing feedback" is the process of collecting evaluations and opinions from users and using them as a reference to improve the performance and accuracy of the system.

[0495] In this embodiment of the invention, three elements are primarily involved: a server, a terminal, and a user.

[0496] First, the server collects data from social networking services. This collection is based on hashtags, keywords, or geographical information specified by the user. The server then converts the collected data into a format that is easy to analyze using natural language processing tools. In this process, the server cleans and tokenizes the text data. Furthermore, it uses AI models to extract data features and classify posts into commercial posts and posts from general users.

[0497] The terminal's role is to display filtered data received from the server on the user interface. This makes it easier for users to effectively obtain information that interests them. The user interface allows users to customize the display according to their preferences. For example, it can help users make choices by clearly highlighting new product reviews.

[0498] Users can provide feedback on the accuracy and usefulness of the displayed information. This feedback is used by the server to improve the accuracy of the AI ​​model. As a concrete example, if a user is looking for reviews of a new electronic device, the server will filter relevant posts based on the prompt "electronic device reviews" and provide actual user reviews as a result. This allows users to easily find reliable information and make purchasing decisions more smoothly.

[0499] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0500] Step 1:

[0501] The server collects posted data from social networking services. User-specified hashtags, keywords, or geographical information are used as input. The collected raw data includes the post text, poster information, and date. This data forms the basis for subsequent processing by the server.

[0502] Step 2:

[0503] The server preprocesses the collected data. Because the input data contains unnecessary noise and formatting, it undergoes cleaning and tokenization. Specifically, it removes special characters and HTML tags and converts the data into a more manageable format by separating it into words. The output of this process is text data suitable for analysis.

[0504] Step 3:

[0505] The server uses natural language processing techniques to extract features from pre-processed data. It analyzes features such as sentiment scores, post length, and the presence or absence of links, and prepares them as input for the AI ​​model. It calculates these attributes from the text data received as input and outputs them as feature vectors.

[0506] Step 4:

[0507] The server classifies posts using an AI model based on feature vectors. A generative AI model is used to distinguish between commercial posts and posts from regular users, based on the prompt text. This classification outputs which category each post belongs to.

[0508] Step 5:

[0509] The server selects posts categorized based on the filtering conditions specified by the user. The input consists of the classification results and the filtering conditions set by the user. The output is the selected post data that matches the conditions.

[0510] Step 6:

[0511] The terminal displays filtered posts sent from the server on the user interface. Information formatted for user readability is received as input and reflected on the terminal. The output is an information display in a format that the user can easily understand.

[0512] Step 7:

[0513] The user evaluates the quality of the information displayed on the device and provides feedback to the server. Based on the feedback, the server adjusts the AI ​​model to improve classification accuracy. The input is the user's feedback, and the output is in the form of fine-tuning the AI ​​model.

[0514] (Application Example 1)

[0515] 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."

[0516] Traditionally, the sheer volume of information on social networks makes it difficult to efficiently extract reliable information. This is especially true when commercial information is prevalent, making it challenging to find posts from ordinary users and requiring significant time and effort for users to sift through the information they need. Therefore, there is a need for a system that allows users to easily access reliable general information and use it to aid in decision-making.

[0517] 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.

[0518] In this invention, the server includes means for collecting multiple data from a social network, means for analyzing the data using natural language processing, means for classifying commercial information and general information based on the attributes of the data, means for selecting the classified information according to conditions specified by the user, and means for displaying the selected information on a user interface and highlighting information of interest to the user. This enables users to easily access reliable general information on social networks and make decisions efficiently.

[0519] A "social network" is an online service that allows people to share information or content over the internet.

[0520] "Data" refers to a collection of information gathered on social networks, including posts, comments, and links.

[0521] "Natural language processing" is a technology for processing and analyzing human language using computers.

[0522] "Analysis" is the process of examining data in detail to understand and classify its contents.

[0523] An "attribute" is a specific characteristic or feature of data, used as a criterion for classification.

[0524] "Commercial information" refers to information disseminated for the purpose of promoting the sale of goods or services.

[0525] "General information" refers to information that is not for commercial purposes and is based on personal experiences and opinions.

[0526] "Selection" is the process of choosing only the necessary elements based on specific criteria.

[0527] A "user interface" refers to the display screens and functions that enable interaction between a computer system and a user.

[0528] "Highlighting" is a technique that visually highlights specific information to attract the user's attention.

[0529] The system of this invention efficiently analyzes data on social networks, enabling users to obtain reliable information. The server first collects posted data from social networks via an internet connection. The collected data is then processed using natural language processing techniques, including text cleaning and tokenization, to convert it into a parseable format. A standard server computer is used as the hardware, and natural language processing libraries and frameworks (such as the Transformers library) are utilized as the software.

[0530] After analysis, the server uses an AI model to classify posts into commercial and general information based on their data attributes. This allows for the selection of reliable information and filtering of information according to conditions specified by individual users. The selected information is then sent to the terminal and displayed via the user interface. Users can review information of interest and provide feedback to the server, contributing to the improvement of the classification algorithm's accuracy.

[0531] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects and analyzes data tagged with "electronic device," and displays only reliable reviews from general users on the device, allowing the user to make product selections based on more accurate information.

[0532] Furthermore, the following prompt statements can be used as input to the generative AI model.

[0533] "I'm looking for smartphone reviews. Please prioritize posts from regular users."

[0534] This allows users to easily obtain the most relevant information.

[0535] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0536] Step 1:

[0537] The server uses the APIs of social networking services to collect posted data based on specified conditions. It receives user-specified hashtags and keywords as input and makes API requests. The output, including the post text, user information, and posting date and time, is returned to the server in JSON format. This data is then stored in internal storage.

[0538] Step 2:

[0539] The server converts the collected data into a format that is easy to analyze using natural language processing techniques. The input is the posted data obtained in step 1. Specifically, it performs text preprocessing (cleaning, normalization, tokenization) and extracts sentiment scores and keywords. The output is an analyzable text dataset.

[0540] Step 3:

[0541] The server inputs the results of natural language processing analysis into an AI model to classify posts into commercial and general information. The feature data obtained in step 2 is used as input. Specifically, the AI ​​model is used to determine the commercial potential of each post and perform the classification. The output is the classification result (data labeled as commercial information).

[0542] Step 4:

[0543] The server sorts the information according to the filtering conditions specified by the user. The input is the data sorted in step 3. Specifically, it removes unnecessary information based on the user's preferences and extracts only the useful information. The output is the sorted information after filtering.

[0544] Step 5:

[0545] The server sends the filtered information to the terminal. The input is the filtering result from step 4. Specifically, it sends the data to the terminal and organizes the information in a user-friendly format. The output is feed data for display on the terminal.

[0546] Step 6:

[0547] The terminal displays the received information on the user interface. The input is feed data sent from the server. Specifically, it displays the data via the user interface and highlights the information that the user is interested in. As output, it provides visual information for the user to view.

[0548] Step 7:

[0549] The user reviews the displayed information and provides feedback. The input is the user's subjective evaluation. Specifically, the user generates feedback by pressing an evaluation button for a particular piece of information and sends it to the server. The output is the evaluation data received by the server.

[0550] Step 8:

[0551] The server learns to improve the accuracy of its classification algorithm based on feedback received from the user. The input is user feedback. Specifically, it retrains the AI ​​model or adjusts its parameters to improve the accuracy of subsequent analyses. The output is the improved model or improved filtering accuracy.

[0552] 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.

[0553] This invention is a system that aims to efficiently and optimally provide users with the information they need by classifying posts on social networking services into promotional posts and posts by general users, and combining this with an emotion engine that recognizes the emotional state of users.

[0554] The system consists of a server, a terminal, and an emotion engine for recognizing user emotions.

[0555] First, the server collects post data via the API of social networking services. The collected data is analyzed using natural language processing techniques to extract features. In this analysis, the context and tone of the posts are evaluated, and an AI model is used to classify them into promotional posts and regular posts. At the same time, sentiment analysis is also performed to calculate the sentiment score of the posts.

[0556] Next, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine analyzes the user's emotions from user interaction data and biometric information (e.g., freely customized input) and extracts that state as a digital signal.

[0557] The device retrieves filtered post information from the server and further adjusts the display of information based on the user's emotional state, determined by the sentiment engine. This is to enhance the user experience by highlighting different information depending on the user's emotions. For example, if the user is in a positive emotional state, positive and affirmative content will be highlighted, while if they are in a negative emotional state, calm and soothing content will be recommended to alleviate that state.

[0558] As a concrete example, consider a scenario where a user is feeling stressed and is searching for reviews about a new hobby. The server collects relevant review posts and analyzes the user's emotions using an emotion engine. On the user's device, posts that are expected to alleviate the user's stress are highlighted, providing a safe and secure environment for the user to access information.

[0559] This system makes it easier for users to obtain information that is best suited to their emotional state at any given time, allowing them to enjoy a more fulfilling user experience.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The server collects post data containing specific keywords and hashtags through the APIs of social networking services. The collected data includes metadata such as post content, images, links, and poster information.

[0563] Step 2:

[0564] The server cleans the collected data. This cleaning process converts the text data into a more easily processed format, removing special characters and HTML tags. It also tokenizes the text, converting it to its base word form, thereby improving the accuracy of natural language processing.

[0565] Step 3:

[0566] The server uses natural language processing techniques to analyze the posted data and extract features from each post. These features include text length, sentiment score, frequency of words used, and image analysis results.

[0567] Step 4:

[0568] The server uses an AI model to classify posts into promotional posts and regular user posts based on extracted features. The AI ​​model is pre-trained and can determine whether or not there is commercial intent.

[0569] Step 5:

[0570] The server filters posts based on user-defined criteria. This filtering process includes excluding promotional posts and prioritizing posts with specific sentiment scores.

[0571] Step 6:

[0572] The emotion engine analyzes user input data and interaction logs to recognize the user's emotional state. The engine identifies the user's emotions from this data and sends that information to the server.

[0573] Step 7:

[0574] The server analyzes the user's sentiment data received from the sentiment engine and evaluates its relevance to the filtered post data. Based on this evaluation, the server selects posts appropriate to the user's emotional state and sends them to the device.

[0575] Step 8:

[0576] The device displays received posts on the user interface. During display, it's possible to apply features such as highlighting content based on the user's emotional state and animation effects to make specific feeds stand out.

[0577] Step 9:

[0578] Users act based on the displayed information and provide feedback as needed. This feedback is sent to the server and used to improve the system and train the model.

[0579] (Example 2)

[0580] 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."

[0581] Conventional information delivery systems lack the ability to select and display information based on the user's emotional state, making it difficult to provide information optimized for the user's psychological condition. Furthermore, there is room for improvement in the accuracy of classifying advertising information from general information, so further efforts are needed to provide the best possible user experience.

[0582] 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.

[0583] In this invention, the server includes means for analyzing information on a digital communication network using natural language processing, means for extracting features of the information and classifying it into advertising information and general information, means for sentiment analysis to recognize the user's emotional state, and means for filtering the classified information based on conditions and emotional states specified by the user. This makes it possible to provide optimal information according to the user's emotional state.

[0584] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0585] A "digital communication network" is a network system used to transmit data between electronic devices.

[0586] "Extracting information features" is the process of identifying and extracting important attributes and patterns from data.

[0587] "Advertising information" refers to information intended to promote products or services.

[0588] "General information" refers to everyday and general information that does not have a specific commercial purpose.

[0589] "Sentiment analysis" is a technology that automatically identifies and evaluates emotions and emotional nuances from text and data.

[0590] "Filtering" is the process of selecting data according to specific criteria and extracting only the necessary information.

[0591] A "user interface" refers to the means and designed screen displays and input devices that allow a system and a user to interact with each other.

[0592] This invention is a system for providing information optimized for the emotional state of users over a digital communication network. Specifically, it consists of a server, a terminal, and an emotion analysis engine for recognizing the user's emotions.

[0593] The server collects post data using social network APIs. During this process, the server analyzes the text data of each post using natural language processing techniques. Specifically, it utilizes programming languages ​​such as Python and natural language processing libraries to extract context and keywords from the text. Then, it uses a generative AI model to classify the posts into promotional and general information. Furthermore, it uses sentiment analysis techniques to calculate a sentiment score for each post.

[0594] The emotion engine uses biosensors and interaction data to analyze data about the user's emotions. This allows it to extract the user's current emotional state as a digital signal and provide that information to the system when needed.

[0595] The device retrieves filtered information from the server and adjusts the information displayed based on the user's emotional state. This adjustment is performed using, for example, a web browser or mobile application. If the user is feeling positive, positive and encouraging information is prioritized; if they are feeling negative, calming content that provides a sense of security is prioritized.

[0596] As a concrete example, consider a situation where a user is feeling stressed while searching for information about a new hobby. The server collects review articles related to the hobby, and the emotion engine evaluates the user's emotional state. The device highlights content that helps reduce the user's stress, providing an environment where they can comfortably access information.

[0597] An example of a prompt message might be, "Suggest a way to provide the user with the most suitable hobby-related reviews based on their emotional state."

[0598] This system allows users to smoothly acquire information that matches their emotional state at the time, enabling them to have a more fulfilling experience.

[0599] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0600] Step 1:

[0601] The server collects posted data using the APIs of social networking services.

[0602] The system receives text data of posts obtained from the API as input. This data is converted to the required format and stored in a temporary data store.

[0603] Step 2:

[0604] The server analyzes the collected post data using natural language processing techniques.

[0605] The text data obtained as input is used to analyze the context and keywords using libraries such as TextBlob and NLTK. This allows for the extraction of key features of the posts.

[0606] Step 3:

[0607] The server uses a generative AI model to classify posts into promotional information and general information.

[0608] The system receives pre-analyzed feature data as input, performs classification calculations using AI models such as BERT and GPT, and determines the class of each post. The classification results are stored in a database.

[0609] Step 4:

[0610] The server uses sentiment analysis technology to calculate a sentiment score for each post.

[0611] Using the category data of the posts obtained in the previous step as input, a sentiment analysis library is used to calculate the sentiment score. The score is expressed as a number ranging from positive to negative, based on common metrics.

[0612] Step 5:

[0613] The emotion engine uses biosensors and interaction data to recognize the user's emotional state.

[0614] It receives user interaction data as input and collects data from biometric information as needed. Based on this, it outputs the user's emotional state as a digital signal.

[0615] Step 6:

[0616] The device retrieves filtered information from the server and adjusts the display of information based on the user's emotional state.

[0617] The device receives filtered post information and digital signals of the user's emotional state as input. Using this information, the device controls the placement and highlighting of information on the screen via a display algorithm. Content that aligns with the user's emotional state is highlighted.

[0618] Step 7:

[0619] The user reviews the information provided on the device and selects the necessary action.

[0620] Users can view content or request additional information based on the information provided and the options displayed.

[0621] (Application Example 2)

[0622] 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."

[0623] In recent years, content distribution services have made it difficult for users to find the information they need from the vast amount of data available. Furthermore, information is often provided without considering the user's emotional state, leading to a diminished user experience. Therefore, there is a need to enhance user satisfaction and provide a high-quality experience through optimal information delivery.

[0624] 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.

[0625] In this invention, the server includes means for analyzing information on a social networking service using natural language processing, means for extracting features of the information and classifying commercial posts and general posts, and means for filtering the classified information according to conditions specified by the user. This enables the optimal display of information based on the user's emotional state.

[0626] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0627] A "social networking service" refers to an online platform on the internet where people share opinions and information.

[0628] "Commercial posts" refer to information posted on social networking services by companies or advertisers for the purpose of promoting products or providing services.

[0629] "General posts" refer to information that individual users post on social networking services to share their everyday opinions and information.

[0630] "Filtering" is the process of selecting data that meets specific criteria from a large amount of information.

[0631] "Emotional state" refers to information that indicates the user's current mental state and emotional tendencies.

[0632] "User experience" refers to the overall experience and satisfaction of users when using a product or service.

[0633] This invention is a system for improving the user experience in content distribution services. This system combines natural language processing and sentiment analysis technologies to provide users with the most relevant information. The overall system flow is shown below.

[0634] The server first collects post data via the APIs of social networking services. At this stage, content from various users is aggregated. Next, natural language processing tools (e.g., Google Cloud Natural Language API) are used to analyze these posts. As a result of the analysis, the characteristics of the posts are extracted and classified into commercial posts and general posts based on these characteristics.

[0635] Next, the server uses an emotion analysis engine (e.g., IBM Watson Emotion Analysis) to diagnose the emotional state of users based on the collected posts and user data. This allows the server to understand the emotional state of users and filter information accordingly.

[0636] The device receives filtered information sent from the server. Here, the device considers the user's emotional state and performs real-time control to highlight appropriate information. For this purpose, a content management system (e.g., Contentful) is utilized.

[0637] For example, if a user is feeling stressed, the server collects relaxing content that can help reduce stress and sends it to the device. The device then presents appropriate videos and content for the user to watch, thus supporting stress reduction.

[0638] Specific examples of prompt messages include, "Suggest video content suitable for reducing user stress," and "Display content that users seeking relaxation and healing can enjoy." This enables a customized experience tailored to individual users.

[0639] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0640] Step 1:

[0641] The server collects posting data through the APIs of social networking services. The input is raw data such as user posts and shared content. The output generates a list of posting data to be analyzed. This data collection is performed in real time, ensuring that the latest posts are readily available.

[0642] Step 2:

[0643] The server analyzes the collected post data using natural language processing tools. This processing step extracts features such as context, tone, and theme from each post. The input is the post data collected in step 1, and the output is a dataset containing the features of each post. The analyzed information is classified into commercial posts and general posts, forming the basis for predicting content that users will be interested in.

[0644] Step 3:

[0645] The server uses an emotion analysis engine to diagnose the emotional state from posts and user data. The input data consists of the output data from step 2 and the user's past interaction history and response data. The output of this step is a score or evaluation indicating the user's emotional state. A generative AI model is used here to perform a detailed analysis of the user's current emotions.

[0646] Step 4:

[0647] The terminal receives filtered information from the server. The input is filtered information from the server based on the user's emotional state. This filtered information is adjusted according to the user's emotional state, governing the display of diverse content. The output is an optimized content list displayed on the user interface. This allows the user to easily access information that matches their own emotions.

[0648] Step 5:

[0649] Users interact with the provided content and provide feedback. This feedback is collected to improve the accuracy of future content recommendations. The input information mainly consists of user impressions and ratings. Based on this information, the system is continuously improved and used for future content recommendations. The feedback data is processed through a generative AI model process, based on example prompt sentences, to correct classification accuracy.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] [Fourth Embodiment]

[0654] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] 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".

[0667] This invention provides a system that automatically classifies posts on social networking services into promotional posts and posts from regular users, enabling users to efficiently access reliable information.

[0668] This system consists of servers, terminals, and users.

[0669] First, the server collects multiple posts from social networking services. This includes hashtags, keywords, or geographical information based on user-specified criteria. The collected data is then converted into a format that is easy to parse. This involves cleaning and tokenizing the text.

[0670] Next, the server analyzes the collected post data using natural language processing technology. In this analysis process, features are extracted, and attributes such as the sentiment score, post length, and presence of links for each post are evaluated. Based on these features, the AI ​​model classifies the posts as either promotional posts or posts from regular users.

[0671] After classification, the server filters posts based on the user's specified filtering criteria. For example, if a user wants to avoid promotional posts, the server will exclude data identified as promotional and send only posts from regular users to the device.

[0672] The terminal receives filtered information from the server and displays it on the user interface. The display can be customized by the user, for example, by highlighting information of particular interest to the user.

[0673] Users can verify whether the displayed information meets their needs and provide feedback to the server. This feedback is used to improve subsequent analysis models and forms the basis for providing highly accurate classification results.

[0674] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects posts with hashtags related to "electronic devices" and uses an AI model to categorize them into promotional posts and genuine reviews. The device then displays only reviews from actual purchasers, excluding promotional posts. This allows the user to confidently select a product.

[0675] Thus, this system provides an environment in which users can efficiently obtain reliable information on social networks and make informed decisions.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The server collects post data that meets specified conditions (e.g., specific keywords or hashtags) through the API of social networking services. At the same time, it also retrieves metadata such as post content, poster information, and posting time.

[0679] Step 2:

[0680] The server cleans the acquired raw data. The cleaning process removes unnecessary HTML tags and special characters, making the text a plain format. This prepares the data for efficient natural language processing.

[0681] Step 3:

[0682] The server tokenizes the cleaned text data. Tokenization is the process of dividing the text into words and phrases. After this, stemming and lemmatization are performed to unify the base form of the words.

[0683] Step 4:

[0684] The server uses natural language processing technology to extract features from each post. These features include the length of the text, sentiment score (positive, negative, neutral), and whether or not there are links.

[0685] Step 5:

[0686] The server uses a pre-trained AI model to classify each post into promotional posts and regular posts based on the extracted features. This AI model takes feature vectors as input to determine the nature of the posts.

[0687] Step 6:

[0688] The server filters categorized posts based on user-specified criteria. Depending on user settings, it is possible to exclude promotional posts or select only posts with a specific sentiment.

[0689] Step 7:

[0690] The server sends filtered post data to the user's device. During transmission, the information is organized chronologically and by relevance to improve readability.

[0691] Step 8:

[0692] The device displays the received information on the user interface. The display reflects the user's customization settings, including highlighting of important information and hiding of promotional posts.

[0693] Step 9:

[0694] Users review the displayed information and provide feedback as needed. This feedback is sent to the server and used for the continuous improvement of the AI ​​model.

[0695] (Example 1)

[0696] 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".

[0697] The amount of information on social networking services is vast, making it difficult for users to efficiently access reliable information. In particular, the mix of commercial posts and posts from general users makes it difficult for users to quickly find the information they need. Furthermore, mechanisms for improving the accuracy of information classification are currently insufficient.

[0698] 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.

[0699] In this invention, the server includes means for analyzing data using natural language processing, means for extracting data characteristics and classifying them based on specific conditions, and means for selecting data classified based on conditions specified by the user. This enables users to efficiently access reliable information they need and utilize feedback to further improve classification accuracy.

[0700] "Natural language processing" is a technology that enables computers to understand and analyze human language, and is used to analyze the meaning and structure of text.

[0701] "Methods for extracting data characteristics" refer to the process of finding distinctive information from data, and include evaluating attributes such as text sentiment scores, post length, and the presence or absence of links.

[0702] "Means of classification based on specific conditions" refers to the process of dividing data into defined categories based on extracted characteristics, with the aim of distinguishing between commercial posts and posts from general users.

[0703] "Means of sorting based on user-specified conditions" refers to the process of extracting only the necessary information from pre-classified data according to the user's set requirements.

[0704] An "output device" is a device used to provide information to a user visually, and includes, but is not limited to, displays and monitors.

[0705] "Utilizing feedback" is the process of collecting evaluations and opinions from users and using them as a reference to improve the performance and accuracy of the system.

[0706] In this embodiment of the invention, three elements are primarily involved: a server, a terminal, and a user.

[0707] First, the server collects data from social networking services. This collection is based on hashtags, keywords, or geographical information specified by the user. The server then converts the collected data into a format that is easy to analyze using natural language processing tools. In this process, the server cleans and tokenizes the text data. Furthermore, it uses AI models to extract data features and classify posts into commercial posts and posts from general users.

[0708] The terminal's role is to display filtered data received from the server on the user interface. This makes it easier for users to effectively obtain information that interests them. The user interface allows users to customize the display according to their preferences. For example, it can help users make choices by clearly highlighting new product reviews.

[0709] Users can provide feedback on the accuracy and usefulness of the displayed information. This feedback is used by the server to improve the accuracy of the AI ​​model. As a concrete example, if a user is looking for reviews of a new electronic device, the server will filter relevant posts based on the prompt "electronic device reviews" and provide actual user reviews as a result. This allows users to easily find reliable information and make purchasing decisions more smoothly.

[0710] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0711] Step 1:

[0712] The server collects posted data from social networking services. User-specified hashtags, keywords, or geographical information are used as input. The collected raw data includes the post text, poster information, and date. This data forms the basis for subsequent processing by the server.

[0713] Step 2:

[0714] The server preprocesses the collected data. Because the input data contains unnecessary noise and formatting, it undergoes cleaning and tokenization. Specifically, it removes special characters and HTML tags and converts the data into a more manageable format by separating it into words. The output of this process is text data suitable for analysis.

[0715] Step 3:

[0716] The server uses natural language processing techniques to extract features from pre-processed data. It analyzes features such as sentiment scores, post length, and the presence or absence of links, and prepares them as input for the AI ​​model. It calculates these attributes from the text data received as input and outputs them as feature vectors.

[0717] Step 4:

[0718] The server classifies posts using an AI model based on feature vectors. A generative AI model is used to distinguish between commercial posts and posts from regular users, based on the prompt text. This classification outputs which category each post belongs to.

[0719] Step 5:

[0720] The server selects posts categorized based on the filtering conditions specified by the user. The input consists of the classification results and the filtering conditions set by the user. The output is the selected post data that matches the conditions.

[0721] Step 6:

[0722] The terminal displays filtered posts sent from the server on the user interface. Information formatted for user readability is received as input and reflected on the terminal. The output is an information display in a format that the user can easily understand.

[0723] Step 7:

[0724] The user evaluates the quality of the information displayed on the device and provides feedback to the server. Based on the feedback, the server adjusts the AI ​​model to improve classification accuracy. The input is the user's feedback, and the output is in the form of fine-tuning the AI ​​model.

[0725] (Application Example 1)

[0726] 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".

[0727] Traditionally, the sheer volume of information on social networks makes it difficult to efficiently extract reliable information. This is especially true when commercial information is prevalent, making it challenging to find posts from ordinary users and requiring significant time and effort for users to sift through the information they need. Therefore, there is a need for a system that allows users to easily access reliable general information and use it to aid in decision-making.

[0728] 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.

[0729] In this invention, the server includes means for collecting multiple data from a social network, means for analyzing the data using natural language processing, means for classifying commercial information and general information based on the attributes of the data, means for selecting the classified information according to conditions specified by the user, and means for displaying the selected information on a user interface and highlighting information of interest to the user. This enables users to easily access reliable general information on social networks and make decisions efficiently.

[0730] A "social network" is an online service that allows people to share information or content over the internet.

[0731] "Data" refers to a collection of information gathered on social networks, including posts, comments, and links.

[0732] "Natural language processing" is a technology for processing and analyzing human language using computers.

[0733] "Analysis" is the process of examining data in detail to understand and classify its contents.

[0734] An "attribute" is a specific characteristic or feature of data, used as a criterion for classification.

[0735] "Commercial information" refers to information disseminated for the purpose of promoting the sale of goods or services.

[0736] "General information" refers to information that is not for commercial purposes and is based on personal experiences and opinions.

[0737] "Selection" is the process of choosing only the necessary elements based on specific criteria.

[0738] A "user interface" refers to the display screens and functions that enable interaction between a computer system and a user.

[0739] "Highlighting" is a technique that visually highlights specific information to attract the user's attention.

[0740] The system of this invention efficiently analyzes data on social networks, enabling users to obtain reliable information. The server first collects posted data from social networks via an internet connection. The collected data is then processed using natural language processing techniques, including text cleaning and tokenization, to convert it into a parseable format. A standard server computer is used as the hardware, and natural language processing libraries and frameworks (such as the Transformers library) are utilized as the software.

[0741] After analysis, the server uses an AI model to classify posts into commercial and general information based on their data attributes. This allows for the selection of reliable information and filtering of information according to conditions specified by individual users. The selected information is then sent to the terminal and displayed via the user interface. Users can review information of interest and provide feedback to the server, contributing to the improvement of the classification algorithm's accuracy.

[0742] As a concrete example, consider a scenario where a user is searching for reviews of a new electronic device. The server collects and analyzes data tagged with "electronic device," and displays only reliable reviews from general users on the device, allowing the user to make product selections based on more accurate information.

[0743] Furthermore, the following prompt statements can be used as input to the generative AI model.

[0744] "I'm looking for smartphone reviews. Please prioritize posts from regular users."

[0745] This allows users to easily obtain the most relevant information.

[0746] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0747] Step 1:

[0748] The server uses the APIs of social networking services to collect posted data based on specified conditions. It receives user-specified hashtags and keywords as input and makes API requests. The output, including the post text, user information, and posting date and time, is returned to the server in JSON format. This data is then stored in internal storage.

[0749] Step 2:

[0750] The server converts the collected data into a format that is easy to analyze using natural language processing techniques. The input is the posted data obtained in step 1. Specifically, it performs text preprocessing (cleaning, normalization, tokenization) and extracts sentiment scores and keywords. The output is an analyzable text dataset.

[0751] Step 3:

[0752] The server inputs the results of natural language processing analysis into an AI model to classify posts into commercial and general information. The feature data obtained in step 2 is used as input. Specifically, the AI ​​model is used to determine the commercial potential of each post and perform the classification. The output is the classification result (data labeled as commercial information).

[0753] Step 4:

[0754] The server sorts the information according to the filtering conditions specified by the user. The input is the data sorted in step 3. Specifically, it removes unnecessary information based on the user's preferences and extracts only the useful information. The output is the sorted information after filtering.

[0755] Step 5:

[0756] The server sends the filtered information to the terminal. The input is the filtering result from step 4. Specifically, it sends the data to the terminal and organizes the information in a user-friendly format. The output is feed data for display on the terminal.

[0757] Step 6:

[0758] The terminal displays the received information on the user interface. The input is feed data sent from the server. Specifically, it displays the data via the user interface and highlights the information that the user is interested in. As output, it provides visual information for the user to view.

[0759] Step 7:

[0760] The user reviews the displayed information and provides feedback. The input is the user's subjective evaluation. Specifically, the user generates feedback by pressing an evaluation button for a particular piece of information and sends it to the server. The output is the evaluation data received by the server.

[0761] Step 8:

[0762] The server learns to improve the accuracy of its classification algorithm based on feedback received from the user. The input is user feedback. Specifically, it retrains the AI ​​model or adjusts its parameters to improve the accuracy of subsequent analyses. The output is the improved model or improved filtering accuracy.

[0763] 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.

[0764] This invention is a system that aims to efficiently and optimally provide users with the information they need by classifying posts on social networking services into promotional posts and posts by general users, and combining this with an emotion engine that recognizes the emotional state of users.

[0765] The system consists of a server, a terminal, and an emotion engine for recognizing user emotions.

[0766] First, the server collects post data via the API of social networking services. The collected data is analyzed using natural language processing techniques to extract features. In this analysis, the context and tone of the posts are evaluated, and an AI model is used to classify them into promotional posts and regular posts. At the same time, sentiment analysis is also performed to calculate the sentiment score of the posts.

[0767] Next, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine analyzes the user's emotions from user interaction data and biometric information (e.g., freely customized input) and extracts that state as a digital signal.

[0768] The device retrieves filtered post information from the server and further adjusts the display of information based on the user's emotional state, determined by the sentiment engine. This is to enhance the user experience by highlighting different information depending on the user's emotions. For example, if the user is in a positive emotional state, positive and affirmative content will be highlighted, while if they are in a negative emotional state, calm and soothing content will be recommended to alleviate that state.

[0769] As a concrete example, consider a scenario where a user is feeling stressed and is searching for reviews about a new hobby. The server collects relevant review posts and analyzes the user's emotions using an emotion engine. On the user's device, posts that are expected to alleviate the user's stress are highlighted, providing a safe and secure environment for the user to access information.

[0770] This system makes it easier for users to obtain information that is best suited to their emotional state at any given time, allowing them to enjoy a more fulfilling user experience.

[0771] The following describes the processing flow.

[0772] Step 1:

[0773] The server collects post data containing specific keywords and hashtags through the APIs of social networking services. The collected data includes metadata such as post content, images, links, and poster information.

[0774] Step 2:

[0775] The server cleans the collected data. This cleaning process converts the text data into a more easily processed format, removing special characters and HTML tags. It also tokenizes the text, converting it to its base word form, thereby improving the accuracy of natural language processing.

[0776] Step 3:

[0777] The server uses natural language processing techniques to analyze the posted data and extract features from each post. These features include text length, sentiment score, frequency of words used, and image analysis results.

[0778] Step 4:

[0779] The server uses an AI model to classify posts into promotional posts and regular user posts based on extracted features. The AI ​​model is pre-trained and can determine whether or not there is commercial intent.

[0780] Step 5:

[0781] The server filters posts based on user-defined criteria. This filtering process includes excluding promotional posts and prioritizing posts with specific sentiment scores.

[0782] Step 6:

[0783] The emotion engine analyzes user input data and interaction logs to recognize the user's emotional state. The engine identifies the user's emotions from this data and sends that information to the server.

[0784] Step 7:

[0785] The server analyzes the user's sentiment data received from the sentiment engine and evaluates its relevance to the filtered post data. Based on this evaluation, the server selects posts appropriate to the user's emotional state and sends them to the device.

[0786] Step 8:

[0787] The device displays received posts on the user interface. During display, it's possible to apply features such as highlighting content based on the user's emotional state and animation effects to make specific feeds stand out.

[0788] Step 9:

[0789] Users act based on the displayed information and provide feedback as needed. This feedback is sent to the server and used to improve the system and train the model.

[0790] (Example 2)

[0791] 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".

[0792] Conventional information delivery systems lack the ability to select and display information based on the user's emotional state, making it difficult to provide information optimized for the user's psychological condition. Furthermore, there is room for improvement in the accuracy of classifying advertising information from general information, so further efforts are needed to provide the best possible user experience.

[0793] 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.

[0794] In this invention, the server includes means for analyzing information on a digital communication network using natural language processing, means for extracting features of the information and classifying it into advertising information and general information, means for sentiment analysis to recognize the user's emotional state, and means for filtering the classified information based on conditions and emotional states specified by the user. This makes it possible to provide optimal information according to the user's emotional state.

[0795] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0796] A "digital communication network" is a network system used to transmit data between electronic devices.

[0797] "Extracting information features" is the process of identifying and extracting important attributes and patterns from data.

[0798] "Advertising information" refers to information intended to promote products or services.

[0799] "General information" refers to everyday and general information that does not have a specific commercial purpose.

[0800] "Sentiment analysis" is a technology that automatically identifies and evaluates emotions and emotional nuances from text and data.

[0801] "Filtering" is the process of selecting data according to specific criteria and extracting only the necessary information.

[0802] A "user interface" refers to the means and designed screen displays and input devices that allow a system and a user to interact with each other.

[0803] This invention is a system for providing information optimized for the emotional state of users over a digital communication network. Specifically, it consists of a server, a terminal, and an emotion analysis engine for recognizing the user's emotions.

[0804] The server collects post data using social network APIs. During this process, the server analyzes the text data of each post using natural language processing techniques. Specifically, it utilizes programming languages ​​such as Python and natural language processing libraries to extract context and keywords from the text. Then, it uses a generative AI model to classify the posts into promotional and general information. Furthermore, it uses sentiment analysis techniques to calculate a sentiment score for each post.

[0805] The emotion engine uses biosensors and interaction data to analyze data about the user's emotions. This allows it to extract the user's current emotional state as a digital signal and provide that information to the system when needed.

[0806] The device retrieves filtered information from the server and adjusts the information displayed based on the user's emotional state. This adjustment is performed using, for example, a web browser or mobile application. If the user is feeling positive, positive and encouraging information is prioritized; if they are feeling negative, calming content that provides a sense of security is prioritized.

[0807] As a concrete example, consider a situation where a user is feeling stressed while searching for information about a new hobby. The server collects review articles related to the hobby, and the emotion engine evaluates the user's emotional state. The device highlights content that helps reduce the user's stress, providing an environment where they can comfortably access information.

[0808] An example of a prompt message might be, "Suggest a way to provide the user with the most suitable hobby-related reviews based on their emotional state."

[0809] This system allows users to smoothly acquire information that matches their emotional state at the time, enabling them to have a more fulfilling experience.

[0810] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0811] Step 1:

[0812] The server collects posted data using the APIs of social networking services.

[0813] The system receives text data of posts obtained from the API as input. This data is converted to the required format and stored in a temporary data store.

[0814] Step 2:

[0815] The server analyzes the collected post data using natural language processing techniques.

[0816] The text data obtained as input is used to analyze the context and keywords using libraries such as TextBlob and NLTK. This allows for the extraction of key features of the posts.

[0817] Step 3:

[0818] The server uses a generative AI model to classify posts into promotional information and general information.

[0819] The system receives pre-analyzed feature data as input, performs classification calculations using AI models such as BERT and GPT, and determines the class of each post. The classification results are stored in a database.

[0820] Step 4:

[0821] The server uses sentiment analysis technology to calculate a sentiment score for each post.

[0822] Using the category data of the posts obtained in the previous step as input, a sentiment analysis library is used to calculate the sentiment score. The score is expressed as a number ranging from positive to negative, based on common metrics.

[0823] Step 5:

[0824] The emotion engine uses biosensors and interaction data to recognize the user's emotional state.

[0825] It receives user interaction data as input and collects data from biometric information as needed. Based on this, it outputs the user's emotional state as a digital signal.

[0826] Step 6:

[0827] The device retrieves filtered information from the server and adjusts the display of information based on the user's emotional state.

[0828] The device receives filtered post information and digital signals of the user's emotional state as input. Using this information, the device controls the placement and highlighting of information on the screen via a display algorithm. Content that aligns with the user's emotional state is highlighted.

[0829] Step 7:

[0830] The user reviews the information provided on the device and selects the necessary action.

[0831] Users can view content or request additional information based on the information provided and the options displayed.

[0832] (Application Example 2)

[0833] 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".

[0834] In recent years, content distribution services have made it difficult for users to find the information they need from the vast amount of data available. Furthermore, information is often provided without considering the user's emotional state, leading to a diminished user experience. Therefore, there is a need to enhance user satisfaction and provide a high-quality experience through optimal information delivery.

[0835] 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.

[0836] In this invention, the server includes means for analyzing information on a social networking service using natural language processing, means for extracting features of the information and classifying commercial posts and general posts, and means for filtering the classified information according to conditions specified by the user. This enables the optimal display of information based on the user's emotional state.

[0837] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0838] A "social networking service" refers to an online platform on the internet where people share opinions and information.

[0839] "Commercial posts" refer to information posted on social networking services by companies or advertisers for the purpose of promoting products or providing services.

[0840] "General posts" refer to information that individual users post on social networking services to share their everyday opinions and information.

[0841] "Filtering" is the process of selecting data that meets specific criteria from a large amount of information.

[0842] "Emotional state" refers to information that indicates the user's current mental state and emotional tendencies.

[0843] "User experience" refers to the overall experience and satisfaction of users when using a product or service.

[0844] This invention is a system for improving the user experience in content distribution services. This system combines natural language processing and sentiment analysis technologies to provide users with the most relevant information. The overall system flow is shown below.

[0845] The server first collects post data via the APIs of social networking services. At this stage, content from various users is aggregated. Next, natural language processing tools (e.g., Google Cloud Natural Language API) are used to analyze these posts. As a result of the analysis, the characteristics of the posts are extracted and classified into commercial posts and general posts based on these characteristics.

[0846] Next, the server uses an emotion analysis engine (e.g., IBM Watson Emotion Analysis) to diagnose the emotional state of users based on the collected posts and user data. This allows the server to understand the emotional state of users and filter information accordingly.

[0847] The device receives filtered information sent from the server. Here, the device considers the user's emotional state and performs real-time control to highlight appropriate information. For this purpose, a content management system (e.g., Contentful) is utilized.

[0848] For example, if a user is feeling stressed, the server collects relaxing content that can help reduce stress and sends it to the device. The device then presents appropriate videos and content for the user to watch, thus supporting stress reduction.

[0849] Specific examples of prompt messages include, "Suggest video content suitable for reducing user stress," and "Display content that users seeking relaxation and healing can enjoy." This enables a customized experience tailored to individual users.

[0850] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0851] Step 1:

[0852] The server collects posting data through the APIs of social networking services. The input is raw data such as user posts and shared content. The output generates a list of posting data to be analyzed. This data collection is performed in real time, ensuring that the latest posts are readily available.

[0853] Step 2:

[0854] The server analyzes the collected post data using natural language processing tools. This processing step extracts features such as context, tone, and theme from each post. The input is the post data collected in step 1, and the output is a dataset containing the features of each post. The analyzed information is classified into commercial posts and general posts, forming the basis for predicting content that users will be interested in.

[0855] Step 3:

[0856] The server uses an emotion analysis engine to diagnose the emotional state from posts and user data. The input data consists of the output data from step 2 and the user's past interaction history and response data. The output of this step is a score or evaluation indicating the user's emotional state. A generative AI model is used here to perform a detailed analysis of the user's current emotions.

[0857] Step 4:

[0858] The terminal receives filtered information from the server. The input is filtered information from the server based on the user's emotional state. This filtered information is adjusted according to the user's emotional state, governing the display of diverse content. The output is an optimized content list displayed on the user interface. This allows the user to easily access information that matches their own emotions.

[0859] Step 5:

[0860] Users interact with the provided content and provide feedback. This feedback is collected to improve the accuracy of future content recommendations. The input information mainly consists of user impressions and ratings. Based on this information, the system is continuously improved and used for future content recommendations. The feedback data is processed through a generative AI model process, based on example prompt sentences, to correct classification accuracy.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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."

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] The following is further disclosed regarding the embodiments described above.

[0883] (Claim 1)

[0884] A method for analyzing information on social networking services using natural language processing,

[0885] A means for extracting the characteristics of the aforementioned information and classifying commercial posts and general posts,

[0886] Means for filtering the classified information according to conditions specified by the user,

[0887] means for displaying the filtered information on a user interface,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, further comprising means of using sentiment analysis in the classification of the aforementioned commercial posts.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for collecting user feedback and utilizing the feedback to improve the accuracy of the classification.

[0893] "Example 1"

[0894] (Claim 1)

[0895] A computing device that analyzes data using natural language processing,

[0896] A means for extracting the characteristics of the aforementioned data and classifying them based on specific conditions,

[0897] A means for selecting the classified data based on conditions specified by the user,

[0898] Means for displaying the selected data on an output device,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, which uses emotion analysis in the classification described above.

[0902] (Claim 3)

[0903] The system according to claim 1, which collects feedback from users and uses the feedback to improve the accuracy of the classification.

[0904] "Application Example 1"

[0905] (Claim 1)

[0906] A means of collecting multiple data from social networks,

[0907] A means for analyzing the data using natural language processing,

[0908] A means for classifying commercial information and general information based on the attributes of the aforementioned data,

[0909] A means for selecting the classified information according to conditions specified by the user,

[0910] The means for displaying the selected information on a user interface and highlighting the information of interest to the user,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, which performs the classification of the aforementioned commercial information in combination with sentiment analysis and measures reliability.

[0914] (Claim 3)

[0915] The system according to claim 1, which collects user evaluations and uses the evaluations to optimize the classification results.

[0916] "Example 2 of combining an emotion engine"

[0917] (Claim 1)

[0918] A means of analyzing information on a digital communication network using natural language processing,

[0919] A means for extracting the characteristics of the aforementioned information and classifying it into advertising information and general information,

[0920] A means of analyzing emotions to recognize the emotional state of a user,

[0921] A means for filtering the classified information based on the conditions and emotional state specified by the user,

[0922] means for displaying the filtered information on a user interface,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, further comprising means for adjusting the provision of information according to the emotional state of the user using the emotion analysis means.

[0926] (Claim 3)

[0927] The system according to claim 1, further comprising means for collecting responses from users and using those responses to improve the accuracy of the classification.

[0928] "Application example 2 when combining with an emotional engine"

[0929] (Claim 1)

[0930] A method for analyzing information on social networking services using natural language processing,

[0931] A means for extracting the characteristics of the aforementioned information and classifying commercial posts and general posts,

[0932] Means for filtering the classified information according to conditions specified by the user,

[0933] The means for adjusting and displaying the filtered information based on the user's emotional state,

[0934] A system that includes this.

[0935] (Claim 2)

[0936] The system according to claim 1, further comprising means of using sentiment analysis in the classification of the aforementioned commercial posts.

[0937] (Claim 3)

[0938] The system according to claim 1, further comprising means for collecting user feedback and utilizing the feedback to improve the accuracy of the classification. [Explanation of Symbols]

[0939] 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 method for analyzing information on social networking services using natural language processing, A means for extracting the characteristics of the aforementioned information and classifying commercial posts and general posts, Means for filtering the classified information according to conditions specified by the user, means for displaying the filtered information on a user interface, A system that includes this.

2. The system according to claim 1, further comprising means for using sentiment analysis in the classification of the aforementioned commercial posts.

3. The system according to claim 1, further comprising means for collecting user feedback and utilizing the feedback to improve the accuracy of the classification.

Images