System

Abstract

A system is provided.SOLUTION: A system, comprising: means for processing information using a generative artificial intelligence model; means for obtaining up-to-date information from an external data source; means for updating original article content based on the obtained up-to-date information; and means for posting the updated content to a blog platform.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In tech blogs, collecting the latest information and updating articles requires a great deal of effort. Writers must constantly revise article content based on the latest information, which can lead to delays in updates. This can result in outdated information being left unedited and articles becoming less useful. The present invention aims to solve this problem by providing a system that automatically updates tech blogs without any effort. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. Specifically, it provides a system including a means for acquiring the latest information from an external data source, a means for updating the original article content based on the acquired latest information using a generative AI model, and a means for posting the updated content to a blog platform. The system also includes a means for linking the acquired latest information with the original article content and inputting it into the generative AI model, and a means for formatting the latest information in JSON format. This makes it possible to provide content based on the latest information while maintaining the atmosphere and style of the original article.

[0006] A "generative artificial intelligence model" is a computer program that has the ability to analyze language and patterns based on large amounts of data and generate unique sentences.

[0007] An "external data source" is a resource that exists outside the system and provides up-to-date information and data.

[0008] "Latest Information" refers to the latest information, such as the latest technology, news, and updates.

[0009] "Original article content" refers to the original text or information that was first posted on a blog or other website.

[0010] "Updating" means correcting existing articles or data based on new information and keeping them up to date.

[0011] A "blog platform" is an online service or software that allows users to post and manage blog posts.

[0012] The "JSON format" is a lightweight format for structuring and storing data, and is a data format supported by many programs and APIs.

[0013] "Input" means to provide information or data to a system or program.

[0014] "Concatenate" means combining multiple pieces of information or data into one continuous form. [Brief explanation of the drawings]

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

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

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

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

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

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

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] System Overview

[0037] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model. Specifically, a server retrieves the latest information from an external data source, uses the generative artificial intelligence model to generate an updated article based on the original article content and the latest information, and then posts the article to a blog platform.

[0038] Program processing and explanation

[0039] Gathering the latest information

[0040] The server retrieves up-to-date information from an external data source (e.g., a tech news API) periodically or based on specified events. To do this, the server sends an API request and parses the received response in JSON format.

[0041] Get the original article

[0042] The server retrieves the URL of the original blog post to be updated and retrieves its content in text form via a GET request, which is then provided to the generative AI model.

[0043] Article Update

[0044] The server uses a generative AI model (e.g., GPT-2) to generate a prompt that combines the original article content with the latest information. This prompt is then input into the generative AI model, which generates a new sentence while maintaining the style of the original article. The generated sentence adds the latest information without losing the atmosphere and tone of the original article.

[0045] Posting an update

[0046] The server posts the generated update to the blog platform using the blog platform's API. If the post is successful, the blog is updated with the latest information, providing readers with the latest technical content.

[0047] Specific examples

[0048] 1. Gathering the latest information

[0049] The server retrieves the latest Python release information from an external data source. For example, it sends an API request to receive information such as "Python 3.10 has been released and adds pattern matching functionality."

[0050] 2. Obtaining the original article

[0051] The server requests the URL of an article about the history of Python and retrieves the original article content, for example, an article that explains the history of Python releases and version changes.

[0052] 3. Update the article

[0053] The server uses a generative artificial intelligence model to add updated information to the original article, including details about "the newly released features of Python 3.10 and the added pattern matching functionality."

[0054] 4. Posting an update

[0055] The server posts the generated update to a blogging platform, for example, "an update to the original article with new information about Python 3.10."

[0056] This system allows tech blogs to be automatically updated with the latest information, making it possible to provide the latest technical information without any hassle while maintaining the writing style of the original author.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The server retrieves the latest information from external data sources by sending a GET request to an API endpoint and receiving a response containing the latest technology news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0060] Step 2:

[0061] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0062] Step 3:

[0063] The server generates a prompt by concatenating the latest information with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content.

[0064] Step 4:

[0065] The server provides the generative AI model with the prompt generated in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0066] Step 5:

[0067] A generative AI model generates new, updated content while preserving the style and tone of the original. The generated text is based on the original article but includes the latest information.

[0068] Step 6:

[0069] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information.

[0070] Step 7:

[0071] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] It takes a lot of time and effort to keep a tech blog up-to-date with the latest information. It's also not easy to maintain the style and tone of the original article while adding the latest information. This makes it difficult to provide accurate and fresh information to readers.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for periodically obtaining the latest information from an external data source, means for analyzing the obtained latest information and extracting necessary information, and means for obtaining the URL of the original article content and obtaining that content in text format, which enables the server to quickly and efficiently obtain the latest information and automatically update the article while maintaining the style of the original article.

[0077] An "external data source" is an external information source for obtaining various data and information provided on the Internet.

[0078] "Latest information" refers to the most current information or data obtained from external data sources.

[0079] "Analysis" is the process of converting acquired data into a predetermined format and extracting necessary information from it.

[0080] The "original article content" is the text data of the existing blog article to be updated.

[0081] A "URL" is an address that identifies a resource on the Internet.

[0082] "Text format" is a format in which data is expressed as a string of characters.

[0083] A "prompt sentence" is text to be input into a generative artificial intelligence model, and is generated by combining the original article content with the latest information.

[0084] A "generative artificial intelligence model" is an artificial intelligence algorithm for generating new text based on given text data.

[0085] A "new sentence" is the output generated by a generative artificial intelligence model using a prompt sentence as input.

[0086] A "blog platform" is an online service that enables users to post and manage blog posts.

[0087] This invention is a system that automatically updates technical blogs with the latest information using a generative artificial intelligence model. The main processing is performed by a server, and the following hardware and software are used:

[0088] Hardware:

[0089] 1. Server: A central processing unit that handles all processes such as collecting the latest information, retrieving original articles, updating articles, and posting updated articles.

[0090] 2. Network connectivity: Required for accessing external data sources and blogging platforms.

[0091] software:

[0092] 1. Generative AI model: Generate new sentences using a generative AI model such as GPT-2.

[0093] 2. Technology News API: An API for getting the latest technology-related information.

[0094] 3. Blog Platform API: An API used to post and update blog posts.

[0095] Data processing and calculation:

[0096] 1. Parsing the latest information: The server parses the JSON response received from the external data source and extracts the latest technical information.

[0097] 2. Obtaining the original article in text format: The server obtains the content of the original article in text format from the specified URL and extracts the necessary content.

[0098] 3. Prompt sentence generation: The content of the original article is combined with the latest information to generate a prompt sentence, which is then input into the generative artificial intelligence model.

[0099] Examples:

[0100] Gathering the latest information:

[0101] The server makes a request to the tech news API and receives the latest information: "Python 3.10 has been released and adds pattern matching functionality."

[0102] Get the original article:

[0103] The server retrieves the URL of the "Python history article" and retrieves its contents in text format. The original article contains an article explaining the history of Python releases and version changes.

[0104] Generate prompt statement:

[0105] The server concatenates the original article content with the latest information and generates a prompt for the generative AI model, such as:

[0106] Example: Original article content + "Python 3.10 has been released. Its main feature is the addition of pattern matching functionality."

[0107] Generate and post an update:

[0108] The server inputs a prompt into the generative AI model and posts the generated new text to a blog platform, for example, "an updated version of the original article with new information about Python 3.10."

[0109] This system allows the server to quickly and efficiently retrieve the latest information and automatically update it while maintaining the style of the original article, ensuring that the blog always provides readers with the latest technical information.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1:

[0112] The server sends an HTTP GET request to the API endpoint of the external data source. The input is the API endpoint URL, and the output is a JSON-formatted response containing the latest technical information. The server parses this response and extracts the required up-to-date information. Specifically, the server issues an API request, parses the received JSON data, and extracts the information that "Python 3.10 has been released."

[0113] Step 2:

[0114] The server retrieves the URL of the original article to be updated and sends an HTTP GET request. The input is the URL of the original article, and the output is the original article in text format. The server analyzes this text data and extracts the necessary content from the original article. Specifically, the server sends a request to the URL and retrieves the text data for the "article about the history of Python."

[0115] Step 3:

[0116] The server generates a prompt sentence by concatenating the latest information obtained in step 1 with the original article content obtained in step 2. The input is the original article content and the latest information, and the output is the prompt sentence to be input into the generative artificial intelligence model. Specifically, the server concatenates the original article content "Information about Python releases and version changes" with the latest information "Python 3.10 has been released. Its main feature is the addition of a pattern matching function" to generate a prompt sentence in the format of "original article content + latest information."

[0117] Step 4:

[0118] The server inputs the prompt sentence generated in step 3 into the generative AI model to generate a new sentence. The input is the prompt sentence, and the output is the generated new sentence. Specifically, the server sends the prompt sentence to the API of the generative AI model (e.g., GPT-2) to generate new text.

[0119] Step 5:

[0120] The server posts the generated new text to the blog platform. The input is the generated new text, and the output is the result of posting to the blog platform. Specifically, the server sends an HTTP POST request to the blog platform's API endpoint to upload the generated new article content. If posting is successful, the blog is automatically updated.

[0121] (Application example 1)

[0122] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0123] Currently, tech blogs are often updated manually, resulting in outdated information. Collecting the latest information from vast amounts of data and updating it in blog posts takes time and effort. Furthermore, the lack of a way to view information in real time on a smart device or have it read aloud presents a challenge in improving the user experience.

[0124] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0125] In this invention, the server includes a means for processing information using a generative artificial intelligence model, a means for obtaining the latest information from an external data source, a means for updating the original article content based on the obtained latest information, a means for posting the updated content to a blog platform, and a means for reading out the content displayed on the smart glasses, so that the blog article is automatically updated with the latest information, and users can view and listen to the latest technical information in real time through the smart glasses.

[0126] A "generative artificial intelligence model" refers to a generative artificial intelligence model, a machine learning model for generating natural-looking sentences from specific input data.

[0127] "External Data Sources" refers to external data sources that provide up-to-date information, such as technology news APIs.

[0128] "Latest News" refers to the latest data and news related to technology or other specific fields.

[0129] "Original article content" refers to the text of the existing blog post or document that is being updated.

[0130] "Blog Platform" refers to a web service for hosting and publishing blog posts.

[0131] "Smart glasses" refers to a wearable display device worn by the user that has the ability to display information in conjunction with smartphones and other devices.

[0132] "Reading means" refers to the functionality or technology used to convert text into audio and read it to the user.

[0133] "Means for processing information" refers to a method for generating new information or content based on input data using a generative artificial intelligence model.

[0134] "Means of updating" refers to the process of creating a new article by adding the latest information obtained to the original article content.

[0135] "Means of posting" refers to the technology and functionality used to upload generated updates to the blog platform.

[0136] System Overview

[0137] This invention is a system that combines multiple components to automatically update a tech blog and enable it to be viewed in real time through smart glasses. The server has functions such as information processing using a generative artificial intelligence model, retrieving the latest information from external data sources, updating blog articles, and posting them to a blog platform. It also includes a function to display and read the updated content on the smart glasses.

[0138] Hardware and software used

[0139] The server generates articles using generative artificial intelligence models such as the GPT-2 model. Data is obtained via API requests and parsed in JSON format. The smart glasses are wearable display devices with information display and audio playback functions. The server uses gTTS (Google (registered trademark) Text-to-Speech) for voice synthesis.

[0140] Program processing and explanation

[0141] Gathering the latest information

[0142] The server periodically retrieves the latest technical information from external data sources, sends API requests, and parses the received data in JSON format. For example, it may retrieve the latest release information from a technology news API.

[0143] Get the original article

[0144] The server retrieves the URL of the article to be updated from the blog platform and retrieves the article content in text format. For example, it may retrieve an article about the history of technology.

[0145] Article Update

[0146] The server generates a prompt by concatenating the original article content with the latest information, and inputs it into the generative AI model. The following prompts may be used:

[0147] Original Article: The History of Technology and Its Evolution

[0148] Latest Updates:

[0149] The latest technology has been released and new features have been added.

[0150] When generating an article using this prompt, the GPT-2 model preserves the feel of the original article while adding new information.

[0151] Posting an update

[0152] The generated update is posted using the blog platform's API, and if successful, the blog is updated with the latest technical content.

[0153] View and read updates

[0154] The updated article content will be displayed on the smart glasses, and in addition, the text will be converted to speech using gTTS and read aloud to the user through the smart glasses' speaker.

[0155] With this invention, blog posts are automatically updated with the latest information, allowing users to view and listen to the latest technical information in real time through the smart glasses.

[0156] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0157] Step 1:

[0158] The server retrieves the latest information from an external data source. First, it sends an API request to the technology news API to retrieve the latest information in JSON format. The input is the latest technology data, and the output is parsed JSON data. Specifically, it includes information such as "latest release information."

[0159] Step 2:

[0160] The server retrieves the original article content from the blog platform. It sends a GET request to the specified URL to retrieve the text of the original article. This retrieved text is the input data, and the output is the original article content. For example, let's say the target is an article about the history of technology.

[0161] Step 3:

[0162] The server generates a prompt by concatenating the original article content with the latest information. The input is the text of the original article content and the latest information obtained in step 1, and the server combines these two to create a prompt. The output is a prompt that is input to the generative AI model. For example:

[0163] Original Article: The History of Technology and Its Evolution

[0164] Latest Updates:

[0165] The latest technology has been released and new features have been added.

[0166] Step 4:

[0167] The server generates a new article using a generative artificial intelligence model. The prompt sentence is input into the GPT-2 model to generate the new article text. The input is the prompt sentence created in step 3, and the output is an updated article with the latest information. The updated article maintains the feel of the original article while adding new information.

[0168] Step 5:

[0169] The server posts the generated update to the blog platform. It uses the blog platform's API to publish the update on the Internet. The input is the generated update, and the output is the post on the blog platform.

[0170] Step 6:

[0171] The server displays the updated article content on the smart glasses and reads it aloud. It uses gTTS (Google Text-to-Speech) to convert the text into audio data and plays it through the smart glasses' speakers. The input is the text of the updated article, and the output is the audio data and the text displayed on the smart glasses. Users can receive the latest technical information visually and audibly through the smart glasses.

[0172] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0173] System Overview

[0174] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model and an emotion engine. Specifically, a server retrieves the latest information from external data sources, updates the original article content based on emotions using the generative artificial intelligence model and the emotion engine, and posts the article to a blog platform.

[0175] Program processing and explanation

[0176] Gathering the latest information

[0177] The server retrieves the latest information from an external data source (e.g., a tech news API). The server sends an API request and parses the received response in JSON format to retrieve the latest information.

[0178] Get the original article

[0179] The server retrieves the URL of the original blog post to be updated, retrieves the post's content in text format via a GET request, and stores it in the system.

[0180] Article update (using emotion engine)

[0181] The server uses an emotion engine to recognize and analyze the user's emotions. By linking the acquired latest information with the original article content and inputting the generated prompt and the analyzed emotion information into a generative AI model, an updated article is generated that contains expressions that best reflect the user's emotions while maintaining the original writing style.

[0182] Posting an update

[0183] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content.

[0184] Specific examples

[0185] 1. Gathering the latest information

[0186] The server retrieves the latest programming language release information from an external data source, for example by sending an API request to receive information about new programming language features.

[0187] 2. Obtaining the original article

[0188] The server requests the URL of the original blog post and retrieves the original content, e.g., "An article explaining an older version of a programming language."

[0189] 3. Using the Emotion Engine and Updating Articles

[0190] The server uses an emotion engine to recognize the user's emotions and analyze their "curiosity." For example, it analyzes "curious reactions" from user comments and feedback. Based on this, it inputs a prompt to "explain new features in an inquisitive style" into the generative AI model, and generates an updated article that adds the latest information to the original article content.

[0191] 4. Posting an update

[0192] The server takes the generated update and posts it to a blogging platform, for example, "the original post with an enthusiastic commentary on the latest features of a new programming language."

[0193] This system not only ensures that tech blogs are always automatically updated with the latest information, but also includes expressions that take into account user emotions, helping to keep readers interested.

[0194] The processing flow will be explained below.

[0195] Step 1:

[0196] The server retrieves the latest information from an external data source. Specifically, the server sends a GET request to an API endpoint and receives a response containing the latest tech news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0197] Step 2:

[0198] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0199] Step 3:

[0200] The user accesses the system through a terminal and inputs or provides feedback on their emotions. The emotion engine analyzes the user's input and identifies their emotional state (e.g., excitement, curiosity, surprise, etc.).

[0201] Step 4:

[0202] The server generates a prompt by concatenating the latest information obtained with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content as the premise context for future sentences.

[0203] Step 5:

[0204] The server provides the generative AI model with the prompt generated in step 4 and the emotional information analyzed in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0205] Step 6:

[0206] The generative AI model generates updated article content that best reflects the user's emotions while maintaining the original style and tone. The generated text is based on the original article but includes the latest information and emotionally sensitive content.

[0207] Step 7:

[0208] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content to readers.

[0209] Step 8:

[0210] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[0211] Example 2

[0212] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0213] Conventional blog update systems do not automatically add the latest information or generate content that takes user emotions into consideration, making it difficult to maintain reader interest. Furthermore, there is a need for systems that not only simply update information but also incorporate appropriate expressions based on emotions.

[0214] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for processing information using a generative AI model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for analyzing the user's emotions using an emotion analysis engine, means for generating an article by inputting a prompt sentence to the generative AI model based on the analyzed emotion information, and means for posting the updated content to a blog platform. This enables automatic updating of articles based on the latest information and generation of content taking user emotions into consideration.

[0215] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information using machine learning technology.

[0216] An "external data source" is a data provider or information source that exists outside the system, not within it.

[0217] An "emotion analysis engine" is software or hardware used to analyze and identify a user's emotional state from text or voice.

[0218] A "blog platform" is a web service or software that allows users to create, manage, and publish blog posts online.

[0219] A "prompt" is an instruction or question input to a generative AI model, which instructs the AI ​​to generate output based on this.

[0220] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a lightweight data description format used for storing and exchanging data.

[0221] An "API request" is a communication made via an application program interface to request a specific service or data.

[0222] "Means for processing information" refers to a program or device that receives data, analyzes it, and outputs results according to the purpose.

[0223] "Means for updating the original article content based on the latest information obtained" refers to methods or techniques for changing or adding to the existing article content based on newly obtained information.

[0224] An "article generation means" is a program or device that automatically creates new articles or documents based on input information.

[0225] "Means for posting articles" refers to the technology or method used to upload and publish generated articles to an online blog or website.

[0226] This invention relates to a system for automatically updating tech blogs using a generative artificial intelligence model and a sentiment analysis engine, specifically to optimize content based on user sentiment and provide always-up-to-date information.

[0227] Hardware and Software Used

[0228] Server: Cloud-based server (e.g., AWS®, Azure®) or on-premise server

[0229] Tech News API: API for retrieving the latest information from external data sources

[0230] Generative AI model: Using GPT-3 (registered trademark) as an example

[0231] Sentiment Analysis Engine: An engine that analyzes the user's emotional state

[0232] Blog platform API: API for posting blog posts (e.g., WordPress API)

[0233] Explanation of program processing

[0234] First, the server sends a request to the technology news API to get the latest programming language release information, which is received in JSON format and parsed.

[0235] Next, the server sends a GET request using the URL of the blog post to retrieve the original blog post to be updated. The retrieved original post content is saved in text format.

[0236] The server then uses a sentiment analysis engine to analyze the user's emotions, including collecting comments and feedback from the user, and generates prompts for the generative AI model based on the results of this analysis.

[0237] As a concrete example, consider a case where the original article content is "An article about new features in Python 3.9" and the latest information is "A new match statement has been introduced in Python 3.10." In this case, if the result of the user sentiment analysis is "Curious," the prompt statement will be as follows:

[0238] Prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[0239] The server then feeds this prompt into a generative AI model to generate new article content, which combines the original article with the latest information and is updated in an intriguing style.

[0240] Finally, the server posts the generated update using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and sensitive content.

[0241] This system allows tech blogs to be automatically updated with the latest information and keeps readers interested with expressions that reflect the emotions of users.

[0242] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0243] Step 1: Get the latest information from an external data source

[0244] Specific behavior:

[0245] The server sends an API request to the technology news API to retrieve the latest programming language release information.

[0246] Input: Request to the Tech News API

[0247] Data processing: Analyze data obtained in JSON format

[0248] Output: Latest programming language release information

[0249] Specifically, the server sends an HTTP GET request to the technology news API, receives JSON data as a response, and then parses this JSON data to extract important information (e.g., new features and version numbers).

[0250] Step 2: Get the original article

[0251] Specific behavior:

[0252] The server sends a GET request using the URL of the original blog post to be updated to retrieve the post's contents.

[0253] Input: Original blog post URL

[0254] Data processing: Save the article content obtained in text format

[0255] Output: Original blog post content

[0256] Specifically, the server sends an HTTP GET request to the specified URL, retrieves the original blog post content in text format as a response, and saves it in the system.

[0257] Step 3: Analyzing user sentiment

[0258] Specific behavior:

[0259] The server uses a sentiment analysis engine to analyze the user's comments and feedback and identify the user's sentiment.

[0260] Input: User comments and feedback

[0261] Data processing: Identifying emotional states with a sentiment analysis engine

[0262] Output: User's emotional state (e.g., curiosity, excitement)

[0263] Specifically, the server inputs collected user comments and feedback into an emotion analysis engine, and obtains the user's emotional state (e.g., "curious") as the analysis result.

[0264] Step 4: Update the article with a generative AI model

[0265] Specific behavior:

[0266] The server inputs prompt sentences into the generative AI model based on the analyzed emotional information, and generates the article content.

[0267] Input: Original article content, latest information, sentiment analysis results

[0268] Data processing: Prompt generation and article content generation using a generative AI model

[0269] Output: Updated blog post content

[0270] Specifically, the server generates a prompt message that says, "Explain the new features in an inquisitive style," and inputs the original article content and the latest information into a generative AI model (e.g., GPT-3). The model then generates new article content.

[0271] Example prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[0272] Step 5: Post your post to your blogging platform

[0273] Specific behavior:

[0274] The server posts the generated updated article content using the blog platform's API.

[0275] Input: Updated blog post content

[0276] Data processing: Formatting post data for the blog platform's API

[0277] Output: Blog post successful

[0278] Specifically, the server sends the updated blog post content to the blog platform's API as a POST request, and if successful, the post is published.

[0279] By implementing each step, the system can automatically update blog posts based on the latest information and reflect user sentiment. Through this process, it is possible to generate effective content that keeps readers interested.

[0280] (Application example 2)

[0281] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0282] Conventional automatic article updating systems have the function of obtaining the latest information and updating blogs, but they do not generate content based on user emotions, and therefore have the problem of not being able to effectively reflect the emotions and interests of individual users.In addition, since they are unable to analyze data according to user emotions or adjust content using a generative AI model based on that data, there are limitations to improving user engagement.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0284] In this invention, the server includes means for processing information using a generative artificial intelligence model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for posting the updated content to a blog platform, means for analyzing user emotions in real time, and means for adjusting the content based on the analyzed emotions, thereby enabling content generation and updating that takes user emotions into consideration.

[0285] A "generative artificial intelligence model" is an algorithm designed for natural language processing, specifically a trained model for generating and converting text.

[0286] An "external data source" is an information provider, such as a database or API, that exists outside the system and provides up-to-date and relevant information.

[0287] "Up-to-date information" refers to the most recent information or data provided by external data sources that the system uses to update its content.

[0288] "Original article content" refers to the content of the existing blog article before it is updated, and is text data that is acquired and saved within the system.

[0289] "Updated content" refers to article content that has been modified or added to the original article content based on the latest information and analysis results obtained.

[0290] A "blog platform" is an online platform for posting, managing, and viewing blog posts.

[0291] "User emotions" refers to the psychological state and emotional reactions that a user shows while viewing content, and are analyzed in real time using an emotion analysis engine.

[0292] "Real-time" refers to processes and operations that reflect values ​​immediately without delay, including the immediate analysis and use of user emotion data.

[0293] "Analyzed emotions" refers to the results of analyzing a user's emotions using an emotion analysis engine, and is data that the system uses to adjust content based on that information.

[0294] "Adjusting content" refers to the process of modifying, adding, or deleting content such as articles or text generated based on the analyzed sentiment, depending on the user's sentiment.

[0295] A system for implementing this invention includes a server, a user terminal, and an external data source. The server acquires, analyzes, and updates information using a generative artificial intelligence model, an emotion analysis engine, and an API access function. The user terminal refers to a device such as a smartphone or smart glasses, and is equipped with an emotion sensor function for acquiring user emotion data. The specific processing steps are as follows.

[0296] 1. Acquiring user emotion data

[0297] The user device collects the user's facial recognition data in real time and analyzes the user's emotions using an emotion analysis engine. For example, a smartphone camera can be used to analyze the user's facial expressions and obtain their current emotional state. This analysis can be performed using software such as the Emotion SDK. The analyzed emotion data is then sent to a server.

[0298] 2. Get the latest information from external data sources

[0299] The server retrieves the latest information from external data sources, for example, using a tech news API to retrieve the latest release information for a programming language. The retrieved data is formatted in JSON format and stored in an internal database. This process can use NewsAPI, TechCrunch API, etc.

[0300] 3. Obtaining the original article content

[0301] The server retrieves the original article content to be updated. For example, it retrieves the past article content in text format from a blog platform via a GET request. This retrieved data is also stored on the server.

[0302] 4. Updating and generating articles

[0303] The server updates the original article content based on the latest information and analyzed user sentiment data. To do so, it uses a generative artificial intelligence model (e.g., OpenAI's GPT-4®) and generates a new article by inputting the following prompt:

[0304] Example prompt sentence:

[0305] Original content: This tutorial explains list operations in Python.

[0306] New: A new Python version has been released, adding new list manipulation capabilities.

[0307] Emotion: Confused

[0308] Please update the original article based on this information to alleviate user confusion.

[0309] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[0310] 5. Posting updated content

[0311] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles with emotionally sensitive and up-to-date information. This process improves the user experience and leads to higher engagement.

[0312] As described above, this invention provides a content generation and updating system that takes into consideration the user's feelings and reflects the latest information.

[0313] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0314] Step 1:

[0315] The server receives facial recognition data from the user's device in real time. The user's device uses the smartphone camera to recognize the user's facial expressions and analyzes the data using the Emotion SDK. This analysis determines the user's emotional state (e.g., confusion, excitement, relief, etc.) and sends the results to the server. The input is facial recognition data, and the output is emotional data.

[0316] Step 2:

[0317] The server retrieves the latest information from external data sources. For example, it uses technology news APIs (NewsAPI, TechCrunch API, etc.) to retrieve the latest release information for programming languages. The retrieved data is formatted in JSON format and stored in an internal database. The input is the API request, and the output is the JSON data of the latest information.

[0318] Step 3:

[0319] The server retrieves the original post content to be updated. This involves using the blog platform's API to retrieve the previous post content in text format via a GET request. This data is also stored locally on the server. The input is the blog post URL, and the output is the original post content.

[0320] Step 4:

[0321] The server updates the original article content based on the latest information and analyzed emotion data. To do this, it uses a generative AI model (OpenAI GPT-4) and inputs the following prompt sentence into the generative AI model. The input-output relationship is the prompt sentence and the generated new article content.

[0322] Example prompt sentence:

[0323] Original content: This tutorial explains list operations in Python.

[0324] New: A new Python version has been released, adding new list manipulation capabilities.

[0325] Emotion: Confused

[0326] Please update the original article based on this information to alleviate user confusion.

[0327] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[0328] Step 5:

[0329] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles containing the latest information that takes sentiment into consideration. The input is the new article content, and the output is the posting result to the blog platform.

[0330] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0331] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0332] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0333] [Second embodiment]

[0334] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0335] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0336] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0337] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0338] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0339] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0340] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0341] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0342] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0343] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0344] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0345] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0346] System Overview

[0347] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model. Specifically, a server retrieves the latest information from an external data source, uses the generative artificial intelligence model to generate an updated article based on the original article content and the latest information, and then posts the article to a blog platform.

[0348] Program processing and explanation

[0349] Gathering the latest information

[0350] The server retrieves up-to-date information from an external data source (e.g., a tech news API) periodically or based on specified events. To do this, the server sends an API request and parses the received response in JSON format.

[0351] Get the original article

[0352] The server retrieves the URL of the original blog post to be updated and retrieves its content in text form via a GET request, which is then provided to the generative AI model.

[0353] Article Update

[0354] The server uses a generative AI model (e.g., GPT-2) to generate a prompt that combines the original article content with the latest information. This prompt is then input into the generative AI model, which generates a new sentence while maintaining the style of the original article. The generated sentence adds the latest information without losing the atmosphere and tone of the original article.

[0355] Posting an update

[0356] The server posts the generated update to the blog platform using the blog platform's API. If the post is successful, the blog is updated with the latest information, providing readers with the latest technical content.

[0357] Specific examples

[0358] 1. Gathering the latest information

[0359] The server retrieves the latest Python release information from an external data source. For example, it sends an API request to receive information such as "Python 3.10 has been released and adds pattern matching functionality."

[0360] 2. Obtaining the original article

[0361] The server requests the URL of an article about the history of Python and retrieves the original article content, for example, an article that explains the history of Python releases and version changes.

[0362] 3. Update the article

[0363] The server uses a generative artificial intelligence model to add updated information to the original article, including details about "the newly released features of Python 3.10 and the added pattern matching functionality."

[0364] 4. Posting an update

[0365] The server posts the generated update to a blogging platform, for example, "an update to the original article with new information about Python 3.10."

[0366] This system allows tech blogs to be automatically updated with the latest information, making it possible to provide the latest technical information without any hassle while maintaining the writing style of the original author.

[0367] The processing flow will be explained below.

[0368] Step 1:

[0369] The server retrieves the latest information from external data sources by sending a GET request to an API endpoint and receiving a response containing the latest technology news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0370] Step 2:

[0371] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0372] Step 3:

[0373] The server generates a prompt by concatenating the latest information with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content.

[0374] Step 4:

[0375] The server provides the generative AI model with the prompt generated in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0376] Step 5:

[0377] A generative AI model generates new, updated content while preserving the style and tone of the original. The generated text is based on the original article but includes the latest information.

[0378] Step 6:

[0379] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information.

[0380] Step 7:

[0381] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[0382] Example 1

[0383] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0384] It takes a lot of time and effort to keep a tech blog up-to-date with the latest information. It's also not easy to maintain the style and tone of the original article while adding the latest information. This makes it difficult to provide accurate and fresh information to readers.

[0385] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0386] In this invention, the server includes means for periodically obtaining the latest information from an external data source, means for analyzing the obtained latest information and extracting necessary information, and means for obtaining the URL of the original article content and obtaining that content in text format, which enables the server to quickly and efficiently obtain the latest information and automatically update the article while maintaining the style of the original article.

[0387] An "external data source" is an external information source for obtaining various data and information provided on the Internet.

[0388] "Latest information" refers to the most current information or data obtained from external data sources.

[0389] "Analysis" is the process of converting acquired data into a predetermined format and extracting necessary information from it.

[0390] The "original article content" is the text data of the existing blog article to be updated.

[0391] A "URL" is an address that identifies a resource on the Internet.

[0392] "Text format" is a format in which data is expressed as a string of characters.

[0393] A "prompt sentence" is text to be input into a generative artificial intelligence model, and is generated by combining the original article content with the latest information.

[0394] A "generative artificial intelligence model" is an artificial intelligence algorithm for generating new text based on given text data.

[0395] A "new sentence" is the output generated by a generative artificial intelligence model using a prompt sentence as input.

[0396] A "blog platform" is an online service that enables users to post and manage blog posts.

[0397] This invention is a system that automatically updates technical blogs with the latest information using a generative artificial intelligence model. The main processing is performed by a server, and the following hardware and software are used:

[0398] Hardware:

[0399] 1. Server: A central processing unit that handles all processes such as collecting the latest information, retrieving original articles, updating articles, and posting updated articles.

[0400] 2. Network connectivity: Required for accessing external data sources and blogging platforms.

[0401] software:

[0402] 1. Generative AI model: Generate new sentences using a generative AI model such as GPT-2.

[0403] 2. Technology News API: An API for getting the latest technology-related information.

[0404] 3. Blog Platform API: An API used to post and update blog posts.

[0405] Data processing and calculation:

[0406] 1. Parsing the latest information: The server parses the JSON response received from the external data source and extracts the latest technical information.

[0407] 2. Obtaining the original article in text format: The server obtains the content of the original article in text format from the specified URL and extracts the necessary content.

[0408] 3. Prompt sentence generation: The content of the original article is combined with the latest information to generate a prompt sentence, which is then input into the generative artificial intelligence model.

[0409] Examples:

[0410] Gathering the latest information:

[0411] The server makes a request to the tech news API and receives the latest information: "Python 3.10 has been released and adds pattern matching functionality."

[0412] Get the original article:

[0413] The server retrieves the URL of the "Python history article" and retrieves its contents in text format. The original article contains an article explaining the history of Python releases and version changes.

[0414] Generate prompt statement:

[0415] The server concatenates the original article content with the latest information and generates a prompt for the generative AI model, such as:

[0416] Example: Original article content + "Python 3.10 has been released. Its main feature is the addition of pattern matching functionality."

[0417] Generate and post an update:

[0418] The server inputs a prompt into the generative AI model and posts the generated new text to a blog platform, for example, "an updated version of the original article with new information about Python 3.10."

[0419] This system allows the server to quickly and efficiently retrieve the latest information and automatically update it while maintaining the style of the original article, ensuring that the blog always provides readers with the latest technical information.

[0420] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0421] Step 1:

[0422] The server sends an HTTP GET request to the API endpoint of the external data source. The input is the API endpoint URL, and the output is a JSON-formatted response containing the latest technical information. The server parses this response and extracts the required up-to-date information. Specifically, the server issues an API request, parses the received JSON data, and extracts the information that "Python 3.10 has been released."

[0423] Step 2:

[0424] The server retrieves the URL of the original article to be updated and sends an HTTP GET request. The input is the URL of the original article, and the output is the original article in text format. The server analyzes this text data and extracts the necessary content from the original article. Specifically, the server sends a request to the URL and retrieves the text data for the "article about the history of Python."

[0425] Step 3:

[0426] The server generates a prompt sentence by concatenating the latest information obtained in step 1 with the original article content obtained in step 2. The input is the original article content and the latest information, and the output is the prompt sentence to be input into the generative artificial intelligence model. Specifically, the server concatenates the original article content "Information about Python releases and version changes" with the latest information "Python 3.10 has been released. Its main feature is the addition of a pattern matching function" to generate a prompt sentence in the format of "original article content + latest information."

[0427] Step 4:

[0428] The server inputs the prompt sentence generated in step 3 into the generative AI model to generate a new sentence. The input is the prompt sentence, and the output is the generated new sentence. Specifically, the server sends the prompt sentence to the API of the generative AI model (e.g., GPT-2) to generate new text.

[0429] Step 5:

[0430] The server posts the generated new text to the blog platform. The input is the generated new text, and the output is the result of posting to the blog platform. Specifically, the server sends an HTTP POST request to the blog platform's API endpoint to upload the generated new article content. If posting is successful, the blog is automatically updated.

[0431] (Application example 1)

[0432] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0433] Currently, tech blogs are often updated manually, resulting in outdated information. Collecting the latest information from vast amounts of data and updating it in blog posts takes time and effort. Furthermore, the lack of a way to view information in real time on a smart device or have it read aloud presents a challenge in improving the user experience.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0435] In this invention, the server includes a means for processing information using a generative artificial intelligence model, a means for obtaining the latest information from an external data source, a means for updating the original article content based on the obtained latest information, a means for posting the updated content to a blog platform, and a means for reading out the content displayed on the smart glasses, so that the blog article is automatically updated with the latest information, and users can view and listen to the latest technical information in real time through the smart glasses.

[0436] A "generative artificial intelligence model" refers to a generative artificial intelligence model, a machine learning model for generating natural-looking sentences from specific input data.

[0437] "External Data Sources" refers to external data sources that provide up-to-date information, such as technology news APIs.

[0438] "Latest News" refers to the latest data and news related to technology or other specific fields.

[0439] "Original article content" refers to the text of the existing blog post or document that is being updated.

[0440] "Blog Platform" refers to a web service for hosting and publishing blog posts.

[0441] "Smart glasses" refers to a wearable display device worn by the user that has the ability to display information in conjunction with smartphones and other devices.

[0442] "Reading means" refers to the functionality or technology used to convert text into audio and read it to the user.

[0443] "Means for processing information" refers to a method for generating new information or content based on input data using a generative artificial intelligence model.

[0444] "Means of updating" refers to the process of creating a new article by adding the latest information obtained to the original article content.

[0445] "Means of posting" refers to the technology and functionality used to upload generated updates to the blog platform.

[0446] System Overview

[0447] This invention is a system that combines multiple components to automatically update a tech blog and enable it to be viewed in real time through smart glasses. The server has functions such as information processing using a generative artificial intelligence model, retrieving the latest information from external data sources, updating blog articles, and posting them to a blog platform. It also includes a function to display and read the updated content on the smart glasses.

[0448] Hardware and software used

[0449] The server generates articles using generative artificial intelligence models such as the GPT-2 model. Data is obtained via API requests and parsed in JSON format. The smart glasses are wearable display devices with information display and audio playback functions. The server uses gTTS (Google Text-to-Speech) for voice synthesis.

[0450] Program processing and explanation

[0451] Gathering the latest information

[0452] The server periodically retrieves the latest technical information from external data sources, sends API requests, and parses the received data in JSON format. For example, it may retrieve the latest release information from a technology news API.

[0453] Get the original article

[0454] The server retrieves the URL of the article to be updated from the blog platform and retrieves the article content in text format. For example, it may retrieve an article about the history of technology.

[0455] Article Update

[0456] The server generates a prompt by concatenating the original article content with the latest information, and inputs it into the generative AI model. The following prompts may be used:

[0457] Original Article: The History of Technology and Its Evolution

[0458] Latest Updates:

[0459] The latest technology has been released and new features have been added.

[0460] When generating an article using this prompt, the GPT-2 model preserves the feel of the original article while adding new information.

[0461] Posting an update

[0462] The generated update is posted using the blog platform's API, and if successful, the blog is updated with the latest technical content.

[0463] View and read updates

[0464] The updated article content will be displayed on the smart glasses, and in addition, the text will be converted to speech using gTTS and read aloud to the user through the smart glasses' speaker.

[0465] With this invention, blog posts are automatically updated with the latest information, allowing users to view and listen to the latest technical information in real time through the smart glasses.

[0466] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0467] Step 1:

[0468] The server retrieves the latest information from an external data source. First, it sends an API request to the technology news API to retrieve the latest information in JSON format. The input is the latest technology data, and the output is parsed JSON data. Specifically, it includes information such as "latest release information."

[0469] Step 2:

[0470] The server retrieves the original article content from the blog platform. It sends a GET request to the specified URL to retrieve the text of the original article. This retrieved text is the input data, and the output is the original article content. For example, let's say the target is an article about the history of technology.

[0471] Step 3:

[0472] The server generates a prompt by concatenating the original article content with the latest information. The input is the text of the original article content and the latest information obtained in step 1, and the server combines these two to create a prompt. The output is a prompt that is input to the generative AI model. For example:

[0473] Original Article: The History of Technology and Its Evolution

[0474] Latest Updates:

[0475] The latest technology has been released and new features have been added.

[0476] Step 4:

[0477] The server generates a new article using a generative artificial intelligence model. The prompt sentence is input into the GPT-2 model to generate the new article text. The input is the prompt sentence created in step 3, and the output is an updated article with the latest information. The updated article maintains the feel of the original article while adding new information.

[0478] Step 5:

[0479] The server posts the generated update to the blog platform. It uses the blog platform's API to publish the update on the Internet. The input is the generated update, and the output is the post on the blog platform.

[0480] Step 6:

[0481] The server displays the updated article content on the smart glasses and reads it aloud. It uses gTTS (Google Text-to-Speech) to convert the text into audio data and plays it through the smart glasses' speakers. The input is the text of the updated article, and the output is the audio data and the text displayed on the smart glasses. Users can receive the latest technical information visually and audibly through the smart glasses.

[0482] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0483] System Overview

[0484] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model and an emotion engine. Specifically, a server retrieves the latest information from external data sources, updates the original article content based on emotions using the generative artificial intelligence model and the emotion engine, and posts the article to a blog platform.

[0485] Program processing and explanation

[0486] Gathering the latest information

[0487] The server retrieves the latest information from an external data source (e.g., a tech news API). The server sends an API request and parses the received response in JSON format to retrieve the latest information.

[0488] Get the original article

[0489] The server retrieves the URL of the original blog post to be updated, retrieves the post's content in text format via a GET request, and stores it in the system.

[0490] Article update (using emotion engine)

[0491] The server uses an emotion engine to recognize and analyze the user's emotions. By linking the acquired latest information with the original article content and inputting the generated prompt and the analyzed emotion information into a generative AI model, an updated article is generated that contains expressions that best reflect the user's emotions while maintaining the original writing style.

[0492] Posting an update

[0493] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content.

[0494] Specific examples

[0495] 1. Gathering the latest information

[0496] The server retrieves the latest programming language release information from an external data source, for example by sending an API request to receive information about new programming language features.

[0497] 2. Obtaining the original article

[0498] The server requests the URL of the original blog post and retrieves the original content, e.g., "An article explaining an older version of a programming language."

[0499] 3. Using the Emotion Engine and Updating Articles

[0500] The server uses an emotion engine to recognize the user's emotions and analyze their "curiosity." For example, it analyzes "curious reactions" from user comments and feedback. Based on this, it inputs a prompt to "explain new features in an inquisitive style" into the generative AI model, and generates an updated article that adds the latest information to the original article content.

[0501] 4. Posting an update

[0502] The server takes the generated update and posts it to a blogging platform, for example, "the original post with an enthusiastic commentary on the latest features of a new programming language."

[0503] This system not only ensures that tech blogs are always automatically updated with the latest information, but also includes expressions that take into account user emotions, helping to keep readers interested.

[0504] The processing flow will be explained below.

[0505] Step 1:

[0506] The server retrieves the latest information from an external data source. Specifically, the server sends a GET request to an API endpoint and receives a response containing the latest tech news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0507] Step 2:

[0508] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0509] Step 3:

[0510] The user accesses the system through a terminal and inputs or provides feedback on their emotions. The emotion engine analyzes the user's input and identifies their emotional state (e.g., excitement, curiosity, surprise, etc.).

[0511] Step 4:

[0512] The server generates a prompt by concatenating the latest information obtained with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content as the premise context for future sentences.

[0513] Step 5:

[0514] The server provides the generative AI model with the prompt generated in step 4 and the emotional information analyzed in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0515] Step 6:

[0516] The generative AI model generates updated article content that best reflects the user's emotions while maintaining the original style and tone. The generated text is based on the original article but includes the latest information and emotionally sensitive content.

[0517] Step 7:

[0518] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content to readers.

[0519] Step 8:

[0520] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[0521] Example 2

[0522] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0523] Conventional blog update systems do not automatically add the latest information or generate content that takes user emotions into consideration, making it difficult to maintain reader interest. Furthermore, there is a need for systems that not only simply update information but also incorporate appropriate expressions based on emotions.

[0524] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for processing information using a generative AI model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for analyzing the user's emotions using an emotion analysis engine, means for generating an article by inputting a prompt sentence to the generative AI model based on the analyzed emotion information, and means for posting the updated content to a blog platform. This enables automatic updating of articles based on the latest information and generation of content taking user emotions into consideration.

[0525] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information using machine learning technology.

[0526] An "external data source" is a data provider or information source that exists outside the system, not within it.

[0527] An "emotion analysis engine" is software or hardware used to analyze and identify a user's emotional state from text or voice.

[0528] A "blog platform" is a web service or software that allows users to create, manage, and publish blog posts online.

[0529] A "prompt" is an instruction or question input to a generative AI model, which instructs the AI ​​to generate output based on this.

[0530] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data description format used for storing and exchanging data.

[0531] An "API request" is a communication made via an application program interface to request a specific service or data.

[0532] "Means for processing information" refers to a program or device that receives data, analyzes it, and outputs results according to the purpose.

[0533] "Means for updating the original article content based on the latest information obtained" refers to methods or techniques for changing or adding to the existing article content based on newly obtained information.

[0534] An "article generation means" is a program or device that automatically creates new articles or documents based on input information.

[0535] "Means for posting articles" refers to the technology or method used to upload and publish generated articles to an online blog or website.

[0536] This invention relates to a system for automatically updating tech blogs using a generative artificial intelligence model and a sentiment analysis engine, specifically to optimize content based on user sentiment and provide always-up-to-date information.

[0537] Hardware and Software Used

[0538] Server: Cloud-based server (e.g. AWS, Azure) or on-premise server

[0539] Tech News API: API for retrieving the latest information from external data sources

[0540] Generative AI models: Using GPT-3 as an example

[0541] Sentiment Analysis Engine: An engine that analyzes the user's emotional state

[0542] Blog platform API: API for posting blog posts (e.g., WordPress API)

[0543] Explanation of program processing

[0544] First, the server sends a request to the technology news API to get the latest programming language release information, which is received in JSON format and parsed.

[0545] Next, the server sends a GET request using the URL of the blog post to retrieve the original blog post to be updated. The retrieved original post content is saved in text format.

[0546] The server then uses a sentiment analysis engine to analyze the user's emotions, including collecting comments and feedback from the user, and generates prompts for the generative AI model based on the results of this analysis.

[0547] As a concrete example, consider a case where the original article content is "An article about new features in Python 3.9" and the latest information is "A new match statement has been introduced in Python 3.10." In this case, if the result of the user sentiment analysis is "Curious," the prompt statement will be as follows:

[0548] Prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[0549] The server then feeds this prompt into a generative AI model to generate new article content, which combines the original article with the latest information and is updated in an intriguing style.

[0550] Finally, the server posts the generated update using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and sensitive content.

[0551] This system allows tech blogs to be automatically updated with the latest information and keeps readers interested with expressions that reflect the emotions of users.

[0552] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0553] Step 1: Get the latest information from an external data source

[0554] Specific behavior:

[0555] The server sends an API request to the technology news API to retrieve the latest programming language release information.

[0556] Input: Request to the Tech News API

[0557] Data processing: Analyze data obtained in JSON format

[0558] Output: Latest programming language release information

[0559] Specifically, the server sends an HTTP GET request to the technology news API, receives JSON data as a response, and then parses this JSON data to extract important information (e.g., new features and version numbers).

[0560] Step 2: Get the original article

[0561] Specific behavior:

[0562] The server sends a GET request using the URL of the original blog post to be updated to retrieve the post's contents.

[0563] Input: Original blog post URL

[0564] Data processing: Save the article content obtained in text format

[0565] Output: Original blog post content

[0566] Specifically, the server sends an HTTP GET request to the specified URL, retrieves the original blog post content in text format as a response, and saves it in the system.

[0567] Step 3: Analyzing user sentiment

[0568] Specific behavior:

[0569] The server uses a sentiment analysis engine to analyze the user's comments and feedback and identify the user's sentiment.

[0570] Input: User comments and feedback

[0571] Data processing: Identifying emotional states with a sentiment analysis engine

[0572] Output: User's emotional state (e.g., curiosity, excitement)

[0573] Specifically, the server inputs collected user comments and feedback into an emotion analysis engine, and obtains the user's emotional state (e.g., "curious") as the analysis result.

[0574] Step 4: Update the article with a generative AI model

[0575] Specific behavior:

[0576] The server inputs prompt sentences into the generative AI model based on the analyzed emotional information, and generates the article content.

[0577] Input: Original article content, latest information, sentiment analysis results

[0578] Data processing: Prompt generation and article content generation using a generative AI model

[0579] Output: Updated blog post content

[0580] Specifically, the server generates a prompt message that says, "Explain the new features in an inquisitive style," and inputs the original article content and the latest information into a generative AI model (e.g., GPT-3). The model then generates new article content.

[0581] Example prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[0582] Step 5: Post your post to your blogging platform

[0583] Specific behavior:

[0584] The server posts the generated updated article content using the blog platform's API.

[0585] Input: Updated blog post content

[0586] Data processing: Formatting post data for the blog platform's API

[0587] Output: Blog post successful

[0588] Specifically, the server sends the updated blog post content to the blog platform's API as a POST request, and if successful, the post is published.

[0589] By implementing each step, the system can automatically update blog posts based on the latest information and reflect user sentiment. Through this process, it is possible to generate effective content that keeps readers interested.

[0590] (Application example 2)

[0591] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] Conventional automatic article updating systems have the function of obtaining the latest information and updating blogs, but they do not generate content based on user emotions, and therefore have the problem of not being able to effectively reflect the emotions and interests of individual users.In addition, since they are unable to analyze data according to user emotions or adjust content using a generative AI model based on that data, there are limitations to improving user engagement.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0594] In this invention, the server includes means for processing information using a generative artificial intelligence model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for posting the updated content to a blog platform, means for analyzing user emotions in real time, and means for adjusting the content based on the analyzed emotions, thereby enabling content generation and updating that takes user emotions into consideration.

[0595] A "generative artificial intelligence model" is an algorithm designed for natural language processing, specifically a trained model for generating and converting text.

[0596] An "external data source" is an information provider, such as a database or API, that exists outside the system and provides up-to-date and relevant information.

[0597] "Up-to-date information" refers to the most recent information or data provided by external data sources that the system uses to update its content.

[0598] "Original article content" refers to the content of the existing blog article before it is updated, and is text data that is acquired and saved within the system.

[0599] "Updated content" refers to article content that has been modified or added to the original article content based on the latest information and analysis results obtained.

[0600] A "blog platform" is an online platform for posting, managing, and viewing blog posts.

[0601] "User emotions" refers to the psychological state and emotional reactions that a user shows while viewing content, and are analyzed in real time using an emotion analysis engine.

[0602] "Real-time" refers to processes and operations that reflect values ​​immediately without delay, including the immediate analysis and use of user emotion data.

[0603] "Analyzed emotions" refers to the results of analyzing a user's emotions using an emotion analysis engine, and is data that the system uses to adjust content based on that information.

[0604] "Adjusting content" refers to the process of modifying, adding, or deleting content such as articles or text generated based on the analyzed sentiment, depending on the user's sentiment.

[0605] A system for implementing this invention includes a server, a user terminal, and an external data source. The server acquires, analyzes, and updates information using a generative artificial intelligence model, an emotion analysis engine, and an API access function. The user terminal refers to a device such as a smartphone or smart glasses, and is equipped with an emotion sensor function for acquiring user emotion data. The specific processing steps are as follows.

[0606] 1. Acquiring user emotion data

[0607] The user device collects the user's facial recognition data in real time and analyzes the user's emotions using an emotion analysis engine. For example, a smartphone camera can be used to analyze the user's facial expressions and obtain their current emotional state. This analysis can be performed using software such as the Emotion SDK. The analyzed emotion data is then sent to a server.

[0608] 2. Get the latest information from external data sources

[0609] The server retrieves the latest information from external data sources, for example, using a tech news API to retrieve the latest release information for a programming language. The retrieved data is formatted in JSON format and stored in an internal database. This process can use NewsAPI, TechCrunch API, etc.

[0610] 3. Obtaining the original article content

[0611] The server retrieves the original article content to be updated. For example, it retrieves the past article content in text format from a blog platform via a GET request. This retrieved data is also stored on the server.

[0612] 4. Updating and generating articles

[0613] The server updates the original article content based on the latest information and analyzed user sentiment data. To do so, it uses a generative artificial intelligence model (e.g., OpenAI's GPT-4) and generates a new article by inputting the following prompt:

[0614] Example prompt sentence:

[0615] Original content: This tutorial explains list operations in Python.

[0616] New: A new Python version has been released, adding new list manipulation capabilities.

[0617] Emotion: Confused

[0618] Please update the original article based on this information to alleviate user confusion.

[0619] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[0620] 5. Posting updated content

[0621] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles with emotionally sensitive and up-to-date information. This process improves the user experience and leads to higher engagement.

[0622] As described above, this invention provides a content generation and updating system that takes into consideration the user's feelings and reflects the latest information.

[0623] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0624] Step 1:

[0625] The server receives facial recognition data from the user's device in real time. The user's device uses the smartphone camera to recognize the user's facial expressions and analyzes the data using the Emotion SDK. This analysis determines the user's emotional state (e.g., confusion, excitement, relief, etc.) and sends the results to the server. The input is facial recognition data, and the output is emotional data.

[0626] Step 2:

[0627] The server retrieves the latest information from external data sources. For example, it uses technology news APIs (NewsAPI, TechCrunch API, etc.) to retrieve the latest release information for programming languages. The retrieved data is formatted in JSON format and stored in an internal database. The input is the API request, and the output is the JSON data of the latest information.

[0628] Step 3:

[0629] The server retrieves the original post content to be updated. This involves using the blog platform's API to retrieve the previous post content in text format via a GET request. This data is also stored locally on the server. The input is the blog post URL, and the output is the original post content.

[0630] Step 4:

[0631] The server updates the original article content based on the latest information and analyzed emotion data. To do this, it uses a generative AI model (OpenAI GPT-4) and inputs the following prompt sentence into the generative AI model. The input-output relationship is the prompt sentence and the generated new article content.

[0632] Example prompt sentence:

[0633] Original content: This tutorial explains list operations in Python.

[0634] New: A new Python version has been released, adding new list manipulation capabilities.

[0635] Emotion: Confused

[0636] Please update the original article based on this information to alleviate user confusion.

[0637] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[0638] Step 5:

[0639] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles containing the latest information that takes sentiment into consideration. The input is the new article content, and the output is the posting result to the blog platform.

[0640] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0641] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0642] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0643] [Third embodiment]

[0644] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0645] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0646] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0647] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0648] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0649] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0650] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0651] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0652] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0653] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0654] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0655] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0656] System Overview

[0657] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model. Specifically, a server retrieves the latest information from an external data source, uses the generative artificial intelligence model to generate an updated article based on the original article content and the latest information, and then posts the article to a blog platform.

[0658] Program processing and explanation

[0659] Gathering the latest information

[0660] The server retrieves up-to-date information from an external data source (e.g., a tech news API) periodically or based on specified events. To do this, the server sends an API request and parses the received response in JSON format.

[0661] Get the original article

[0662] The server retrieves the URL of the original blog post to be updated and retrieves its content in text form via a GET request, which is then provided to the generative AI model.

[0663] Article Update

[0664] The server uses a generative AI model (e.g., GPT-2) to generate a prompt that combines the original article content with the latest information. This prompt is then input into the generative AI model, which generates a new sentence while maintaining the style of the original article. The generated sentence adds the latest information without losing the atmosphere and tone of the original article.

[0665] Posting an update

[0666] The server posts the generated update to the blog platform using the blog platform's API. If the post is successful, the blog is updated with the latest information, providing readers with the latest technical content.

[0667] Specific examples

[0668] 1. Gathering the latest information

[0669] The server retrieves the latest Python release information from an external data source. For example, it sends an API request to receive information such as "Python 3.10 has been released and adds pattern matching functionality."

[0670] 2. Obtaining the original article

[0671] The server requests the URL of an article about the history of Python and retrieves the original article content, for example, an article that explains the history of Python releases and version changes.

[0672] 3. Update the article

[0673] The server uses a generative artificial intelligence model to add updated information to the original article, including details about "the newly released features of Python 3.10 and the added pattern matching functionality."

[0674] 4. Posting an update

[0675] The server posts the generated update to a blogging platform, for example, "an update to the original article with new information about Python 3.10."

[0676] This system allows tech blogs to be automatically updated with the latest information, making it possible to provide the latest technical information without any hassle while maintaining the writing style of the original author.

[0677] The processing flow will be explained below.

[0678] Step 1:

[0679] The server retrieves the latest information from external data sources by sending a GET request to an API endpoint and receiving a response containing the latest technology news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0680] Step 2:

[0681] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0682] Step 3:

[0683] The server generates a prompt by concatenating the latest information with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content.

[0684] Step 4:

[0685] The server provides the generative AI model with the prompt generated in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0686] Step 5:

[0687] A generative AI model generates new, updated content while preserving the style and tone of the original. The generated text is based on the original article but includes the latest information.

[0688] Step 6:

[0689] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information.

[0690] Step 7:

[0691] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[0692] Example 1

[0693] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0694] It takes a lot of time and effort to keep a tech blog up-to-date with the latest information. It's also not easy to maintain the style and tone of the original article while adding the latest information. This makes it difficult to provide accurate and fresh information to readers.

[0695] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0696] In this invention, the server includes means for periodically obtaining the latest information from an external data source, means for analyzing the obtained latest information and extracting necessary information, and means for obtaining the URL of the original article content and obtaining that content in text format, which enables the server to quickly and efficiently obtain the latest information and automatically update the article while maintaining the style of the original article.

[0697] An "external data source" is an external information source for obtaining various data and information provided on the Internet.

[0698] "Latest information" refers to the most current information or data obtained from external data sources.

[0699] "Analysis" is the process of converting acquired data into a predetermined format and extracting necessary information from it.

[0700] The "original article content" is the text data of the existing blog article to be updated.

[0701] A "URL" is an address that identifies a resource on the Internet.

[0702] "Text format" is a format in which data is expressed as a string of characters.

[0703] A "prompt sentence" is text to be input into a generative artificial intelligence model, and is generated by combining the original article content with the latest information.

[0704] A "generative artificial intelligence model" is an artificial intelligence algorithm for generating new text based on given text data.

[0705] A "new sentence" is the output generated by a generative artificial intelligence model using a prompt sentence as input.

[0706] A "blog platform" is an online service that enables users to post and manage blog posts.

[0707] This invention is a system that automatically updates technical blogs with the latest information using a generative artificial intelligence model. The main processing is performed by a server, and the following hardware and software are used:

[0708] Hardware:

[0709] 1. Server: A central processing unit that handles all processes such as collecting the latest information, retrieving original articles, updating articles, and posting updated articles.

[0710] 2. Network connectivity: Required for accessing external data sources and blogging platforms.

[0711] software:

[0712] 1. Generative AI model: Generate new sentences using a generative AI model such as GPT-2.

[0713] 2. Technology News API: An API for getting the latest technology-related information.

[0714] 3. Blog Platform API: An API used to post and update blog posts.

[0715] Data processing and calculation:

[0716] 1. Parsing the latest information: The server parses the JSON response received from the external data source and extracts the latest technical information.

[0717] 2. Obtaining the original article in text format: The server obtains the content of the original article in text format from the specified URL and extracts the necessary content.

[0718] 3. Prompt sentence generation: The content of the original article is combined with the latest information to generate a prompt sentence, which is then input into the generative artificial intelligence model.

[0719] Examples:

[0720] Gathering the latest information:

[0721] The server makes a request to the tech news API and receives the latest information: "Python 3.10 has been released and adds pattern matching functionality."

[0722] Get the original article:

[0723] The server retrieves the URL of the "Python history article" and retrieves its contents in text format. The original article contains an article explaining the history of Python releases and version changes.

[0724] Generate prompt statement:

[0725] The server concatenates the original article content with the latest information and generates a prompt for the generative AI model, such as:

[0726] Example: Original article content + "Python 3.10 has been released. Its main feature is the addition of pattern matching functionality."

[0727] Generate and post an update:

[0728] The server inputs a prompt into the generative AI model and posts the generated new text to a blog platform, for example, "an updated version of the original article with new information about Python 3.10."

[0729] This system allows the server to quickly and efficiently retrieve the latest information and automatically update it while maintaining the style of the original article, ensuring that the blog always provides readers with the latest technical information.

[0730] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0731] Step 1:

[0732] The server sends an HTTP GET request to the API endpoint of the external data source. The input is the API endpoint URL, and the output is a JSON-formatted response containing the latest technical information. The server parses this response and extracts the required up-to-date information. Specifically, the server issues an API request, parses the received JSON data, and extracts the information that "Python 3.10 has been released."

[0733] Step 2:

[0734] The server retrieves the URL of the original article to be updated and sends an HTTP GET request. The input is the URL of the original article, and the output is the original article in text format. The server analyzes this text data and extracts the necessary content from the original article. Specifically, the server sends a request to the URL and retrieves the text data for the "article about the history of Python."

[0735] Step 3:

[0736] The server generates a prompt sentence by concatenating the latest information obtained in step 1 with the original article content obtained in step 2. The input is the original article content and the latest information, and the output is the prompt sentence to be input into the generative artificial intelligence model. Specifically, the server concatenates the original article content "Information about Python releases and version changes" with the latest information "Python 3.10 has been released. Its main feature is the addition of a pattern matching function" to generate a prompt sentence in the format of "original article content + latest information."

[0737] Step 4:

[0738] The server inputs the prompt sentence generated in step 3 into the generative AI model to generate a new sentence. The input is the prompt sentence, and the output is the generated new sentence. Specifically, the server sends the prompt sentence to the API of the generative AI model (e.g., GPT-2) to generate new text.

[0739] Step 5:

[0740] The server posts the generated new text to the blog platform. The input is the generated new text, and the output is the result of posting to the blog platform. Specifically, the server sends an HTTP POST request to the blog platform's API endpoint to upload the generated new article content. If posting is successful, the blog is automatically updated.

[0741] (Application example 1)

[0742] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0743] Currently, tech blogs are often updated manually, resulting in outdated information. Collecting the latest information from vast amounts of data and updating it in blog posts takes time and effort. Furthermore, the lack of a way to view information in real time on a smart device or have it read aloud presents a challenge in improving the user experience.

[0744] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0745] In this invention, the server includes a means for processing information using a generative artificial intelligence model, a means for obtaining the latest information from an external data source, a means for updating the original article content based on the obtained latest information, a means for posting the updated content to a blog platform, and a means for reading out the content displayed on the smart glasses, so that the blog article is automatically updated with the latest information, and users can view and listen to the latest technical information in real time through the smart glasses.

[0746] A "generative artificial intelligence model" refers to a generative artificial intelligence model, a machine learning model for generating natural-looking sentences from specific input data.

[0747] "External Data Sources" refers to external data sources that provide up-to-date information, such as technology news APIs.

[0748] "Latest News" refers to the latest data and news related to technology or other specific fields.

[0749] "Original article content" refers to the text of the existing blog post or document that is being updated.

[0750] "Blog Platform" refers to a web service for hosting and publishing blog posts.

[0751] "Smart glasses" refers to a wearable display device worn by the user that has the ability to display information in conjunction with smartphones and other devices.

[0752] "Reading means" refers to the functionality or technology used to convert text into audio and read it to the user.

[0753] "Means for processing information" refers to a method for generating new information or content based on input data using a generative artificial intelligence model.

[0754] "Means of updating" refers to the process of creating a new article by adding the latest information obtained to the original article content.

[0755] "Means of posting" refers to the technology and functionality used to upload generated updates to the blog platform.

[0756] System Overview

[0757] This invention is a system that combines multiple components to automatically update a tech blog and enable it to be viewed in real time through smart glasses. The server has functions such as information processing using a generative artificial intelligence model, retrieving the latest information from external data sources, updating blog articles, and posting them to a blog platform. It also includes a function to display and read the updated content on the smart glasses.

[0758] Hardware and software used

[0759] The server generates articles using generative artificial intelligence models such as the GPT-2 model. Data is obtained via API requests and parsed in JSON format. The smart glasses are wearable display devices with information display and audio playback functions. The server uses gTTS (Google Text-to-Speech) for voice synthesis.

[0760] Program processing and explanation

[0761] Gathering the latest information

[0762] The server periodically retrieves the latest technical information from external data sources, sends API requests, and parses the received data in JSON format. For example, it may retrieve the latest release information from a technology news API.

[0763] Get the original article

[0764] The server retrieves the URL of the article to be updated from the blog platform and retrieves the article content in text format. For example, it may retrieve an article about the history of technology.

[0765] Article Update

[0766] The server generates a prompt by concatenating the original article content with the latest information, and inputs it into the generative AI model. The following prompts may be used:

[0767] Original Article: The History of Technology and Its Evolution

[0768] Latest Updates:

[0769] The latest technology has been released and new features have been added.

[0770] When generating an article using this prompt, the GPT-2 model preserves the feel of the original article while adding new information.

[0771] Posting an update

[0772] The generated update is posted using the blog platform's API, and if successful, the blog is updated with the latest technical content.

[0773] View and read updates

[0774] The updated article content will be displayed on the smart glasses, and in addition, the text will be converted to speech using gTTS and read aloud to the user through the smart glasses' speaker.

[0775] With this invention, blog posts are automatically updated with the latest information, allowing users to view and listen to the latest technical information in real time through the smart glasses.

[0776] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0777] Step 1:

[0778] The server retrieves the latest information from an external data source. First, it sends an API request to the technology news API to retrieve the latest information in JSON format. The input is the latest technology data, and the output is parsed JSON data. Specifically, it includes information such as "latest release information."

[0779] Step 2:

[0780] The server retrieves the original article content from the blog platform. It sends a GET request to the specified URL to retrieve the text of the original article. This retrieved text is the input data, and the output is the original article content. For example, let's say the target is an article about the history of technology.

[0781] Step 3:

[0782] The server generates a prompt by concatenating the original article content with the latest information. The input is the text of the original article content and the latest information obtained in step 1, and the server combines these two to create a prompt. The output is a prompt that is input to the generative AI model. For example:

[0783] Original Article: The History of Technology and Its Evolution

[0784] Latest Updates:

[0785] The latest technology has been released and new features have been added.

[0786] Step 4:

[0787] The server generates a new article using a generative artificial intelligence model. The prompt sentence is input into the GPT-2 model to generate the new article text. The input is the prompt sentence created in step 3, and the output is an updated article with the latest information. The updated article maintains the feel of the original article while adding new information.

[0788] Step 5:

[0789] The server posts the generated update to the blog platform. It uses the blog platform's API to publish the update on the Internet. The input is the generated update, and the output is the post on the blog platform.

[0790] Step 6:

[0791] The server displays the updated article content on the smart glasses and reads it aloud. It uses gTTS (Google Text-to-Speech) to convert the text into audio data and plays it through the smart glasses' speakers. The input is the text of the updated article, and the output is the audio data and the text displayed on the smart glasses. Users can receive the latest technical information visually and audibly through the smart glasses.

[0792] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0793] System Overview

[0794] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model and an emotion engine. Specifically, a server retrieves the latest information from external data sources, updates the original article content based on emotions using the generative artificial intelligence model and the emotion engine, and posts the article to a blog platform.

[0795] Program processing and explanation

[0796] Gathering the latest information

[0797] The server retrieves the latest information from an external data source (e.g., a tech news API). The server sends an API request and parses the received response in JSON format to retrieve the latest information.

[0798] Get the original article

[0799] The server retrieves the URL of the original blog post to be updated, retrieves the post's content in text format via a GET request, and stores it in the system.

[0800] Article update (using emotion engine)

[0801] The server uses an emotion engine to recognize and analyze the user's emotions. By linking the acquired latest information with the original article content and inputting the generated prompt and the analyzed emotion information into a generative AI model, an updated article is generated that contains expressions that best reflect the user's emotions while maintaining the original writing style.

[0802] Posting an update

[0803] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content.

[0804] Specific examples

[0805] 1. Gathering the latest information

[0806] The server retrieves the latest programming language release information from an external data source, for example by sending an API request to receive information about new programming language features.

[0807] 2. Obtaining the original article

[0808] The server requests the URL of the original blog post and retrieves the original content, e.g., "An article explaining an older version of a programming language."

[0809] 3. Using the Emotion Engine and Updating Articles

[0810] The server uses an emotion engine to recognize the user's emotions and analyze their "curiosity." For example, it analyzes "curious reactions" from user comments and feedback. Based on this, it inputs a prompt to "explain new features in an inquisitive style" into the generative AI model, and generates an updated article that adds the latest information to the original article content.

[0811] 4. Posting an update

[0812] The server takes the generated update and posts it to a blogging platform, for example, "the original post with an enthusiastic commentary on the latest features of a new programming language."

[0813] This system not only ensures that tech blogs are always automatically updated with the latest information, but also includes expressions that take into account user emotions, helping to keep readers interested.

[0814] The processing flow will be explained below.

[0815] Step 1:

[0816] The server retrieves the latest information from an external data source. Specifically, the server sends a GET request to an API endpoint and receives a response containing the latest tech news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0817] Step 2:

[0818] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0819] Step 3:

[0820] The user accesses the system through a terminal and inputs or provides feedback on their emotions. The emotion engine analyzes the user's input and identifies their emotional state (e.g., excitement, curiosity, surprise, etc.).

[0821] Step 4:

[0822] The server generates a prompt by concatenating the latest information obtained with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content as the premise context for future sentences.

[0823] Step 5:

[0824] The server provides the generative AI model with the prompt generated in step 4 and the emotional information analyzed in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0825] Step 6:

[0826] The generative AI model generates updated article content that best reflects the user's emotions while maintaining the original style and tone. The generated text is based on the original article but includes the latest information and emotionally sensitive content.

[0827] Step 7:

[0828] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content to readers.

[0829] Step 8:

[0830] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[0831] Example 2

[0832] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0833] Conventional blog update systems do not automatically add the latest information or generate content that takes user emotions into consideration, making it difficult to maintain reader interest. Furthermore, there is a need for systems that not only simply update information but also incorporate appropriate expressions based on emotions.

[0834] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for processing information using a generative AI model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for analyzing the user's emotions using an emotion analysis engine, means for generating an article by inputting a prompt sentence to the generative AI model based on the analyzed emotion information, and means for posting the updated content to a blog platform. This enables automatic updating of articles based on the latest information and generation of content taking user emotions into consideration.

[0835] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information using machine learning technology.

[0836] An "external data source" is a data provider or information source that exists outside the system, not within it.

[0837] An "emotion analysis engine" is software or hardware used to analyze and identify a user's emotional state from text or voice.

[0838] A "blog platform" is a web service or software that allows users to create, manage, and publish blog posts online.

[0839] A "prompt" is an instruction or question input to a generative AI model, which instructs the AI ​​to generate output based on this.

[0840] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data description format used for storing and exchanging data.

[0841] An "API request" is a communication made via an application program interface to request a specific service or data.

[0842] "Means for processing information" refers to a program or device that receives data, analyzes it, and outputs results according to the purpose.

[0843] "Means for updating the original article content based on the latest information obtained" refers to methods or techniques for changing or adding to the existing article content based on newly obtained information.

[0844] An "article generation means" is a program or device that automatically creates new articles or documents based on input information.

[0845] "Means for posting articles" refers to the technology or method used to upload and publish generated articles to an online blog or website.

[0846] This invention relates to a system for automatically updating tech blogs using a generative artificial intelligence model and a sentiment analysis engine, specifically to optimize content based on user sentiment and provide always-up-to-date information.

[0847] Hardware and Software Used

[0848] Server: Cloud-based server (e.g. AWS, Azure) or on-premise server

[0849] Tech News API: API for retrieving the latest information from external data sources

[0850] Generative AI models: Using GPT-3 as an example

[0851] Sentiment Analysis Engine: An engine that analyzes the user's emotional state

[0852] Blog platform API: API for posting blog posts (e.g., WordPress API)

[0853] Explanation of program processing

[0854] First, the server sends a request to the technology news API to get the latest programming language release information, which is received in JSON format and parsed.

[0855] Next, the server sends a GET request using the URL of the blog post to retrieve the original blog post to be updated. The retrieved original post content is saved in text format.

[0856] The server then uses a sentiment analysis engine to analyze the user's emotions, including collecting comments and feedback from the user, and generates prompts for the generative AI model based on the results of this analysis.

[0857] As a concrete example, consider a case where the original article content is "An article about new features in Python 3.9" and the latest information is "A new match statement has been introduced in Python 3.10." In this case, if the result of the user sentiment analysis is "Curious," the prompt statement will be as follows:

[0858] Prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[0859] The server then feeds this prompt into a generative AI model to generate new article content, which combines the original article with the latest information and is updated in an intriguing style.

[0860] Finally, the server posts the generated update using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and sensitive content.

[0861] This system allows tech blogs to be automatically updated with the latest information and keeps readers interested with expressions that reflect the emotions of users.

[0862] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0863] Step 1: Get the latest information from an external data source

[0864] Specific behavior:

[0865] The server sends an API request to the technology news API to retrieve the latest programming language release information.

[0866] Input: Request to the Tech News API

[0867] Data processing: Analyze data obtained in JSON format

[0868] Output: Latest programming language release information

[0869] Specifically, the server sends an HTTP GET request to the technology news API, receives JSON data as a response, and then parses this JSON data to extract important information (e.g., new features and version numbers).

[0870] Step 2: Get the original article

[0871] Specific behavior:

[0872] The server sends a GET request using the URL of the original blog post to be updated to retrieve the post's contents.

[0873] Input: Original blog post URL

[0874] Data processing: Save the article content obtained in text format

[0875] Output: Original blog post content

[0876] Specifically, the server sends an HTTP GET request to the specified URL, retrieves the original blog post content in text format as a response, and saves it in the system.

[0877] Step 3: Analyzing user sentiment

[0878] Specific behavior:

[0879] The server uses a sentiment analysis engine to analyze the user's comments and feedback and identify the user's sentiment.

[0880] Input: User comments and feedback

[0881] Data processing: Identifying emotional states with a sentiment analysis engine

[0882] Output: User's emotional state (e.g., curiosity, excitement)

[0883] Specifically, the server inputs collected user comments and feedback into an emotion analysis engine, and obtains the user's emotional state (e.g., "curious") as the analysis result.

[0884] Step 4: Update the article with a generative AI model

[0885] Specific behavior:

[0886] The server inputs prompt sentences into the generative AI model based on the analyzed emotional information, and generates the article content.

[0887] Input: Original article content, latest information, sentiment analysis results

[0888] Data processing: Prompt generation and article content generation using a generative AI model

[0889] Output: Updated blog post content

[0890] Specifically, the server generates a prompt message that says, "Explain the new features in an inquisitive style," and inputs the original article content and the latest information into a generative AI model (e.g., GPT-3). The model then generates new article content.

[0891] Example prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[0892] Step 5: Post your post to your blogging platform

[0893] Specific behavior:

[0894] The server posts the generated updated article content using the blog platform's API.

[0895] Input: Updated blog post content

[0896] Data processing: Formatting post data for the blog platform's API

[0897] Output: Blog post successful

[0898] Specifically, the server sends the updated blog post content to the blog platform's API as a POST request, and if successful, the post is published.

[0899] By implementing each step, the system can automatically update blog posts based on the latest information and reflect user sentiment. Through this process, it is possible to generate effective content that keeps readers interested.

[0900] (Application example 2)

[0901] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0902] Conventional automatic article updating systems have the function of obtaining the latest information and updating blogs, but they do not generate content based on user emotions, and therefore have the problem of not being able to effectively reflect the emotions and interests of individual users.In addition, since they are unable to analyze data according to user emotions or adjust content using a generative AI model based on that data, there are limitations to improving user engagement.

[0903] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0904] In this invention, the server includes means for processing information using a generative artificial intelligence model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for posting the updated content to a blog platform, means for analyzing user emotions in real time, and means for adjusting the content based on the analyzed emotions, thereby enabling content generation and updating that takes user emotions into consideration.

[0905] A "generative artificial intelligence model" is an algorithm designed for natural language processing, specifically a trained model for generating and converting text.

[0906] An "external data source" is an information provider, such as a database or API, that exists outside the system and provides up-to-date and relevant information.

[0907] "Up-to-date information" refers to the most recent information or data provided by external data sources that the system uses to update its content.

[0908] "Original article content" refers to the content of the existing blog article before it is updated, and is text data that is acquired and saved within the system.

[0909] "Updated content" refers to article content that has been modified or added to the original article content based on the latest information and analysis results obtained.

[0910] A "blog platform" is an online platform for posting, managing, and viewing blog posts.

[0911] "User emotions" refers to the psychological state and emotional reactions that a user shows while viewing content, and are analyzed in real time using an emotion analysis engine.

[0912] "Real-time" refers to processes and operations that reflect values ​​immediately without delay, including the immediate analysis and use of user emotion data.

[0913] "Analyzed emotions" refers to the results of analyzing a user's emotions using an emotion analysis engine, and is data that the system uses to adjust content based on that information.

[0914] "Adjusting content" refers to the process of modifying, adding, or deleting content such as articles or text generated based on the analyzed sentiment, depending on the user's sentiment.

[0915] A system for implementing this invention includes a server, a user terminal, and an external data source. The server acquires, analyzes, and updates information using a generative artificial intelligence model, an emotion analysis engine, and an API access function. The user terminal refers to a device such as a smartphone or smart glasses, and is equipped with an emotion sensor function for acquiring user emotion data. The specific processing steps are as follows.

[0916] 1. Acquiring user emotion data

[0917] The user device collects the user's facial recognition data in real time and analyzes the user's emotions using an emotion analysis engine. For example, a smartphone camera can be used to analyze the user's facial expressions and obtain their current emotional state. This analysis can be performed using software such as the Emotion SDK. The analyzed emotion data is then sent to a server.

[0918] 2. Get the latest information from external data sources

[0919] The server retrieves the latest information from external data sources, for example, using a tech news API to retrieve the latest release information for a programming language. The retrieved data is formatted in JSON format and stored in an internal database. This process can use NewsAPI, TechCrunch API, etc.

[0920] 3. Obtaining the original article content

[0921] The server retrieves the original article content to be updated. For example, it retrieves the past article content in text format from a blog platform via a GET request. This retrieved data is also stored on the server.

[0922] 4. Updating and generating articles

[0923] The server updates the original article content based on the latest information and analyzed user sentiment data. To do so, it uses a generative artificial intelligence model (e.g., OpenAI's GPT-4) and generates a new article by inputting the following prompt:

[0924] Example prompt sentence:

[0925] Original content: This tutorial explains list operations in Python.

[0926] New: A new Python version has been released, adding new list manipulation capabilities.

[0927] Emotion: Confused

[0928] Please update the original article based on this information to alleviate user confusion.

[0929] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[0930] 5. Posting updated content

[0931] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles with emotionally sensitive and up-to-date information. This process improves the user experience and leads to higher engagement.

[0932] As described above, this invention provides a content generation and updating system that takes into consideration the user's feelings and reflects the latest information.

[0933] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0934] Step 1:

[0935] The server receives facial recognition data from the user's device in real time. The user's device uses the smartphone camera to recognize the user's facial expressions and analyzes the data using the Emotion SDK. This analysis determines the user's emotional state (e.g., confusion, excitement, relief, etc.) and sends the results to the server. The input is facial recognition data, and the output is emotional data.

[0936] Step 2:

[0937] The server retrieves the latest information from external data sources. For example, it uses technology news APIs (NewsAPI, TechCrunch API, etc.) to retrieve the latest release information for programming languages. The retrieved data is formatted in JSON format and stored in an internal database. The input is the API request, and the output is the JSON data of the latest information.

[0938] Step 3:

[0939] The server retrieves the original post content to be updated. This involves using the blog platform's API to retrieve the previous post content in text format via a GET request. This data is also stored locally on the server. The input is the blog post URL, and the output is the original post content.

[0940] Step 4:

[0941] The server updates the original article content based on the latest information and analyzed emotion data. To do this, it uses a generative AI model (OpenAI GPT-4) and inputs the following prompt sentence into the generative AI model. The input-output relationship is the prompt sentence and the generated new article content.

[0942] Example prompt sentence:

[0943] Original content: This tutorial explains list operations in Python.

[0944] New: A new Python version has been released, adding new list manipulation capabilities.

[0945] Emotion: Confused

[0946] Please update the original article based on this information to alleviate user confusion.

[0947] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[0948] Step 5:

[0949] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles containing the latest information that takes sentiment into consideration. The input is the new article content, and the output is the posting result to the blog platform.

[0950] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0951] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0952] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0953] [Fourth embodiment]

[0954] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0955] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0956] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0957] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0958] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0959] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0960] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0961] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0962] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0963] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0964] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0965] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0966] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0967] System Overview

[0968] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model. Specifically, a server retrieves the latest information from an external data source, uses the generative artificial intelligence model to generate an updated article based on the original article content and the latest information, and then posts the article to a blog platform.

[0969] Program processing and explanation

[0970] Gathering the latest information

[0971] The server retrieves up-to-date information from an external data source (e.g., a tech news API) periodically or based on specified events. To do this, the server sends an API request and parses the received response in JSON format.

[0972] Get the original article

[0973] The server retrieves the URL of the original blog post to be updated and retrieves its content in text form via a GET request, which is then provided to the generative AI model.

[0974] Article Update

[0975] The server uses a generative AI model (e.g., GPT-2) to generate a prompt that combines the original article content with the latest information. This prompt is then input into the generative AI model, which generates a new sentence while maintaining the style of the original article. The generated sentence adds the latest information without losing the atmosphere and tone of the original article.

[0976] Posting an update

[0977] The server posts the generated update to the blog platform using the blog platform's API. If the post is successful, the blog is updated with the latest information, providing readers with the latest technical content.

[0978] Specific examples

[0979] 1. Gathering the latest information

[0980] The server retrieves the latest Python release information from an external data source. For example, it sends an API request to receive information such as "Python 3.10 has been released and adds pattern matching functionality."

[0981] 2. Obtaining the original article

[0982] The server requests the URL of an article about the history of Python and retrieves the original article content, for example, an article that explains the history of Python releases and version changes.

[0983] 3. Update the article

[0984] The server uses a generative artificial intelligence model to add updated information to the original article, including details about "the newly released features of Python 3.10 and the added pattern matching functionality."

[0985] 4. Posting an update

[0986] The server posts the generated update to a blogging platform, for example, "an update to the original article with new information about Python 3.10."

[0987] This system allows tech blogs to be automatically updated with the latest information, making it possible to provide the latest technical information without any hassle while maintaining the writing style of the original author.

[0988] The processing flow will be explained below.

[0989] Step 1:

[0990] The server retrieves the latest information from external data sources by sending a GET request to an API endpoint and receiving a response containing the latest technology news and information. The response is parsed in JSON format and stored in the system as the latest information.

[0991] Step 2:

[0992] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[0993] Step 3:

[0994] The server generates a prompt by concatenating the latest information with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content.

[0995] Step 4:

[0996] The server provides the generative AI model with the prompt generated in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[0997] Step 5:

[0998] A generative AI model generates new, updated content while preserving the style and tone of the original. The generated text is based on the original article but includes the latest information.

[0999] Step 6:

[1000] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information.

[1001] Step 7:

[1002] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[1003] Example 1

[1004] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1005] It takes a lot of time and effort to keep a tech blog up-to-date with the latest information. It's also not easy to maintain the style and tone of the original article while adding the latest information. This makes it difficult to provide accurate and fresh information to readers.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1007] In this invention, the server includes means for periodically obtaining the latest information from an external data source, means for analyzing the obtained latest information and extracting necessary information, and means for obtaining the URL of the original article content and obtaining that content in text format, which enables the server to quickly and efficiently obtain the latest information and automatically update the article while maintaining the style of the original article.

[1008] An "external data source" is an external information source for obtaining various data and information provided on the Internet.

[1009] "Latest information" refers to the most current information or data obtained from external data sources.

[1010] "Analysis" is the process of converting acquired data into a predetermined format and extracting necessary information from it.

[1011] The "original article content" is the text data of the existing blog article to be updated.

[1012] A "URL" is an address that identifies a resource on the Internet.

[1013] "Text format" is a format in which data is expressed as a string of characters.

[1014] A "prompt sentence" is text to be input into a generative artificial intelligence model, and is generated by combining the original article content with the latest information.

[1015] A "generative artificial intelligence model" is an artificial intelligence algorithm for generating new text based on given text data.

[1016] A "new sentence" is the output generated by a generative artificial intelligence model using a prompt sentence as input.

[1017] A "blog platform" is an online service that enables users to post and manage blog posts.

[1018] This invention is a system that automatically updates technical blogs with the latest information using a generative artificial intelligence model. The main processing is performed by a server, and the following hardware and software are used:

[1019] Hardware:

[1020] 1. Server: A central processing unit that handles all processes such as collecting the latest information, retrieving original articles, updating articles, and posting updated articles.

[1021] 2. Network connectivity: Required for accessing external data sources and blogging platforms.

[1022] software:

[1023] 1. Generative AI model: Generate new sentences using a generative AI model such as GPT-2.

[1024] 2. Technology News API: An API for getting the latest technology-related information.

[1025] 3. Blog Platform API: An API used to post and update blog posts.

[1026] Data processing and calculation:

[1027] 1. Parsing the latest information: The server parses the JSON response received from the external data source and extracts the latest technical information.

[1028] 2. Obtaining the original article in text format: The server obtains the content of the original article in text format from the specified URL and extracts the necessary content.

[1029] 3. Prompt sentence generation: The content of the original article is combined with the latest information to generate a prompt sentence, which is then input into the generative artificial intelligence model.

[1030] Examples:

[1031] Gathering the latest information:

[1032] The server makes a request to the tech news API and receives the latest information: "Python 3.10 has been released and adds pattern matching functionality."

[1033] Get the original article:

[1034] The server retrieves the URL of the "Python history article" and retrieves its contents in text format. The original article contains an article explaining the history of Python releases and version changes.

[1035] Generate prompt statement:

[1036] The server concatenates the original article content with the latest information and generates a prompt for the generative AI model, such as:

[1037] Example: Original article content + "Python 3.10 has been released. Its main feature is the addition of pattern matching functionality."

[1038] Generate and post an update:

[1039] The server inputs a prompt into the generative AI model and posts the generated new text to a blog platform, for example, "an updated version of the original article with new information about Python 3.10."

[1040] This system allows the server to quickly and efficiently retrieve the latest information and automatically update it while maintaining the style of the original article, ensuring that the blog always provides readers with the latest technical information.

[1041] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1042] Step 1:

[1043] The server sends an HTTP GET request to the API endpoint of the external data source. The input is the API endpoint URL, and the output is a JSON-formatted response containing the latest technical information. The server parses this response and extracts the required up-to-date information. Specifically, the server issues an API request, parses the received JSON data, and extracts the information that "Python 3.10 has been released."

[1044] Step 2:

[1045] The server retrieves the URL of the original article to be updated and sends an HTTP GET request. The input is the URL of the original article, and the output is the original article in text format. The server analyzes this text data and extracts the necessary content from the original article. Specifically, the server sends a request to the URL and retrieves the text data for the "article about the history of Python."

[1046] Step 3:

[1047] The server generates a prompt sentence by concatenating the latest information obtained in step 1 with the original article content obtained in step 2. The input is the original article content and the latest information, and the output is the prompt sentence to be input into the generative artificial intelligence model. Specifically, the server concatenates the original article content "Information about Python releases and version changes" with the latest information "Python 3.10 has been released. Its main feature is the addition of a pattern matching function" to generate a prompt sentence in the format of "original article content + latest information."

[1048] Step 4:

[1049] The server inputs the prompt sentence generated in step 3 into the generative AI model to generate a new sentence. The input is the prompt sentence, and the output is the generated new sentence. Specifically, the server sends the prompt sentence to the API of the generative AI model (e.g., GPT-2) to generate new text.

[1050] Step 5:

[1051] The server posts the generated new text to the blog platform. The input is the generated new text, and the output is the result of posting to the blog platform. Specifically, the server sends an HTTP POST request to the blog platform's API endpoint to upload the generated new article content. If posting is successful, the blog is automatically updated.

[1052] (Application example 1)

[1053] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1054] Currently, tech blogs are often updated manually, resulting in outdated information. Collecting the latest information from vast amounts of data and updating it in blog posts takes time and effort. Furthermore, the lack of a way to view information in real time on a smart device or have it read aloud presents a challenge in improving the user experience.

[1055] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1056] In this invention, the server includes a means for processing information using a generative artificial intelligence model, a means for obtaining the latest information from an external data source, a means for updating the original article content based on the obtained latest information, a means for posting the updated content to a blog platform, and a means for reading out the content displayed on the smart glasses, so that the blog article is automatically updated with the latest information, and users can view and listen to the latest technical information in real time through the smart glasses.

[1057] A "generative artificial intelligence model" refers to a generative artificial intelligence model, a machine learning model for generating natural-looking sentences from specific input data.

[1058] "External Data Sources" refers to external data sources that provide up-to-date information, such as technology news APIs.

[1059] "Latest News" refers to the latest data and news related to technology or other specific fields.

[1060] "Original article content" refers to the text of the existing blog post or document that is being updated.

[1061] "Blog Platform" refers to a web service for hosting and publishing blog posts.

[1062] "Smart glasses" refers to a wearable display device worn by the user that has the ability to display information in conjunction with smartphones and other devices.

[1063] "Reading means" refers to the functionality or technology used to convert text into audio and read it to the user.

[1064] "Means for processing information" refers to a method for generating new information or content based on input data using a generative artificial intelligence model.

[1065] "Means of updating" refers to the process of creating a new article by adding the latest information obtained to the original article content.

[1066] "Means of posting" refers to the technology and functionality used to upload generated updates to the blog platform.

[1067] System Overview

[1068] This invention is a system that combines multiple components to automatically update a tech blog and enable it to be viewed in real time through smart glasses. The server has functions such as information processing using a generative artificial intelligence model, retrieving the latest information from external data sources, updating blog articles, and posting them to a blog platform. It also includes a function to display and read the updated content on the smart glasses.

[1069] Hardware and software used

[1070] The server generates articles using generative artificial intelligence models such as the GPT-2 model. Data is obtained via API requests and parsed in JSON format. The smart glasses are wearable display devices with information display and audio playback functions. The server uses gTTS (Google Text-to-Speech) for voice synthesis.

[1071] Program processing and explanation

[1072] Gathering the latest information

[1073] The server periodically retrieves the latest technical information from external data sources, sends API requests, and parses the received data in JSON format. For example, it may retrieve the latest release information from a technology news API.

[1074] Get the original article

[1075] The server retrieves the URL of the article to be updated from the blog platform and retrieves the article content in text format. For example, it may retrieve an article about the history of technology.

[1076] Article Update

[1077] The server generates a prompt by concatenating the original article content with the latest information, and inputs it into the generative AI model. The following prompts may be used:

[1078] Original Article: The History of Technology and Its Evolution

[1079] Latest Updates:

[1080] The latest technology has been released and new features have been added.

[1081] When generating an article using this prompt, the GPT-2 model preserves the feel of the original article while adding new information.

[1082] Posting an update

[1083] The generated update is posted using the blog platform's API, and if successful, the blog is updated with the latest technical content.

[1084] View and read updates

[1085] The updated article content will be displayed on the smart glasses, and in addition, the text will be converted to speech using gTTS and read aloud to the user through the smart glasses' speaker.

[1086] With this invention, blog posts are automatically updated with the latest information, allowing users to view and listen to the latest technical information in real time through the smart glasses.

[1087] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1088] Step 1:

[1089] The server retrieves the latest information from an external data source. First, it sends an API request to the technology news API to retrieve the latest information in JSON format. The input is the latest technology data, and the output is parsed JSON data. Specifically, it includes information such as "latest release information."

[1090] Step 2:

[1091] The server retrieves the original article content from the blog platform. It sends a GET request to the specified URL to retrieve the text of the original article. This retrieved text is the input data, and the output is the original article content. For example, let's say the target is an article about the history of technology.

[1092] Step 3:

[1093] The server generates a prompt by concatenating the original article content with the latest information. The input is the text of the original article content and the latest information obtained in step 1, and the server combines these two to create a prompt. The output is a prompt that is input to the generative AI model. For example:

[1094] Original Article: The History of Technology and Its Evolution

[1095] Latest Updates:

[1096] The latest technology has been released and new features have been added.

[1097] Step 4:

[1098] The server generates a new article using a generative artificial intelligence model. The prompt sentence is input into the GPT-2 model to generate the new article text. The input is the prompt sentence created in step 3, and the output is an updated article with the latest information. The updated article maintains the feel of the original article while adding new information.

[1099] Step 5:

[1100] The server posts the generated update to the blog platform. It uses the blog platform's API to publish the update on the Internet. The input is the generated update, and the output is the post on the blog platform.

[1101] Step 6:

[1102] The server displays the updated article content on the smart glasses and reads it aloud. It uses gTTS (Google Text-to-Speech) to convert the text into audio data and plays it through the smart glasses' speakers. The input is the text of the updated article, and the output is the audio data and the text displayed on the smart glasses. Users can receive the latest technical information visually and audibly through the smart glasses.

[1103] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1104] System Overview

[1105] The present invention is a system for automatically updating tech blogs using a generative artificial intelligence model and an emotion engine. Specifically, a server retrieves the latest information from external data sources, updates the original article content based on emotions using the generative artificial intelligence model and the emotion engine, and posts the article to a blog platform.

[1106] Program processing and explanation

[1107] Gathering the latest information

[1108] The server retrieves the latest information from an external data source (e.g., a tech news API). The server sends an API request and parses the received response in JSON format to retrieve the latest information.

[1109] Get the original article

[1110] The server retrieves the URL of the original blog post to be updated, retrieves the post's content in text format via a GET request, and stores it in the system.

[1111] Article update (using emotion engine)

[1112] The server uses an emotion engine to recognize and analyze the user's emotions. By linking the acquired latest information with the original article content and inputting the generated prompt and the analyzed emotion information into a generative AI model, an updated article is generated that contains expressions that best reflect the user's emotions while maintaining the original writing style.

[1113] Posting an update

[1114] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content.

[1115] Specific examples

[1116] 1. Gathering the latest information

[1117] The server retrieves the latest programming language release information from an external data source, for example by sending an API request to receive information about new programming language features.

[1118] 2. Obtaining the original article

[1119] The server requests the URL of the original blog post and retrieves the original content, e.g., "An article explaining an older version of a programming language."

[1120] 3. Using the Emotion Engine and Updating Articles

[1121] The server uses an emotion engine to recognize the user's emotions and analyze their "curiosity." For example, it analyzes "curious reactions" from user comments and feedback. Based on this, it inputs a prompt to "explain new features in an inquisitive style" into the generative AI model, and generates an updated article that adds the latest information to the original article content.

[1122] 4. Posting an update

[1123] The server takes the generated update and posts it to a blogging platform, for example, "the original post with an enthusiastic commentary on the latest features of a new programming language."

[1124] This system not only ensures that tech blogs are always automatically updated with the latest information, but also includes expressions that take into account user emotions, helping to keep readers interested.

[1125] The processing flow will be explained below.

[1126] Step 1:

[1127] The server retrieves the latest information from an external data source. Specifically, the server sends a GET request to an API endpoint and receives a response containing the latest tech news and information. The response is parsed in JSON format and stored in the system as the latest information.

[1128] Step 2:

[1129] The server retrieves the URL of the original blog post to be updated and retrieves its contents in text format via a GET request. This original post content is used for further processing.

[1130] Step 3:

[1131] The user accesses the system through a terminal and inputs or provides feedback on their emotions. The emotion engine analyzes the user's input and identifies their emotional state (e.g., excitement, curiosity, surprise, etc.).

[1132] Step 4:

[1133] The server generates a prompt by concatenating the latest information obtained with the original article content. Specifically, the prompt is created by adding the latest information to the end of the original article content as the premise context for future sentences.

[1134] Step 5:

[1135] The server provides the generative AI model with the prompt generated in step 4 and the emotional information analyzed in step 3 as input. The prompt is encoded into a token and input to the generative AI model.

[1136] Step 6:

[1137] The generative AI model generates updated article content that best reflects the user's emotions while maintaining the original style and tone. The generated text is based on the original article but includes the latest information and emotionally sensitive content.

[1138] Step 7:

[1139] The server retrieves the generated update content and posts it using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and provides emotionally sensitive content to readers.

[1140] Step 8:

[1141] The server records the results and status of the update and notifies the user as needed, so that the user can be sure that the article was updated successfully.

[1142] Example 2

[1143] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1144] Conventional blog update systems do not automatically add the latest information or generate content that takes user emotions into consideration, making it difficult to maintain reader interest. Furthermore, there is a need for systems that not only simply update information but also incorporate appropriate expressions based on emotions.

[1145] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for processing information using a generative AI model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for analyzing the user's emotions using an emotion analysis engine, means for generating an article by inputting a prompt sentence to the generative AI model based on the analyzed emotion information, and means for posting the updated content to a blog platform. This enables automatic updating of articles based on the latest information and generation of content taking user emotions into consideration.

[1146] A "generative artificial intelligence model" is an artificial intelligence model that has the ability to generate new information using machine learning technology.

[1147] An "external data source" is a data provider or information source that exists outside the system, not within it.

[1148] An "emotion analysis engine" is software or hardware used to analyze and identify a user's emotional state from text or voice.

[1149] A "blog platform" is a web service or software that allows users to create, manage, and publish blog posts online.

[1150] A "prompt" is an instruction or question input to a generative AI model, which instructs the AI ​​to generate output based on this.

[1151] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data description format used for storing and exchanging data.

[1152] An "API request" is a communication made via an application program interface to request a specific service or data.

[1153] "Means for processing information" refers to a program or device that receives data, analyzes it, and outputs results according to the purpose.

[1154] "Means for updating the original article content based on the latest information obtained" refers to methods or techniques for changing or adding to the existing article content based on newly obtained information.

[1155] An "article generation means" is a program or device that automatically creates new articles or documents based on input information.

[1156] "Means for posting articles" refers to the technology or method used to upload and publish generated articles to an online blog or website.

[1157] This invention relates to a system for automatically updating tech blogs using a generative artificial intelligence model and a sentiment analysis engine, specifically to optimize content based on user sentiment and provide always-up-to-date information.

[1158] Hardware and Software Used

[1159] Server: Cloud-based server (e.g. AWS, Azure) or on-premise server

[1160] Tech News API: API for retrieving the latest information from external data sources

[1161] Generative AI models: Using GPT-3 as an example

[1162] Sentiment Analysis Engine: An engine that analyzes the user's emotional state

[1163] Blog platform API: API for posting blog posts (e.g., WordPress API)

[1164] Explanation of program processing

[1165] First, the server sends a request to the technology news API to get the latest programming language release information, which is received in JSON format and parsed.

[1166] Next, the server sends a GET request using the URL of the blog post to retrieve the original blog post to be updated. The retrieved original post content is saved in text format.

[1167] The server then uses a sentiment analysis engine to analyze the user's emotions, including collecting comments and feedback from the user, and generates prompts for the generative AI model based on the results of this analysis.

[1168] As a concrete example, consider a case where the original article content is "An article about new features in Python 3.9" and the latest information is "A new match statement has been introduced in Python 3.10." In this case, if the result of the user sentiment analysis is "Curious," the prompt statement will be as follows:

[1169] Prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[1170] The server then feeds this prompt into a generative AI model to generate new article content, which combines the original article with the latest information and is updated in an intriguing style.

[1171] Finally, the server posts the generated update using the blog platform's API. If the post is successful, the blog is automatically updated with the latest information and sensitive content.

[1172] This system allows tech blogs to be automatically updated with the latest information and keeps readers interested with expressions that reflect the emotions of users.

[1173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1174] Step 1: Get the latest information from an external data source

[1175] Specific behavior:

[1176] The server sends an API request to the technology news API to retrieve the latest programming language release information.

[1177] Input: Request to the Tech News API

[1178] Data processing: Analyze data obtained in JSON format

[1179] Output: Latest programming language release information

[1180] Specifically, the server sends an HTTP GET request to the technology news API, receives JSON data as a response, and then parses this JSON data to extract important information (e.g., new features and version numbers).

[1181] Step 2: Get the original article

[1182] Specific behavior:

[1183] The server sends a GET request using the URL of the original blog post to be updated to retrieve the post's contents.

[1184] Input: Original blog post URL

[1185] Data processing: Save the article content obtained in text format

[1186] Output: Original blog post content

[1187] Specifically, the server sends an HTTP GET request to the specified URL, retrieves the original blog post content in text format as a response, and saves it in the system.

[1188] Step 3: Analyzing user sentiment

[1189] Specific behavior:

[1190] The server uses a sentiment analysis engine to analyze the user's comments and feedback and identify the user's sentiment.

[1191] Input: User comments and feedback

[1192] Data processing: Identifying emotional states with a sentiment analysis engine

[1193] Output: User's emotional state (e.g., curiosity, excitement)

[1194] Specifically, the server inputs collected user comments and feedback into an emotion analysis engine, and obtains the user's emotional state (e.g., "curious") as the analysis result.

[1195] Step 4: Update the article with a generative AI model

[1196] Specific behavior:

[1197] The server inputs prompt sentences into the generative AI model based on the analyzed emotional information, and generates the article content.

[1198] Input: Original article content, latest information, sentiment analysis results

[1199] Data processing: Prompt generation and article content generation using a generative AI model

[1200] Output: Updated blog post content

[1201] Specifically, the server generates a prompt message that says, "Explain the new features in an inquisitive style," and inputs the original article content and the latest information into a generative AI model (e.g., GPT-3). The model then generates new article content.

[1202] Example prompt: "Add original article content here. This update should explain the latest programming language features in an inquisitive style."

[1203] Step 5: Post your post to your blogging platform

[1204] Specific behavior:

[1205] The server posts the generated updated article content using the blog platform's API.

[1206] Input: Updated blog post content

[1207] Data processing: Formatting post data for the blog platform's API

[1208] Output: Blog post successful

[1209] Specifically, the server sends the updated blog post content to the blog platform's API as a POST request, and if successful, the post is published.

[1210] By implementing each step, the system can automatically update blog posts based on the latest information and reflect user sentiment. Through this process, it is possible to generate effective content that keeps readers interested.

[1211] (Application example 2)

[1212] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1213] Conventional automatic article updating systems have the function of obtaining the latest information and updating blogs, but they do not generate content based on user emotions, and therefore have the problem of not being able to effectively reflect the emotions and interests of individual users.In addition, since they are unable to analyze data according to user emotions or adjust content using a generative AI model based on that data, there are limitations to improving user engagement.

[1214] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1215] In this invention, the server includes means for processing information using a generative artificial intelligence model, means for acquiring the latest information from an external data source, means for updating the original article content based on the acquired latest information, means for posting the updated content to a blog platform, means for analyzing user emotions in real time, and means for adjusting the content based on the analyzed emotions, thereby enabling content generation and updating that takes user emotions into consideration.

[1216] A "generative artificial intelligence model" is an algorithm designed for natural language processing, specifically a trained model for generating and converting text.

[1217] An "external data source" is an information provider, such as a database or API, that exists outside the system and provides up-to-date and relevant information.

[1218] "Up-to-date information" refers to the most recent information or data provided by external data sources that the system uses to update its content.

[1219] "Original article content" refers to the content of the existing blog article before it is updated, and is text data that is acquired and saved within the system.

[1220] "Updated content" refers to article content that has been modified or added to the original article content based on the latest information and analysis results obtained.

[1221] A "blog platform" is an online platform for posting, managing, and viewing blog posts.

[1222] "User emotions" refers to the psychological state and emotional reactions that a user shows while viewing content, and are analyzed in real time using an emotion analysis engine.

[1223] "Real-time" refers to processes and operations that reflect values ​​immediately without delay, including the immediate analysis and use of user emotion data.

[1224] "Analyzed emotions" refers to the results of analyzing a user's emotions using an emotion analysis engine, and is data that the system uses to adjust content based on that information.

[1225] "Adjusting content" refers to the process of modifying, adding, or deleting content such as articles or text generated based on the analyzed sentiment, depending on the user's sentiment.

[1226] A system for implementing this invention includes a server, a user terminal, and an external data source. The server acquires, analyzes, and updates information using a generative artificial intelligence model, an emotion analysis engine, and an API access function. The user terminal refers to a device such as a smartphone or smart glasses, and is equipped with an emotion sensor function for acquiring user emotion data. The specific processing steps are as follows.

[1227] 1. Acquiring user emotion data

[1228] The user device collects the user's facial recognition data in real time and analyzes the user's emotions using an emotion analysis engine. For example, a smartphone camera can be used to analyze the user's facial expressions and obtain their current emotional state. This analysis can be performed using software such as the Emotion SDK. The analyzed emotion data is then sent to a server.

[1229] 2. Get the latest information from external data sources

[1230] The server retrieves the latest information from external data sources, for example, using a tech news API to retrieve the latest release information for a programming language. The retrieved data is formatted in JSON format and stored in an internal database. This process can use NewsAPI, TechCrunch API, etc.

[1231] 3. Obtaining the original article content

[1232] The server retrieves the original article content to be updated. For example, it retrieves the past article content in text format from a blog platform via a GET request. This retrieved data is also stored on the server.

[1233] 4. Updating and generating articles

[1234] The server updates the original article content based on the latest information and analyzed user sentiment data. To do so, it uses a generative artificial intelligence model (e.g., OpenAI's GPT-4) and generates a new article by inputting the following prompt:

[1235] Example prompt sentence:

[1236] Original content: This tutorial explains list operations in Python.

[1237] New: A new Python version has been released, adding new list manipulation capabilities.

[1238] Emotion: Confused

[1239] Please update the original article based on this information to alleviate user confusion.

[1240] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[1241] 5. Posting updated content

[1242] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles with emotionally sensitive and up-to-date information. This process improves the user experience and leads to higher engagement.

[1243] As described above, this invention provides a content generation and updating system that takes into consideration the user's feelings and reflects the latest information.

[1244] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1245] Step 1:

[1246] The server receives facial recognition data from the user's device in real time. The user's device uses the smartphone camera to recognize the user's facial expressions and analyzes the data using the Emotion SDK. This analysis determines the user's emotional state (e.g., confusion, excitement, relief, etc.) and sends the results to the server. The input is facial recognition data, and the output is emotional data.

[1247] Step 2:

[1248] The server retrieves the latest information from external data sources. For example, it uses technology news APIs (NewsAPI, TechCrunch API, etc.) to retrieve the latest release information for programming languages. The retrieved data is formatted in JSON format and stored in an internal database. The input is the API request, and the output is the JSON data of the latest information.

[1249] Step 3:

[1250] The server retrieves the original post content to be updated. This involves using the blog platform's API to retrieve the previous post content in text format via a GET request. This data is also stored locally on the server. The input is the blog post URL, and the output is the original post content.

[1251] Step 4:

[1252] The server updates the original article content based on the latest information and analyzed emotion data. To do this, it uses a generative AI model (OpenAI GPT-4) and inputs the following prompt sentence into the generative AI model. The input-output relationship is the prompt sentence and the generated new article content.

[1253] Example prompt sentence:

[1254] Original content: This tutorial explains list operations in Python.

[1255] New: A new Python version has been released, adding new list manipulation capabilities.

[1256] Emotion: Confused

[1257] Please update the original article based on this information to alleviate user confusion.

[1258] Based on this prompt, the generative AI model generates new article content that corresponds to the analyzed emotion.

[1259] Step 5:

[1260] The server posts the generated new article content to the blog platform. The updated article is automatically posted using the blog platform's API, allowing users to view articles containing the latest information that takes sentiment into consideration. The input is the new article content, and the output is the posting result to the blog platform.

[1261] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1262] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1263] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1264] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1265] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1266] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1267] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1268] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1269] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1270] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1271] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1272] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1273] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1274] 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.

[1275] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1276] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1277] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1278] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1279] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1280] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1281] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1282] The following is further disclosed regarding the above embodiment.

[1283] (Claim 1)

[1284] means for processing information using a generative artificial intelligence model;

[1285] A means of obtaining up-to-date information from external data sources; and

[1286] A means to update the original article content based on the latest information obtained,

[1287] A means of posting updates to a blogging platform;

[1288] A system including:

[1289] (Claim 2)

[1290] 2. The system of claim 1, further comprising means for linking the acquired latest information with the original article content and inputting the linked information into the generative artificial intelligence model.

[1291] (Claim 3)

[1292] 10. The system of claim 1, further comprising means for formatting the retrieved up-to-date information in JSON format.

[1293] "Example 1"

[1294] (Claim 1)

[1295] A means of periodically obtaining up-to-date information from external data sources; and

[1296] A means for analyzing the acquired latest information and extracting necessary information;

[1297] A means to obtain the URL of the original article content and obtain its content in text format,

[1298] A means for generating a prompt sentence that combines the original article content and the latest information using a generative artificial intelligence model;

[1299] A means for inputting the generated prompt sentence into a generative artificial intelligence model to generate a new sentence;

[1300] A means of posting the generated new text to a blogging platform;

[1301] A system including:

[1302] (Claim 2)

[1303] The system according to claim 1, further comprising means for analyzing the acquired latest information in JSON format and extracting necessary information.

[1304] (Claim 3)

[1305] 2. The system of claim 1, further comprising means for generating a prompt sentence by linking the retrieved original article content with the latest information.

[1306] "Application Example 1"

[1307] (Claim 1)

[1308] means for processing information using a generative artificial intelligence model;

[1309] A means of obtaining up-to-date information from external data sources; and

[1310] A means to update the original article content based on the latest information obtained,

[1311] A means of posting updates to a blogging platform;

[1312] a means for reading aloud the content displayed on the smart glasses;

[1313] A system including:

[1314] (Claim 2)

[1315] 2. The system of claim 1, further comprising means for linking the acquired latest information with the original article content and inputting the linked information into the generative artificial intelligence model.

[1316] (Claim 3)

[1317] 10. The system of claim 1, further comprising means for formatting the retrieved up-to-date information in JSON format.

[1318] "Example 2: Combining Emotion Engines"

[1319] (Claim 1)

[1320] means for processing information using a generative artificial intelligence model;

[1321] A means of obtaining up-to-date information from external data sources; and

[1322] A means to update the original article content based on the latest information obtained,

[1323] A means for analyzing user emotions using an emotion analysis engine;

[1324] A means for generating articles by inputting prompt sentences into a generative AI model based on the analyzed emotional information;

[1325] A means of posting updates to a blogging platform;

[1326] A system including:

[1327] (Claim 2)

[1328] 2. The system of claim 1, further comprising means for linking the acquired latest information with the original article content and inputting the linked information into the generative artificial intelligence model.

[1329] (Claim 3)

[1330] 10. The system of claim 1, further comprising means for formatting the retrieved up-to-date information in JSON format.

[1331] "Application example 2 when combining emotion engines"

[1332] (Claim 1)

[1333] means for processing information using a generative artificial intelligence model;

[1334] A means of obtaining up-to-date information from external data sources; and

[1335] A means to update the original article content based on the latest information obtained,

[1336] A means of posting updates to a blogging platform;

[1337] A means for analyzing user emotions in real time;

[1338] means for adjusting content based on the analyzed sentiment;

[1339] A system including:

[1340] (Claim 2)

[1341] 2. The system of claim 1, further comprising means for linking the acquired latest information with the original article content and inputting the linked information into the generative artificial intelligence model.

[1342] (Claim 3)

[1343] 10. The system of claim 1, further comprising means for formatting the retrieved up-to-date information in JSON format. [Explanation of symbols]

[1344] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for processing information using a generative artificial intelligence model; A means of obtaining up-to-date information from external data sources; and A means to update the original article content based on the latest information obtained, A means of posting updates to a blogging platform; A system including:

2. 2. The system according to claim 1, further comprising means for linking the acquired latest information with the original article content and inputting the linked information into the generative artificial intelligence model.

3. The system of claim 1 , further comprising means for formatting the obtained up-to-date information in JSON format.

Images