system

Abstract

We provide the system. [Solution] Information and communication equipment includes means for collecting data from information sources, A means for analyzing data using natural language processing technology and extracting trend information and keywords, A means of generating content based on extracted trend information using a generative artificial intelligence model, A means of translating the generated content into multiple languages ​​and applying localization to each region, A method for automatically posting to multiple information distribution platforms by setting a schedule, A system that includes means for collecting feedback data for each post, analyzing it, and generating a report.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern enterprises are required to disseminate information in multiple languages and on multiple platforms for diverse markets, but this poses challenges that require a lot of resources and time. Therefore, it is difficult to disseminate information quickly and effectively with limited resources. Also, it is difficult to respond sensitively to trend changes and provide appropriate content for each market, which has become a factor in reducing engagement.

Means for Solving the Problems

[0005] This invention provides a system in which an information and communication device collects data from information sources, automatically analyzes it using natural language processing technology, and extracts trend information and keywords. Furthermore, it can generate content based on the trend information using a generative artificial intelligence model, and automatically post this content to multiple information distribution platforms after multilingual translation and localization according to region. In this process, feedback data is collected after posting, and analysis and report generation are performed, thereby creating a more optimized information dissemination cycle. This enables companies to conduct effective marketing activities even with limited resources.

[0006] An "information and communication device" is a device used for collecting, processing, analyzing, and distributing data.

[0007] "Information source" refers to a medium or platform that provides data, such as social media or news websites.

[0008] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0009] "Trend information" refers to information about current topics of interest or importance.

[0010] A "keyword" is an important word or phrase used to represent a particular topic or theme.

[0011] A "generative artificial intelligence model" is an algorithm or system for generating new text or content based on specific input data.

[0012] "Content" refers to text or other media generated to convey information, such as blog posts or social media posts.

[0013] "Multilingual translation" is the process of converting content from one language to another.

[0014] "Localization" is the process of adjusting content according to a specific region or culture.

[0015] "Information delivery platform" refers to an online service or application for delivering content to users.

[0016] "Feedback data" refers to data regarding user reactions and engagement obtained after content is posted.

[0017] "Report" refers to a document summarizing the results and insights obtained from analyzed data.

Brief Explanation of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention provides a system for companies to efficiently disseminate information in multiple languages ​​and across multiple platforms. The following describes embodiments for carrying out this invention.

[0040] First, the server collects data in real time from information sources such as social media and news sites. This includes data retrieval using APIs. For example, it might use the Twitter API to retrieve posts related to a specific hashtag.

[0041] Next, the server analyzes the collected data using natural language processing techniques. This extracts trend information and important keywords. For example, machine learning algorithms are used to form topic models and identify currently trending topics.

[0042] Next, the server utilizes a generative artificial intelligence model to generate content based on the extracted trend information. This content generation is automated, minimizing the need for manual editing. For example, it can create articles on the latest eco-friendly trends related to a specific product.

[0043] The server then uses multilingual translation technology to translate the generated content for each country and further localizes it. This makes it possible to provide the same content in a form that is adapted to the culture and customs of each region. For example, content for Japan is adjusted to be related to specific cultural events in that region.

[0044] Next, the server schedules the content and automatically posts it to multiple information distribution platforms. This process optimizes reaching the target audience by formatting the content to match each platform's format and setting the optimal posting time.

[0045] Finally, the server collects feedback data after posting and analyzes performance. This analytical data is provided to users as a visual dashboard and used to improve content strategies. For example, it can show real-time statistics on post engagement rates and click-through rates.

[0046] Through the process described above, the system of the present invention effectively and efficiently implements multilingual marketing strategies. This enables companies to improve engagement in the global market while saving resources.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server configures APIs to retrieve data from information sources such as social media and news sites, and collects data periodically. During this process, it filters the data using specific keywords and hashtags to include only relevant posts.

[0050] Step 2:

[0051] The server stores the collected data in a database and cleans it up using a filtering function to remove duplicate data and spam. This improves the quality of the data being analyzed.

[0052] Step 3:

[0053] The server analyzes the cleaned-up data using natural language processing techniques to extract frequently occurring keywords and trend information. This process also includes topic modeling and sentiment analysis to understand the trends.

[0054] Step 4:

[0055] The server generates content using an artificial intelligence model based on extracted trend information. This includes automatic text generation based on templates and image selection as needed.

[0056] Step 5:

[0057] The server translates the generated content into each target language via a multilingual translation API and then localizes it for each region, adding regionally specific expressions and cultural elements for adjustment.

[0058] Step 6:

[0059] The server formats translated and localized content into the appropriate format for each information distribution platform and automatically posts it at the optimal time. The posting schedule is set considering the target audience's usage times.

[0060] Step 7:

[0061] The server uses each platform's API to collect feedback data (e.g., engagement rate, clicks) after posting. This information plays a crucial role in optimizing future content strategies.

[0062] Step 8:

[0063] The server analyzes the collected feedback data and compiles the results into a report. This report is then provided to the user as a visual dashboard, which can be used to review performance and revise strategies.

[0064] (Example 1)

[0065] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] In today's business world, efficient information dissemination across multiple languages ​​and platforms is crucial. However, traditional methods require significant effort and resources to create and distribute content tailored to each country's language and culture. Furthermore, accurately collecting and analyzing feedback after posting is not easy. There is a need for a system that efficiently addresses these challenges and enables companies to quickly and effectively increase engagement in the global market.

[0067] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0068] In this invention, the server includes means for acquiring information from information providers, means for analyzing the information using natural language processing technology and extracting trend data and keywords, means for creating content based on the extracted trend data using generative artificial intelligence technology, means for converting the created content into multiple languages ​​and applying localization according to each region, means for setting a plan and automatically posting to multiple information distribution platforms, and means for acquiring response data for each post, analyzing it, and generating visual indicators. As a result, companies can efficiently and comprehensively disseminate information that is appropriate for the culture and language of each country, and can more effectively improve global engagement through a data-driven improvement cycle.

[0069] "Information and communication equipment" is a general term for devices that have the function of sending, receiving, and processing digital information.

[0070] "Information source" refers to the source from which digital data is transmitted or supplied.

[0071] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0072] "Generative artificial intelligence technology" refers to artificial intelligence technology that has the ability to learn from large amounts of data and generate new data.

[0073] "Trend data" refers to a collection of information or topics that have attracted significant attention within a specific time period.

[0074] A "keyword" is an important word used to characterize or summarize information or a topic.

[0075] "Localization" refers to the process of adjusting content to suit a specific region or culture.

[0076] An "information distribution platform" refers to an online platform for providing digital data to users.

[0077] "Response data" refers to data that shows users' reactions and evaluations of content.

[0078] "Visual metrics" are visualized information used to display data analysis results in a way that is easy for users to understand.

[0079] This system is implemented using information and communication equipment and efficiently performs the collection, analysis, generation, distribution, and feedback analysis of digital data. Servers, in particular, play a crucial role, and the system is structured around their functions.

[0080] First, regarding information gathering, the server retrieves data from social media and news sites that serve as information sources via APIs. In this process, common APIs such as Twitter are used to collect posts related to specific hashtags or keywords. For example, posts containing "eco-friendly" are targeted.

[0081] Next, the server applies natural language processing techniques to the collected data. Specifically, it performs text analysis and uses machine learning algorithms such as the LDA (Latent Dirichlet Allocation) model to extract trend data and keywords. As a result, currently trending topics and trends can be identified.

[0082] Subsequently, the server utilizes generative artificial intelligence technology to create new content based on the extracted data. For example, it uses OpenAI's GPT model as a generative AI model and automatically generates articles that resonate with the target audience using prompts such as, "Create an article based on the latest information on eco-friendly trends."

[0083] After the content is generated, the server translates it using a multilingual translation tool (for example, Google Translate API) and then localizes it to suit the culture of each region. This involves adjusting it to match the cultural events and customs of Japan and other countries and regions.

[0084] Finally, the server uses an information distribution infrastructure to deliver content to multiple platforms. Posting times are scheduled systematically, and content is published in an optimized format for each platform.

[0085] The feedback data collected through these processes is also analyzed by the server and provided to the user as visual indicators. The visualized dashboard allows users to view data such as engagement rates and click-through rates in real time, which can be used to improve future strategies.

[0086] In this way, companies can efficiently and effectively disseminate information in multiple languages ​​and across multiple platforms, thereby enhancing their presence in the global market.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server collects data from social media and news sites that serve as information sources. The input is a list of specific hashtags and keywords. Based on this input, the server retrieves relevant posts by calling the APIs of each information source. The output is a list of the collected posts. Specifically, the server checks the APIs at regular intervals to see if new data is available.

[0090] Step 2:

[0091] The server performs natural language processing on the collected post data. The input is a list of post data obtained in step 1. The server cleans this data and applies text analysis techniques to extract trend data and keywords. Techniques used include topic models (e.g., LDA models). The output is a set of extracted trend information and keywords. Specifically, the server analyzes the text data to identify frequently occurring words and themes.

[0092] Step 3:

[0093] The server generates content using a generative AI model. The input consists of trend information and keywords extracted in step 2. The server converts this information into prompt sentences and inputs them into the generative AI model. The output is the generated text content. Specifically, the server generates the prompt sentence "Create an article introducing eco-friendly products" and passes it to the AI ​​model.

[0094] Step 4:

[0095] The server translates and localizes the generated content into multiple languages. The input is the generated content obtained in step 3. The server uses a multilingual translation tool to translate the content into the languages ​​of each country. It also localizes the content to suit the local culture. The output is the translated and localized multilingual content. Specifically, for Japan, adjustments are made to match specific local festivals and events.

[0096] Step 5:

[0097] The server schedules the delivery of content. The input is content that is ready in multiple languages. The server analyzes the characteristics of each distribution platform, formats it into an optimized format, and automates posting at the optimal time for each platform. The output is the published content. Specifically, the server sets up and executes the procedure for automated posting using the API of each platform.

[0098] Step 6:

[0099] The server collects and analyzes feedback data after posting. The input is response data collected from each platform where the content was distributed. The server analyzes this data and generates visual metrics such as engagement rate and click-through rate. The output is a dashboard showing the analysis results. Specifically, the server uses an API to retrieve feedback data and visualizes it for the user in real time.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Modern businesses need to deploy advertising efficiently and effectively across multiple languages ​​and platforms. However, it is difficult to respond to diverse cultures and markets, understand trends in real time, and deliver ads at the optimal time. A system is needed to solve these challenges and maximize the performance of advertising campaigns.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes means for collecting information from information sources, means for analyzing the information using natural language processing technology and extracting trend information and keywords, means for creating content based on the extracted trend information using a generative intelligence model, means for translating the created content into multiple languages ​​and making adjustments to suit each region, means for planning and automatically posting to multiple information transmission platforms, and means for collecting reaction information related to each post, analyzing it, and generating a visual report. This enables the efficient generation and distribution of multilingual and region-appropriate advertising content, and optimizes advertising strategies by performing real-time performance analysis.

[0105] An "information processing device" is a system that has the functions of collecting, analyzing, generating, and distributing information.

[0106] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0107] A "generative intelligence model" is an algorithm that automatically generates new information or content based on data.

[0108] "Trend information" refers to information that indicates current market and social changes and trends.

[0109] A "word or phrase" is a word or phrase expressed in language that has some kind of meaning.

[0110] An "information transmission infrastructure" refers to the means of communication and platforms used to deliver information to users.

[0111] "Response information" refers to data related to feedback and engagement from recipients.

[0112] A "visual report" is a report that visually represents data, providing analysis results in a way that can be intuitively understood.

[0113] To implement this invention, a server plays a primary role. The server first collects information from information sources, which include online media and social networks. Information collection is performed via APIs; for example, posts related to a specific hashtag can be retrieved from Twitter.

[0114] Next, the server analyzes the collected information using natural language processing techniques to extract trend information and important keywords. Natural language processing libraries such as spaCy and NLTK are used here. This process identifies currently trending themes and keywords.

[0115] Next, the server uses a generative intelligence model to generate new advertising content based on the extracted trend information. This generation utilizes generative artificial intelligence technology. The generated content may include, for example, catchphrases and advertising copy related to a new product.

[0116] The server then translates the generated content into multiple languages ​​and localizes it to suit each region. A standard translation API is used for this translation. During this process, adjustments are made to accommodate local culture and customs.

[0117] Furthermore, the server uses an automated scheduling function to post advertisements to multiple information transmission platforms at the optimal time. The format is adjusted according to the characteristics of each platform, and the ads are delivered at the measured optimal time.

[0118] Finally, users can receive a visual report based on the reaction information for each post collected by the server. This report graphically displays the data analysis results and helps improve advertising strategies. For example, the following prompt is used in the generating AI model: "Based on today's trends, create an advertising tagline for a refreshing new beverage."

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server collects information from various sources. Specifically, it uses APIs to retrieve data from social media and online news sites. The input consists of parameters and search criteria set in the API, and the output is the retrieved raw post data. This data is stored in a database for subsequent processing.

[0122] Step 2:

[0123] The server analyzes the collected data using natural language processing techniques to extract trend information and important keywords. Specifically, it uses the spaCy library to build a topic model of the data and identify currently trending themes. The input is the collected post data, and the output is the extracted topics and keywords.

[0124] Step 3:

[0125] The server uses a generative intelligence model to generate advertising content based on extracted trend information. The input consists of extracted topics and keywords, and the output is the generated advertising copy and text. The generated content is obtained by inputting prompt sentences into the generative artificial intelligence model.

[0126] Step 4:

[0127] The server translates the generated content into multiple languages ​​and localizes it to suit each region. A multilingual translation API is used for translation. The input is the generated content, and the output is the translated and localized content.

[0128] Step 5:

[0129] The server automatically posts content to each information dissemination platform according to a set schedule. The input is translated and localized content, and the output is the media posted to each platform. The optimal posting time is measured and set accordingly.

[0130] Step 6:

[0131] Users review the reaction information for each post collected by the server and receive a visual report. The input is reaction data from each platform, and the output is a visualized report including engagement rates and click-through rates. This report provides insights to improve advertising strategies.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention relates to a system that combines an emotion engine with an information and communication device. The system aims to recognize the user's emotions using the emotion engine and optimize content generation and distribution based on the results. The following describes embodiments for carrying out the invention.

[0134] First, the server collects data from social media and news sites. It initially uses APIs to retrieve posts related to specific keywords and stores them in a database. Next, it utilizes a sentiment engine to analyze user sentiment trends from this data. For example, it might identify a product where users have a high proportion of positive sentiment towards it.

[0135] Next, the server analyzes the data using natural language processing techniques to extract trend information and keywords. By combining this information with the results of sentiment analysis, content that is more suitable for the target user is determined. For example, content is created prioritizing topics that receive many positive responses in sentiment analysis.

[0136] Next, the server uses a generative artificial intelligence model to generate content based on extracted trend information and sentiment data. During this process, the tone and style of the content can be adjusted based on the results of the sentiment engine. For example, expressions emphasizing humor or a sense of reassurance can be incorporated.

[0137] The server then translates the generated content into multiple languages ​​and localizes it for each region. It also takes sentiment analysis into account, adjusting expressions and tones to suit different regions. For example, it might select more formal language for business users.

[0138] Next, the server posts the optimized content to the information distribution platform. The content is automatically posted at the optimal time, aiming to reach users at their peak interest. During posting, the target audience is further segmented based on sentiment data.

[0139] Finally, the server collects feedback data after posting and identifies engagement trends based on analysis by the sentiment engine. Based on these results, a report is generated and provided to the user as insights for future strategies. For example, the dashboard may display analysis results on topics that received the most emotional responses in past posts.

[0140] Through this system, companies can understand user emotions and provide content tailored to those emotions, thereby optimizing engagement with their target market.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The server uses APIs from social media and news sites to collect new posts related to specific topics or keywords. The collected data is processed in real time and stored in a database.

[0144] Step 2:

[0145] The server filters out duplicates and spam from the collected submission data, improving data quality. At this stage, the purified data is passed on to the next processing step.

[0146] Step 3:

[0147] The server uses natural language processing techniques to extract trend information and key keywords from clean data. Specifically, it performs word frequency analysis and topic modeling to identify themes of high interest.

[0148] Step 4:

[0149] The server utilizes an emotion engine to recognize user emotions from posted data. As a result of the emotion analysis, an emotion score, such as positive or negative, is calculated, and the target user's emotional tendencies are understood based on this score.

[0150] Step 5:

[0151] The server uses an artificial intelligence model to generate content based on trend information and sentiment analysis results. The generated content is tailored to the target audience, with a tone and style that matches their emotions. For example, it might create articles using friendly language to evoke positive emotions.

[0152] Step 6:

[0153] The server translates the generated content into each language using a multilingual translation API, and then localizes it for each region. During this process, it adjusts the expression to take into account local customs and cultures.

[0154] Step 7:

[0155] The server posts translated and localized content to each information distribution platform. The posting timing is scheduled to take into account the times when users are most active.

[0156] Step 8:

[0157] The server collects feedback data after a post is published and analyzes it again using an emotion engine. This analysis identifies engagement trends and changes in user sentiment, which can then be used to inform future content strategies.

[0158] Step 9:

[0159] The server generates a report based on the aggregated feedback data and sentiment analysis results. This report is provided to users as a visual dashboard or report, and can be used as a resource to review content performance and identify areas for improvement.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] In today's information society, generating content that matches users' interests and emotions quickly and accurately, and delivering it across diverse information transmission platforms, is a challenging task. In particular, the lack of systems to efficiently automate the processes of multilingual support, regional optimization, and emotionally resonant content is a significant problem. Furthermore, the process of immediately analyzing user feedback after content distribution and incorporating it into future strategies is still underdeveloped, which also presents a challenge.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes means for collecting information from a data source, means for analyzing the information using natural language processing technology to extract trending topics and key words, and means for generating content based on the extracted trending topics using a generation algorithm. This makes it possible to automatically generate multilingual content that matches the user's emotions and provide it in a way that is tailored to the characteristics of each region. Furthermore, by quickly analyzing feedback after distribution and reflecting it in the next content strategy, it is possible to achieve higher user satisfaction.

[0165] An "information processing device" is a device equipped with functions for collecting and analyzing data, and for generating and transmitting necessary information.

[0166] "Data source" refers to the origin or platform from which information is obtained, and includes social media and news sites.

[0167] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0168] "Trends" refer to themes or phenomena that have attracted attention within a certain period, and may include popular themes in a particular industry or field.

[0169] "Key terms" are important keywords or phrases that indicate a specific topic or content in data analysis.

[0170] A "generating algorithm" is a computational method that automatically creates new information or content from data according to specific rules or procedures.

[0171] "Multilingual translation" is the process of converting content written in one language into multiple other languages ​​to make it understandable.

[0172] "Regional optimization" refers to adjusting the content and expression to suit the culture, customs, and linguistic characteristics of each region.

[0173] An "information transmission infrastructure" is the infrastructure used to deliver generated content to users, and includes social media and websites.

[0174] "Emotion analysis technology" is a technique that extracts emotions from text and audio data and identifies the type and intensity of those emotions.

[0175] "Evaluation data" refers to information that numerically or qualitatively demonstrates the effectiveness and impact of content based on user reactions and feedback.

[0176] "Documents showing analysis results" refer to documents or reports that analyze collected evaluation data and include insights and conclusions based on that analysis.

[0177] In this invention, the information processing device is configured to enable the generation and distribution of highly accurate content that meets the user's needs. The embodiments thereof are described in detail below.

[0178] First, the server collects information from sources such as social media and news sites. Python is used for data collection, and data associated with specific keywords is retrieved through appropriate APIs. This enables real-time information gathering. The collected data is stored in a database such as PostgreSQL.

[0179] Next, the server applies natural language processing techniques to the collected data. Specifically, it analyzes the data using Python NLP libraries (such as NLTK and spaCy) to extract trends and key terms. This allows for the efficient identification of necessary keywords and topics.

[0180] Furthermore, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate content based on the extracted information. The generated content is then refined using sentiment analysis technology, with its tone and style set based on the user's emotions or predicted emotions. An example of a prompt to input to the generative AI model might be, "Generate promotional content that evokes positive emotions in the user, based on the latest trending information."

[0181] The server then translates the generated content into multiple languages ​​and localizes it for each region. Translation services such as Amazon Translate and DeepL are used to translate the content into different languages. The language is optimized to suit the culture and context of each region, with adjustments such as adopting a more formal tone for business use.

[0182] Finally, the server automatically distributes the refined content to the information transmission platform. This process utilizes tools such as Buffer and Hootsuite to ensure timely posting. After distribution, feedback data is collected, analyzed again, and incorporated into the next content strategy. This entire process strengthens engagement between users and the company, enabling effective information dissemination.

[0183] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0184] Step 1:

[0185] The server collects information from data sources. Specifically, it uses Python scripts to retrieve information from social media and news sites via APIs. It collects data based on specified keywords (e.g., "new products," "popular events") as input and stores the raw text data as output in a database. During this collection process, it retrieves data using HTTP requests and handles the data in JSON format.

[0186] Step 2:

[0187] The server applies natural language processing (NLP) techniques to the collected text data. It uses previously stored raw data as input. Then, using Python NLP libraries (such as NLTK or spaCy), it performs tokenization and part-of-speech tagging to extract trending topics and key words. The output is a list of extracted keywords and trend information. This information is added to a database and used for subsequent processing.

[0188] Step 3:

[0189] The server generates content using a generative AI model. Keywords and trend information obtained in step 2 are used as input. A prompt is input to the generative AI model (e.g., the GPT series) to prompt it to generate new content. For example, using the prompt "Create a campaign proposal based on this summer's trends," the output will be a campaign proposal written in natural language.

[0190] Step 4:

[0191] The server converts the generated content into multilingual translated data and performs localization tailored to each region. The input is the content generated in step 3. Using APIs such as Amazon Translate and DeepL, it translates the content into each region's language and adjusts it to the most appropriate expression, taking cultural context into account. The output is language-specific content optimized for each region.

[0192] Step 5:

[0193] The server delivers the adjusted content to the designated information transmission platform. Multilingual translated and localized content is used as input. By utilizing distribution tools such as Buffer and Hootsuite and setting an optimal distribution schedule, the output is posted to each platform at the specified time.

[0194] Step 6:

[0195] The server collects and analyzes feedback data after delivery to inform future strategies. It uses user feedback as input. Sentiment analysis technology is employed to identify positive or negative responses, generating reports on emotional tendencies and suggestions for improvement. This contributes to improving future content strategies.

[0196] (Application Example 2)

[0197] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0198] In today's information society, providing appropriate content that aligns with consumers' emotions and interests quickly and effectively is a critical challenge for many companies. However, conventional systems lack the ability to accurately reflect user emotions in content generation and delivery, making it difficult to optimize engagement with target users. Therefore, there is a need for a method that can evaluate user emotions in real time and provide content tailored to their emotional state.

[0199] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0200] In this invention, the server includes means for collecting data from information sources and performing sentiment analysis to evaluate the user's emotions; means for analyzing the data using natural language processing technology and extracting trend information and keywords; and means for generating content based on the user's emotional state using a generative artificial intelligence model. This enables the delivery of optimal content that reflects the user's emotions.

[0201] An "information and communication device" is an electronic device used to collect, process, and analyze data, and to distribute it in an appropriate format.

[0202] "Sentiment analysis" is a technology that analyzes a user's emotional state from data and identifies emotions such as positive, negative, and neutral.

[0203] "Natural language processing technology" refers to methods for analyzing, understanding, and generating human language using computers.

[0204] "Trending information" refers to themes and keywords that are popular during a specific period, and is information of high social interest.

[0205] A "generative artificial intelligence model" is an artificial intelligence algorithm that automatically generates new content using data as input.

[0206] "Localization" is the act of adapting content to suit different regions or specific groups, taking into account multiple languages ​​and cultures.

[0207] An "information distribution platform" is an online system or service for distributing content to a wide range of users.

[0208] "Feedback data" refers to information about the evaluations and reactions that users give back to the content provided.

[0209] "User emotional state" refers to the type and intensity of emotions a user is experiencing at a particular point in time.

[0210] This system configuration consists of a server that functions as an information and communication device, collecting, processing, and analyzing data from information sources. The server collects data from social networking services (SNS) and news sites via the internet using APIs. This data is stored in a database and then sent to a sentiment analysis engine to evaluate the user's emotional state. This sentiment analysis is achieved by utilizing natural language processing technology to analyze the emotional elements of user posts and responses.

[0211] Trend information and extracted keywords are input into a generative artificial intelligence model, which then generates content. The generative AI model adjusts the style and tone of the content according to the user's emotional state, optimizing the interaction. For example, it can provide humorous content to users with many positive emotions and encouragement to those with negative emotions. The generative AI model used here is implemented using frameworks such as PyTorch and Transformers.

[0212] Next, the generated content is translated into multiple languages, and the server localizes it to suit the region and user sentiment. This ensures appropriate content delivery that reflects cultural backgrounds and linguistic nuances. Furthermore, the information distribution platform automatically posts content on an optimal schedule based on user sentiment analysis results. User feedback data after distribution is also collected and used to inform future strategies through further sentiment analysis.

[0213] For example, if a user is feeling stressed, the server can generate content recommending relaxing music or videos and deliver it to the user at a time that matches their emotions. An example of a prompt that might be used is, "Generate new content that reflects the user's current emotions!"

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server collects data from information sources. It uses APIs to retrieve user posts from social media and news sites and stores them in a database. This data collection is performed in real time, handling text and multimedia data collected from the information sources as input. The output is a dataset ready for use by the sentiment analysis engine.

[0217] Step 2:

[0218] The server processes data using an emotion analysis engine to evaluate the user's emotions. The input data is the posted content collected in step 1, and is analyzed using natural language processing techniques. This analysis identifies emotional states such as positive, negative, and neutral, and the output is the emotion evaluation result for each user.

[0219] Step 3:

[0220] The server analyzes the data using natural language processing to extract trend information and keywords. In this step, the server uses posts that have undergone sentiment analysis as input, summarizing the content and extracting elements of high social interest. The output is extracted trend data for use by the generative AI model.

[0221] Step 4:

[0222] The server uses a generative artificial intelligence model to generate content that responds to the user's emotional state. The input requires trend information, keywords, and user sentiment data, which the generative AI model then uses to output optimized content. This content has a tone and style that matches the user's emotions.

[0223] Step 5:

[0224] The server translates the generated content into multiple languages ​​and localizes it according to region and user sentiment. It takes the user's cultural background and linguistic needs as input to perform the translation and localization process, resulting in adjusted content as output.

[0225] Step 6:

[0226] The server posts the adjusted content to the information distribution platform. This step utilizes a pre-configured schedule and sentiment analysis results as input to automatically post at the optimal time. The output is content delivered appropriately to the user.

[0227] Step 7:

[0228] The server collects feedback data after delivery and analyzes it again using a sentiment analysis engine. The input is user response data, which is analyzed to evaluate engagement trends. The output is a report containing insights for the next delivery.

[0229] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0230] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0231] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0235] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0236] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0237] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0238] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0239] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0240] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0241] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0242] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0243] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0244] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0245] This invention provides a system for companies to efficiently disseminate information in multiple languages ​​and across multiple platforms. The following describes embodiments for carrying out this invention.

[0246] First, the server collects data in real time from information sources such as social media and news sites. This includes data retrieval using APIs. For example, it might use the Twitter API to retrieve posts related to a specific hashtag.

[0247] Next, the server analyzes the collected data using natural language processing techniques. This extracts trend information and important keywords. For example, machine learning algorithms are used to form topic models and identify currently trending topics.

[0248] Next, the server utilizes a generative artificial intelligence model to generate content based on the extracted trend information. This content generation is automated, minimizing the need for manual editing. For example, it can create articles on the latest eco-friendly trends related to a specific product.

[0249] The server then uses multilingual translation technology to translate the generated content for each country and further localizes it. This makes it possible to provide the same content in a form that is adapted to the culture and customs of each region. For example, content for Japan is adjusted to be related to specific cultural events in that region.

[0250] Next, the server schedules the content and automatically posts it to multiple information distribution platforms. This process optimizes reaching the target audience by formatting the content to match each platform's format and setting the optimal posting time.

[0251] Finally, the server collects feedback data after posting and analyzes performance. This analytical data is provided to users as a visual dashboard and used to improve content strategies. For example, it can show real-time statistics on post engagement rates and click-through rates.

[0252] Through the process described above, the system of the present invention effectively and efficiently implements multilingual marketing strategies. This enables companies to improve engagement in the global market while saving resources.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The server configures APIs to retrieve data from information sources such as social media and news sites, and collects data periodically. During this process, it filters the data using specific keywords and hashtags to include only relevant posts.

[0256] Step 2:

[0257] The server stores the collected data in a database and cleans it up using a filtering function to remove duplicate data and spam. This improves the quality of the data being analyzed.

[0258] Step 3:

[0259] The server analyzes the cleaned-up data using natural language processing techniques to extract frequently occurring keywords and trend information. This process also includes topic modeling and sentiment analysis to understand the trends.

[0260] Step 4:

[0261] The server generates content using an artificial intelligence model based on extracted trend information. This includes automatic text generation based on templates and image selection as needed.

[0262] Step 5:

[0263] The server translates the generated content into each target language via a multilingual translation API and then localizes it for each region, adding regionally specific expressions and cultural elements for adjustment.

[0264] Step 6:

[0265] The server formats translated and localized content into the appropriate format for each information distribution platform and automatically posts it at the optimal time. The posting schedule is set considering the target audience's usage times.

[0266] Step 7:

[0267] The server uses each platform's API to collect feedback data (e.g., engagement rate, clicks) after posting. This information plays a crucial role in optimizing future content strategies.

[0268] Step 8:

[0269] The server analyzes the collected feedback data and compiles the results into a report. This report is then provided to the user as a visual dashboard, which can be used to review performance and revise strategies.

[0270] (Example 1)

[0271] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] In today's business world, efficient information dissemination across multiple languages ​​and platforms is crucial. However, traditional methods require significant effort and resources to create and distribute content tailored to each country's language and culture. Furthermore, accurately collecting and analyzing feedback after posting is not easy. There is a need for a system that efficiently addresses these challenges and enables companies to quickly and effectively increase engagement in the global market.

[0273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0274] In this invention, the server includes means for acquiring information from information providers, means for analyzing the information using natural language processing technology and extracting trend data and keywords, means for creating content based on the extracted trend data using generative artificial intelligence technology, means for converting the created content into multiple languages ​​and applying localization according to each region, means for setting a plan and automatically posting to multiple information distribution platforms, and means for acquiring response data for each post, analyzing it, and generating visual indicators. As a result, companies can efficiently and comprehensively disseminate information that is appropriate for the culture and language of each country, and can more effectively improve global engagement through a data-driven improvement cycle.

[0275] "Information and communication equipment" is a general term for devices that have the function of sending, receiving, and processing digital information.

[0276] "Information source" refers to the source from which digital data is transmitted or supplied.

[0277] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0278] "Generative artificial intelligence technology" refers to artificial intelligence technology that has the ability to learn from large amounts of data and generate new data.

[0279] "Trend data" refers to a collection of information or topics that have attracted significant attention within a specific time period.

[0280] A "keyword" is an important word used to characterize or summarize information or a topic.

[0281] "Localization" refers to the process of adjusting content to suit a specific region or culture.

[0282] An "information distribution platform" refers to an online platform for providing digital data to users.

[0283] "Response data" refers to data indicating the reactions and evaluations of users towards content.

[0284] "Visual indicators" refer to visualized information for presenting the analysis results of data in a form that is easy for users to understand.

[0285] This system is realized by information and communication equipment and efficiently performs the collection, analysis, generation, distribution, and feedback analysis of digital data. In particular, the server plays an important role and the system is configured around its functions.

[0286] First, regarding information collection, the server obtains data from SNS and news sites that are information providers through APIs. In this process, common APIs such as Twitter are used to collect posts related to specific hashtags or keywords. For example, posts containing "eco-friendly" are targeted.

[0287] Subsequently, the server applies natural language processing technology to the collected data. Specifically, text analysis is performed, and machine learning algorithms such as the LDA (Latent Dirichlet Allocation) model are used to extract trend data and keywords. As a result, currently popular topics and trends can be identified.

[0288] After that, the server makes full use of generative artificial intelligence technology to create new content based on the extracted data. For example, the GPT model of OpenAI is utilized as a generative AI model, and an article that resonates with the target layer is automatically generated using a prompt sentence such as "Please create an article based on the latest information on the eco-friendly trend".

[0289] After the content is generated, the server translates it using a multilingual conversion tool (e.g., Google Translate API) and further localizes it into a form suitable for the culture of each region. This is adjusted according to cultural events and habits in Japan and other countries and regions.

[0290] Finally, the server uses an information distribution infrastructure to deliver content to multiple platforms. Posting times are scheduled systematically, and content is published in an optimized format for each platform.

[0291] The feedback data collected through these processes is also analyzed by the server and provided to the user as visual indicators. The visualized dashboard allows users to view data such as engagement rates and click-through rates in real time, which can be used to improve future strategies.

[0292] In this way, companies can efficiently and effectively disseminate information in multiple languages ​​and across multiple platforms, thereby enhancing their presence in the global market.

[0293] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0294] Step 1:

[0295] The server collects data from social media and news sites that serve as information sources. The input is a list of specific hashtags and keywords. Based on this input, the server retrieves relevant posts by calling the APIs of each information source. The output is a list of the collected posts. Specifically, the server checks the APIs at regular intervals to see if new data is available.

[0296] Step 2:

[0297] The server performs natural language processing on the collected post data. The input is a list of post data obtained in step 1. The server cleans this data and applies text analysis techniques to extract trend data and keywords. Techniques used include topic models (e.g., LDA models). The output is a set of extracted trend information and keywords. Specifically, the server analyzes the text data to identify frequently occurring words and themes.

[0298] Step 3:

[0299] The server generates content using a generative AI model. The input consists of trend information and keywords extracted in step 2. The server converts this information into prompt sentences and inputs them into the generative AI model. The output is the generated text content. Specifically, the server generates the prompt sentence "Create an article introducing eco-friendly products" and passes it to the AI ​​model.

[0300] Step 4:

[0301] The server translates and localizes the generated content into multiple languages. The input is the generated content obtained in step 3. The server uses a multilingual translation tool to translate the content into the languages ​​of each country. It also localizes the content to suit the local culture. The output is the translated and localized multilingual content. Specifically, for Japan, adjustments are made to match specific local festivals and events.

[0302] Step 5:

[0303] The server schedules the delivery of content. The input is content that is ready in multiple languages. The server analyzes the characteristics of each distribution platform, formats it into an optimized format, and automates posting at the optimal time for each platform. The output is the published content. Specifically, the server sets up and executes the procedure for automated posting using the API of each platform.

[0304] Step 6:

[0305] After posting, the server collects feedback data and performs analysis. The input is response data collected from each platform where the content was distributed. The server analyzes these data and generates visual metrics such as engagement rate and click-through rate. The output is a dashboard showing the analysis results. Specifically, the server uses an API to obtain feedback data and visualizes it for users in real time.

[0306] (Application Example 1)

[0307] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0308] Modern enterprises need to efficiently and effectively deploy advertisements in multiple languages and on multiple platforms. However, it is difficult to keep up with trends in real time and deliver advertisements at the optimal timing while accommodating diverse cultures and markets. There is a need for a system to solve such problems and maximize the performance of advertising campaigns.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0310] In this invention, the server includes means for collecting information from information sources, means for analyzing information using natural language analysis technology to extract trend information and phrases, means for creating content based on the extracted trend information using a generative intelligence model, means for multilingual translation of the created content and making adjustments suitable for each region, means for automatically posting planned content to multiple information dissemination platforms, and means for collecting reaction information regarding each post and analyzing it to generate a visual report. As a result, it is possible to efficiently generate and distribute multilingual and regionally adapted advertisement content, and optimize the advertising strategy by performing real-time performance analysis.

[0311] An "information processing device" is a system that has the functions of collecting, analyzing, generating, and distributing information.

[0312] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0313] A "generative intelligence model" is an algorithm that automatically generates new information or content based on data.

[0314] "Trend information" refers to information that indicates current market and social changes and trends.

[0315] A "word or phrase" is a word or phrase expressed in language that has some kind of meaning.

[0316] An "information transmission infrastructure" refers to the means of communication and platforms used to deliver information to users.

[0317] "Response information" refers to data related to feedback and engagement from recipients.

[0318] A "visual report" is a report that visually represents data, providing analysis results in a way that can be intuitively understood.

[0319] To implement this invention, a server plays a primary role. The server first collects information from information sources, which include online media and social networks. Information collection is performed via APIs; for example, posts related to a specific hashtag can be retrieved from Twitter.

[0320] Next, the server analyzes the collected information using natural language processing techniques to extract trend information and important keywords. Natural language processing libraries such as spaCy and NLTK are used here. This process identifies currently trending themes and keywords.

[0321] Next, the server uses a generative intelligence model to generate new advertising content based on the extracted trend information. This generation utilizes generative artificial intelligence technology. The generated content may include, for example, catchphrases and advertising copy related to a new product.

[0322] The server then translates the generated content into multiple languages ​​and localizes it to suit each region. A standard translation API is used for this translation. During this process, adjustments are made to accommodate local culture and customs.

[0323] Furthermore, the server uses an automated scheduling function to post advertisements to multiple information transmission platforms at the optimal time. The format is adjusted according to the characteristics of each platform, and the ads are delivered at the measured optimal time.

[0324] Finally, users can receive a visual report based on the reaction information for each post collected by the server. This report graphically displays the data analysis results and helps improve advertising strategies. For example, the following prompt is used in the generating AI model: "Based on today's trends, create an advertising tagline for a refreshing new beverage."

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

[0326] Step 1:

[0327] The server collects information from various sources. Specifically, it uses APIs to retrieve data from social media and online news sites. The input consists of parameters and search criteria set in the API, and the output is the retrieved raw post data. This data is stored in a database for subsequent processing.

[0328] Step 2:

[0329] The server analyzes the collected data using natural language processing techniques to extract trend information and important keywords. Specifically, it uses the spaCy library to build a topic model of the data and identify currently trending themes. The input is the collected post data, and the output is the extracted topics and keywords.

[0330] Step 3:

[0331] The server uses a generative intelligence model to generate advertising content based on extracted trend information. The input consists of extracted topics and keywords, and the output is the generated advertising copy and text. The generated content is obtained by inputting prompt sentences into the generative artificial intelligence model.

[0332] Step 4:

[0333] The server translates the generated content into multiple languages ​​and localizes it to suit each region. A multilingual translation API is used for translation. The input is the generated content, and the output is the translated and localized content.

[0334] Step 5:

[0335] The server automatically posts content to each information dissemination platform according to a set schedule. The input is translated and localized content, and the output is the media posted to each platform. The optimal posting time is measured and set accordingly.

[0336] Step 6:

[0337] Users review the reaction information for each post collected by the server and receive a visual report. The input is reaction data from each platform, and the output is a visualized report including engagement rates and click-through rates. This report provides insights to improve advertising strategies.

[0338] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0339] This invention relates to a system that combines an emotion engine with an information and communication device. The system aims to recognize the user's emotions using the emotion engine and optimize content generation and distribution based on the results. The following describes embodiments for carrying out the invention.

[0340] First, the server collects data from social media and news sites. It initially uses APIs to retrieve posts related to specific keywords and stores them in a database. Next, it utilizes a sentiment engine to analyze user sentiment trends from this data. For example, it might identify a product where users have a high proportion of positive sentiment towards it.

[0341] Next, the server analyzes the data using natural language processing techniques to extract trend information and keywords. By combining this information with the results of sentiment analysis, content that is more suitable for the target user is determined. For example, content is created prioritizing topics that receive many positive responses in sentiment analysis.

[0342] Next, the server uses a generative artificial intelligence model to generate content based on extracted trend information and sentiment data. During this process, the tone and style of the content can be adjusted based on the results of the sentiment engine. For example, expressions emphasizing humor or a sense of reassurance can be incorporated.

[0343] The server then translates the generated content into multiple languages ​​and localizes it for each region. It also takes sentiment analysis into account, adjusting expressions and tones to suit different regions. For example, it might select more formal language for business users.

[0344] Next, the server posts the optimized content to the information distribution platform. The content is automatically posted at the optimal time, aiming to reach users at their peak interest. During posting, the target audience is further segmented based on sentiment data.

[0345] Finally, the server collects feedback data after posting and identifies engagement trends based on analysis by the sentiment engine. Based on these results, a report is generated and provided to the user as insights for future strategies. For example, the dashboard may display analysis results on topics that received the most emotional responses in past posts.

[0346] Through this system, companies can understand user emotions and provide content tailored to those emotions, thereby optimizing engagement with their target market.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The server uses APIs from social media and news sites to collect new posts related to specific topics or keywords. The collected data is processed in real time and stored in a database.

[0350] Step 2:

[0351] The server filters out duplicates and spam from the collected submission data, improving data quality. At this stage, the purified data is passed on to the next processing step.

[0352] Step 3:

[0353] The server uses natural language processing techniques to extract trend information and key keywords from clean data. Specifically, it performs word frequency analysis and topic modeling to identify themes of high interest.

[0354] Step 4:

[0355] The server utilizes an emotion engine to recognize user emotions from posted data. As a result of the emotion analysis, an emotion score, such as positive or negative, is calculated, and the target user's emotional tendencies are understood based on this score.

[0356] Step 5:

[0357] The server uses an artificial intelligence model to generate content based on trend information and sentiment analysis results. The generated content is tailored to the target audience, with a tone and style that matches their emotions. For example, it might create articles using friendly language to evoke positive emotions.

[0358] Step 6:

[0359] The server translates the generated content into each language using a multilingual translation API, and then localizes it for each region. During this process, it adjusts the expression to take into account local customs and cultures.

[0360] Step 7:

[0361] The server posts translated and localized content to each information distribution platform. The posting timing is scheduled to take into account the times when users are most active.

[0362] Step 8:

[0363] The server collects feedback data after a post is published and analyzes it again using an emotion engine. This analysis identifies engagement trends and changes in user sentiment, which can then be used to inform future content strategies.

[0364] Step 9:

[0365] The server generates a report based on the aggregated feedback data and sentiment analysis results. This report is provided to users as a visual dashboard or report, and can be used as a resource to review content performance and identify areas for improvement.

[0366] (Example 2)

[0367] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0368] In today's information society, generating content that matches users' interests and emotions quickly and accurately, and delivering it across diverse information transmission platforms, is a challenging task. In particular, the lack of systems to efficiently automate the processes of multilingual support, regional optimization, and emotionally resonant content is a significant problem. Furthermore, the process of immediately analyzing user feedback after content distribution and incorporating it into future strategies is still underdeveloped, which also presents a challenge.

[0369] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0370] In this invention, the server includes means for collecting information from a data source, means for analyzing the information using natural language processing technology to extract trending topics and key words, and means for generating content based on the extracted trending topics using a generation algorithm. This makes it possible to automatically generate multilingual content that matches the user's emotions and provide it in a way that is tailored to the characteristics of each region. Furthermore, by quickly analyzing feedback after distribution and reflecting it in the next content strategy, it is possible to achieve higher user satisfaction.

[0371] An "information processing device" is a device equipped with functions for collecting and analyzing data, and for generating and transmitting necessary information.

[0372] "Data source" refers to the origin or platform from which information is obtained, and includes social media and news sites.

[0373] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0374] "Trends" refer to themes or phenomena that have attracted attention within a certain period, and may include popular themes in a particular industry or field.

[0375] "Key terms" are important keywords or phrases that indicate a specific topic or content in data analysis.

[0376] A "generating algorithm" is a computational method that automatically creates new information or content from data according to specific rules or procedures.

[0377] "Multilingual translation" is the process of converting content written in one language into multiple other languages ​​to make it understandable.

[0378] "Regional optimization" refers to adjusting the content and expression to suit the culture, customs, and linguistic characteristics of each region.

[0379] An "information transmission infrastructure" is the infrastructure used to deliver generated content to users, and includes social media and websites.

[0380] "Emotion analysis technology" is a technique that extracts emotions from text and audio data and identifies the type and intensity of those emotions.

[0381] "Evaluation data" refers to information that numerically or qualitatively demonstrates the effectiveness and impact of content based on user reactions and feedback.

[0382] "Documents showing analysis results" refer to documents or reports that analyze collected evaluation data and include insights and conclusions based on that analysis.

[0383] In this invention, the information processing device is configured to enable the generation and distribution of highly accurate content that meets the user's needs. The embodiments thereof are described in detail below.

[0384] First, the server collects information from sources such as social media and news sites. Python is used for data collection, and data associated with specific keywords is retrieved through appropriate APIs. This enables real-time information gathering. The collected data is stored in a database such as PostgreSQL.

[0385] Next, the server applies natural language processing techniques to the collected data. Specifically, it analyzes the data using Python NLP libraries (such as NLTK and spaCy) to extract trends and key terms. This allows for the efficient identification of necessary keywords and topics.

[0386] Furthermore, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate content based on the extracted information. The generated content is then refined using sentiment analysis technology, with its tone and style set based on the user's emotions or predicted emotions. An example of a prompt to input to the generative AI model might be, "Generate promotional content that evokes positive emotions in the user, based on the latest trending information."

[0387] The server then translates the generated content into multiple languages ​​and localizes it for each region. Translation services such as Amazon Translate and DeepL are used to translate the content into different languages. The language is optimized to suit the culture and context of each region, with adjustments such as adopting a more formal tone for business use.

[0388] Finally, the server automatically distributes the refined content to the information transmission platform. This process utilizes tools such as Buffer and Hootsuite to ensure timely posting. After distribution, feedback data is collected, analyzed again, and incorporated into the next content strategy. This entire process strengthens engagement between users and the company, enabling effective information dissemination.

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

[0390] Step 1:

[0391] The server collects information from data sources. Specifically, it uses Python scripts to retrieve information from social media and news sites via APIs. It collects data based on specified keywords (e.g., "new products," "popular events") as input and stores the raw text data as output in a database. During this collection process, it retrieves data using HTTP requests and handles the data in JSON format.

[0392] Step 2:

[0393] The server applies natural language processing (NLP) techniques to the collected text data. It uses previously stored raw data as input. Then, using Python NLP libraries (such as NLTK or spaCy), it performs tokenization and part-of-speech tagging to extract trending topics and key words. The output is a list of extracted keywords and trend information. This information is added to a database and used for subsequent processing.

[0394] Step 3:

[0395] The server generates content using a generative AI model. Keywords and trend information obtained in step 2 are used as input. A prompt is input to the generative AI model (e.g., the GPT series) to prompt it to generate new content. For example, using the prompt "Create a campaign proposal based on this summer's trends," the output will be a campaign proposal written in natural language.

[0396] Step 4:

[0397] The server converts the generated content into multilingual translated data and performs localization tailored to each region. The input is the content generated in step 3. Using APIs such as Amazon Translate and DeepL, it translates the content into each region's language and adjusts it to the most appropriate expression, taking cultural context into account. The output is language-specific content optimized for each region.

[0398] Step 5:

[0399] The server delivers the adjusted content to the designated information transmission platform. Multilingual translated and localized content is used as input. By utilizing distribution tools such as Buffer and Hootsuite and setting an optimal distribution schedule, the output is posted to each platform at the specified time.

[0400] Step 6:

[0401] The server collects and analyzes feedback data after delivery to inform future strategies. It uses user feedback as input. Sentiment analysis technology is employed to identify positive or negative responses, generating reports on emotional tendencies and suggestions for improvement. This contributes to improving future content strategies.

[0402] (Application Example 2)

[0403] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0404] In today's information society, providing appropriate content that aligns with consumers' emotions and interests quickly and effectively is a critical challenge for many companies. However, conventional systems lack the ability to accurately reflect user emotions in content generation and delivery, making it difficult to optimize engagement with target users. Therefore, there is a need for a method that can evaluate user emotions in real time and provide content tailored to their emotional state.

[0405] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0406] In this invention, the server includes means for collecting data from information sources and performing sentiment analysis to evaluate the user's emotions; means for analyzing the data using natural language processing technology and extracting trend information and keywords; and means for generating content based on the user's emotional state using a generative artificial intelligence model. This enables the delivery of optimal content that reflects the user's emotions.

[0407] An "information and communication device" is an electronic device used to collect, process, and analyze data, and to distribute it in an appropriate format.

[0408] "Sentiment analysis" is a technology that analyzes a user's emotional state from data and identifies emotions such as positive, negative, and neutral.

[0409] "Natural language processing technology" refers to methods for analyzing, understanding, and generating human language using computers.

[0410] "Trending information" refers to themes and keywords that are popular during a specific period, and is information of high social interest.

[0411] A "generative artificial intelligence model" is an artificial intelligence algorithm that automatically generates new content using data as input.

[0412] "Localization" is the act of adapting content to suit different regions or specific groups, taking into account multiple languages ​​and cultures.

[0413] An "information distribution platform" is an online system or service for distributing content to a wide range of users.

[0414] "Feedback data" refers to information about the evaluations and reactions that users give back to the content provided.

[0415] "User emotional state" refers to the type and intensity of emotions a user is experiencing at a particular point in time.

[0416] This system configuration consists of a server that functions as an information and communication device, collecting, processing, and analyzing data from information sources. The server collects data from social networking services (SNS) and news sites via the internet using APIs. This data is stored in a database and then sent to a sentiment analysis engine to evaluate the user's emotional state. This sentiment analysis is achieved by utilizing natural language processing technology to analyze the emotional elements of user posts and responses.

[0417] Trend information and extracted keywords are input into a generative artificial intelligence model, which then generates content. The generative AI model adjusts the style and tone of the content according to the user's emotional state, optimizing the interaction. For example, it can provide humorous content to users with many positive emotions and encouragement to those with negative emotions. The generative AI model used here is implemented using frameworks such as PyTorch and Transformers.

[0418] Next, the generated content is translated into multiple languages, and the server localizes it to suit the region and user sentiment. This ensures appropriate content delivery that reflects cultural backgrounds and linguistic nuances. Furthermore, the information distribution platform automatically posts content on an optimal schedule based on user sentiment analysis results. User feedback data after distribution is also collected and used to inform future strategies through further sentiment analysis.

[0419] For example, if a user is feeling stressed, the server can generate content recommending relaxing music or videos and deliver it to the user at a time that matches their emotions. An example of a prompt that might be used is, "Generate new content that reflects the user's current emotions!"

[0420] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0421] Step 1:

[0422] The server collects data from information sources. It uses APIs to retrieve user posts from social media and news sites and stores them in a database. This data collection is performed in real time, handling text and multimedia data collected from the information sources as input. The output is a dataset ready for use by the sentiment analysis engine.

[0423] Step 2:

[0424] The server processes data using an emotion analysis engine to evaluate the user's emotions. The input data is the posted content collected in step 1, and is analyzed using natural language processing techniques. This analysis identifies emotional states such as positive, negative, and neutral, and the output is the emotion evaluation result for each user.

[0425] Step 3:

[0426] The server analyzes the data using natural language processing to extract trend information and keywords. In this step, the server uses posts that have undergone sentiment analysis as input, summarizing the content and extracting elements of high social interest. The output is extracted trend data for use by the generative AI model.

[0427] Step 4:

[0428] The server uses a generative artificial intelligence model to generate content that responds to the user's emotional state. The input requires trend information, keywords, and user sentiment data, which the generative AI model then uses to output optimized content. This content has a tone and style that matches the user's emotions.

[0429] Step 5:

[0430] The server translates the generated content into multiple languages ​​and localizes it according to region and user sentiment. It takes the user's cultural background and linguistic needs as input to perform the translation and localization process, resulting in adjusted content as output.

[0431] Step 6:

[0432] The server posts the adjusted content to the information distribution platform. This step utilizes a pre-configured schedule and sentiment analysis results as input to automatically post at the optimal time. The output is content delivered appropriately to the user.

[0433] Step 7:

[0434] The server collects feedback data after delivery and analyzes it again using a sentiment analysis engine. The input is user response data, which is analyzed to evaluate engagement trends. The output is a report containing insights for the next delivery.

[0435] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0436] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0437] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0441] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0442] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0443] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0444] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0445] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0446] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0447] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0448] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0449] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0450] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0451] This invention provides a system for companies to efficiently disseminate information in multiple languages ​​and across multiple platforms. The following describes embodiments for carrying out this invention.

[0452] First, the server collects data in real time from information sources such as social media and news sites. This includes data retrieval using APIs. For example, it might use the Twitter API to retrieve posts related to a specific hashtag.

[0453] Next, the server analyzes the collected data using natural language processing techniques. This extracts trend information and important keywords. For example, machine learning algorithms are used to form topic models and identify currently trending topics.

[0454] Next, the server utilizes a generative artificial intelligence model to generate content based on the extracted trend information. This content generation is automated, minimizing the need for manual editing. For example, it can create articles on the latest eco-friendly trends related to a specific product.

[0455] The server then uses multilingual translation technology to translate the generated content for each country and further localizes it. This makes it possible to provide the same content in a form that is adapted to the culture and customs of each region. For example, content for Japan is adjusted to be related to specific cultural events in that region.

[0456] Next, the server schedules the content and automatically posts it to multiple information distribution platforms. This process optimizes reaching the target audience by formatting the content to match each platform's format and setting the optimal posting time.

[0457] Finally, the server collects feedback data after posting and analyzes performance. This analytical data is provided to users as a visual dashboard and used to improve content strategies. For example, it can show real-time statistics on post engagement rates and click-through rates.

[0458] Through the process described above, the system of the present invention effectively and efficiently implements multilingual marketing strategies. This enables companies to improve engagement in the global market while saving resources.

[0459] The following describes the processing flow.

[0460] Step 1:

[0461] The server configures APIs to retrieve data from information sources such as social media and news sites, and collects data periodically. During this process, it filters the data using specific keywords and hashtags to include only relevant posts.

[0462] Step 2:

[0463] The server stores the collected data in a database and cleans it up using a filtering function to remove duplicate data and spam. This improves the quality of the data being analyzed.

[0464] Step 3:

[0465] The server analyzes the cleaned-up data using natural language processing techniques to extract frequently occurring keywords and trend information. This process also includes topic modeling and sentiment analysis to understand the trends.

[0466] Step 4:

[0467] The server generates content using an artificial intelligence model based on extracted trend information. This includes automatic text generation based on templates and image selection as needed.

[0468] Step 5:

[0469] The server translates the generated content into each target language via a multilingual translation API and then localizes it for each region, adding regionally specific expressions and cultural elements for adjustment.

[0470] Step 6:

[0471] The server formats translated and localized content into the appropriate format for each information distribution platform and automatically posts it at the optimal time. The posting schedule is set considering the target audience's usage times.

[0472] Step 7:

[0473] The server uses each platform's API to collect feedback data (e.g., engagement rate, clicks) after posting. This information plays a crucial role in optimizing future content strategies.

[0474] Step 8:

[0475] The server analyzes the collected feedback data and compiles the results into a report. This report is then provided to the user as a visual dashboard, which can be used to review performance and revise strategies.

[0476] (Example 1)

[0477] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0478] In today's business world, efficient information dissemination across multiple languages ​​and platforms is crucial. However, traditional methods require significant effort and resources to create and distribute content tailored to each country's language and culture. Furthermore, accurately collecting and analyzing feedback after posting is not easy. There is a need for a system that efficiently addresses these challenges and enables companies to quickly and effectively increase engagement in the global market.

[0479] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0480] In this invention, the server includes means for acquiring information from information providers, means for analyzing the information using natural language processing technology and extracting trend data and keywords, means for creating content based on the extracted trend data using generative artificial intelligence technology, means for converting the created content into multiple languages ​​and applying localization according to each region, means for setting a plan and automatically posting to multiple information distribution platforms, and means for acquiring response data for each post, analyzing it, and generating visual indicators. As a result, companies can efficiently and comprehensively disseminate information that is appropriate for the culture and language of each country, and can more effectively improve global engagement through a data-driven improvement cycle.

[0481] "Information and communication equipment" is a general term for devices that have the function of sending, receiving, and processing digital information.

[0482] "Information source" refers to the source from which digital data is transmitted or supplied.

[0483] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0484] "Generative artificial intelligence technology" refers to artificial intelligence technology that has the ability to learn from large amounts of data and generate new data.

[0485] "Trend data" refers to a collection of information or topics that have attracted significant attention within a specific time period.

[0486] A "keyword" is an important word used to characterize or summarize information or a topic.

[0487] "Localization" refers to the process of adjusting content to suit a specific region or culture.

[0488] An "information distribution platform" refers to an online platform for providing digital data to users.

[0489] "Response data" refers to data that shows users' reactions and evaluations of content.

[0490] "Visual metrics" are visualized information used to display data analysis results in a way that is easy for users to understand.

[0491] This system is implemented using information and communication equipment and efficiently performs the collection, analysis, generation, distribution, and feedback analysis of digital data. Servers, in particular, play a crucial role, and the system is structured around their functions.

[0492] First, regarding information gathering, the server retrieves data from social media and news sites that serve as information sources via APIs. In this process, common APIs such as Twitter are used to collect posts related to specific hashtags or keywords. For example, posts containing "eco-friendly" are targeted.

[0493] Next, the server applies natural language processing techniques to the collected data. Specifically, it performs text analysis and uses machine learning algorithms such as the LDA (Latent Dirichlet Allocation) model to extract trend data and keywords. As a result, currently trending topics and trends can be identified.

[0494] Subsequently, the server utilizes generative artificial intelligence technology to create new content based on the extracted data. For example, it uses OpenAI's GPT model as a generative AI model and automatically generates articles that resonate with the target audience using prompts such as, "Create an article based on the latest information on eco-friendly trends."

[0495] After the content is generated, the server translates it using a multilingual translation tool (e.g., Google Translate API) and then localizes it to suit the culture of each region. This involves adjusting it to the cultural events and customs of Japan and other countries and regions.

[0496] Finally, the server uses an information distribution infrastructure to deliver content to multiple platforms. Posting times are scheduled systematically, and content is published in an optimized format for each platform.

[0497] The feedback data collected through these processes is also analyzed by the server and provided to the user as visual indicators. The visualized dashboard allows users to view data such as engagement rates and click-through rates in real time, which can be used to improve future strategies.

[0498] In this way, companies can efficiently and effectively disseminate information in multiple languages ​​and across multiple platforms, thereby enhancing their presence in the global market.

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

[0500] Step 1:

[0501] The server collects data from social media and news sites that serve as information sources. The input is a list of specific hashtags and keywords. Based on this input, the server retrieves relevant posts by calling the APIs of each information source. The output is a list of the collected posts. Specifically, the server checks the APIs at regular intervals to see if new data is available.

[0502] Step 2:

[0503] The server performs natural language processing on the collected post data. The input is a list of post data obtained in step 1. The server cleans this data and applies text analysis techniques to extract trend data and keywords. Techniques used include topic models (e.g., LDA models). The output is a set of extracted trend information and keywords. Specifically, the server analyzes the text data to identify frequently occurring words and themes.

[0504] Step 3:

[0505] The server generates content using a generative AI model. The input consists of trend information and keywords extracted in step 2. The server converts this information into prompt sentences and inputs them into the generative AI model. The output is the generated text content. Specifically, the server generates the prompt sentence "Create an article introducing eco-friendly products" and passes it to the AI ​​model.

[0506] Step 4:

[0507] The server translates and localizes the generated content into multiple languages. The input is the generated content obtained in step 3. The server uses a multilingual translation tool to translate the content into the languages ​​of each country. It also localizes the content to suit the local culture. The output is the translated and localized multilingual content. Specifically, for Japan, adjustments are made to match specific local festivals and events.

[0508] Step 5:

[0509] The server schedules the delivery of content. The input is content that is ready in multiple languages. The server analyzes the characteristics of each distribution platform, formats it into an optimized format, and automates posting at the optimal time for each platform. The output is the published content. Specifically, the server sets up and executes the procedure for automated posting using the API of each platform.

[0510] Step 6:

[0511] The server collects and analyzes feedback data after posting. The input is response data collected from each platform where the content was distributed. The server analyzes this data and generates visual metrics such as engagement rate and click-through rate. The output is a dashboard showing the analysis results. Specifically, the server uses an API to retrieve feedback data and visualizes it for the user in real time.

[0512] (Application Example 1)

[0513] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0514] Modern businesses need to deploy advertising efficiently and effectively across multiple languages ​​and platforms. However, it is difficult to respond to diverse cultures and markets, understand trends in real time, and deliver ads at the optimal time. A system is needed to solve these challenges and maximize the performance of advertising campaigns.

[0515] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0516] In this invention, the server includes means for collecting information from information sources, means for analyzing the information using natural language processing technology and extracting trend information and keywords, means for creating content based on the extracted trend information using a generative intelligence model, means for translating the created content into multiple languages ​​and making adjustments to suit each region, means for planning and automatically posting to multiple information transmission platforms, and means for collecting reaction information related to each post, analyzing it, and generating a visual report. This enables the efficient generation and distribution of multilingual and region-appropriate advertising content, and optimizes advertising strategies by performing real-time performance analysis.

[0517] An "information processing device" is a system that has the functions of collecting, analyzing, generating, and distributing information.

[0518] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0519] A "generative intelligence model" is an algorithm that automatically generates new information or content based on data.

[0520] "Trend information" refers to information that indicates current market and social changes and trends.

[0521] A "word or phrase" is a word or phrase expressed in language that has some kind of meaning.

[0522] An "information transmission infrastructure" refers to the means of communication and platforms used to deliver information to users.

[0523] "Response information" refers to data related to feedback and engagement from recipients.

[0524] A "visual report" is a report that visually represents data, providing analysis results in a way that can be intuitively understood.

[0525] To implement this invention, a server plays a primary role. The server first collects information from information sources, which include online media and social networks. Information collection is performed via APIs; for example, posts related to a specific hashtag can be retrieved from Twitter.

[0526] Next, the server analyzes the collected information using natural language processing techniques to extract trend information and important keywords. Natural language processing libraries such as spaCy and NLTK are used here. This process identifies currently trending themes and keywords.

[0527] Next, the server uses a generative intelligence model to generate new advertising content based on the extracted trend information. This generation utilizes generative artificial intelligence technology. The generated content may include, for example, catchphrases and advertising copy related to a new product.

[0528] The server then translates the generated content into multiple languages ​​and localizes it to suit each region. A standard translation API is used for this translation. During this process, adjustments are made to accommodate local culture and customs.

[0529] Furthermore, the server uses an automated scheduling function to post advertisements to multiple information transmission platforms at the optimal time. The format is adjusted according to the characteristics of each platform, and the ads are delivered at the measured optimal time.

[0530] Finally, users can receive a visual report based on the reaction information for each post collected by the server. This report graphically displays the data analysis results and helps improve advertising strategies. For example, the following prompt is used in the generating AI model: "Based on today's trends, create an advertising tagline for a refreshing new beverage."

[0531] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0532] Step 1:

[0533] The server collects information from various sources. Specifically, it uses APIs to retrieve data from social media and online news sites. The input consists of parameters and search criteria set in the API, and the output is the retrieved raw post data. This data is stored in a database for subsequent processing.

[0534] Step 2:

[0535] The server analyzes the collected data using natural language processing techniques to extract trend information and important keywords. Specifically, it uses the spaCy library to build a topic model of the data and identify currently trending themes. The input is the collected post data, and the output is the extracted topics and keywords.

[0536] Step 3:

[0537] The server uses a generative intelligence model to generate advertising content based on extracted trend information. The input consists of extracted topics and keywords, and the output is the generated advertising copy and text. The generated content is obtained by inputting prompt sentences into the generative artificial intelligence model.

[0538] Step 4:

[0539] The server translates the generated content into multiple languages ​​and localizes it to suit each region. A multilingual translation API is used for translation. The input is the generated content, and the output is the translated and localized content.

[0540] Step 5:

[0541] The server automatically posts content to each information dissemination platform according to a set schedule. The input is translated and localized content, and the output is the media posted to each platform. The optimal posting time is measured and set accordingly.

[0542] Step 6:

[0543] Users review the reaction information for each post collected by the server and receive a visual report. The input is reaction data from each platform, and the output is a visualized report including engagement rates and click-through rates. This report provides insights to improve advertising strategies.

[0544] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0545] This invention relates to a system that combines an emotion engine with an information and communication device. The system aims to recognize the user's emotions using the emotion engine and optimize content generation and distribution based on the results. The following describes embodiments for carrying out the invention.

[0546] First, the server collects data from social media and news sites. It initially uses APIs to retrieve posts related to specific keywords and stores them in a database. Next, it utilizes a sentiment engine to analyze user sentiment trends from this data. For example, it might identify a product where users have a high proportion of positive sentiment towards it.

[0547] Next, the server analyzes the data using natural language processing techniques to extract trend information and keywords. By combining this information with the results of sentiment analysis, content that is more suitable for the target user is determined. For example, content is created prioritizing topics that receive many positive responses in sentiment analysis.

[0548] Next, the server uses a generative artificial intelligence model to generate content based on extracted trend information and sentiment data. During this process, the tone and style of the content can be adjusted based on the results of the sentiment engine. For example, expressions emphasizing humor or a sense of reassurance can be incorporated.

[0549] The server then translates the generated content into multiple languages ​​and localizes it for each region. It also takes sentiment analysis into account, adjusting expressions and tones to suit different regions. For example, it might select more formal language for business users.

[0550] Next, the server posts the optimized content to the information distribution platform. The content is automatically posted at the optimal time, aiming to reach users at their peak interest. During posting, the target audience is further segmented based on sentiment data.

[0551] Finally, the server collects feedback data after posting and identifies engagement trends based on analysis by the sentiment engine. Based on these results, a report is generated and provided to the user as insights for future strategies. For example, the dashboard may display analysis results on topics that received the most emotional responses in past posts.

[0552] Through this system, companies can understand user emotions and provide content tailored to those emotions, thereby optimizing engagement with their target market.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] The server uses APIs from social media and news sites to collect new posts related to specific topics or keywords. The collected data is processed in real time and stored in a database.

[0556] Step 2:

[0557] The server filters out duplicates and spam from the collected submission data, improving data quality. At this stage, the purified data is passed on to the next processing step.

[0558] Step 3:

[0559] The server uses natural language processing techniques to extract trend information and key keywords from clean data. Specifically, it performs word frequency analysis and topic modeling to identify themes of high interest.

[0560] Step 4:

[0561] The server utilizes an emotion engine to recognize user emotions from posted data. As a result of the emotion analysis, an emotion score, such as positive or negative, is calculated, and the target user's emotional tendencies are understood based on this score.

[0562] Step 5:

[0563] The server uses an artificial intelligence model to generate content based on trend information and sentiment analysis results. The generated content is tailored to the target audience, with a tone and style that matches their emotions. For example, it might create articles using friendly language to evoke positive emotions.

[0564] Step 6:

[0565] The server translates the generated content into each language using a multilingual translation API, and then localizes it for each region. During this process, it adjusts the expression to take into account local customs and cultures.

[0566] Step 7:

[0567] The server posts translated and localized content to each information distribution platform. The posting timing is scheduled to take into account the times when users are most active.

[0568] Step 8:

[0569] The server collects feedback data after a post is published and analyzes it again using an emotion engine. This analysis identifies engagement trends and changes in user sentiment, which can then be used to inform future content strategies.

[0570] Step 9:

[0571] The server generates a report based on the aggregated feedback data and sentiment analysis results. This report is provided to users as a visual dashboard or report, and can be used as a resource to review content performance and identify areas for improvement.

[0572] (Example 2)

[0573] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0574] In today's information society, generating content that matches users' interests and emotions quickly and accurately, and delivering it across diverse information transmission platforms, is a challenging task. In particular, the lack of systems to efficiently automate the processes of multilingual support, regional optimization, and emotionally resonant content is a significant problem. Furthermore, the process of immediately analyzing user feedback after content distribution and incorporating it into future strategies is still underdeveloped, which also presents a challenge.

[0575] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0576] In this invention, the server includes means for collecting information from a data source, means for analyzing the information using natural language processing technology to extract trending topics and key words, and means for generating content based on the extracted trending topics using a generation algorithm. This makes it possible to automatically generate multilingual content that matches the user's emotions and provide it in a way that is tailored to the characteristics of each region. Furthermore, by quickly analyzing feedback after distribution and reflecting it in the next content strategy, it is possible to achieve higher user satisfaction.

[0577] An "information processing device" is a device equipped with functions for collecting and analyzing data, and for generating and transmitting necessary information.

[0578] "Data source" refers to the origin or platform from which information is obtained, and includes social media and news sites.

[0579] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0580] "Trends" refer to themes or phenomena that have attracted attention within a certain period, and may include popular themes in a particular industry or field.

[0581] "Key terms" are important keywords or phrases that indicate a specific topic or content in data analysis.

[0582] A "generating algorithm" is a computational method that automatically creates new information or content from data according to specific rules or procedures.

[0583] "Multilingual translation" is the process of converting content written in one language into multiple other languages ​​to make it understandable.

[0584] "Regional optimization" refers to adjusting the content and expression to suit the culture, customs, and linguistic characteristics of each region.

[0585] An "information transmission infrastructure" is the infrastructure used to deliver generated content to users, and includes social media and websites.

[0586] "Emotion analysis technology" is a technique that extracts emotions from text and audio data and identifies the type and intensity of those emotions.

[0587] "Evaluation data" refers to information that numerically or qualitatively demonstrates the effectiveness and impact of content based on user reactions and feedback.

[0588] "Documents showing analysis results" refer to documents or reports that analyze collected evaluation data and include insights and conclusions based on that analysis.

[0589] In this invention, the information processing device is configured to enable the generation and distribution of highly accurate content that meets the user's needs. The embodiments thereof are described in detail below.

[0590] First, the server collects information from sources such as social media and news sites. Python is used for data collection, and data associated with specific keywords is retrieved through appropriate APIs. This enables real-time information gathering. The collected data is stored in a database such as PostgreSQL.

[0591] Next, the server applies natural language processing techniques to the collected data. Specifically, it analyzes the data using Python NLP libraries (such as NLTK and spaCy) to extract trends and key terms. This allows for the efficient identification of necessary keywords and topics.

[0592] Furthermore, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate content based on the extracted information. The generated content is then refined using sentiment analysis technology, with its tone and style set based on the user's emotions or predicted emotions. An example of a prompt to input to the generative AI model might be, "Generate promotional content that evokes positive emotions in the user, based on the latest trending information."

[0593] The server then translates the generated content into multiple languages ​​and localizes it for each region. Translation services such as Amazon Translate and DeepL are used to translate the content into different languages. The language is optimized to suit the culture and context of each region, with adjustments such as adopting a more formal tone for business use.

[0594] Finally, the server automatically distributes the refined content to the information transmission platform. This process utilizes tools such as Buffer and Hootsuite to ensure timely posting. After distribution, feedback data is collected, analyzed again, and incorporated into the next content strategy. This entire process strengthens engagement between users and the company, enabling effective information dissemination.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The server collects information from data sources. Specifically, it uses Python scripts to retrieve information from social media and news sites via APIs. It collects data based on specified keywords (e.g., "new products," "popular events") as input and stores the raw text data as output in a database. During this collection process, it retrieves data using HTTP requests and handles the data in JSON format.

[0598] Step 2:

[0599] The server applies natural language processing (NLP) techniques to the collected text data. It uses previously stored raw data as input. Then, using Python NLP libraries (such as NLTK or spaCy), it performs tokenization and part-of-speech tagging to extract trending topics and key words. The output is a list of extracted keywords and trend information. This information is added to a database and used for subsequent processing.

[0600] Step 3:

[0601] The server generates content using a generative AI model. Keywords and trend information obtained in step 2 are used as input. A prompt is input to the generative AI model (e.g., the GPT series) to prompt it to generate new content. For example, using the prompt "Create a campaign proposal based on this summer's trends," the output will be a campaign proposal written in natural language.

[0602] Step 4:

[0603] The server converts the generated content into multilingual translated data and performs localization tailored to each region. The input is the content generated in step 3. Using APIs such as Amazon Translate and DeepL, it translates the content into each region's language and adjusts it to the most appropriate expression, taking cultural context into account. The output is language-specific content optimized for each region.

[0604] Step 5:

[0605] The server delivers the adjusted content to the designated information transmission platform. Multilingual translated and localized content is used as input. By utilizing distribution tools such as Buffer and Hootsuite and setting an optimal distribution schedule, the output is posted to each platform at the specified time.

[0606] Step 6:

[0607] The server collects and analyzes feedback data after delivery to inform future strategies. It uses user feedback as input. Sentiment analysis technology is employed to identify positive or negative responses, generating reports on emotional tendencies and suggestions for improvement. This contributes to improving future content strategies.

[0608] (Application Example 2)

[0609] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0610] In today's information society, providing appropriate content that aligns with consumers' emotions and interests quickly and effectively is a critical challenge for many companies. However, conventional systems lack the ability to accurately reflect user emotions in content generation and delivery, making it difficult to optimize engagement with target users. Therefore, there is a need for a method that can evaluate user emotions in real time and provide content tailored to their emotional state.

[0611] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0612] In this invention, the server includes means for collecting data from information sources and performing sentiment analysis to evaluate the user's emotions; means for analyzing the data using natural language processing technology and extracting trend information and keywords; and means for generating content based on the user's emotional state using a generative artificial intelligence model. This enables the delivery of optimal content that reflects the user's emotions.

[0613] An "information and communication device" is an electronic device used to collect, process, and analyze data, and to distribute it in an appropriate format.

[0614] "Sentiment analysis" is a technology that analyzes a user's emotional state from data and identifies emotions such as positive, negative, and neutral.

[0615] "Natural language processing technology" refers to methods for analyzing, understanding, and generating human language using computers.

[0616] "Trending information" refers to themes and keywords that are popular during a specific period, and is information of high social interest.

[0617] A "generative artificial intelligence model" is an artificial intelligence algorithm that automatically generates new content using data as input.

[0618] "Localization" is the act of adapting content to suit different regions or specific groups, taking into account multiple languages ​​and cultures.

[0619] An "information distribution platform" is an online system or service for distributing content to a wide range of users.

[0620] "Feedback data" refers to information about the evaluations and reactions that users give back to the content provided.

[0621] "User emotional state" refers to the type and intensity of emotions a user is experiencing at a particular point in time.

[0622] This system configuration consists of a server that functions as an information and communication device, collecting, processing, and analyzing data from information sources. The server collects data from social networking services (SNS) and news sites via the internet using APIs. This data is stored in a database and then sent to a sentiment analysis engine to evaluate the user's emotional state. This sentiment analysis is achieved by utilizing natural language processing technology to analyze the emotional elements of user posts and responses.

[0623] Trend information and extracted keywords are input into a generative artificial intelligence model, which then generates content. The generative AI model adjusts the style and tone of the content according to the user's emotional state, optimizing the interaction. For example, it can provide humorous content to users with many positive emotions and encouragement to those with negative emotions. The generative AI model used here is implemented using frameworks such as PyTorch and Transformers.

[0624] Next, the generated content is translated into multiple languages, and the server localizes it to suit the region and user sentiment. This ensures appropriate content delivery that reflects cultural backgrounds and linguistic nuances. Furthermore, the information distribution platform automatically posts content on an optimal schedule based on user sentiment analysis results. User feedback data after distribution is also collected and used to inform future strategies through further sentiment analysis.

[0625] For example, if a user is feeling stressed, the server can generate content recommending relaxing music or videos and deliver it to the user at a time that matches their emotions. An example of a prompt that might be used is, "Generate new content that reflects the user's current emotions!"

[0626] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0627] Step 1:

[0628] The server collects data from information sources. It uses APIs to retrieve user posts from social media and news sites and stores them in a database. This data collection is performed in real time, handling text and multimedia data collected from the information sources as input. The output is a dataset ready for use by the sentiment analysis engine.

[0629] Step 2:

[0630] The server processes data using an emotion analysis engine to evaluate the user's emotions. The input data is the posted content collected in step 1, and is analyzed using natural language processing techniques. This analysis identifies emotional states such as positive, negative, and neutral, and the output is the emotion evaluation result for each user.

[0631] Step 3:

[0632] The server analyzes the data using natural language processing to extract trend information and keywords. In this step, the server uses posts that have undergone sentiment analysis as input, summarizing the content and extracting elements of high social interest. The output is extracted trend data for use by the generative AI model.

[0633] Step 4:

[0634] The server uses a generative artificial intelligence model to generate content that responds to the user's emotional state. The input requires trend information, keywords, and user sentiment data, which the generative AI model then uses to output optimized content. This content has a tone and style that matches the user's emotions.

[0635] Step 5:

[0636] The server translates the generated content into multiple languages ​​and localizes it according to region and user sentiment. It takes the user's cultural background and linguistic needs as input to perform the translation and localization process, resulting in adjusted content as output.

[0637] Step 6:

[0638] The server posts the adjusted content to the information distribution platform. This step utilizes a pre-configured schedule and sentiment analysis results as input to automatically post at the optimal time. The output is content delivered appropriately to the user.

[0639] Step 7:

[0640] The server collects feedback data after delivery and analyzes it again using a sentiment analysis engine. The input is user response data, which is analyzed to evaluate engagement trends. The output is a report containing insights for the next delivery.

[0641] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0642] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0643] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0644] [Fourth Embodiment]

[0645] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0646] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0647] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0648] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0649] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0650] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0651] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0652] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0653] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0654] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0655] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0656] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0657] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] This invention provides a system for companies to efficiently disseminate information in multiple languages ​​and across multiple platforms. The following describes embodiments for carrying out this invention.

[0659] First, the server collects data in real time from information sources such as social media and news sites. This includes data retrieval using APIs. For example, it might use the Twitter API to retrieve posts related to a specific hashtag.

[0660] Next, the server analyzes the collected data using natural language processing techniques. This extracts trend information and important keywords. For example, machine learning algorithms are used to form topic models and identify currently trending topics.

[0661] Next, the server utilizes a generative artificial intelligence model to generate content based on the extracted trend information. This content generation is automated, minimizing the need for manual editing. For example, it can create articles on the latest eco-friendly trends related to a specific product.

[0662] The server then uses multilingual translation technology to translate the generated content for each country and further localizes it. This makes it possible to provide the same content in a form that is adapted to the culture and customs of each region. For example, content for Japan is adjusted to be related to specific cultural events in that region.

[0663] Next, the server schedules the content and automatically posts it to multiple information distribution platforms. This process optimizes reaching the target audience by formatting the content to match each platform's format and setting the optimal posting time.

[0664] Finally, the server collects feedback data after posting and analyzes performance. This analytical data is provided to users as a visual dashboard and used to improve content strategies. For example, it can show real-time statistics on post engagement rates and click-through rates.

[0665] Through the process described above, the system of the present invention effectively and efficiently implements multilingual marketing strategies. This enables companies to improve engagement in the global market while saving resources.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The server configures APIs to retrieve data from information sources such as social media and news sites, and collects data periodically. During this process, it filters the data using specific keywords and hashtags to include only relevant posts.

[0669] Step 2:

[0670] The server stores the collected data in a database and cleans it up using a filtering function to remove duplicate data and spam. This improves the quality of the data being analyzed.

[0671] Step 3:

[0672] The server analyzes the cleaned-up data using natural language processing techniques to extract frequently occurring keywords and trend information. This process also includes topic modeling and sentiment analysis to understand the trends.

[0673] Step 4:

[0674] The server generates content using an artificial intelligence model based on extracted trend information. This includes automatic text generation based on templates and image selection as needed.

[0675] Step 5:

[0676] The server translates the generated content into each target language via a multilingual translation API and then localizes it for each region, adding regionally specific expressions and cultural elements for adjustment.

[0677] Step 6:

[0678] The server formats translated and localized content into the appropriate format for each information distribution platform and automatically posts it at the optimal time. The posting schedule is set considering the target audience's usage times.

[0679] Step 7:

[0680] The server uses each platform's API to collect feedback data (e.g., engagement rate, clicks) after posting. This information plays a crucial role in optimizing future content strategies.

[0681] Step 8:

[0682] The server analyzes the collected feedback data and compiles the results into a report. This report is then provided to the user as a visual dashboard, which can be used to review performance and revise strategies.

[0683] (Example 1)

[0684] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0685] In today's business world, efficient information dissemination across multiple languages ​​and platforms is crucial. However, traditional methods require significant effort and resources to create and distribute content tailored to each country's language and culture. Furthermore, accurately collecting and analyzing feedback after posting is not easy. There is a need for a system that efficiently addresses these challenges and enables companies to quickly and effectively increase engagement in the global market.

[0686] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0687] In this invention, the server includes means for acquiring information from information providers, means for analyzing the information using natural language processing technology and extracting trend data and keywords, means for creating content based on the extracted trend data using generative artificial intelligence technology, means for converting the created content into multiple languages ​​and applying localization according to each region, means for setting a plan and automatically posting to multiple information distribution platforms, and means for acquiring response data for each post, analyzing it, and generating visual indicators. As a result, companies can efficiently and comprehensively disseminate information that is appropriate for the culture and language of each country, and can more effectively improve global engagement through a data-driven improvement cycle.

[0688] "Information and communication equipment" is a general term for devices that have the function of sending, receiving, and processing digital information.

[0689] "Information source" refers to the source from which digital data is transmitted or supplied.

[0690] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0691] "Generative artificial intelligence technology" refers to artificial intelligence technology that has the ability to learn from large amounts of data and generate new data.

[0692] "Trend data" refers to a collection of information or topics that have attracted significant attention within a specific time period.

[0693] A "keyword" is an important word used to characterize or summarize information or a topic.

[0694] "Localization" refers to the process of adjusting content to suit a specific region or culture.

[0695] An "information distribution platform" refers to an online platform for providing digital data to users.

[0696] "Response data" refers to data that shows users' reactions and evaluations of content.

[0697] "Visual metrics" are visualized information used to display data analysis results in a way that is easy for users to understand.

[0698] This system is implemented using information and communication equipment and efficiently performs the collection, analysis, generation, distribution, and feedback analysis of digital data. Servers, in particular, play a crucial role, and the system is structured around their functions.

[0699] First, regarding information gathering, the server retrieves data from social media and news sites that serve as information sources via APIs. In this process, common APIs such as Twitter are used to collect posts related to specific hashtags or keywords. For example, posts containing "eco-friendly" are targeted.

[0700] Next, the server applies natural language processing techniques to the collected data. Specifically, it performs text analysis and uses machine learning algorithms such as the LDA (Latent Dirichlet Allocation) model to extract trend data and keywords. As a result, currently trending topics and trends can be identified.

[0701] Subsequently, the server utilizes generative artificial intelligence technology to create new content based on the extracted data. For example, it uses OpenAI's GPT model as a generative AI model and automatically generates articles that resonate with the target audience using prompts such as, "Create an article based on the latest information on eco-friendly trends."

[0702] After the content is generated, the server translates it using a multilingual translation tool (e.g., Google Translate API) and then localizes it to suit the culture of each region. This involves adjusting it to the cultural events and customs of Japan and other countries and regions.

[0703] Finally, the server uses an information distribution infrastructure to deliver content to multiple platforms. Posting times are scheduled systematically, and content is published in an optimized format for each platform.

[0704] The feedback data collected through these processes is also analyzed by the server and provided to the user as visual indicators. The visualized dashboard allows users to view data such as engagement rates and click-through rates in real time, which can be used to improve future strategies.

[0705] In this way, companies can efficiently and effectively disseminate information in multiple languages ​​and across multiple platforms, thereby enhancing their presence in the global market.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] The server collects data from social media and news sites that serve as information sources. The input is a list of specific hashtags and keywords. Based on this input, the server retrieves relevant posts by calling the APIs of each information source. The output is a list of the collected posts. Specifically, the server checks the APIs at regular intervals to see if new data is available.

[0709] Step 2:

[0710] The server performs natural language processing on the collected post data. The input is a list of post data obtained in step 1. The server cleans this data and applies text analysis techniques to extract trend data and keywords. Techniques used include topic models (e.g., LDA models). The output is a set of extracted trend information and keywords. Specifically, the server analyzes the text data to identify frequently occurring words and themes.

[0711] Step 3:

[0712] The server generates content using a generative AI model. The input consists of trend information and keywords extracted in step 2. The server converts this information into prompt sentences and inputs them into the generative AI model. The output is the generated text content. Specifically, the server generates the prompt sentence "Create an article introducing eco-friendly products" and passes it to the AI ​​model.

[0713] Step 4:

[0714] The server translates and localizes the generated content into multiple languages. The input is the generated content obtained in step 3. The server uses a multilingual translation tool to translate the content into the languages ​​of each country. It also localizes the content to suit the local culture. The output is the translated and localized multilingual content. Specifically, for Japan, adjustments are made to match specific local festivals and events.

[0715] Step 5:

[0716] The server schedules the delivery of content. The input is content that is ready in multiple languages. The server analyzes the characteristics of each distribution platform, formats it into an optimized format, and automates posting at the optimal time for each platform. The output is the published content. Specifically, the server sets up and executes the procedure for automated posting using the API of each platform.

[0717] Step 6:

[0718] The server collects and analyzes feedback data after posting. The input is response data collected from each platform where the content was distributed. The server analyzes this data and generates visual metrics such as engagement rate and click-through rate. The output is a dashboard showing the analysis results. Specifically, the server uses an API to retrieve feedback data and visualizes it for the user in real time.

[0719] (Application Example 1)

[0720] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] Modern businesses need to deploy advertising efficiently and effectively across multiple languages ​​and platforms. However, it is difficult to respond to diverse cultures and markets, understand trends in real time, and deliver ads at the optimal time. A system is needed to solve these challenges and maximize the performance of advertising campaigns.

[0722] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0723] In this invention, the server includes means for collecting information from information sources, means for analyzing the information using natural language processing technology and extracting trend information and keywords, means for creating content based on the extracted trend information using a generative intelligence model, means for translating the created content into multiple languages ​​and making adjustments to suit each region, means for planning and automatically posting to multiple information transmission platforms, and means for collecting reaction information related to each post, analyzing it, and generating a visual report. This enables the efficient generation and distribution of multilingual and region-appropriate advertising content, and optimizes advertising strategies by performing real-time performance analysis.

[0724] An "information processing device" is a system that has the functions of collecting, analyzing, generating, and distributing information.

[0725] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0726] A "generative intelligence model" is an algorithm that automatically generates new information or content based on data.

[0727] "Trend information" refers to information that indicates current market and social changes and trends.

[0728] A "word or phrase" is a word or phrase expressed in language that has some kind of meaning.

[0729] An "information transmission infrastructure" refers to the means of communication and platforms used to deliver information to users.

[0730] "Response information" refers to data related to feedback and engagement from recipients.

[0731] A "visual report" is a report that visually represents data, providing analysis results in a way that can be intuitively understood.

[0732] To implement this invention, a server plays a primary role. The server first collects information from information sources, which include online media and social networks. Information collection is performed via APIs; for example, posts related to a specific hashtag can be retrieved from Twitter.

[0733] Next, the server analyzes the collected information using natural language processing techniques to extract trend information and important keywords. Natural language processing libraries such as spaCy and NLTK are used here. This process identifies currently trending themes and keywords.

[0734] Next, the server uses a generative intelligence model to generate new advertising content based on the extracted trend information. This generation utilizes generative artificial intelligence technology. The generated content may include, for example, catchphrases and advertising copy related to a new product.

[0735] The server then translates the generated content into multiple languages ​​and localizes it to suit each region. A standard translation API is used for this translation. During this process, adjustments are made to accommodate local culture and customs.

[0736] Furthermore, the server uses an automated scheduling function to post advertisements to multiple information transmission platforms at the optimal time. The format is adjusted according to the characteristics of each platform, and the ads are delivered at the measured optimal time.

[0737] Finally, users can receive a visual report based on the reaction information for each post collected by the server. This report graphically displays the data analysis results and helps improve advertising strategies. For example, the following prompt is used in the generating AI model: "Based on today's trends, create an advertising tagline for a refreshing new beverage."

[0738] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0739] Step 1:

[0740] The server collects information from various sources. Specifically, it uses APIs to retrieve data from social media and online news sites. The input consists of parameters and search criteria set in the API, and the output is the retrieved raw post data. This data is stored in a database for subsequent processing.

[0741] Step 2:

[0742] The server analyzes the collected data using natural language processing techniques to extract trend information and important keywords. Specifically, it uses the spaCy library to build a topic model of the data and identify currently trending themes. The input is the collected post data, and the output is the extracted topics and keywords.

[0743] Step 3:

[0744] The server uses a generative intelligence model to generate advertising content based on extracted trend information. The input consists of extracted topics and keywords, and the output is the generated advertising copy and text. The generated content is obtained by inputting prompt sentences into the generative artificial intelligence model.

[0745] Step 4:

[0746] The server translates the generated content into multiple languages ​​and localizes it to suit each region. A multilingual translation API is used for translation. The input is the generated content, and the output is the translated and localized content.

[0747] Step 5:

[0748] The server automatically posts content to each information dissemination platform according to a set schedule. The input is translated and localized content, and the output is the media posted to each platform. The optimal posting time is measured and set accordingly.

[0749] Step 6:

[0750] Users review the reaction information for each post collected by the server and receive a visual report. The input is reaction data from each platform, and the output is a visualized report including engagement rates and click-through rates. This report provides insights to improve advertising strategies.

[0751] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0752] This invention relates to a system that combines an emotion engine with an information and communication device. The system aims to recognize the user's emotions using the emotion engine and optimize content generation and distribution based on the results. The following describes embodiments for carrying out the invention.

[0753] First, the server collects data from social media and news sites. It initially uses APIs to retrieve posts related to specific keywords and stores them in a database. Next, it utilizes a sentiment engine to analyze user sentiment trends from this data. For example, it might identify a product where users have a high proportion of positive sentiment towards it.

[0754] Next, the server analyzes the data using natural language processing techniques to extract trend information and keywords. By combining this information with the results of sentiment analysis, content that is more suitable for the target user is determined. For example, content is created prioritizing topics that receive many positive responses in sentiment analysis.

[0755] Next, the server uses a generative artificial intelligence model to generate content based on extracted trend information and sentiment data. During this process, the tone and style of the content can be adjusted based on the results of the sentiment engine. For example, expressions emphasizing humor or a sense of reassurance can be incorporated.

[0756] The server then translates the generated content into multiple languages ​​and localizes it for each region. It also takes sentiment analysis into account, adjusting expressions and tones to suit different regions. For example, it might select more formal language for business users.

[0757] Next, the server posts the optimized content to the information distribution platform. The content is automatically posted at the optimal time, aiming to reach users at their peak interest. During posting, the target audience is further segmented based on sentiment data.

[0758] Finally, the server collects feedback data after posting and identifies engagement trends based on analysis by the sentiment engine. Based on these results, a report is generated and provided to the user as insights for future strategies. For example, the dashboard may display analysis results on topics that received the most emotional responses in past posts.

[0759] Through this system, companies can understand user emotions and provide content tailored to those emotions, thereby optimizing engagement with their target market.

[0760] The following describes the processing flow.

[0761] Step 1:

[0762] The server uses APIs from social media and news sites to collect new posts related to specific topics or keywords. The collected data is processed in real time and stored in a database.

[0763] Step 2:

[0764] The server filters out duplicates and spam from the collected submission data, improving data quality. At this stage, the purified data is passed on to the next processing step.

[0765] Step 3:

[0766] The server uses natural language processing techniques to extract trend information and key keywords from clean data. Specifically, it performs word frequency analysis and topic modeling to identify themes of high interest.

[0767] Step 4:

[0768] The server utilizes an emotion engine to recognize user emotions from posted data. As a result of the emotion analysis, an emotion score, such as positive or negative, is calculated, and the target user's emotional tendencies are understood based on this score.

[0769] Step 5:

[0770] The server uses an artificial intelligence model to generate content based on trend information and sentiment analysis results. The generated content is tailored to the target audience, with a tone and style that matches their emotions. For example, it might create articles using friendly language to evoke positive emotions.

[0771] Step 6:

[0772] The server translates the generated content into each language using a multilingual translation API, and then localizes it for each region. During this process, it adjusts the expression to take into account local customs and cultures.

[0773] Step 7:

[0774] The server posts translated and localized content to each information distribution platform. The posting timing is scheduled to take into account the times when users are most active.

[0775] Step 8:

[0776] The server collects feedback data after a post is published and analyzes it again using an emotion engine. This analysis identifies engagement trends and changes in user sentiment, which can then be used to inform future content strategies.

[0777] Step 9:

[0778] The server generates a report based on the aggregated feedback data and sentiment analysis results. This report is provided to users as a visual dashboard or report, and can be used as a resource to review content performance and identify areas for improvement.

[0779] (Example 2)

[0780] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0781] In today's information society, generating content that matches users' interests and emotions quickly and accurately, and delivering it across diverse information transmission platforms, is a challenging task. In particular, the lack of systems to efficiently automate the processes of multilingual support, regional optimization, and emotionally resonant content is a significant problem. Furthermore, the process of immediately analyzing user feedback after content distribution and incorporating it into future strategies is still underdeveloped, which also presents a challenge.

[0782] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0783] In this invention, the server includes means for collecting information from a data source, means for analyzing the information using natural language processing technology to extract trending topics and key words, and means for generating content based on the extracted trending topics using a generation algorithm. This makes it possible to automatically generate multilingual content that matches the user's emotions and provide it in a way that is tailored to the characteristics of each region. Furthermore, by quickly analyzing feedback after distribution and reflecting it in the next content strategy, it is possible to achieve higher user satisfaction.

[0784] An "information processing device" is a device equipped with functions for collecting and analyzing data, and for generating and transmitting necessary information.

[0785] "Data source" refers to the origin or platform from which information is obtained, and includes social media and news sites.

[0786] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and process human language.

[0787] "Trends" refer to themes or phenomena that have attracted attention within a certain period, and may include popular themes in a particular industry or field.

[0788] "Key terms" are important keywords or phrases that indicate a specific topic or content in data analysis.

[0789] A "generating algorithm" is a computational method that automatically creates new information or content from data according to specific rules or procedures.

[0790] "Multilingual translation" is the process of converting content written in one language into multiple other languages ​​to make it understandable.

[0791] "Regional optimization" refers to adjusting the content and expression to suit the culture, customs, and linguistic characteristics of each region.

[0792] An "information transmission infrastructure" is the infrastructure used to deliver generated content to users, and includes social media and websites.

[0793] "Emotion analysis technology" is a technique that extracts emotions from text and audio data and identifies the type and intensity of those emotions.

[0794] "Evaluation data" refers to information that numerically or qualitatively demonstrates the effectiveness and impact of content based on user reactions and feedback.

[0795] "Documents showing analysis results" refer to documents or reports that analyze collected evaluation data and include insights and conclusions based on that analysis.

[0796] In this invention, the information processing device is configured to enable the generation and distribution of highly accurate content that meets the user's needs. The embodiments thereof are described in detail below.

[0797] First, the server collects information from sources such as social media and news sites. Python is used for data collection, and data associated with specific keywords is retrieved through appropriate APIs. This enables real-time information gathering. The collected data is stored in a database such as PostgreSQL.

[0798] Next, the server applies natural language processing techniques to the collected data. Specifically, it analyzes the data using Python NLP libraries (such as NLTK and spaCy) to extract trends and key terms. This allows for the efficient identification of necessary keywords and topics.

[0799] Furthermore, the server uses a generative AI model (e.g., OpenAI's GPT series) to generate content based on the extracted information. The generated content is then refined using sentiment analysis technology, with its tone and style set based on the user's emotions or predicted emotions. An example of a prompt to input to the generative AI model might be, "Generate promotional content that evokes positive emotions in the user, based on the latest trending information."

[0800] The server then translates the generated content into multiple languages ​​and localizes it for each region. Translation services such as Amazon Translate and DeepL are used to translate the content into different languages. The language is optimized to suit the culture and context of each region, with adjustments such as adopting a more formal tone for business use.

[0801] Finally, the server automatically distributes the refined content to the information transmission platform. This process utilizes tools such as Buffer and Hootsuite to ensure timely posting. After distribution, feedback data is collected, analyzed again, and incorporated into the next content strategy. This entire process strengthens engagement between users and the company, enabling effective information dissemination.

[0802] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0803] Step 1:

[0804] The server collects information from data sources. Specifically, it uses Python scripts to retrieve information from social media and news sites via APIs. It collects data based on specified keywords (e.g., "new products," "popular events") as input and stores the raw text data as output in a database. During this collection process, it retrieves data using HTTP requests and handles the data in JSON format.

[0805] Step 2:

[0806] The server applies natural language processing (NLP) techniques to the collected text data. It uses previously stored raw data as input. Then, using Python NLP libraries (such as NLTK or spaCy), it performs tokenization and part-of-speech tagging to extract trending topics and key words. The output is a list of extracted keywords and trend information. This information is added to a database and used for subsequent processing.

[0807] Step 3:

[0808] The server generates content using a generative AI model. Keywords and trend information obtained in step 2 are used as input. A prompt is input to the generative AI model (e.g., the GPT series) to prompt it to generate new content. For example, using the prompt "Create a campaign proposal based on this summer's trends," the output will be a campaign proposal written in natural language.

[0809] Step 4:

[0810] The server converts the generated content into multilingual translated data and performs localization tailored to each region. The input is the content generated in step 3. Using APIs such as Amazon Translate and DeepL, it translates the content into each region's language and adjusts it to the most appropriate expression, taking cultural context into account. The output is language-specific content optimized for each region.

[0811] Step 5:

[0812] The server delivers the adjusted content to the designated information transmission platform. Multilingual translated and localized content is used as input. By utilizing distribution tools such as Buffer and Hootsuite and setting an optimal distribution schedule, the output is posted to each platform at the specified time.

[0813] Step 6:

[0814] The server collects and analyzes feedback data after delivery to inform future strategies. It uses user feedback as input. Sentiment analysis technology is employed to identify positive or negative responses, generating reports on emotional tendencies and suggestions for improvement. This contributes to improving future content strategies.

[0815] (Application Example 2)

[0816] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0817] In today's information society, providing appropriate content that aligns with consumers' emotions and interests quickly and effectively is a critical challenge for many companies. However, conventional systems lack the ability to accurately reflect user emotions in content generation and delivery, making it difficult to optimize engagement with target users. Therefore, there is a need for a method that can evaluate user emotions in real time and provide content tailored to their emotional state.

[0818] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0819] In this invention, the server includes means for collecting data from information sources and performing sentiment analysis to evaluate the user's emotions; means for analyzing the data using natural language processing technology and extracting trend information and keywords; and means for generating content based on the user's emotional state using a generative artificial intelligence model. This enables the delivery of optimal content that reflects the user's emotions.

[0820] An "information and communication device" is an electronic device used to collect, process, and analyze data, and to distribute it in an appropriate format.

[0821] "Sentiment analysis" is a technology that analyzes a user's emotional state from data and identifies emotions such as positive, negative, and neutral.

[0822] "Natural language processing technology" refers to methods for analyzing, understanding, and generating human language using computers.

[0823] "Trending information" refers to themes and keywords that are popular during a specific period, and is information of high social interest.

[0824] A "generative artificial intelligence model" is an artificial intelligence algorithm that automatically generates new content using data as input.

[0825] "Localization" is the act of adapting content to suit different regions or specific groups, taking into account multiple languages ​​and cultures.

[0826] An "information distribution platform" is an online system or service for distributing content to a wide range of users.

[0827] "Feedback data" refers to information about the evaluations and reactions that users give back to the content provided.

[0828] "User emotional state" refers to the type and intensity of emotions a user is experiencing at a particular point in time.

[0829] This system configuration consists of a server that functions as an information and communication device, collecting, processing, and analyzing data from information sources. The server collects data from social networking services (SNS) and news sites via the internet using APIs. This data is stored in a database and then sent to a sentiment analysis engine to evaluate the user's emotional state. This sentiment analysis is achieved by utilizing natural language processing technology to analyze the emotional elements of user posts and responses.

[0830] Trend information and extracted keywords are input into a generative artificial intelligence model, which then generates content. The generative AI model adjusts the style and tone of the content according to the user's emotional state, optimizing the interaction. For example, it can provide humorous content to users with many positive emotions and encouragement to those with negative emotions. The generative AI model used here is implemented using frameworks such as PyTorch and Transformers.

[0831] Next, the generated content is translated into multiple languages, and the server localizes it to suit the region and user sentiment. This ensures appropriate content delivery that reflects cultural backgrounds and linguistic nuances. Furthermore, the information distribution platform automatically posts content on an optimal schedule based on user sentiment analysis results. User feedback data after distribution is also collected and used to inform future strategies through further sentiment analysis.

[0832] For example, if a user is feeling stressed, the server can generate content recommending relaxing music or videos and deliver it to the user at a time that matches their emotions. An example of a prompt that might be used is, "Generate new content that reflects the user's current emotions!"

[0833] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0834] Step 1:

[0835] The server collects data from information sources. It uses APIs to retrieve user posts from social media and news sites and stores them in a database. This data collection is performed in real time, handling text and multimedia data collected from the information sources as input. The output is a dataset ready for use by the sentiment analysis engine.

[0836] Step 2:

[0837] The server processes data using an emotion analysis engine to evaluate the user's emotions. The input data is the posted content collected in step 1, and is analyzed using natural language processing techniques. This analysis identifies emotional states such as positive, negative, and neutral, and the output is the emotion evaluation result for each user.

[0838] Step 3:

[0839] The server analyzes the data using natural language processing to extract trend information and keywords. In this step, the server uses posts that have undergone sentiment analysis as input, summarizing the content and extracting elements of high social interest. The output is extracted trend data for use by the generative AI model.

[0840] Step 4:

[0841] The server uses a generative artificial intelligence model to generate content that responds to the user's emotional state. The input requires trend information, keywords, and user sentiment data, which the generative AI model then uses to output optimized content. This content has a tone and style that matches the user's emotions.

[0842] Step 5:

[0843] The server translates the generated content into multiple languages ​​and localizes it according to region and user sentiment. It takes the user's cultural background and linguistic needs as input to perform the translation and localization process, resulting in adjusted content as output.

[0844] Step 6:

[0845] The server posts the adjusted content to the information distribution platform. This step utilizes a pre-configured schedule and sentiment analysis results as input to automatically post at the optimal time. The output is content delivered appropriately to the user.

[0846] Step 7:

[0847] The server collects feedback data after delivery and analyzes it again using a sentiment analysis engine. The input is user response data, which is analyzed to evaluate engagement trends. The output is a report containing insights for the next delivery.

[0848] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0849] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0850] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0851] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0852] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0853] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0854] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0855] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0856] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0857] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0858] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0859] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0860] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0861] 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.

[0862] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0863] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0864] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0865] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0866] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0867] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0868] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0869] The following is further disclosed regarding the embodiments described above.

[0870] (Claim 1)

[0871] Information and communication equipment includes means for collecting data from information sources,

[0872] A means for analyzing data using natural language processing technology and extracting trend information and keywords,

[0873] A means of generating content based on extracted trend information using a generative artificial intelligence model,

[0874] A means of translating the generated content into multiple languages ​​and applying localization to each region,

[0875] A method for automatically posting to multiple information distribution platforms by setting a schedule,

[0876] A system that includes means for collecting feedback data for each post, analyzing it, and generating a report.

[0877] (Claim 2)

[0878] The system according to claim 1, wherein the information and communication device applies duplicate and spam filters to the collected posted data.

[0879] (Claim 3)

[0880] The system according to claim 1, wherein the information communication device monitors the posting status of generated content on each information distribution platform after posting, and retries when an error occurs.

[0881] "Example 1"

[0882] (Claim 1)

[0883] Information and communication equipment provides means for obtaining information from information providers,

[0884] A means for analyzing information using natural language processing technology and extracting trend data and keywords,

[0885] A means of creating content based on extracted trend data using generative artificial intelligence technology,

[0886] A means of translating the created content into multiple languages ​​and applying localization to each region,

[0887] A means of setting a plan and automatically posting to multiple information distribution platforms,

[0888] A system that includes means for acquiring response data for each post, analyzing it, and generating visual indicators.

[0889] (Claim 2)

[0890] The system according to claim 1, wherein the information and communication equipment applies duplicate and spam detection functions to the acquired posted data.

[0891] (Claim 3)

[0892] The system according to claim 1, in which information and communication equipment monitors the posting status of content on each information distribution platform after posting the created content, and retries in the event of a failure.

[0893] "Application Example 1"

[0894] (Claim 1)

[0895] An information processing device is a means of collecting information from an information source,

[0896] A means for analyzing information using natural language processing technology and extracting trend information and keywords,

[0897] A means of creating content based on extracted trend information using a generative intelligence model,

[0898] A means of translating the created content into multiple languages ​​and making adjustments to suit each region,

[0899] A means of planning and automatically posting to multiple information transmission platforms,

[0900] A system that includes means for collecting reaction information on each post, analyzing it, and generating a visual report.

[0901] (Claim 2)

[0902] The system according to claim 1, wherein a smartphone device adjusts the generated content to match the operating base and sets the optimal notification time.

[0903] (Claim 3)

[0904] The system according to claim 1, wherein a smartphone device analyzes the response rate after posting and adaptively improves the advertising strategy in order to improve the efficiency of the advertising campaign.

[0905] "Example 2 of combining an emotion engine"

[0906] (Claim 1)

[0907] An information processing device includes means for collecting information from a data source,

[0908] A means for analyzing information using natural language processing technology and extracting trending topics and key words,

[0909] A means for generating content based on extracted trending topics using a generation algorithm,

[0910] A means of translating the generated content into multiple languages ​​and optimizing it according to each region,

[0911] A means of setting a plan and automatically posting to multiple information transmission platforms,

[0912] A means of identifying the user's emotions using emotion analysis technology and adjusting the tone and style of the generated content,

[0913] A system that includes means for collecting evaluation data for each post, analyzing it, and generating materials that show the analysis results.

[0914] (Claim 2)

[0915] The system according to claim 1, wherein the information processing device removes duplicate and fraudulent information from the collected information data.

[0916] (Claim 3)

[0917] The system according to claim 1, wherein the information processing device monitors the transmission status of each information transmission infrastructure after posting the generated content and retries in the event of a failure.

[0918] "Application example 2 when combining with an emotional engine"

[0919] (Claim 1)

[0920] An information and communication device collects data from information sources and performs sentiment analysis to evaluate the user's emotions,

[0921] A means for analyzing data using natural language processing technology and extracting trend information and keywords,

[0922] A means of generating content based on the user's emotional state using a generative artificial intelligence model,

[0923] A means of translating the generated content into multiple languages ​​and applying localization that is appropriate for each region and user's sentiment,

[0924] A means of automatically posting to multiple information distribution platforms based on user sentiment analysis results,

[0925] A system that includes means for collecting feedback data for each post and generating a report based on the results of analysis by an emotion engine.

[0926] (Claim 2)

[0927] The system according to claim 1, wherein the information and communication device applies duplicate and spam filters to the collected posted data.

[0928] (Claim 3)

[0929] The system according to claim 1, wherein the information and communication device monitors the posting status of generated content on each information distribution platform after posting, retries when an error occurs, and optimizes reposting based on the results of user sentiment analysis. [Explanation of symbols]

[0930] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information and communication equipment includes means for collecting data from information sources, A means for analyzing data using natural language processing technology and extracting trend information and keywords, A means of generating content based on extracted trend information using a generative artificial intelligence model, A means of translating the generated content into multiple languages ​​and applying localization to each region, A method for automatically posting to multiple information distribution platforms by setting a schedule, A system that includes means for collecting feedback data for each post, analyzing it, and generating a report.

2. The system according to claim 1, wherein the information and communication device applies duplicate and spam filters to the collected posted data.

3. The system according to claim 1, wherein the information communication device monitors the posting status of generated content on each information distribution platform after posting, and retries when an error occurs.

Images