system

Abstract

We provide the system. [Solution] A means of accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods, A means for inputting collected message information into an analysis engine and generating prompts to identify trend information, A means of obtaining trend information returned from the analysis engine and outputting that trend information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern digital society, social media is an important source of information. However, due to the large amount of information flowing in real - time, it is difficult to quickly and accurately extract useful trend information from it. Also, conventional methods require a great deal of time and effort for information collection and analysis, and there is a problem of lacking immediacy. For this reason, there is a demand for a system that news agencies and research institutions can obtain trend information in real - time.

Means for Solving the Problems

[0005] The present invention solves the above problem with a system that includes means for accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods, means for inputting the collected message information into an analysis engine and generating prompts for identifying trend information, and means for obtaining the trend information returned from the analysis engine and outputting that trend information. Furthermore, by converting the collected message information into JSON format and passing the prompts to the analysis engine for analyzing the trend information, and by having the analysis engine perform natural language processing, it becomes possible to extract useful trend information quickly and accurately in real time.

[0006] "Authentication information" refers to authentication data required to grant access to a specific system or service.

[0007] A "social media API" refers to an interface provided by a social media platform that allows external applications to access its data and functions.

[0008] "Message information" refers to content such as text, images, and videos posted by users on social media.

[0009] An "analysis engine" refers to an algorithm or program used to analyze collected data and extract or generate specific information.

[0010] A "prompt" refers to input data or commands used to give instructions to the analysis engine.

[0011] "Trending information" refers to content or themes that are particularly popular on social media within a specified period.

[0012] "JSON format" is an abbreviation for JavaScript® Object Notation, and refers to a lightweight, text-based format for structuring, storing, and exchanging data.

[0013] "Natural language processing" refers to the field of technology that uses computers to analyze, understand, and generate human language. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

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

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

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

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. Specific embodiments of this invention are described in detail below.

[0036] 1. Setting up authentication information

[0037] The server first configures the authentication credentials for accessing the social media API. These credentials are for accessing a specific social media platform and consist of API keys, tokens, and other information provided by each platform.

[0038] 2. Setting Keywords and Time Period

[0039] The device retrieves keywords and a survey period specified by the user. Typically, keywords are tags or specific phrases, and the period is often set to the past day or several days.

[0040] 3. Collection of message information

[0041] The server uses social media APIs to collect message information based on specified keywords and time periods. In this step, social media post data is collected via API calls. The collected message information is stored in text format.

[0042] 4. Message Information Conversion

[0043] The server converts the collected message information into JSON format. This is because JSON format is suitable for structuring data and passing it to the analysis engine.

[0044] 5. Prompt generation

[0045] The server uses the message information, converted into JSON format, to generate a prompt for the analysis engine. The prompt might take the form of, for example, "Analyze the following message information and summarize the trends."

[0046] 6. Trend Analysis

[0047] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it analyzes the collected social media posts to identify frequently occurring themes and topics.

[0048] 7. Acquisition and Output of Trend Information

[0049] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user. It is also distributed to multiple subscriber clients (e.g., news organizations and research institutions) as needed. Distribution methods include email, web application dashboards, and API endpoints.

[0050] Specific example

[0051] For example, if the keyword "AI" is set and social media data from the past day is collected, the server will collect tweets related to "AI". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". As a result of the analysis, trend information is obtained such as "The main topics related to AI recently are advancements in medical technology and future technologies". This information is provided to news organizations and research institutions through the server.

[0052] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trending information on social media and the provision of information in real time.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] The server configures the authentication credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information to perform the authentication process enables the use of the social media API.

[0056] Step 2:

[0057] The device receives specific keywords and time period settings from the user. These keywords are strings representing specific topics or subjects on social media, and the time period refers to any date range in the past. This information is entered by the user through the device's interface.

[0058] Step 3:

[0059] The server uses social media APIs to collect relevant message information based on configured keywords and time periods. The server makes API calls to retrieve posts that match the specified conditions, including metadata such as the post's text, author, and posting date and time.

[0060] Step 4:

[0061] The server converts the collected message information into JSON format. JSON is widely used to represent data structures and is suitable for efficient data processing by the parsing engine. The conversion results are stored in memory or a file.

[0062] Step 5:

[0063] The server uses message information stored in JSON format to generate a prompt to pass to the analysis engine. This prompt is text data that instructs the analysis engine on what kind of analysis to perform. Specifically, it might say something like, "Analyze the following tweets and extract trend information."

[0064] Step 6:

[0065] The server sends the generated prompt to the analysis engine. The analysis engine performs analysis based on the prompt, for example, using natural language processing techniques. This includes topic analysis of the collected message information and extraction of frequently occurring words.

[0066] Step 7:

[0067] The server retrieves trend information returned from the analysis engine. The analysis results include summarized information indicating which themes and topics are receiving particular attention. This information is then organized on the server into a format suitable for storage, analysis, and display.

[0068] Step 8:

[0069] The server displays the acquired trend information on the user's device. This information can be displayed via a web dashboard, a mobile application, or a dedicated software interface. Through this, users can understand currently trending topics and issues.

[0070] Step 9:

[0071] The server distributes trend information to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, or file uploads to an FTP server. This ensures that real-time trend information is widely available.

[0072] (Example 1)

[0073] 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."

[0074] With the increasing sharing of information on social media, there is a growing need to quickly and efficiently collect and analyze message information based on specific keywords and timeframes. However, traditional methods require considerable time and effort to structure the collected information and compile it into trending data. This makes it difficult to provide information in real time.

[0075] 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.

[0076] In this invention, the server includes means for accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods; means for converting the collected message information into JSON format; means for generating prompts for an analysis engine using the message information converted into JSON format; means for passing the generated prompts to the analysis engine and analyzing trend information; and means for obtaining the trend information returned from the analysis engine and outputting that trend information. This enables the rapid and efficient collection and analysis of information on social media, thereby providing real-time trend information.

[0077] "Authentication information" refers to information such as API keys and tokens required to access social media APIs.

[0078] A "social media API" is an interface provided by a social media platform that allows external applications and services to access the platform's data and functions.

[0079] A "keyword" is a specific hashtag or phrase designated by the user and is used to collect specific information from posts on social media.

[0080] "Period" refers to a specific time range specified by the user, and the collection of information is limited to social media posts within that range.

[0081] "Message information" refers to text data and posts collected on social media.

[0082] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a lightweight data exchange format for structuring, storing, and transmitting data.

[0083] An "analysis engine" is software or an algorithm used to analyze collected data and extract specific patterns or trends.

[0084] A "prompt" is an instruction or query used to give instructions to an analysis engine for analysis.

[0085] "Trend information" refers to information extracted by an analysis engine that shows frequently occurring patterns and tendencies related to a specific topic or theme.

[0086] "Output means" refers to methods or devices for displaying or providing analyzed trend information to users or other systems.

[0087] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. This system makes it possible to quickly and efficiently acquire trend information on social media and provide it to users in real time.

[0088] 1. Setting up authentication information

[0089] The server first configures the authentication credentials for accessing the social media APIs. These credentials consist of API keys, tokens, etc., and are configured based on the API documentation of each social media platform. The server uses these credentials to securely access the APIs.

[0090] 2. Setting Keywords and Time Period

[0091] The terminal retrieves keywords and a survey period specified by the user. Users enter keywords and a period through input fields in web forms or applications. This input data is sent from the terminal to the server.

[0092] 3. Collection of message information

[0093] The server uses social media APIs to collect message information based on specified keywords and time periods. By calling the search APIs of social media platforms, relevant post data is retrieved in text format. This allows for the collection of a vast amount of post data in real time.

[0094] 4. Message Information Conversion

[0095] The server converts the collected message information into JSON format. JSON format is suitable for structuring and storing data, and can be easily handled as input for parsing engines. The converted data is temporarily stored.

[0096] 5. Prompt generation

[0097] The server uses the message information, converted to JSON format, to generate a prompt for the parsing engine. The prompt contains instructions for the parsing engine and takes the following format:

[0098] "Analyze the following message information and summarize the trends."

[0099] 6. Trend Analysis

[0100] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from the posted content and generate trend information.

[0101] 7. Acquisition and Output of Trend Information

[0102] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via the terminal. Furthermore, it is distributed to multiple subscriber clients (e.g., news organizations and research institutions) via email or API endpoints as needed.

[0103] Specific example

[0104] For example, if a user sets "AI" as a keyword and specifies the time period as the past day, the server will collect tweets related to "AI". These tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". An example of a specific prompt would be:

[0105] "Analyze the following message information and summarize the trends."

[0106] The analysis results in trend information indicating that "the main topics related to AI recently are advancements in medical technology and future technologies." This information is provided to news organizations and research institutions via a server.

[0107] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0108] Step 1:

[0109] The server configures the authentication credentials for accessing social media APIs. Authentication credentials, such as API keys and tokens, are stored securely and used when accessing the API. Specifically, the server reads a configuration file containing the stored credentials and uses that information to make API requests. Authentication credentials are required as input, and authenticated API access is obtained as output.

[0110] Step 2:

[0111] The terminal retrieves keywords and a survey period specified by the user. The user enters the keywords and period using a web form or application input field. The entered data is sent from the terminal to the server. The user-specified keywords and period are required as input, and this information is passed to the server as output.

[0112] Step 3:

[0113] The server uses social media APIs to collect message information based on specified keywords and time periods. It calls social media search APIs to retrieve relevant post data in text format. Keywords and time periods are required as input, and relevant message information is obtained as output. Specifically, it makes API calls and saves the results to an internal database or file system.

[0114] Step 4:

[0115] The server converts the collected message information into JSON format. JSON format is an efficient way to structure data and is suitable as input for the parsing engine. The collected message information is required as input, and the output is data in JSON format. Specifically, the raw text data is converted into a JSON object and temporarily stored.

[0116] Step 5:

[0117] The server generates a prompt for the parsing engine using message information converted to JSON format. The prompt instructs the parsing engine on what processing to perform. JSON format message information is required as input, and the prompt is obtained as output. Specifically, the server incorporates the message information into the prompt statement, preparing it for transmission to the parsing engine.

[0118] Step 6:

[0119] The analysis engine performs natural language processing based on prompts provided by the server to analyze trend information. A prompt is required as input, and the analyzed trend information is obtained as output. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from message information.

[0120] Step 7:

[0121] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via their terminal. Furthermore, it is distributed to news organizations and research institutions via email or API endpoints as needed. The server requires trend information from the analysis engine as input and provides information to users and subscribers as output. Specific actions include displaying the information on a dashboard, sending emails, and making API calls.

[0122] (Application Example 1)

[0123] 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."

[0124] Traditional advertising analytics systems struggled to grasp market reactions in real time, making immediate optimization of advertising campaigns difficult. Furthermore, data collection and analysis from social networking services were cumbersome, lacking the means to quickly develop effective advertising strategies. This hindered the maximization of advertising effectiveness.

[0125] 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.

[0126] This invention includes a server that accesses a social networking service API using authentication information and collects text information based on specified search words and time periods; a server that inputs the collected text information into an analysis device and generates a generative AI model prompt for identifying trend information; a server that retrieves the trend information returned from the analysis device and outputs that trend information; and a server that grasps market reactions in real time and optimizes advertising content. This enables advertisers to immediately grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[0127] "Authentication information" refers to a collection of information used to ensure security, such as access keys and tokens, for accessing social networking service APIs.

[0128] A "Social Networking Service API" is an application programming interface for programmatically retrieving user-generated data, profile information, and other data from a specified platform.

[0129] "Search terms" refer to keywords or hashtags related to a specific topic or theme, and are the criteria used to collect data from social networking services.

[0130] "Period" refers to the time frame for data collection, specifying a time range such as the past hour, day, or week.

[0131] "Text information" refers to character data such as messages, posts, and comments collected from social networking services.

[0132] An "analysis device" is a computer device used to analyze collected data and derive specific meanings or trends.

[0133] A "generated AI model prompt" is a specific instruction given when inputting collected data into an analysis device, and it specifies the input data required to perform a particular task.

[0134] "Trend information" refers to important themes and trends derived from collected and analyzed data, and is used in marketing and advertising strategies.

[0135] "Real-time" refers to a situation where data collection, analysis, and output occur almost instantly, meaning that the latest information is provided without delay.

[0136] "Optimization" refers to the process of adjusting and modifying advertising content and strategies based on data to achieve maximum effectiveness.

[0137] System Configuration

[0138] This invention is a system for collecting and analyzing advertising-related trend information in real time from specific social networking services and for quickly understanding market reactions based on the results. This system consists of three main components: a server, a terminal, and a user.

[0139] Hardware and software

[0140] Hardware: Servers are high-performance computer devices used for data collection and analysis. Smartphones, tablets, and PCs are used as user terminals. For analysis, computing resources are needed to run generative AI models such as GPT-3 (registered trademark).

[0141] Software: Data collection, transformation, and analysis are performed using Python and other programming languages. Specifically, the requests library and natural language processing libraries are used.

[0142] Data flow

[0143] 1. Setting up authentication information

[0144] The server first configures the authentication credentials for accessing the social networking service API. These credentials include security information such as API keys and tokens.

[0145] 2. Setting Keywords and Time Period

[0146] The user enters a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their device. This information is sent to the server and configured.

[0147] 3. Collection of text information

[0148] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. The collected text information is stored on the server in text format.

[0149] 4. Message Information Conversion

[0150] The server converts the collected text information into JSON format before passing it to the analysis device (generating AI model). The JSON format makes it easy to structure data and allows for efficient analysis.

[0151] 5. Generating AI Model Prompts

[0152] Based on the text information converted to JSON format, the server generates a prompt message that reads, "Analyze the following message information and summarize the trends related to advertising."

[0153] 6. Analysis of trend information

[0154] The server passes the generated prompt messages to the analysis device, which uses a generation AI model to analyze trend information. This allows for the identification of frequently occurring themes and topics.

[0155] 7. Acquisition and Output of Trend Information

[0156] The server retrieves trend information returned from the analysis device and outputs this information to the user. Output methods include displaying a dashboard, email notifications, and generating reports. It also provides means to understand market reactions in real time and optimize advertising content.

[0157] Specific example

[0158] For example, if a user sets the search term "new products" and requests data for the past day, the server will collect posts related to "new products." After collection, these posts are converted to JSON format, and a prompt message like the following is generated:

[0159] "Analyze the following message information and summarize the advertising-related trends: {Message data in JSON format}"

[0160] The generative AI model analyzes this data and generates trend information, such as "Recent key topics regarding new products are environmentally friendly packaging and the adoption of new technologies." This information is then displayed to the user via the server.

[0161] This allows advertisers to instantly grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[0162] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0163] Step 1:

[0164] The server configures the authentication information (API key and token) for accessing the social networking service API. It receives the authentication information as input and uses it to establish a session for the API connection. The output of this step indicates that the API connection has been established.

[0165] Step 2:

[0166] The user inputs a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their terminal. This input is sent to the server and saved as settings for analysis. The input consists of the search term and period, and the output is the configured analysis parameters.

[0167] Step 3:

[0168] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. It makes API calls to retrieve the corresponding post data. The input is the authentication credentials and parsing parameters, and the output is the collected text information.

[0169] Step 4:

[0170] The server converts the collected text information into JSON format before passing it to the analysis device. This structures the data, allowing for more efficient analysis. The input is the collected text information, and the output is data in JSON format.

[0171] Step 5:

[0172] The server generates a prompt message based on the text information converted to JSON format, which reads, "Analyze the following message information and summarize the trends related to advertising." The prompt message is an instruction to the parser. The input is text information in JSON format, and the output is the generated prompt message.

[0173] Step 6:

[0174] The server passes the generated prompt sentences to the analysis device (generating AI model) for analysis. Based on the prompt sentences, the analysis device identifies frequently occurring themes and trends from the data. The input consists of prompt sentences and text information in JSON format, and the output is trend information.

[0175] Step 7:

[0176] The server retrieves trend information returned from the analysis device and outputs this information to the user. This information is provided to the user through methods such as dashboard display, email notifications, and report generation. The input is trend information, and the output is the presentation of information to the user. It also includes means for understanding market reactions in real time and optimizing advertising content.

[0177] By following these steps, advertisers can instantly grasp market reactions in real time and quickly plan and execute the optimal advertising strategy.

[0178] 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.

[0179] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, and analyzes trend information and user sentiment data using a sentiment engine. Specific embodiments of this invention are described in detail below.

[0180] 1. Setting up authentication information

[0181] The server configures the authentication credentials for accessing social media APIs. These credentials include API keys, API secrets, access tokens, and access token secrets. Using this information, the server successfully authenticates to the social media platform.

[0182] 2. Setting Keywords and Time Period

[0183] The device receives specific keywords and a research period from the user. These keywords represent specific topics or subjects gaining attention on social media, and the research period refers to any date range in the past. The user enters this information through the device's interface.

[0184] 3. Collection of message information

[0185] The server uses social media APIs to collect relevant message information based on the configured keywords and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[0186] 4. Message Information Conversion

[0187] The server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[0188] 5. Prompt generation and analysis request

[0189] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how, and takes the form of "analyze the following messages and extract trend information."

[0190] 6. Analysis of trend information

[0191] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[0192] 7. Analysis of emotional data

[0193] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotional data.

[0194] 8. Acquisition and output of trend information and sentiment data

[0195] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is integrated and provided to the user. The information is also displayed through a dashboard and a dedicated application interface.

[0196] 9. Distribution of trend information and sentiment data

[0197] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[0198] Specific example

[0199] For example, if the keyword "ClimateChange" is set and social media data for the past day is collected, the server will collect tweets related to "ClimateChange". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this and generates trend information such as "Recent major topics related to ClimateChange show increased public interest in policy changes." At the same time, the sentiment engine analyzes sentiment data and obtains information such as "Many users are expressing anger towards policy changes." This trend information and sentiment data are provided to news organizations and research institutions through the server.

[0200] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trend information and user sentiment data from social media, and the provision of information in real time.

[0201] The following describes the processing flow.

[0202] Step 1:

[0203] The server configures the credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information, the server performs an authentication process against the social media platform. Upon successful authentication, access to the API endpoint is granted.

[0204] Step 2:

[0205] The device receives specific keywords and survey period settings from the user. These keywords are strings of characters that indicate specific topics or subjects gaining attention on social media. The survey period specifies an arbitrary date range, such as the past 1 to 7 days. The user enters this information through the device's user interface.

[0206] Step 3:

[0207] The server calls social media APIs based on configured keywords and time periods to collect relevant message information. The API calls retrieve posts that match the specified criteria. During this process, metadata such as the post text, author, posting date and time, and the number of retweets and likes are also collected.

[0208] Step 4:

[0209] The server converts the collected message information into JSON format. This conversion simplifies data structuring and makes the data suitable for passing to the analysis engine. The modified data is stored in memory or a database.

[0210] Step 5:

[0211] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on how to analyze the specified data, and takes the form of "Analyze the following message and extract trend information."

[0212] Step 6:

[0213] The server sends data, including the generated prompts, to the analysis engine. The analysis engine uses natural language processing techniques to perform data analysis based on the prompts. Specifically, it identifies frequently occurring words, phrases, themes, or topics from the collected social media posts and extracts trend information.

[0214] Step 7:

[0215] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine uses text analysis techniques to identify the emotion in the message, classifying it into emotions such as joy, sadness, and anger. It then outputs the emotional state for each message as numerical data or tags.

[0216] Step 8:

[0217] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is appropriately formatted and prepared for user presentation. Possible output formats include reports and dashboards.

[0218] Step 9:

[0219] The server displays acquired trend information and sentiment data on the terminal. Through the terminal's interface, users can access the information in real time. Based on the information provided, users can understand currently trending topics and their own sentiment towards them.

[0220] Step 10:

[0221] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, a web dashboard, or file uploads to an FTP server. This makes the analysis results widely available.

[0222] Specific example

[0223] For example, consider a scenario where social media data for the past day is collected using the keyword "ClimateChange." The server collects relevant tweets and converts them into JSON format. Then, an analysis engine generates trend information such as, "The main topic related to ClimateChange recently is the growing public interest in policy changes." Simultaneously, a sentiment engine analyzes sentiment data such as, "Many users are expressing anger towards policy changes." This information is integrated and distributed in real time to news organizations and research institutions via the server.

[0224] (Example 2)

[0225] 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".

[0226] Conventional systems have struggled to efficiently and immediately integrate and provide trend information and sentiment data when analyzing information collected from online platforms such as social media. Furthermore, inconsistencies in data structuring, generation of analysis instructions, and distribution methods of analysis results have sometimes hindered real-time information provision.

[0227] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention,

[0228] The server has means to access the online platform API using authentication information and to collect communication information based on specified search terms and time ranges.

[0229] A means for inputting collected communication information into an analysis device and generating instruction sentences to identify trend information,

[0230] A means for acquiring trend information returned from an analysis device and outputting that trend information,

[0231] A means of inputting collected communication information into an emotion analysis device and analyzing the user's emotional data,

[0232] A means for integrating trend information and emotional data acquired from an analysis device and an emotion analysis device,

[0233] A means of providing integrated information to users and distributing it to information recipients,

[0234] This includes the ability to efficiently analyze collected communication information and immediately integrate and provide trend information and sentiment data.

[0235] "Authentication information" refers to the identification information required to access online platform APIs, and includes API keys, API secrets, access tokens, and access token secrets.

[0236] An "online platform API" is a programmatic interface for accessing specific functions or data provided by social media and other internet services.

[0237] A "search term" is a word or phrase specified to search for specific information on an online platform.

[0238] "Time range" refers to the period over which information collected on an online platform is collected, and can include any date range in the past.

[0239] "Communication information" refers to data such as messages, posts, and comments collected from online platforms, as well as their metadata.

[0240] An "analysis device" is a device or software used to analyze collected communication information and identify trend information, employing technologies such as natural language processing.

[0241] "Trend information" refers to information based on the frequency and relevance of topics and themes on online platforms, as identified by analytical tools.

[0242] An "instruction document" is a document or format that shows the analysis device how to analyze the collected communication information.

[0243] An "emotion analysis device" is a device or software that analyzes a user's emotions from text communication information and generates emotional data.

[0244] "Emotional data" refers to information about the type and intensity of emotions contained in text, generated by an emotion analysis device.

[0245] "Integration" refers to the process of combining trend information and emotional data obtained from analysis devices and emotion analysis devices into a single, consistent set of information.

[0246] "Information recipients" refers to news organizations, research institutions, and other groups that have subscribed to receive the analysis results.

[0247] This invention relates to a system that utilizes an online platform API to collect communication information based on specified search terms and time ranges, and analyzes trend information and user sentiment data using an analysis device and a sentiment analysis device. Specific embodiments of the present invention are described below.

[0248] Authentication information settings (server)

[0249] The server configures the authentication credentials for accessing the online platform API. These credentials include the API key, API secret, access token, and access token secret. The server uses this information to successfully authenticate to the online platform.

[0250] Setting keywords and time periods (device)

[0251] The terminal receives specific search terms and a search period from the user. The user enters the search term "ClimateChange" and the search period "Past 1 day" through the terminal's interface. The terminal receives this information and sends it to the server for the next processing.

[0252] Collection of communication information (server)

[0253] The server collects relevant communication information using the online platform API based on the configured search terms and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[0254] Conversion of communication information (server)

[0255] The server converts the collected communication information into a structured data format (e.g., JSON format). This improves the efficiency of data structuring and analysis.

[0256] Prompt generation and parsing request (server)

[0257] The server generates prompt statements to pass to the analysis device based on the communication information converted into JSON format. These prompt statements instruct the analysis device on which data to analyze and how. For example, the following prompt statements are generated:

[0258] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[0259] The server sends the generated prompt message to the analysis device and requests analysis.

[0260] Analysis of trend information (analysis device)

[0261] The analysis device uses natural language processing techniques to analyze trend information based on prompt messages received from the server. For example, the analysis device identifies frequently occurring themes and topics from the collected communication information and generates trend information such as "interest in policy changes is increasing."

[0262] Analysis of emotional data (emotion analysis device)

[0263] The server passes the collected communication information to an emotion analysis device, which analyzes the users' emotional data. The emotion analysis device classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text of the communication information and generates emotional data such as "Many users are showing anger towards the policy change."

[0264] Acquisition and output of trend information and sentiment data (server)

[0265] The server acquires trend information returned from the analysis device and sentiment data obtained from the sentiment analysis device, and integrates this data. The integrated information is provided to the user through a dashboard or dedicated application interface.

[0266] Distribution of trend information and sentiment data (server)

[0267] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[0268] Specifically, the process is carried out as follows: When the user enters the search term "ClimateChange" and the time period "Past 1 day" through the terminal interface, the server generates an API request and collects relevant data from the online platform. The collected data is converted into a structured data format, and a prompt message like the following is generated and sent to the analysis device:

[0269] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[0270] The analysis device analyzes trend information, and the sentiment analysis device generates sentiment data. The server integrates this information and distributes it to news organizations and research institutions.

[0271] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0272] Step 1:

[0273] The server reads authentication information such as API keys, API secrets, access tokens, and access token secrets from configuration files and databases, and issues authentication requests to the online platform API. This allows it to obtain an authentication token for accessing the online platform. The authentication information is used as input, and the authentication token is output.

[0274] Step 2:

[0275] The terminal receives specific search terms (e.g., "ClimateChange") and a search period (e.g., "Past 1 day") from the user. The user inputs this information through the interface, and the terminal receives it and sends it to the server. The input consists of the search terms and the search period, which are then output as a request to the server.

[0276] Step 3:

[0277] The server generates a request to the online platform API based on the search terms and research period received from the terminal. The generated request is constructed to include the search terms and research period as query parameters. This is output as an API request and sent to the online platform.

[0278] Step 4:

[0279] The server receives communication information collected from the online platform API. This communication information includes metadata such as the post text, author, and posting date and time. The response from the API is used as input data, and this is output as communication information.

[0280] Step 5:

[0281] The server converts the collected communication information into a structured data format (e.g., JSON format). This enables data structuring and more efficient analysis. The input is unstructured communication information, and the output is data in JSON format.

[0282] Step 6:

[0283] Based on the structured communication information, the server generates a prompt sentence for passing to the analysis device. The prompt sentence contains specific analysis requirements (e.g., "Analyze the following message and extract trend information. Identify the latest topics related to 'ClimateChange'."). The input is communication information in JSON format, and the output is the prompt sentence.

[0284] Step 7:

[0285] The server sends the generated prompt sentence and JSON data to the analysis device to request the analysis of trend information. The input is the prompt sentence and JSON data, and the output is the request for the analysis request.

[0286] Step 8:

[0287] Based on the prompt sentence received from the server, the analysis device uses natural language processing technology to extract trend information. For example, it generates information such as "Interest in policy changes is increasing." The input is the prompt sentence and JSON data, and the output is the trend information.

[0288] Step 9:

[0289] The server obtains the trend information returned by the analysis device. At the same time, it passes the communication information to the sentiment analysis device and requests the analysis of sentiment data. The input is the trend information and communication information, and the output is the request for sentiment data analysis.

[0290] Step 10:

[0291] The emotion analysis device analyzes the text of communication information and classifies the type of emotion (e.g., joy, sadness, anger). For example, it might generate information such as "Many users are expressing anger towards the policy change." The input is the text of the communication information, and the output is emotion data.

[0292] Step 11:

[0293] The server integrates trend information returned from the analysis device and sentiment data acquired from the sentiment analysis device. The input is trend information and sentiment data, and the output is the integrated information.

[0294] Step 12:

[0295] The server provides integrated information to users through dashboards and dedicated application interfaces. The information is displayed visually, making it easily accessible to users. The input is integrated information, and the output is data displayed to the user.

[0296] Step 13:

[0297] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Information is distributed via dedicated APIs, email notifications, and file uploads to an FTP server. The input is integrated information, and the output is distributed data.

[0298] (Application Example 2)

[0299] 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 device 14 will be referred to as the "terminal."

[0300] Traditional advertising delivery systems have struggled to grasp user interests and emotions in real time, making it difficult to deliver effective advertisements. Furthermore, advertising based on trend information and sentiment data is rarely used, highlighting the need for methods that maximize advertising effectiveness.

[0301] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing a social media API using authentication information and collecting message information based on a specified keyword and period, means for inputting the collected message information into an analysis engine and generating a prompt for identifying trend information, and means for acquiring the trend information and sentiment data returned from the analysis engine and displaying advertisement information using that data. Thereby, real-time advertisement distribution based on trend information and sentiment data becomes possible.

[0302] "Authentication information" refers to information such as an API key, API secret, access token, access token secret, etc. necessary for accessing a social media API.

[0303] "Social media API" refers to a program interface provided by a social media platform, which refers to the function that an external application can use to access data on the social media.

[0304] "Keyword" refers to a term indicating a specific topic or subject matter that is attracting attention on social media.

[0305] "Period" refers to an arbitrary date range in the past for which data is to be collected.

[0306] "Message information" refers to data such as posts, posters, posting dates and times, etc. on social media.

[0307] "Analysis engine" refers to a system using natural language processing technology for identifying trend information based on the collected message information.

[0308] "Prompt" refers to an instruction text for instructing the analysis engine on what data to analyze and how to analyze it.

[0309] "Trend information" refers to information that indicates frequently occurring themes and topics extracted from collected social media posts.

[0310] "Emotional data" refers to information extracted from social media messages that indicates a user's emotional state (e.g., joy, sadness, anger, etc.).

[0311] "Advertising information" refers to the content of advertisements displayed to users, and is generated based on trend information and sentiment data.

[0312] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, analyzes trend information and user sentiment data using an analysis engine, and uses that data to display optimal advertisements.

[0313] First, the server configures the authentication credentials (API key, API secret, access token, and access token secret) for accessing the social media API. These credentials are crucial for successful authentication to the social media platform.

[0314] Next, the device receives specific keywords and a search period from the user. For example, if the user sets the keyword "ClimateChange" and the time period to the past day, this information will indicate specific topics that are trending on social media.

[0315] Based on its configuration, the server uses social media APIs to collect relevant message information. This step includes information such as the post text, the poster, and the date and time of posting.

[0316] Next, the server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[0317] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how. For example, it might say, "Analyze the following messages and extract trend information."

[0318] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[0319] Next, the server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotion data.

[0320] The server then integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine and provides it to the user. It also includes means of displaying optimal advertisements using this data. For example, it might display an advertisement using trend information such as "A major topic regarding recent ClimateChange is the growing public interest in policy changes" and sentiment data such as "Many users are expressing anger towards policy changes."

[0321] Examples of prompt statements used include the following:

[0322] "Please analyze the following text data to extract trend information and sentiment."

[0323] [

[0324] {"text": "Climate change is real and urgent!", "user": "user1", "date": "2023-10-01 12:00:00"},

[0325] ...

[0326] ]

[0327] This system enables the rapid and accurate acquisition of trending information and user sentiment data from social media, allowing for real-time information delivery. Furthermore, by displaying advertising information based on the analysis results, it maximizes advertising effectiveness.

[0328] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0329] Step 1:

[0330] The server configures the credentials for accessing the social media API. Specifically, it uses credentials including the API key, API secret, access token, and access token secret to successfully authenticate to the social media platform. The input for this step is the credentials, and the output is a state where the social media API is accessible.

[0331] Step 2:

[0332] The terminal receives specific keywords and a survey period from the user. The user enters keywords (e.g., ClimateChange) and a period (e.g., the past day) through the terminal's interface. This information is used as the basis for data collection. The input for this step is the keywords and period entered by the user, and the output is the keyword and period settings.

[0333] Step 3:

[0334] The server collects relevant message information using social media APIs based on the configured keywords and time period. It retrieves metadata such as post text, author, and posting date and time from social media platforms. The input for this step is the keyword and time period settings, and the output is the collected message information.

[0335] Step 4:

[0336] The server converts the collected message information into JSON format. Using JSON format streamlines data structuring and analysis. The input for this step is the collected message information, and the output is data in JSON format.

[0337] Step 5:

[0338] The server generates a prompt to pass to the analysis engine based on the message information converted to JSON format. It creates a prompt statement and prepares it for passing to the analysis engine. Specifically, it generates an instruction statement in the format of "Analyze the following message and extract trend information." The input for this step is data in JSON format, and the output is the generated prompt statement.

[0339] Step 6:

[0340] The server passes the prompt message to the analysis engine, which then analyzes the trend information. The analysis engine uses natural language processing techniques to identify frequently occurring themes and topics from the collected social media posts. The input for this step is the generated prompt message, and the output is the identified trend information.

[0341] Step 7:

[0342] The server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text and generates emotion data. The input for this step is message information, and the output is emotion data.

[0343] Step 8:

[0344] The server integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. It then provides this information to the user through a means of displaying advertising information. For example, it selects and displays the most suitable advertisement based on the trend information and sentiment data. The input for this step is trend information and sentiment data, and the output is the display of the most suitable advertising information.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] [Second Embodiment]

[0349] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0350] 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.

[0351] 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).

[0352] 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.

[0353] 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.

[0354] 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).

[0355] 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.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] 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".

[0361] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. Specific embodiments of this invention are described in detail below.

[0362] 1. Setting up authentication information

[0363] The server first configures the authentication credentials for accessing the social media API. These credentials are for accessing a specific social media platform and consist of API keys, tokens, and other information provided by each platform.

[0364] 2. Setting Keywords and Time Period

[0365] The device retrieves keywords and a survey period specified by the user. Typically, keywords are tags or specific phrases, and the period is often set to the past day or several days.

[0366] 3. Collection of message information

[0367] The server uses social media APIs to collect message information based on specified keywords and time periods. In this step, social media post data is collected via API calls. The collected message information is stored in text format.

[0368] 4. Message Information Conversion

[0369] The server converts the collected message information into JSON format. This is because JSON format is suitable for structuring data and passing it to the analysis engine.

[0370] 5. Prompt generation

[0371] The server uses the message information, converted into JSON format, to generate a prompt for the analysis engine. The prompt might take the form of, for example, "Analyze the following message information and summarize the trends."

[0372] 6. Trend Analysis

[0373] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it analyzes the collected social media posts to identify frequently occurring themes and topics.

[0374] 7. Acquisition and Output of Trend Information

[0375] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user. It is also distributed to multiple subscriber clients (e.g., news organizations and research institutions) as needed. Distribution methods include email, web application dashboards, and API endpoints.

[0376] Specific example

[0377] For example, if the keyword "AI" is set and social media data from the past day is collected, the server will collect tweets related to "AI". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". As a result of the analysis, trend information is obtained such as "The main topics related to AI recently are advancements in medical technology and future technologies". This information is provided to news organizations and research institutions through the server.

[0378] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trending information on social media and the provision of information in real time.

[0379] The following describes the processing flow.

[0380] Step 1:

[0381] The server configures the authentication credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information to perform the authentication process enables the use of the social media API.

[0382] Step 2:

[0383] The device receives specific keywords and time period settings from the user. These keywords are strings representing specific topics or subjects on social media, and the time period refers to any date range in the past. This information is entered by the user through the device's interface.

[0384] Step 3:

[0385] The server uses social media APIs to collect relevant message information based on configured keywords and time periods. The server makes API calls to retrieve posts that match the specified conditions, including metadata such as the post's text, author, and posting date and time.

[0386] Step 4:

[0387] The server converts the collected message information into JSON format. JSON is widely used to represent data structures and is suitable for efficient data processing by the parsing engine. The conversion results are stored in memory or a file.

[0388] Step 5:

[0389] The server uses message information stored in JSON format to generate a prompt to pass to the analysis engine. This prompt is text data that instructs the analysis engine on what kind of analysis to perform. Specifically, it might say something like, "Analyze the following tweets and extract trend information."

[0390] Step 6:

[0391] The server sends the generated prompt to the analysis engine. The analysis engine performs analysis based on the prompt, for example, using natural language processing techniques. This includes topic analysis of the collected message information and extraction of frequently occurring words.

[0392] Step 7:

[0393] The server retrieves trend information returned from the analysis engine. The analysis results include summarized information indicating which themes and topics are receiving particular attention. This information is then organized on the server into a format suitable for storage, analysis, and display.

[0394] Step 8:

[0395] The server displays the acquired trend information on the user's device. This information can be displayed via a web dashboard, a mobile application, or a dedicated software interface. Through this, users can understand currently trending topics and issues.

[0396] Step 9:

[0397] The server distributes trend information to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, or file uploads to an FTP server. This ensures that real-time trend information is widely available.

[0398] (Example 1)

[0399] 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".

[0400] With the increasing sharing of information on social media, there is a growing need to quickly and efficiently collect and analyze message information based on specific keywords and timeframes. However, traditional methods require considerable time and effort to structure the collected information and compile it into trending data. This makes it difficult to provide information in real time.

[0401] 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.

[0402] In this invention, the server includes means for accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods; means for converting the collected message information into JSON format; means for generating prompts for an analysis engine using the message information converted into JSON format; means for passing the generated prompts to the analysis engine and analyzing trend information; and means for obtaining the trend information returned from the analysis engine and outputting that trend information. This enables the rapid and efficient collection and analysis of information on social media, thereby providing real-time trend information.

[0403] "Authentication information" refers to information such as API keys and tokens required to access social media APIs.

[0404] A "social media API" is an interface provided by a social media platform that allows external applications and services to access the platform's data and functions.

[0405] A "keyword" is a specific hashtag or phrase designated by the user and is used to collect specific information from posts on social media.

[0406] "Period" refers to a specific time range specified by the user, and the collection of information is limited to social media posts within that range.

[0407] "Message information" refers to text data and posts collected on social media.

[0408] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a lightweight data exchange format for structuring, storing, and transmitting data.

[0409] An "analysis engine" is software or an algorithm used to analyze collected data and extract specific patterns or trends.

[0410] A "prompt" is an instruction or query used to give instructions to an analysis engine for analysis.

[0411] "Trend information" refers to information extracted by an analysis engine that shows frequently occurring patterns and tendencies related to a specific topic or theme.

[0412] "Output means" refers to methods or devices for displaying or providing analyzed trend information to users or other systems.

[0413] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. This system makes it possible to quickly and efficiently acquire trend information on social media and provide it to users in real time.

[0414] 1. Setting up authentication information

[0415] The server first configures the authentication credentials for accessing the social media APIs. These credentials consist of API keys, tokens, etc., and are configured based on the API documentation of each social media platform. The server uses these credentials to securely access the APIs.

[0416] 2. Setting Keywords and Time Period

[0417] The terminal retrieves keywords and a survey period specified by the user. Users enter keywords and a period through input fields in web forms or applications. This input data is sent from the terminal to the server.

[0418] 3. Collection of message information

[0419] The server uses social media APIs to collect message information based on specified keywords and time periods. By calling the search APIs of social media platforms, relevant post data is retrieved in text format. This allows for the collection of a vast amount of post data in real time.

[0420] 4. Message Information Conversion

[0421] The server converts the collected message information into JSON format. JSON format is suitable for structuring and storing data, and can be easily handled as input for parsing engines. The converted data is temporarily stored.

[0422] 5. Prompt generation

[0423] The server uses the message information, converted to JSON format, to generate a prompt for the parsing engine. The prompt contains instructions for the parsing engine and takes the following format:

[0424] "Analyze the following message information and summarize the trends."

[0425] 6. Trend Analysis

[0426] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from the posted content and generate trend information.

[0427] 7. Acquisition and Output of Trend Information

[0428] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via the terminal. Furthermore, it is distributed to multiple subscriber clients (e.g., news organizations and research institutions) via email or API endpoints as needed.

[0429] Specific example

[0430] For example, if a user sets "AI" as a keyword and specifies the time period as the past day, the server will collect tweets related to "AI". These tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". An example of a specific prompt would be:

[0431] "Analyze the following message information and summarize the trends."

[0432] The analysis results in trend information indicating that "the main topics related to AI recently are advancements in medical technology and future technologies." This information is provided to news organizations and research institutions via a server.

[0433] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0434] Step 1:

[0435] The server configures the authentication credentials for accessing social media APIs. Authentication credentials, such as API keys and tokens, are stored securely and used when accessing the API. Specifically, the server reads a configuration file containing the stored credentials and uses that information to make API requests. Authentication credentials are required as input, and authenticated API access is obtained as output.

[0436] Step 2:

[0437] The terminal retrieves keywords and a survey period specified by the user. The user enters the keywords and period using a web form or application input field. The entered data is sent from the terminal to the server. The user-specified keywords and period are required as input, and this information is passed to the server as output.

[0438] Step 3:

[0439] The server uses social media APIs to collect message information based on specified keywords and time periods. It calls social media search APIs to retrieve relevant post data in text format. Keywords and time periods are required as input, and relevant message information is obtained as output. Specifically, it makes API calls and saves the results to an internal database or file system.

[0440] Step 4:

[0441] The server converts the collected message information into JSON format. JSON format is an efficient way to structure data and is suitable as input for the parsing engine. The collected message information is required as input, and the output is data in JSON format. Specifically, the raw text data is converted into a JSON object and temporarily stored.

[0442] Step 5:

[0443] The server generates a prompt for the parsing engine using message information converted to JSON format. The prompt instructs the parsing engine on what processing to perform. JSON format message information is required as input, and the prompt is obtained as output. Specifically, the server incorporates the message information into the prompt statement, preparing it for transmission to the parsing engine.

[0444] Step 6:

[0445] The analysis engine performs natural language processing based on prompts provided by the server to analyze trend information. A prompt is required as input, and the analyzed trend information is obtained as output. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from message information.

[0446] Step 7:

[0447] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via their terminal. Furthermore, it is distributed to news organizations and research institutions via email or API endpoints as needed. The server requires trend information from the analysis engine as input and provides information to users and subscribers as output. Specific actions include displaying the information on a dashboard, sending emails, and making API calls.

[0448] (Application Example 1)

[0449] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0450] Traditional advertising analytics systems struggled to grasp market reactions in real time, making immediate optimization of advertising campaigns difficult. Furthermore, data collection and analysis from social networking services were cumbersome, lacking the means to quickly develop effective advertising strategies. This hindered the maximization of advertising effectiveness.

[0451] 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.

[0452] This invention includes a server that accesses a social networking service API using authentication information and collects text information based on specified search words and time periods; a server that inputs the collected text information into an analysis device and generates a generative AI model prompt for identifying trend information; a server that retrieves the trend information returned from the analysis device and outputs that trend information; and a server that grasps market reactions in real time and optimizes advertising content. This enables advertisers to immediately grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[0453] "Authentication information" refers to a collection of information used to ensure security, such as access keys and tokens, for accessing social networking service APIs.

[0454] A "Social Networking Service API" is an application programming interface for programmatically retrieving user-generated data, profile information, and other data from a specified platform.

[0455] "Search terms" refer to keywords or hashtags related to a specific topic or theme, and are the criteria used to collect data from social networking services.

[0456] "Period" refers to the time frame for data collection, specifying a time range such as the past hour, day, or week.

[0457] "Text information" refers to character data such as messages, posts, and comments collected from social networking services.

[0458] An "analysis device" is a computer device used to analyze collected data and derive specific meanings or trends.

[0459] A "generated AI model prompt" is a specific instruction given when inputting collected data into an analysis device, and it specifies the input data required to perform a particular task.

[0460] "Trend information" refers to important themes and trends derived from collected and analyzed data, and is used in marketing and advertising strategies.

[0461] "Real-time" refers to a situation where data collection, analysis, and output occur almost instantly, meaning that the latest information is provided without delay.

[0462] "Optimization" refers to the process of adjusting and modifying advertising content and strategies based on data to achieve maximum effectiveness.

[0463] System Configuration

[0464] This invention is a system for collecting and analyzing advertising-related trend information in real time from specific social networking services and for quickly understanding market reactions based on the results. This system consists of three main components: a server, a terminal, and a user.

[0465] Hardware and software

[0466] Hardware: Servers are high-performance computer devices used for data collection and analysis. Smartphones, tablets, and PCs are used as user terminals. For analysis, computing resources are needed to run generative AI models such as GPT-3.

[0467] Software: Data collection, transformation, and analysis are performed using Python and other programming languages. Specifically, the requests library and natural language processing libraries are used.

[0468] Data flow

[0469] 1. Setting up authentication information

[0470] The server first configures the authentication credentials for accessing the social networking service API. These credentials include security information such as API keys and tokens.

[0471] 2. Setting Keywords and Time Period

[0472] The user enters a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their device. This information is sent to the server and configured.

[0473] 3. Collection of text information

[0474] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. The collected text information is stored on the server in text format.

[0475] 4. Message Information Conversion

[0476] The server converts the collected text information into JSON format before passing it to the analysis device (generating AI model). The JSON format makes it easy to structure data and allows for efficient analysis.

[0477] 5. Generating AI Model Prompts

[0478] Based on the text information converted to JSON format, the server generates a prompt message that reads, "Analyze the following message information and summarize the trends related to advertising."

[0479] 6. Analysis of trend information

[0480] The server passes the generated prompt messages to the analysis device, which uses a generation AI model to analyze trend information. This allows for the identification of frequently occurring themes and topics.

[0481] 7. Acquisition and Output of Trend Information

[0482] The server retrieves trend information returned from the analysis device and outputs this information to the user. Output methods include displaying a dashboard, email notifications, and generating reports. It also provides means to understand market reactions in real time and optimize advertising content.

[0483] Specific example

[0484] For example, if a user sets the search term "new products" and requests data for the past day, the server will collect posts related to "new products." After collection, these posts are converted to JSON format, and a prompt message like the following is generated:

[0485] "Analyze the following message information and summarize the advertising-related trends: {Message data in JSON format}"

[0486] The generative AI model analyzes this data and generates trend information, such as "Recent key topics regarding new products are environmentally friendly packaging and the adoption of new technologies." This information is then displayed to the user via the server.

[0487] This allows advertisers to instantly grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[0488] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0489] Step 1:

[0490] The server configures the authentication information (API key and token) for accessing the social networking service API. It receives the authentication information as input and uses it to establish a session for the API connection. The output of this step indicates that the API connection has been established.

[0491] Step 2:

[0492] The user inputs a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their terminal. This input is sent to the server and saved as settings for analysis. The input consists of the search term and period, and the output is the configured analysis parameters.

[0493] Step 3:

[0494] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. It makes API calls to retrieve the corresponding post data. The input is the authentication credentials and parsing parameters, and the output is the collected text information.

[0495] Step 4:

[0496] The server converts the collected text information into JSON format before passing it to the analysis device. This structures the data, allowing for more efficient analysis. The input is the collected text information, and the output is data in JSON format.

[0497] Step 5:

[0498] The server generates a prompt message based on the text information converted to JSON format, which reads, "Analyze the following message information and summarize the trends related to advertising." The prompt message is an instruction to the parser. The input is text information in JSON format, and the output is the generated prompt message.

[0499] Step 6:

[0500] The server passes the generated prompt sentences to the analysis device (generating AI model) for analysis. Based on the prompt sentences, the analysis device identifies frequently occurring themes and trends from the data. The input consists of prompt sentences and text information in JSON format, and the output is trend information.

[0501] Step 7:

[0502] The server retrieves trend information returned from the analysis device and outputs this information to the user. This information is provided to the user through methods such as dashboard display, email notifications, and report generation. The input is trend information, and the output is the presentation of information to the user. It also includes means for understanding market reactions in real time and optimizing advertising content.

[0503] By following these steps, advertisers can instantly grasp market reactions in real time and quickly plan and execute the optimal advertising strategy.

[0504] 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.

[0505] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, and analyzes trend information and user sentiment data using a sentiment engine. Specific embodiments of this invention are described in detail below.

[0506] 1. Setting up authentication information

[0507] The server configures the authentication credentials for accessing social media APIs. These credentials include API keys, API secrets, access tokens, and access token secrets. Using this information, the server successfully authenticates to the social media platform.

[0508] 2. Setting Keywords and Time Period

[0509] The device receives specific keywords and a research period from the user. These keywords represent specific topics or subjects gaining attention on social media, and the research period refers to any date range in the past. The user enters this information through the device's interface.

[0510] 3. Collection of message information

[0511] The server uses social media APIs to collect relevant message information based on the configured keywords and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[0512] 4. Message Information Conversion

[0513] The server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[0514] 5. Prompt generation and analysis request

[0515] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how, and takes the form of "analyze the following messages and extract trend information."

[0516] 6. Analysis of trend information

[0517] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[0518] 7. Analysis of emotional data

[0519] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotional data.

[0520] 8. Acquisition and output of trend information and sentiment data

[0521] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is integrated and provided to the user. The information is also displayed through a dashboard and a dedicated application interface.

[0522] 9. Distribution of trend information and sentiment data

[0523] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[0524] Specific example

[0525] For example, if the keyword "ClimateChange" is set and social media data for the past day is collected, the server will collect tweets related to "ClimateChange". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this and generates trend information such as "Recent major topics related to ClimateChange show increased public interest in policy changes." At the same time, the sentiment engine analyzes sentiment data and obtains information such as "Many users are expressing anger towards policy changes." This trend information and sentiment data are provided to news organizations and research institutions through the server.

[0526] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trend information and user sentiment data from social media, and the provision of information in real time.

[0527] The following describes the processing flow.

[0528] Step 1:

[0529] The server configures the credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information, the server performs an authentication process against the social media platform. Upon successful authentication, access to the API endpoint is granted.

[0530] Step 2:

[0531] The device receives specific keywords and survey period settings from the user. These keywords are strings of characters that indicate specific topics or subjects gaining attention on social media. The survey period specifies an arbitrary date range, such as the past 1 to 7 days. The user enters this information through the device's user interface.

[0532] Step 3:

[0533] The server calls social media APIs based on configured keywords and time periods to collect relevant message information. The API calls retrieve posts that match the specified criteria. During this process, metadata such as the post text, author, posting date and time, and the number of retweets and likes are also collected.

[0534] Step 4:

[0535] The server converts the collected message information into JSON format. This conversion simplifies data structuring and makes the data suitable for passing to the analysis engine. The modified data is stored in memory or a database.

[0536] Step 5:

[0537] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on how to analyze the specified data, and takes the form of "Analyze the following message and extract trend information."

[0538] Step 6:

[0539] The server sends data, including the generated prompts, to the analysis engine. The analysis engine uses natural language processing techniques to perform data analysis based on the prompts. Specifically, it identifies frequently occurring words, phrases, themes, or topics from the collected social media posts and extracts trend information.

[0540] Step 7:

[0541] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine uses text analysis techniques to identify the emotion in the message, classifying it into emotions such as joy, sadness, and anger. It then outputs the emotional state for each message as numerical data or tags.

[0542] Step 8:

[0543] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is appropriately formatted and prepared for user presentation. Possible output formats include reports and dashboards.

[0544] Step 9:

[0545] The server displays acquired trend information and sentiment data on the terminal. Through the terminal's interface, users can access the information in real time. Based on the information provided, users can understand currently trending topics and their own sentiment towards them.

[0546] Step 10:

[0547] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, a web dashboard, or file uploads to an FTP server. This makes the analysis results widely available.

[0548] Specific example

[0549] For example, consider a scenario where social media data for the past day is collected using the keyword "ClimateChange." The server collects relevant tweets and converts them into JSON format. Then, an analysis engine generates trend information such as, "The main topic related to ClimateChange recently is the growing public interest in policy changes." Simultaneously, a sentiment engine analyzes sentiment data such as, "Many users are expressing anger towards policy changes." This information is integrated and distributed in real time to news organizations and research institutions via the server.

[0550] (Example 2)

[0551] 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".

[0552] Conventional systems have struggled to efficiently and immediately integrate and provide trend information and sentiment data when analyzing information collected from online platforms such as social media. Furthermore, inconsistencies in data structuring, generation of analysis instructions, and distribution methods of analysis results have sometimes hindered real-time information provision.

[0553] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention,

[0554] The server has means to access the online platform API using authentication information and to collect communication information based on specified search terms and time ranges.

[0555] A means for inputting collected communication information into an analysis device and generating instruction sentences to identify trend information,

[0556] A means for acquiring trend information returned from an analysis device and outputting that trend information,

[0557] A means of inputting collected communication information into an emotion analysis device and analyzing the user's emotional data,

[0558] A means for integrating trend information and emotional data acquired from an analysis device and an emotion analysis device,

[0559] A means of providing integrated information to users and distributing it to information recipients,

[0560] This includes the ability to efficiently analyze collected communication information and immediately integrate and provide trend information and sentiment data.

[0561] "Authentication information" refers to the identification information required to access online platform APIs, and includes API keys, API secrets, access tokens, and access token secrets.

[0562] An "online platform API" is a programmatic interface for accessing specific functions or data provided by social media and other internet services.

[0563] A "search term" is a word or phrase specified to search for specific information on an online platform.

[0564] "Time range" refers to the period over which information collected on an online platform is collected, and can include any date range in the past.

[0565] "Communication information" refers to data such as messages, posts, and comments collected from online platforms, as well as their metadata.

[0566] An "analysis device" is a device or software used to analyze collected communication information and identify trend information, employing technologies such as natural language processing.

[0567] "Trend information" refers to information based on the frequency and relevance of topics and themes on online platforms, as identified by analytical tools.

[0568] An "instruction document" is a document or format that shows the analysis device how to analyze the collected communication information.

[0569] An "emotion analysis device" is a device or software that analyzes a user's emotions from text communication information and generates emotional data.

[0570] "Emotional data" refers to information about the type and intensity of emotions contained in text, generated by an emotion analysis device.

[0571] "Integration" refers to the process of combining trend information and emotional data obtained from analysis devices and emotion analysis devices into a single, consistent set of information.

[0572] "Information recipients" refers to news organizations, research institutions, and other groups that have subscribed to receive the analysis results.

[0573] This invention relates to a system that utilizes an online platform API to collect communication information based on specified search terms and time ranges, and analyzes trend information and user sentiment data using an analysis device and a sentiment analysis device. Specific embodiments of the present invention are described below.

[0574] Authentication information settings (server)

[0575] The server configures the authentication credentials for accessing the online platform API. These credentials include the API key, API secret, access token, and access token secret. The server uses this information to successfully authenticate to the online platform.

[0576] Setting keywords and time periods (device)

[0577] The terminal receives specific search terms and a search period from the user. The user enters the search term "ClimateChange" and the search period "Past 1 day" through the terminal's interface. The terminal receives this information and sends it to the server for the next processing.

[0578] Collection of communication information (server)

[0579] The server collects relevant communication information using the online platform API based on the configured search terms and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[0580] Conversion of communication information (server)

[0581] The server converts the collected communication information into a structured data format (e.g., JSON format). This improves the efficiency of data structuring and analysis.

[0582] Prompt generation and parsing request (server)

[0583] The server generates prompt statements to pass to the analysis device based on the communication information converted into JSON format. These prompt statements instruct the analysis device on which data to analyze and how. For example, the following prompt statements are generated:

[0584] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[0585] The server sends the generated prompt message to the analysis device and requests analysis.

[0586] Analysis of trend information (analysis device)

[0587] The analysis device uses natural language processing techniques to analyze trend information based on prompt messages received from the server. For example, the analysis device identifies frequently occurring themes and topics from the collected communication information and generates trend information such as "interest in policy changes is increasing."

[0588] Analysis of emotional data (emotion analysis device)

[0589] The server passes the collected communication information to an emotion analysis device, which analyzes the users' emotional data. The emotion analysis device classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text of the communication information and generates emotional data such as "Many users are showing anger towards the policy change."

[0590] Acquisition and output of trend information and sentiment data (server)

[0591] The server acquires trend information returned from the analysis device and sentiment data obtained from the sentiment analysis device, and integrates this data. The integrated information is provided to the user through a dashboard or dedicated application interface.

[0592] Distribution of trend information and sentiment data (server)

[0593] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[0594] Specifically, the process is carried out as follows: When the user enters the search term "ClimateChange" and the time period "Past 1 day" through the terminal interface, the server generates an API request and collects relevant data from the online platform. The collected data is converted into a structured data format, and a prompt message like the following is generated and sent to the analysis device:

[0595] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[0596] The analysis device analyzes trend information, and the sentiment analysis device generates sentiment data. The server integrates this information and distributes it to news organizations and research institutions.

[0597] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0598] Step 1:

[0599] The server reads authentication information such as API keys, API secrets, access tokens, and access token secrets from configuration files and databases, and issues authentication requests to the online platform API. This allows it to obtain an authentication token for accessing the online platform. The authentication information is used as input, and the authentication token is output.

[0600] Step 2:

[0601] The terminal receives specific search terms (e.g., "ClimateChange") and a search period (e.g., "Past 1 day") from the user. The user inputs this information through the interface, and the terminal receives it and sends it to the server. The input consists of the search terms and the search period, which are then output as a request to the server.

[0602] Step 3:

[0603] The server generates a request to the online platform API based on the search terms and research period received from the terminal. The generated request is constructed to include the search terms and research period as query parameters. This is output as an API request and sent to the online platform.

[0604] Step 4:

[0605] The server receives communication information collected from the online platform API. This communication information includes metadata such as the post text, author, and posting date and time. The response from the API is used as input data, and this is output as communication information.

[0606] Step 5:

[0607] The server converts the collected communication information into a structured data format (e.g., JSON). This improves the efficiency of data structuring and analysis. The input is unstructured communication information, and the output is JSON formatted data.

[0608] Step 6:

[0609] The server generates prompt messages to pass to the analysis device based on structured communication information. These prompt messages include specific analysis requirements (e.g., "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."). The input is communication information in JSON format, and the output is prompt messages.

[0610] Step 7:

[0611] The server sends the generated prompt message and JSON data to the analysis device, requesting analysis of trend information. The input is the prompt message and JSON data, and the output is the analysis request.

[0612] Step 8:

[0613] The analysis device extracts trend information using natural language processing techniques based on prompt messages received from the server. For example, it generates information such as "interest in policy changes is increasing." The input is prompt messages and JSON data, and the output is trend information.

[0614] Step 9:

[0615] The server retrieves trend information returned from the analysis device. Simultaneously, it passes communication information to the emotion analysis device and requests it to analyze the emotion data. The inputs are trend information and communication information, and the output is a request for emotion data analysis.

[0616] Step 10:

[0617] The emotion analysis device analyzes the text of communication information and classifies the type of emotion (e.g., joy, sadness, anger). For example, it might generate information such as "Many users are expressing anger towards the policy change." The input is the text of the communication information, and the output is emotion data.

[0618] Step 11:

[0619] The server integrates trend information returned from the analysis device and sentiment data acquired from the sentiment analysis device. The input is trend information and sentiment data, and the output is the integrated information.

[0620] Step 12:

[0621] The server provides integrated information to users through dashboards and dedicated application interfaces. The information is displayed visually, making it easily accessible to users. The input is integrated information, and the output is data displayed to the user.

[0622] Step 13:

[0623] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Information is distributed via dedicated APIs, email notifications, and file uploads to an FTP server. The input is integrated information, and the output is distributed data.

[0624] (Application Example 2)

[0625] 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."

[0626] Traditional advertising delivery systems have struggled to grasp user interests and emotions in real time, making it difficult to deliver effective advertisements. Furthermore, advertising based on trend information and sentiment data is rarely used, highlighting the need for methods that maximize advertising effectiveness.

[0627] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing a social media API using authentication information and collecting message information based on specified keywords and time periods; means for inputting the collected message information into an analysis engine and generating prompts for identifying trend information; and means for obtaining the trend information and sentiment data returned from the analysis engine and displaying advertising information using that data. This enables real-time advertising delivery based on trend information and sentiment data.

[0628] "Authentication information" refers to information such as API keys, API secrets, access tokens, and access token secrets required to access social media APIs.

[0629] A "social media API" refers to a programmatic interface provided by a social media platform, which allows external applications to access data on social media.

[0630] A "keyword" is a term used to refer to a specific topic or subject that is gaining attention on social media.

[0631] "Period" refers to any past date range for which data will be collected.

[0632] "Message information" refers to data such as posts on social media, the poster, and the date and time of posting.

[0633] An "analysis engine" is a system that uses natural language processing technology to identify trend information based on collected message data.

[0634] A "prompt" is a set of instructions that tells the analysis engine which data to analyze and how to analyze it.

[0635] "Trend information" refers to information that indicates frequently occurring themes and topics extracted from collected social media posts.

[0636] "Emotional data" refers to information extracted from social media messages that indicates a user's emotional state (e.g., joy, sadness, anger, etc.).

[0637] "Advertising information" refers to the content of advertisements displayed to users, and is generated based on trend information and sentiment data.

[0638] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, analyzes trend information and user sentiment data using an analysis engine, and uses that data to display optimal advertisements.

[0639] First, the server configures the authentication credentials (API key, API secret, access token, and access token secret) for accessing the social media API. These credentials are crucial for successful authentication to the social media platform.

[0640] Next, the device receives specific keywords and a search period from the user. For example, if the user sets the keyword "ClimateChange" and the time period to the past day, this information will indicate specific topics that are trending on social media.

[0641] Based on its configuration, the server uses social media APIs to collect relevant message information. This step includes information such as the post text, the poster, and the date and time of posting.

[0642] Next, the server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[0643] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how. For example, it might say, "Analyze the following messages and extract trend information."

[0644] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[0645] Next, the server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotion data.

[0646] The server then integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine and provides it to the user. It also includes means of displaying optimal advertisements using this data. For example, it might display an advertisement using trend information such as "A major topic regarding recent ClimateChange is the growing public interest in policy changes" and sentiment data such as "Many users are expressing anger towards policy changes."

[0647] Examples of prompt statements used include the following:

[0648] "Please analyze the following text data to extract trend information and sentiment."

[0649] [

[0650] {"text": "Climate change is real and urgent!", "user": "user1", "date": "2023-10-01 12:00:00"},

[0651] ...

[0652] ]

[0653] This system enables the rapid and accurate acquisition of trending information and user sentiment data from social media, allowing for real-time information delivery. Furthermore, by displaying advertising information based on the analysis results, it maximizes advertising effectiveness.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1:

[0656] The server configures the credentials for accessing the social media API. Specifically, it uses credentials including the API key, API secret, access token, and access token secret to successfully authenticate to the social media platform. The input for this step is the credentials, and the output is a state where the social media API is accessible.

[0657] Step 2:

[0658] The terminal receives specific keywords and a survey period from the user. The user enters keywords (e.g., ClimateChange) and a period (e.g., the past day) through the terminal's interface. This information is used as the basis for data collection. The input for this step is the keywords and period entered by the user, and the output is the keyword and period settings.

[0659] Step 3:

[0660] The server collects relevant message information using social media APIs based on the configured keywords and time period. It retrieves metadata such as post text, author, and posting date and time from social media platforms. The input for this step is the keyword and time period settings, and the output is the collected message information.

[0661] Step 4:

[0662] The server converts the collected message information into JSON format. Using JSON format streamlines data structuring and analysis. The input for this step is the collected message information, and the output is data in JSON format.

[0663] Step 5:

[0664] The server generates a prompt to pass to the analysis engine based on the message information converted to JSON format. It creates a prompt statement and prepares it for passing to the analysis engine. Specifically, it generates an instruction statement in the format of "Analyze the following message and extract trend information." The input for this step is data in JSON format, and the output is the generated prompt statement.

[0665] Step 6:

[0666] The server passes the prompt message to the analysis engine, which then analyzes the trend information. The analysis engine uses natural language processing techniques to identify frequently occurring themes and topics from the collected social media posts. The input for this step is the generated prompt message, and the output is the identified trend information.

[0667] Step 7:

[0668] The server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text and generates emotion data. The input for this step is message information, and the output is emotion data.

[0669] Step 8:

[0670] The server integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. It then provides this information to the user through a means of displaying advertising information. For example, it selects and displays the most suitable advertisement based on the trend information and sentiment data. The input for this step is trend information and sentiment data, and the output is the display of the most suitable advertising information.

[0671] 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.

[0672] 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.

[0673] 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.

[0674] [Third Embodiment]

[0675] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0676] 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.

[0677] 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).

[0678] 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.

[0679] 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.

[0680] 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).

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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".

[0687] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. Specific embodiments of this invention are described in detail below.

[0688] 1. Setting up authentication information

[0689] The server first configures the authentication credentials for accessing the social media API. These credentials are for accessing a specific social media platform and consist of API keys, tokens, and other information provided by each platform.

[0690] 2. Setting Keywords and Time Period

[0691] The device retrieves keywords and a survey period specified by the user. Typically, keywords are tags or specific phrases, and the period is often set to the past day or several days.

[0692] 3. Collection of message information

[0693] The server uses social media APIs to collect message information based on specified keywords and time periods. In this step, social media post data is collected via API calls. The collected message information is stored in text format.

[0694] 4. Message Information Conversion

[0695] The server converts the collected message information into JSON format. This is because JSON format is suitable for structuring data and passing it to the analysis engine.

[0696] 5. Prompt generation

[0697] The server uses the message information, converted into JSON format, to generate a prompt for the analysis engine. The prompt might take the form of, for example, "Analyze the following message information and summarize the trends."

[0698] 6. Trend Analysis

[0699] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it analyzes the collected social media posts to identify frequently occurring themes and topics.

[0700] 7. Acquisition and Output of Trend Information

[0701] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user. It is also distributed to multiple subscriber clients (e.g., news organizations and research institutions) as needed. Distribution methods include email, web application dashboards, and API endpoints.

[0702] Specific example

[0703] For example, if the keyword "AI" is set and social media data from the past day is collected, the server will collect tweets related to "AI". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". As a result of the analysis, trend information is obtained such as "The main topics related to AI recently are advancements in medical technology and future technologies". This information is provided to news organizations and research institutions through the server.

[0704] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trending information on social media and the provision of information in real time.

[0705] The following describes the processing flow.

[0706] Step 1:

[0707] The server configures the authentication credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information to perform the authentication process enables the use of the social media API.

[0708] Step 2:

[0709] The device receives specific keywords and time period settings from the user. These keywords are strings representing specific topics or subjects on social media, and the time period refers to any date range in the past. This information is entered by the user through the device's interface.

[0710] Step 3:

[0711] The server uses social media APIs to collect relevant message information based on configured keywords and time periods. The server makes API calls to retrieve posts that match the specified conditions, including metadata such as the post's text, author, and posting date and time.

[0712] Step 4:

[0713] The server converts the collected message information into JSON format. JSON is widely used to represent data structures and is suitable for efficient data processing by the parsing engine. The conversion results are stored in memory or a file.

[0714] Step 5:

[0715] The server uses message information stored in JSON format to generate a prompt to pass to the analysis engine. This prompt is text data that instructs the analysis engine on what kind of analysis to perform. Specifically, it might say something like, "Analyze the following tweets and extract trend information."

[0716] Step 6:

[0717] The server sends the generated prompt to the analysis engine. The analysis engine performs analysis based on the prompt, for example, using natural language processing techniques. This includes topic analysis of the collected message information and extraction of frequently occurring words.

[0718] Step 7:

[0719] The server retrieves trend information returned from the analysis engine. The analysis results include summarized information indicating which themes and topics are receiving particular attention. This information is then organized on the server into a format suitable for storage, analysis, and display.

[0720] Step 8:

[0721] The server displays the acquired trend information on the user's device. This information can be displayed via a web dashboard, a mobile application, or a dedicated software interface. Through this, users can understand currently trending topics and issues.

[0722] Step 9:

[0723] The server distributes trend information to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, or file uploads to an FTP server. This ensures that real-time trend information is widely available.

[0724] (Example 1)

[0725] 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."

[0726] With the increasing sharing of information on social media, there is a growing need to quickly and efficiently collect and analyze message information based on specific keywords and timeframes. However, traditional methods require considerable time and effort to structure the collected information and compile it into trending data. This makes it difficult to provide information in real time.

[0727] 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.

[0728] In this invention, the server includes means for accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods; means for converting the collected message information into JSON format; means for generating prompts for an analysis engine using the message information converted into JSON format; means for passing the generated prompts to the analysis engine and analyzing trend information; and means for obtaining the trend information returned from the analysis engine and outputting that trend information. This enables the rapid and efficient collection and analysis of information on social media, thereby providing real-time trend information.

[0729] "Authentication information" refers to information such as API keys and tokens required to access social media APIs.

[0730] A "social media API" is an interface provided by a social media platform that allows external applications and services to access the platform's data and functions.

[0731] A "keyword" is a specific hashtag or phrase designated by the user and is used to collect specific information from posts on social media.

[0732] "Period" refers to a specific time range specified by the user, and the collection of information is limited to social media posts within that range.

[0733] "Message information" refers to text data and posts collected on social media.

[0734] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a lightweight data exchange format for structuring, storing, and transmitting data.

[0735] An "analysis engine" is software or an algorithm used to analyze collected data and extract specific patterns or trends.

[0736] A "prompt" is an instruction or query used to give instructions to an analysis engine for analysis.

[0737] "Trend information" refers to information extracted by an analysis engine that shows frequently occurring patterns and tendencies related to a specific topic or theme.

[0738] "Output means" refers to methods or devices for displaying or providing analyzed trend information to users or other systems.

[0739] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. This system makes it possible to quickly and efficiently acquire trend information on social media and provide it to users in real time.

[0740] 1. Setting up authentication information

[0741] The server first configures the authentication credentials for accessing the social media APIs. These credentials consist of API keys, tokens, etc., and are configured based on the API documentation of each social media platform. The server uses these credentials to securely access the APIs.

[0742] 2. Setting Keywords and Time Period

[0743] The terminal retrieves keywords and a survey period specified by the user. Users enter keywords and a period through input fields in web forms or applications. This input data is sent from the terminal to the server.

[0744] 3. Collection of message information

[0745] The server uses social media APIs to collect message information based on specified keywords and time periods. By calling the search APIs of social media platforms, relevant post data is retrieved in text format. This allows for the collection of a vast amount of post data in real time.

[0746] 4. Message Information Conversion

[0747] The server converts the collected message information into JSON format. JSON format is suitable for structuring and storing data, and can be easily handled as input for parsing engines. The converted data is temporarily stored.

[0748] 5. Prompt generation

[0749] The server uses the message information, converted to JSON format, to generate a prompt for the parsing engine. The prompt contains instructions for the parsing engine and takes the following format:

[0750] "Analyze the following message information and summarize the trends."

[0751] 6. Trend Analysis

[0752] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from the posted content and generate trend information.

[0753] 7. Acquisition and Output of Trend Information

[0754] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via the terminal. Furthermore, it is distributed to multiple subscriber clients (e.g., news organizations and research institutions) via email or API endpoints as needed.

[0755] Specific example

[0756] For example, if a user sets "AI" as a keyword and specifies the time period as the past day, the server will collect tweets related to "AI". These tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". An example of a specific prompt would be:

[0757] "Analyze the following message information and summarize the trends."

[0758] The analysis results in trend information indicating that "the main topics related to AI recently are advancements in medical technology and future technologies." This information is provided to news organizations and research institutions via a server.

[0759] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0760] Step 1:

[0761] The server configures the authentication credentials for accessing social media APIs. Authentication credentials, such as API keys and tokens, are stored securely and used when accessing the API. Specifically, the server reads a configuration file containing the stored credentials and uses that information to make API requests. Authentication credentials are required as input, and authenticated API access is obtained as output.

[0762] Step 2:

[0763] The terminal retrieves keywords and a survey period specified by the user. The user enters the keywords and period using a web form or application input field. The entered data is sent from the terminal to the server. The user-specified keywords and period are required as input, and this information is passed to the server as output.

[0764] Step 3:

[0765] The server uses social media APIs to collect message information based on specified keywords and time periods. It calls social media search APIs to retrieve relevant post data in text format. Keywords and time periods are required as input, and relevant message information is obtained as output. Specifically, it makes API calls and saves the results to an internal database or file system.

[0766] Step 4:

[0767] The server converts the collected message information into JSON format. JSON format is an efficient way to structure data and is suitable as input for the parsing engine. The collected message information is required as input, and the output is data in JSON format. Specifically, the raw text data is converted into a JSON object and temporarily stored.

[0768] Step 5:

[0769] The server generates a prompt for the parsing engine using message information converted to JSON format. The prompt instructs the parsing engine on what processing to perform. JSON format message information is required as input, and the prompt is obtained as output. Specifically, the server incorporates the message information into the prompt statement, preparing it for transmission to the parsing engine.

[0770] Step 6:

[0771] The analysis engine performs natural language processing based on prompts provided by the server to analyze trend information. A prompt is required as input, and the analyzed trend information is obtained as output. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from message information.

[0772] Step 7:

[0773] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via their terminal. Furthermore, it is distributed to news organizations and research institutions via email or API endpoints as needed. The server requires trend information from the analysis engine as input and provides information to users and subscribers as output. Specific actions include displaying the information on a dashboard, sending emails, and making API calls.

[0774] (Application Example 1)

[0775] 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."

[0776] Traditional advertising analytics systems struggled to grasp market reactions in real time, making immediate optimization of advertising campaigns difficult. Furthermore, data collection and analysis from social networking services were cumbersome, lacking the means to quickly develop effective advertising strategies. This hindered the maximization of advertising effectiveness.

[0777] 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.

[0778] This invention includes a server that accesses a social networking service API using authentication information and collects text information based on specified search words and time periods; a server that inputs the collected text information into an analysis device and generates a generative AI model prompt for identifying trend information; a server that retrieves the trend information returned from the analysis device and outputs that trend information; and a server that grasps market reactions in real time and optimizes advertising content. This enables advertisers to immediately grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[0779] "Authentication information" refers to a collection of information used to ensure security, such as access keys and tokens, for accessing social networking service APIs.

[0780] A "Social Networking Service API" is an application programming interface for programmatically retrieving user-generated data, profile information, and other data from a specified platform.

[0781] "Search terms" refer to keywords or hashtags related to a specific topic or theme, and are the criteria used to collect data from social networking services.

[0782] "Period" refers to the time frame for data collection, specifying a time range such as the past hour, day, or week.

[0783] "Text information" refers to character data such as messages, posts, and comments collected from social networking services.

[0784] An "analysis device" is a computer device used to analyze collected data and derive specific meanings or trends.

[0785] A "generated AI model prompt" is a specific instruction given when inputting collected data into an analysis device, and it specifies the input data required to perform a particular task.

[0786] "Trend information" refers to important themes and trends derived from collected and analyzed data, and is used in marketing and advertising strategies.

[0787] "Real-time" refers to a situation where data collection, analysis, and output occur almost instantly, meaning that the latest information is provided without delay.

[0788] "Optimization" refers to the process of adjusting and modifying advertising content and strategies based on data to achieve maximum effectiveness.

[0789] System Configuration

[0790] This invention is a system for collecting and analyzing advertising-related trend information in real time from specific social networking services and for quickly understanding market reactions based on the results. This system consists of three main components: a server, a terminal, and a user.

[0791] Hardware and software

[0792] Hardware: Servers are high-performance computer devices used for data collection and analysis. Smartphones, tablets, and PCs are used as user terminals. For analysis, computing resources are needed to run generative AI models such as GPT-3.

[0793] Software: Data collection, transformation, and analysis are performed using Python and other programming languages. Specifically, the requests library and natural language processing libraries are used.

[0794] Data flow

[0795] 1. Setting up authentication information

[0796] The server first configures the authentication credentials for accessing the social networking service API. These credentials include security information such as API keys and tokens.

[0797] 2. Setting Keywords and Time Period

[0798] The user enters a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their device. This information is sent to the server and configured.

[0799] 3. Collection of text information

[0800] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. The collected text information is stored on the server in text format.

[0801] 4. Message Information Conversion

[0802] The server converts the collected text information into JSON format before passing it to the analysis device (generating AI model). The JSON format makes it easy to structure data and allows for efficient analysis.

[0803] 5. Generating AI Model Prompts

[0804] Based on the text information converted to JSON format, the server generates a prompt message that reads, "Analyze the following message information and summarize the trends related to advertising."

[0805] 6. Analysis of trend information

[0806] The server passes the generated prompt messages to the analysis device, which uses a generation AI model to analyze trend information. This allows for the identification of frequently occurring themes and topics.

[0807] 7. Acquisition and Output of Trend Information

[0808] The server retrieves trend information returned from the analysis device and outputs this information to the user. Output methods include displaying a dashboard, email notifications, and generating reports. It also provides means to understand market reactions in real time and optimize advertising content.

[0809] Specific example

[0810] For example, if a user sets the search term "new products" and requests data for the past day, the server will collect posts related to "new products." After collection, these posts are converted to JSON format, and a prompt message like the following is generated:

[0811] "Analyze the following message information and summarize the advertising-related trends: {Message data in JSON format}"

[0812] The generative AI model analyzes this data and generates trend information, such as "Recent key topics regarding new products are environmentally friendly packaging and the adoption of new technologies." This information is then displayed to the user via the server.

[0813] This allows advertisers to instantly grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[0814] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0815] Step 1:

[0816] The server configures the authentication information (API key and token) for accessing the social networking service API. It receives the authentication information as input and uses it to establish a session for the API connection. The output of this step indicates that the API connection has been established.

[0817] Step 2:

[0818] The user inputs a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their terminal. This input is sent to the server and saved as settings for analysis. The input consists of the search term and period, and the output is the configured analysis parameters.

[0819] Step 3:

[0820] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. It makes API calls to retrieve the corresponding post data. The input is the authentication credentials and parsing parameters, and the output is the collected text information.

[0821] Step 4:

[0822] The server converts the collected text information into JSON format before passing it to the analysis device. This structures the data, allowing for more efficient analysis. The input is the collected text information, and the output is data in JSON format.

[0823] Step 5:

[0824] The server generates a prompt message based on the text information converted to JSON format, which reads, "Analyze the following message information and summarize the trends related to advertising." The prompt message is an instruction to the parser. The input is text information in JSON format, and the output is the generated prompt message.

[0825] Step 6:

[0826] The server passes the generated prompt sentences to the analysis device (generating AI model) for analysis. Based on the prompt sentences, the analysis device identifies frequently occurring themes and trends from the data. The input consists of prompt sentences and text information in JSON format, and the output is trend information.

[0827] Step 7:

[0828] The server retrieves trend information returned from the analysis device and outputs this information to the user. This information is provided to the user through methods such as dashboard display, email notifications, and report generation. The input is trend information, and the output is the presentation of information to the user. It also includes means for understanding market reactions in real time and optimizing advertising content.

[0829] By following these steps, advertisers can instantly grasp market reactions in real time and quickly plan and execute the optimal advertising strategy.

[0830] 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.

[0831] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, and analyzes trend information and user sentiment data using a sentiment engine. Specific embodiments of this invention are described in detail below.

[0832] 1. Setting up authentication information

[0833] The server configures the authentication credentials for accessing social media APIs. These credentials include API keys, API secrets, access tokens, and access token secrets. Using this information, the server successfully authenticates to the social media platform.

[0834] 2. Setting Keywords and Time Period

[0835] The device receives specific keywords and a research period from the user. These keywords represent specific topics or subjects gaining attention on social media, and the research period refers to any date range in the past. The user enters this information through the device's interface.

[0836] 3. Collection of message information

[0837] The server uses social media APIs to collect relevant message information based on the configured keywords and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[0838] 4. Message Information Conversion

[0839] The server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[0840] 5. Prompt generation and analysis request

[0841] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how, and takes the form of "analyze the following messages and extract trend information."

[0842] 6. Analysis of trend information

[0843] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[0844] 7. Analysis of emotional data

[0845] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotional data.

[0846] 8. Acquisition and output of trend information and sentiment data

[0847] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is integrated and provided to the user. The information is also displayed through a dashboard and a dedicated application interface.

[0848] 9. Distribution of trend information and sentiment data

[0849] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[0850] Specific example

[0851] For example, if the keyword "ClimateChange" is set and social media data for the past day is collected, the server will collect tweets related to "ClimateChange". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this and generates trend information such as "Recent major topics related to ClimateChange show increased public interest in policy changes." At the same time, the sentiment engine analyzes sentiment data and obtains information such as "Many users are expressing anger towards policy changes." This trend information and sentiment data are provided to news organizations and research institutions through the server.

[0852] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trend information and user sentiment data from social media, and the provision of information in real time.

[0853] The following describes the processing flow.

[0854] Step 1:

[0855] The server configures the credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information, the server performs an authentication process against the social media platform. Upon successful authentication, access to the API endpoint is granted.

[0856] Step 2:

[0857] The device receives specific keywords and survey period settings from the user. These keywords are strings of characters that indicate specific topics or subjects gaining attention on social media. The survey period specifies an arbitrary date range, such as the past 1 to 7 days. The user enters this information through the device's user interface.

[0858] Step 3:

[0859] The server calls social media APIs based on configured keywords and time periods to collect relevant message information. The API calls retrieve posts that match the specified criteria. During this process, metadata such as the post text, author, posting date and time, and the number of retweets and likes are also collected.

[0860] Step 4:

[0861] The server converts the collected message information into JSON format. This conversion simplifies data structuring and makes the data suitable for passing to the analysis engine. The modified data is stored in memory or a database.

[0862] Step 5:

[0863] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on how to analyze the specified data, and takes the form of "Analyze the following message and extract trend information."

[0864] Step 6:

[0865] The server sends data, including the generated prompts, to the analysis engine. The analysis engine uses natural language processing techniques to perform data analysis based on the prompts. Specifically, it identifies frequently occurring words, phrases, themes, or topics from the collected social media posts and extracts trend information.

[0866] Step 7:

[0867] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine uses text analysis techniques to identify the emotion in the message, classifying it into emotions such as joy, sadness, and anger. It then outputs the emotional state for each message as numerical data or tags.

[0868] Step 8:

[0869] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is appropriately formatted and prepared for user presentation. Possible output formats include reports and dashboards.

[0870] Step 9:

[0871] The server displays acquired trend information and sentiment data on the terminal. Through the terminal's interface, users can access the information in real time. Based on the information provided, users can understand currently trending topics and their own sentiment towards them.

[0872] Step 10:

[0873] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, a web dashboard, or file uploads to an FTP server. This makes the analysis results widely available.

[0874] Specific example

[0875] For example, consider a scenario where social media data for the past day is collected using the keyword "ClimateChange." The server collects relevant tweets and converts them into JSON format. Then, an analysis engine generates trend information such as, "The main topic related to ClimateChange recently is the growing public interest in policy changes." Simultaneously, a sentiment engine analyzes sentiment data such as, "Many users are expressing anger towards policy changes." This information is integrated and distributed in real time to news organizations and research institutions via the server.

[0876] (Example 2)

[0877] 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."

[0878] Conventional systems have struggled to efficiently and immediately integrate and provide trend information and sentiment data when analyzing information collected from online platforms such as social media. Furthermore, inconsistencies in data structuring, generation of analysis instructions, and distribution methods of analysis results have sometimes hindered real-time information provision.

[0879] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention,

[0880] The server has means to access the online platform API using authentication information and to collect communication information based on specified search terms and time ranges.

[0881] A means for inputting collected communication information into an analysis device and generating instruction sentences to identify trend information,

[0882] A means for acquiring trend information returned from an analysis device and outputting that trend information,

[0883] A means of inputting collected communication information into an emotion analysis device and analyzing the user's emotional data,

[0884] A means for integrating trend information and emotional data acquired from an analysis device and an emotion analysis device,

[0885] A means of providing integrated information to users and distributing it to information recipients,

[0886] This includes the ability to efficiently analyze collected communication information and immediately integrate and provide trend information and sentiment data.

[0887] "Authentication information" refers to the identification information required to access online platform APIs, and includes API keys, API secrets, access tokens, and access token secrets.

[0888] An "online platform API" is a programmatic interface for accessing specific functions or data provided by social media and other internet services.

[0889] A "search term" is a word or phrase specified to search for specific information on an online platform.

[0890] "Time range" refers to the period over which information collected on an online platform is collected, and can include any date range in the past.

[0891] "Communication information" refers to data such as messages, posts, and comments collected from online platforms, as well as their metadata.

[0892] An "analysis device" is a device or software used to analyze collected communication information and identify trend information, employing technologies such as natural language processing.

[0893] "Trend information" refers to information based on the frequency and relevance of topics and themes on online platforms, as identified by analytical tools.

[0894] An "instruction document" is a document or format that shows the analysis device how to analyze the collected communication information.

[0895] An "emotion analysis device" is a device or software that analyzes a user's emotions from text communication information and generates emotional data.

[0896] "Emotional data" refers to information about the type and intensity of emotions contained in text, generated by an emotion analysis device.

[0897] "Integration" refers to the process of combining trend information and emotional data obtained from analysis devices and emotion analysis devices into a single, consistent set of information.

[0898] "Information recipients" refers to news organizations, research institutions, and other groups that have subscribed to receive the analysis results.

[0899] This invention relates to a system that utilizes an online platform API to collect communication information based on specified search terms and time ranges, and analyzes trend information and user sentiment data using an analysis device and a sentiment analysis device. Specific embodiments of the present invention are described below.

[0900] Authentication information settings (server)

[0901] The server configures the authentication credentials for accessing the online platform API. These credentials include the API key, API secret, access token, and access token secret. The server uses this information to successfully authenticate to the online platform.

[0902] Setting keywords and time periods (device)

[0903] The terminal receives specific search terms and a search period from the user. The user enters the search term "ClimateChange" and the search period "Past 1 day" through the terminal's interface. The terminal receives this information and sends it to the server for the next processing.

[0904] Collection of communication information (server)

[0905] The server collects relevant communication information using the online platform API based on the configured search terms and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[0906] Conversion of communication information (server)

[0907] The server converts the collected communication information into a structured data format (e.g., JSON format). This improves the efficiency of data structuring and analysis.

[0908] Prompt generation and parsing request (server)

[0909] The server generates prompt statements to pass to the analysis device based on the communication information converted into JSON format. These prompt statements instruct the analysis device on which data to analyze and how. For example, the following prompt statements are generated:

[0910] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[0911] The server sends the generated prompt message to the analysis device and requests analysis.

[0912] Analysis of trend information (analysis device)

[0913] The analysis device uses natural language processing techniques to analyze trend information based on prompt messages received from the server. For example, the analysis device identifies frequently occurring themes and topics from the collected communication information and generates trend information such as "interest in policy changes is increasing."

[0914] Analysis of emotional data (emotion analysis device)

[0915] The server passes the collected communication information to an emotion analysis device, which analyzes the users' emotional data. The emotion analysis device classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text of the communication information and generates emotional data such as "Many users are showing anger towards the policy change."

[0916] Acquisition and output of trend information and sentiment data (server)

[0917] The server acquires trend information returned from the analysis device and sentiment data obtained from the sentiment analysis device, and integrates this data. The integrated information is provided to the user through a dashboard or dedicated application interface.

[0918] Distribution of trend information and sentiment data (server)

[0919] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[0920] Specifically, the process is carried out as follows: When the user enters the search term "ClimateChange" and the time period "Past 1 day" through the terminal interface, the server generates an API request and collects relevant data from the online platform. The collected data is converted into a structured data format, and a prompt message like the following is generated and sent to the analysis device:

[0921] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[0922] The analysis device analyzes trend information, and the sentiment analysis device generates sentiment data. The server integrates this information and distributes it to news organizations and research institutions.

[0923] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0924] Step 1:

[0925] The server reads authentication information such as API keys, API secrets, access tokens, and access token secrets from configuration files and databases, and issues authentication requests to the online platform API. This allows it to obtain an authentication token for accessing the online platform. The authentication information is used as input, and the authentication token is output.

[0926] Step 2:

[0927] The terminal receives specific search terms (e.g., "ClimateChange") and a search period (e.g., "Past 1 day") from the user. The user inputs this information through the interface, and the terminal receives it and sends it to the server. The input consists of the search terms and the search period, which are then output as a request to the server.

[0928] Step 3:

[0929] The server generates a request to the online platform API based on the search terms and research period received from the terminal. The generated request is constructed to include the search terms and research period as query parameters. This is output as an API request and sent to the online platform.

[0930] Step 4:

[0931] The server receives communication information collected from the online platform API. This communication information includes metadata such as the post text, author, and posting date and time. The response from the API is used as input data, and this is output as communication information.

[0932] Step 5:

[0933] The server converts the collected communication information into a structured data format (e.g., JSON). This improves the efficiency of data structuring and analysis. The input is unstructured communication information, and the output is JSON formatted data.

[0934] Step 6:

[0935] The server generates prompt messages to pass to the analysis device based on structured communication information. These prompt messages include specific analysis requirements (e.g., "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."). The input is communication information in JSON format, and the output is prompt messages.

[0936] Step 7:

[0937] The server sends the generated prompt message and JSON data to the analysis device, requesting analysis of trend information. The input is the prompt message and JSON data, and the output is the analysis request.

[0938] Step 8:

[0939] The analysis device extracts trend information using natural language processing techniques based on prompt messages received from the server. For example, it generates information such as "interest in policy changes is increasing." The input is prompt messages and JSON data, and the output is trend information.

[0940] Step 9:

[0941] The server retrieves trend information returned from the analysis device. Simultaneously, it passes communication information to the emotion analysis device and requests it to analyze the emotion data. The inputs are trend information and communication information, and the output is a request for emotion data analysis.

[0942] Step 10:

[0943] The emotion analysis device analyzes the text of communication information and classifies the type of emotion (e.g., joy, sadness, anger). For example, it might generate information such as "Many users are expressing anger towards the policy change." The input is the text of the communication information, and the output is emotion data.

[0944] Step 11:

[0945] The server integrates trend information returned from the analysis device and sentiment data acquired from the sentiment analysis device. The input is trend information and sentiment data, and the output is the integrated information.

[0946] Step 12:

[0947] The server provides integrated information to users through dashboards and dedicated application interfaces. The information is displayed visually, making it easily accessible to users. The input is integrated information, and the output is data displayed to the user.

[0948] Step 13:

[0949] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Information is distributed via dedicated APIs, email notifications, and file uploads to an FTP server. The input is integrated information, and the output is distributed data.

[0950] (Application Example 2)

[0951] 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."

[0952] Traditional advertising delivery systems have struggled to grasp user interests and emotions in real time, making it difficult to deliver effective advertisements. Furthermore, advertising based on trend information and sentiment data is rarely used, highlighting the need for methods that maximize advertising effectiveness.

[0953] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing a social media API using authentication information and collecting message information based on specified keywords and time periods; means for inputting the collected message information into an analysis engine and generating prompts for identifying trend information; and means for obtaining the trend information and sentiment data returned from the analysis engine and displaying advertising information using that data. This enables real-time advertising delivery based on trend information and sentiment data.

[0954] "Authentication information" refers to information such as API keys, API secrets, access tokens, and access token secrets required to access social media APIs.

[0955] A "social media API" refers to a programmatic interface provided by a social media platform, which allows external applications to access data on social media.

[0956] A "keyword" is a term used to refer to a specific topic or subject that is gaining attention on social media.

[0957] "Period" refers to any past date range for which data will be collected.

[0958] "Message information" refers to data such as posts on social media, the poster, and the date and time of posting.

[0959] An "analysis engine" is a system that uses natural language processing technology to identify trend information based on collected message data.

[0960] A "prompt" is a set of instructions that tells the analysis engine which data to analyze and how to analyze it.

[0961] "Trend information" refers to information that indicates frequently occurring themes and topics extracted from collected social media posts.

[0962] "Emotional data" refers to information extracted from social media messages that indicates a user's emotional state (e.g., joy, sadness, anger, etc.).

[0963] "Advertising information" refers to the content of advertisements displayed to users, and is generated based on trend information and sentiment data.

[0964] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, analyzes trend information and user sentiment data using an analysis engine, and uses that data to display optimal advertisements.

[0965] First, the server configures the authentication credentials (API key, API secret, access token, and access token secret) for accessing the social media API. These credentials are crucial for successful authentication to the social media platform.

[0966] Next, the device receives specific keywords and a search period from the user. For example, if the user sets the keyword "ClimateChange" and the time period to the past day, this information will indicate specific topics that are trending on social media.

[0967] Based on its configuration, the server uses social media APIs to collect relevant message information. This step includes information such as the post text, the poster, and the date and time of posting.

[0968] Next, the server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[0969] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how. For example, it might say, "Analyze the following messages and extract trend information."

[0970] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[0971] Next, the server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotion data.

[0972] The server then integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine and provides it to the user. It also includes means of displaying optimal advertisements using this data. For example, it might display an advertisement using trend information such as "A major topic regarding recent ClimateChange is the growing public interest in policy changes" and sentiment data such as "Many users are expressing anger towards policy changes."

[0973] Examples of prompt statements used include the following:

[0974] "Please analyze the following text data to extract trend information and sentiment."

[0975] [

[0976] {"text": "Climate change is real and urgent!", "user": "user1", "date": "2023-10-01 12:00:00"},

[0977] ...

[0978] ]

[0979] This system enables the rapid and accurate acquisition of trending information and user sentiment data from social media, allowing for real-time information delivery. Furthermore, by displaying advertising information based on the analysis results, it maximizes advertising effectiveness.

[0980] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0981] Step 1:

[0982] The server configures the credentials for accessing the social media API. Specifically, it uses credentials including the API key, API secret, access token, and access token secret to successfully authenticate to the social media platform. The input for this step is the credentials, and the output is a state where the social media API is accessible.

[0983] Step 2:

[0984] The terminal receives specific keywords and a survey period from the user. The user enters keywords (e.g., ClimateChange) and a period (e.g., the past day) through the terminal's interface. This information is used as the basis for data collection. The input for this step is the keywords and period entered by the user, and the output is the keyword and period settings.

[0985] Step 3:

[0986] The server collects relevant message information using social media APIs based on the configured keywords and time period. It retrieves metadata such as post text, author, and posting date and time from social media platforms. The input for this step is the keyword and time period settings, and the output is the collected message information.

[0987] Step 4:

[0988] The server converts the collected message information into JSON format. Using JSON format streamlines data structuring and analysis. The input for this step is the collected message information, and the output is data in JSON format.

[0989] Step 5:

[0990] The server generates a prompt to pass to the analysis engine based on the message information converted to JSON format. It creates a prompt statement and prepares it for passing to the analysis engine. Specifically, it generates an instruction statement in the format of "Analyze the following message and extract trend information." The input for this step is data in JSON format, and the output is the generated prompt statement.

[0991] Step 6:

[0992] The server passes the prompt message to the analysis engine, which then analyzes the trend information. The analysis engine uses natural language processing techniques to identify frequently occurring themes and topics from the collected social media posts. The input for this step is the generated prompt message, and the output is the identified trend information.

[0993] Step 7:

[0994] The server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text and generates emotion data. The input for this step is message information, and the output is emotion data.

[0995] Step 8:

[0996] The server integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. It then provides this information to the user through a means of displaying advertising information. For example, it selects and displays the most suitable advertisement based on the trend information and sentiment data. The input for this step is trend information and sentiment data, and the output is the display of the most suitable advertising information.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] [Fourth Embodiment]

[1001] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1002] 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.

[1003] 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).

[1004] 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.

[1005] 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.

[1006] 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).

[1007] 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.

[1008] 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.

[1009] 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.

[1010] 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.

[1011] 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.

[1012] 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.

[1013] 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".

[1014] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. Specific embodiments of this invention are described in detail below.

[1015] 1. Setting up authentication information

[1016] The server first configures the authentication credentials for accessing the social media API. These credentials are for accessing a specific social media platform and consist of API keys, tokens, and other information provided by each platform.

[1017] 2. Setting Keywords and Time Period

[1018] The device retrieves keywords and a survey period specified by the user. Typically, keywords are tags or specific phrases, and the period is often set to the past day or several days.

[1019] 3. Collection of message information

[1020] The server uses social media APIs to collect message information based on specified keywords and time periods. In this step, social media post data is collected via API calls. The collected message information is stored in text format.

[1021] 4. Message Information Conversion

[1022] The server converts the collected message information into JSON format. This is because JSON format is suitable for structuring data and passing it to the analysis engine.

[1023] 5. Prompt generation

[1024] The server uses the message information, converted into JSON format, to generate a prompt for the analysis engine. The prompt might take the form of, for example, "Analyze the following message information and summarize the trends."

[1025] 6. Trend Analysis

[1026] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it analyzes the collected social media posts to identify frequently occurring themes and topics.

[1027] 7. Acquisition and Output of Trend Information

[1028] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user. It is also distributed to multiple subscriber clients (e.g., news organizations and research institutions) as needed. Distribution methods include email, web application dashboards, and API endpoints.

[1029] Specific example

[1030] For example, if the keyword "AI" is set and social media data from the past day is collected, the server will collect tweets related to "AI". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". As a result of the analysis, trend information is obtained such as "The main topics related to AI recently are advancements in medical technology and future technologies". This information is provided to news organizations and research institutions through the server.

[1031] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trending information on social media and the provision of information in real time.

[1032] The following describes the processing flow.

[1033] Step 1:

[1034] The server configures the authentication credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information to perform the authentication process enables the use of the social media API.

[1035] Step 2:

[1036] The device receives specific keywords and time period settings from the user. These keywords are strings representing specific topics or subjects on social media, and the time period refers to any date range in the past. This information is entered by the user through the device's interface.

[1037] Step 3:

[1038] The server uses social media APIs to collect relevant message information based on configured keywords and time periods. The server makes API calls to retrieve posts that match the specified conditions, including metadata such as the post's text, author, and posting date and time.

[1039] Step 4:

[1040] The server converts the collected message information into JSON format. JSON is widely used to represent data structures and is suitable for efficient data processing by the parsing engine. The conversion results are stored in memory or a file.

[1041] Step 5:

[1042] The server uses message information stored in JSON format to generate a prompt to pass to the analysis engine. This prompt is text data that instructs the analysis engine on what kind of analysis to perform. Specifically, it might say something like, "Analyze the following tweets and extract trend information."

[1043] Step 6:

[1044] The server sends the generated prompt to the analysis engine. The analysis engine performs analysis based on the prompt, for example, using natural language processing techniques. This includes topic analysis of the collected message information and extraction of frequently occurring words.

[1045] Step 7:

[1046] The server retrieves trend information returned from the analysis engine. The analysis results include summarized information indicating which themes and topics are receiving particular attention. This information is then organized on the server into a format suitable for storage, analysis, and display.

[1047] Step 8:

[1048] The server displays the acquired trend information on the user's device. This information can be displayed via a web dashboard, a mobile application, or a dedicated software interface. Through this, users can understand currently trending topics and issues.

[1049] Step 9:

[1050] The server distributes trend information to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, or file uploads to an FTP server. This ensures that real-time trend information is widely available.

[1051] (Example 1)

[1052] 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".

[1053] With the increasing sharing of information on social media, there is a growing need to quickly and efficiently collect and analyze message information based on specific keywords and timeframes. However, traditional methods require considerable time and effort to structure the collected information and compile it into trending data. This makes it difficult to provide information in real time.

[1054] 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.

[1055] In this invention, the server includes means for accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods; means for converting the collected message information into JSON format; means for generating prompts for an analysis engine using the message information converted into JSON format; means for passing the generated prompts to the analysis engine and analyzing trend information; and means for obtaining the trend information returned from the analysis engine and outputting that trend information. This enables the rapid and efficient collection and analysis of information on social media, thereby providing real-time trend information.

[1056] "Authentication information" refers to information such as API keys and tokens required to access social media APIs.

[1057] A "social media API" is an interface provided by a social media platform that allows external applications and services to access the platform's data and functions.

[1058] A "keyword" is a specific hashtag or phrase designated by the user and is used to collect specific information from posts on social media.

[1059] "Period" refers to a specific time range specified by the user, and the collection of information is limited to social media posts within that range.

[1060] "Message information" refers to text data and posts collected on social media.

[1061] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a lightweight data exchange format for structuring, storing, and transmitting data.

[1062] An "analysis engine" is software or an algorithm used to analyze collected data and extract specific patterns or trends.

[1063] A "prompt" is an instruction or query used to give instructions to an analysis engine for analysis.

[1064] "Trend information" refers to information extracted by an analysis engine that shows frequently occurring patterns and tendencies related to a specific topic or theme.

[1065] "Output means" refers to methods or devices for displaying or providing analyzed trend information to users or other systems.

[1066] This invention relates to a system that uses social media APIs to collect message information based on specific keywords and time periods, and converts that message information into trend information using an analysis engine. This system makes it possible to quickly and efficiently acquire trend information on social media and provide it to users in real time.

[1067] 1. Setting up authentication information

[1068] The server first configures the authentication credentials for accessing the social media APIs. These credentials consist of API keys, tokens, etc., and are configured based on the API documentation of each social media platform. The server uses these credentials to securely access the APIs.

[1069] 2. Setting Keywords and Time Period

[1070] The terminal retrieves keywords and a survey period specified by the user. Users enter keywords and a period through input fields in web forms or applications. This input data is sent from the terminal to the server.

[1071] 3. Collection of message information

[1072] The server uses social media APIs to collect message information based on specified keywords and time periods. By calling the search APIs of social media platforms, relevant post data is retrieved in text format. This allows for the collection of a vast amount of post data in real time.

[1073] 4. Message Information Conversion

[1074] The server converts the collected message information into JSON format. JSON format is suitable for structuring and storing data, and can be easily handled as input for parsing engines. The converted data is temporarily stored.

[1075] 5. Prompt generation

[1076] The server uses the message information, converted to JSON format, to generate a prompt for the parsing engine. The prompt contains instructions for the parsing engine and takes the following format:

[1077] "Analyze the following message information and summarize the trends."

[1078] 6. Trend Analysis

[1079] The analysis engine performs natural language processing based on prompts received from the server to analyze trend information. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from the posted content and generate trend information.

[1080] 7. Acquisition and Output of Trend Information

[1081] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via the terminal. Furthermore, it is distributed to multiple subscriber clients (e.g., news organizations and research institutions) via email or API endpoints as needed.

[1082] Specific example

[1083] For example, if a user sets "AI" as a keyword and specifies the time period as the past day, the server will collect tweets related to "AI". These tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this data and generates recent trend information related to "AI". An example of a specific prompt would be:

[1084] "Analyze the following message information and summarize the trends."

[1085] The analysis results in trend information indicating that "the main topics related to AI recently are advancements in medical technology and future technologies." This information is provided to news organizations and research institutions via a server.

[1086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1087] Step 1:

[1088] The server configures the authentication credentials for accessing social media APIs. Authentication credentials, such as API keys and tokens, are stored securely and used when accessing the API. Specifically, the server reads a configuration file containing the stored credentials and uses that information to make API requests. Authentication credentials are required as input, and authenticated API access is obtained as output.

[1089] Step 2:

[1090] The terminal retrieves keywords and a survey period specified by the user. The user enters the keywords and period using a web form or application input field. The entered data is sent from the terminal to the server. The user-specified keywords and period are required as input, and this information is passed to the server as output.

[1091] Step 3:

[1092] The server uses social media APIs to collect message information based on specified keywords and time periods. It calls social media search APIs to retrieve relevant post data in text format. Keywords and time periods are required as input, and relevant message information is obtained as output. Specifically, it makes API calls and saves the results to an internal database or file system.

[1093] Step 4:

[1094] The server converts the collected message information into JSON format. JSON format is an efficient way to structure data and is suitable as input for the parsing engine. The collected message information is required as input, and the output is data in JSON format. Specifically, the raw text data is converted into a JSON object and temporarily stored.

[1095] Step 5:

[1096] The server generates a prompt for the parsing engine using message information converted to JSON format. The prompt instructs the parsing engine on what processing to perform. JSON format message information is required as input, and the prompt is obtained as output. Specifically, the server incorporates the message information into the prompt statement, preparing it for transmission to the parsing engine.

[1097] Step 6:

[1098] The analysis engine performs natural language processing based on prompts provided by the server to analyze trend information. A prompt is required as input, and the analyzed trend information is obtained as output. Specifically, it uses a generative AI model (e.g., the GPT series) to extract frequently occurring themes and topics from message information.

[1099] Step 7:

[1100] The server retrieves trend information returned from the analysis engine. This retrieved trend information is displayed to the user via their terminal. Furthermore, it is distributed to news organizations and research institutions via email or API endpoints as needed. The server requires trend information from the analysis engine as input and provides information to users and subscribers as output. Specific actions include displaying the information on a dashboard, sending emails, and making API calls.

[1101] (Application Example 1)

[1102] 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".

[1103] Traditional advertising analytics systems struggled to grasp market reactions in real time, making immediate optimization of advertising campaigns difficult. Furthermore, data collection and analysis from social networking services were cumbersome, lacking the means to quickly develop effective advertising strategies. This hindered the maximization of advertising effectiveness.

[1104] 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.

[1105] This invention includes a server that accesses a social networking service API using authentication information and collects text information based on specified search words and time periods; a server that inputs the collected text information into an analysis device and generates a generative AI model prompt for identifying trend information; a server that retrieves the trend information returned from the analysis device and outputs that trend information; and a server that grasps market reactions in real time and optimizes advertising content. This enables advertisers to immediately grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[1106] "Authentication information" refers to a collection of information used to ensure security, such as access keys and tokens, for accessing social networking service APIs.

[1107] A "Social Networking Service API" is an application programming interface for programmatically retrieving user-generated data, profile information, and other data from a specified platform.

[1108] "Search terms" refer to keywords or hashtags related to a specific topic or theme, and are the criteria used to collect data from social networking services.

[1109] "Period" refers to the time frame for data collection, specifying a time range such as the past hour, day, or week.

[1110] "Text information" refers to character data such as messages, posts, and comments collected from social networking services.

[1111] An "analysis device" is a computer device used to analyze collected data and derive specific meanings or trends.

[1112] A "generated AI model prompt" is a specific instruction given when inputting collected data into an analysis device, and it specifies the input data required to perform a particular task.

[1113] "Trend information" refers to important themes and trends derived from collected and analyzed data, and is used in marketing and advertising strategies.

[1114] "Real-time" refers to a situation where data collection, analysis, and output occur almost instantly, meaning that the latest information is provided without delay.

[1115] "Optimization" refers to the process of adjusting and modifying advertising content and strategies based on data to achieve maximum effectiveness.

[1116] System Configuration

[1117] This invention is a system for collecting and analyzing advertising-related trend information in real time from specific social networking services and for quickly understanding market reactions based on the results. This system consists of three main components: a server, a terminal, and a user.

[1118] Hardware and software

[1119] Hardware: Servers are high-performance computer devices used for data collection and analysis. Smartphones, tablets, and PCs are used as user terminals. For analysis, computing resources are needed to run generative AI models such as GPT-3.

[1120] Software: Data collection, transformation, and analysis are performed using Python and other programming languages. Specifically, the requests library and natural language processing libraries are used.

[1121] Data flow

[1122] 1. Setting up authentication information

[1123] The server first configures the authentication credentials for accessing the social networking service API. These credentials include security information such as API keys and tokens.

[1124] 2. Setting Keywords and Time Period

[1125] The user enters a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their device. This information is sent to the server and configured.

[1126] 3. Collection of text information

[1127] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. The collected text information is stored on the server in text format.

[1128] 4. Message Information Conversion

[1129] The server converts the collected text information into JSON format before passing it to the analysis device (generating AI model). The JSON format makes it easy to structure data and allows for efficient analysis.

[1130] 5. Generating AI Model Prompts

[1131] Based on the text information converted to JSON format, the server generates a prompt message that reads, "Analyze the following message information and summarize the trends related to advertising."

[1132] 6. Analysis of trend information

[1133] The server passes the generated prompt messages to the analysis device, which uses a generation AI model to analyze trend information. This allows for the identification of frequently occurring themes and topics.

[1134] 7. Acquisition and Output of Trend Information

[1135] The server retrieves trend information returned from the analysis device and outputs this information to the user. Output methods include displaying a dashboard, email notifications, and generating reports. It also provides means to understand market reactions in real time and optimize advertising content.

[1136] Specific example

[1137] For example, if a user sets the search term "new products" and requests data for the past day, the server will collect posts related to "new products." After collection, these posts are converted to JSON format, and a prompt message like the following is generated:

[1138] "Analyze the following message information and summarize the advertising-related trends: {Message data in JSON format}"

[1139] The generative AI model analyzes this data and generates trend information, such as "Recent key topics regarding new products are environmentally friendly packaging and the adoption of new technologies." This information is then displayed to the user via the server.

[1140] This allows advertisers to instantly grasp market reactions in real time and quickly plan and execute optimal advertising strategies.

[1141] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1142] Step 1:

[1143] The server configures the authentication information (API key and token) for accessing the social networking service API. It receives the authentication information as input and uses it to establish a session for the API connection. The output of this step indicates that the API connection has been established.

[1144] Step 2:

[1145] The user inputs a specific search term (e.g., "new product") and a data collection period (e.g., the past day) from their terminal. This input is sent to the server and saved as settings for analysis. The input consists of the search term and period, and the output is the configured analysis parameters.

[1146] Step 3:

[1147] The server uses authentication credentials to access the social networking service API and collects text information based on specified search keywords and time periods. It makes API calls to retrieve the corresponding post data. The input is the authentication credentials and parsing parameters, and the output is the collected text information.

[1148] Step 4:

[1149] The server converts the collected text information into JSON format before passing it to the analysis device. This structures the data, allowing for more efficient analysis. The input is the collected text information, and the output is data in JSON format.

[1150] Step 5:

[1151] The server generates a prompt message based on the text information converted to JSON format, which reads, "Analyze the following message information and summarize the trends related to advertising." The prompt message is an instruction to the parser. The input is text information in JSON format, and the output is the generated prompt message.

[1152] Step 6:

[1153] The server passes the generated prompt sentences to the analysis device (generating AI model) for analysis. Based on the prompt sentences, the analysis device identifies frequently occurring themes and trends from the data. The input consists of prompt sentences and text information in JSON format, and the output is trend information.

[1154] Step 7:

[1155] The server retrieves trend information returned from the analysis device and outputs this information to the user. This information is provided to the user through methods such as dashboard display, email notifications, and report generation. The input is trend information, and the output is the presentation of information to the user. It also includes means for understanding market reactions in real time and optimizing advertising content.

[1156] By following these steps, advertisers can instantly grasp market reactions in real time and quickly plan and execute the optimal advertising strategy.

[1157] 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.

[1158] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, and analyzes trend information and user sentiment data using a sentiment engine. Specific embodiments of this invention are described in detail below.

[1159] 1. Setting up authentication information

[1160] The server configures the authentication credentials for accessing social media APIs. These credentials include API keys, API secrets, access tokens, and access token secrets. Using this information, the server successfully authenticates to the social media platform.

[1161] 2. Setting Keywords and Time Period

[1162] The device receives specific keywords and a research period from the user. These keywords represent specific topics or subjects gaining attention on social media, and the research period refers to any date range in the past. The user enters this information through the device's interface.

[1163] 3. Collection of message information

[1164] The server uses social media APIs to collect relevant message information based on the configured keywords and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[1165] 4. Message Information Conversion

[1166] The server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[1167] 5. Prompt generation and analysis request

[1168] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how, and takes the form of "analyze the following messages and extract trend information."

[1169] 6. Analysis of trend information

[1170] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[1171] 7. Analysis of emotional data

[1172] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotional data.

[1173] 8. Acquisition and output of trend information and sentiment data

[1174] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is integrated and provided to the user. The information is also displayed through a dashboard and a dedicated application interface.

[1175] 9. Distribution of trend information and sentiment data

[1176] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[1177] Specific example

[1178] For example, if the keyword "ClimateChange" is set and social media data for the past day is collected, the server will collect tweets related to "ClimateChange". After collection, these tweets are converted to JSON format and passed to the analysis engine. The analysis engine analyzes this and generates trend information such as "Recent major topics related to ClimateChange show increased public interest in policy changes." At the same time, the sentiment engine analyzes sentiment data and obtains information such as "Many users are expressing anger towards policy changes." This trend information and sentiment data are provided to news organizations and research institutions through the server.

[1179] The specific embodiments of the present invention have been described in detail above. This system enables the rapid and accurate acquisition of trend information and user sentiment data from social media, and the provision of information in real time.

[1180] The following describes the processing flow.

[1181] Step 1:

[1182] The server configures the credentials for accessing the social media API. These credentials include the API key, API secret, access token, and access token secret. Using this information, the server performs an authentication process against the social media platform. Upon successful authentication, access to the API endpoint is granted.

[1183] Step 2:

[1184] The device receives specific keywords and survey period settings from the user. These keywords are strings of characters that indicate specific topics or subjects gaining attention on social media. The survey period specifies an arbitrary date range, such as the past 1 to 7 days. The user enters this information through the device's user interface.

[1185] Step 3:

[1186] The server calls social media APIs based on configured keywords and time periods to collect relevant message information. The API calls retrieve posts that match the specified criteria. During this process, metadata such as the post text, author, posting date and time, and the number of retweets and likes are also collected.

[1187] Step 4:

[1188] The server converts the collected message information into JSON format. This conversion simplifies data structuring and makes the data suitable for passing to the analysis engine. The modified data is stored in memory or a database.

[1189] Step 5:

[1190] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on how to analyze the specified data, and takes the form of "Analyze the following message and extract trend information."

[1191] Step 6:

[1192] The server sends data, including the generated prompts, to the analysis engine. The analysis engine uses natural language processing techniques to perform data analysis based on the prompts. Specifically, it identifies frequently occurring words, phrases, themes, or topics from the collected social media posts and extracts trend information.

[1193] Step 7:

[1194] The server passes the collected message information to the emotion engine, which analyzes the user's emotional data. The emotion engine uses text analysis techniques to identify the emotion in the message, classifying it into emotions such as joy, sadness, and anger. It then outputs the emotional state for each message as numerical data or tags.

[1195] Step 8:

[1196] The server retrieves trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. This data is appropriately formatted and prepared for user presentation. Possible output formats include reports and dashboards.

[1197] Step 9:

[1198] The server displays acquired trend information and sentiment data on the terminal. Through the terminal's interface, users can access the information in real time. Based on the information provided, users can understand currently trending topics and their own sentiment towards them.

[1199] Step 10:

[1200] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, a web dashboard, or file uploads to an FTP server. This makes the analysis results widely available.

[1201] Specific example

[1202] For example, consider a scenario where social media data for the past day is collected using the keyword "ClimateChange." The server collects relevant tweets and converts them into JSON format. Then, an analysis engine generates trend information such as, "The main topic related to ClimateChange recently is the growing public interest in policy changes." Simultaneously, a sentiment engine analyzes sentiment data such as, "Many users are expressing anger towards policy changes." This information is integrated and distributed in real time to news organizations and research institutions via the server.

[1203] (Example 2)

[1204] 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".

[1205] Conventional systems have struggled to efficiently and immediately integrate and provide trend information and sentiment data when analyzing information collected from online platforms such as social media. Furthermore, inconsistencies in data structuring, generation of analysis instructions, and distribution methods of analysis results have sometimes hindered real-time information provision.

[1206] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention,

[1207] The server has means to access the online platform API using authentication information and to collect communication information based on specified search terms and time ranges.

[1208] A means for inputting collected communication information into an analysis device and generating instruction sentences to identify trend information,

[1209] A means for acquiring trend information returned from an analysis device and outputting that trend information,

[1210] A means of inputting collected communication information into an emotion analysis device and analyzing the user's emotional data,

[1211] A means for integrating trend information and emotional data acquired from an analysis device and an emotion analysis device,

[1212] A means of providing integrated information to users and distributing it to information recipients,

[1213] This includes the ability to efficiently analyze collected communication information and immediately integrate and provide trend information and sentiment data.

[1214] "Authentication information" refers to the identification information required to access online platform APIs, and includes API keys, API secrets, access tokens, and access token secrets.

[1215] An "online platform API" is a programmatic interface for accessing specific functions or data provided by social media and other internet services.

[1216] A "search term" is a word or phrase specified to search for specific information on an online platform.

[1217] "Time range" refers to the period over which information collected on an online platform is collected, and can include any date range in the past.

[1218] "Communication information" refers to data such as messages, posts, and comments collected from online platforms, as well as their metadata.

[1219] An "analysis device" is a device or software used to analyze collected communication information and identify trend information, employing technologies such as natural language processing.

[1220] "Trend information" refers to information based on the frequency and relevance of topics and themes on online platforms, as identified by analytical tools.

[1221] An "instruction document" is a document or format that shows the analysis device how to analyze the collected communication information.

[1222] An "emotion analysis device" is a device or software that analyzes a user's emotions from text communication information and generates emotional data.

[1223] "Emotional data" refers to information about the type and intensity of emotions contained in text, generated by an emotion analysis device.

[1224] "Integration" refers to the process of combining trend information and emotional data obtained from analysis devices and emotion analysis devices into a single, consistent set of information.

[1225] "Information recipients" refers to news organizations, research institutions, and other groups that have subscribed to receive the analysis results.

[1226] This invention relates to a system that utilizes an online platform API to collect communication information based on specified search terms and time ranges, and analyzes trend information and user sentiment data using an analysis device and a sentiment analysis device. Specific embodiments of the present invention are described below.

[1227] Authentication information settings (server)

[1228] The server configures the authentication credentials for accessing the online platform API. These credentials include the API key, API secret, access token, and access token secret. The server uses this information to successfully authenticate to the online platform.

[1229] Setting keywords and time periods (device)

[1230] The terminal receives specific search terms and a search period from the user. The user enters the search term "ClimateChange" and the search period "Past 1 day" through the terminal's interface. The terminal receives this information and sends it to the server for the next processing.

[1231] Collection of communication information (server)

[1232] The server collects relevant communication information using the online platform API based on the configured search terms and time period. The information obtained in this step includes metadata such as the post text, author, and posting date and time.

[1233] Conversion of communication information (server)

[1234] The server converts the collected communication information into a structured data format (e.g., JSON format). This improves the efficiency of data structuring and analysis.

[1235] Prompt generation and parsing request (server)

[1236] The server generates prompt statements to pass to the analysis device based on the communication information converted into JSON format. These prompt statements instruct the analysis device on which data to analyze and how. For example, the following prompt statements are generated:

[1237] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[1238] The server sends the generated prompt message to the analysis device and requests analysis.

[1239] Analysis of trend information (analysis device)

[1240] The analysis device uses natural language processing techniques to analyze trend information based on prompt messages received from the server. For example, the analysis device identifies frequently occurring themes and topics from the collected communication information and generates trend information such as "interest in policy changes is increasing."

[1241] Analysis of emotional data (emotion analysis device)

[1242] The server passes the collected communication information to an emotion analysis device, which analyzes the users' emotional data. The emotion analysis device classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text of the communication information and generates emotional data such as "Many users are showing anger towards the policy change."

[1243] Acquisition and output of trend information and sentiment data (server)

[1244] The server acquires trend information returned from the analysis device and sentiment data obtained from the sentiment analysis device, and integrates this data. The integrated information is provided to the user through a dashboard or dedicated application interface.

[1245] Distribution of trend information and sentiment data (server)

[1246] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Distribution methods include a dedicated API, email notifications, and file uploads to an FTP server.

[1247] Specifically, the process is carried out as follows: When the user enters the search term "ClimateChange" and the time period "Past 1 day" through the terminal interface, the server generates an API request and collects relevant data from the online platform. The collected data is converted into a structured data format, and a prompt message like the following is generated and sent to the analysis device:

[1248] "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."

[1249] The analysis device analyzes trend information, and the sentiment analysis device generates sentiment data. The server integrates this information and distributes it to news organizations and research institutions.

[1250] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1251] Step 1:

[1252] The server reads authentication information such as API keys, API secrets, access tokens, and access token secrets from configuration files and databases, and issues authentication requests to the online platform API. This allows it to obtain an authentication token for accessing the online platform. The authentication information is used as input, and the authentication token is output.

[1253] Step 2:

[1254] The terminal receives specific search terms (e.g., "ClimateChange") and a search period (e.g., "Past 1 day") from the user. The user inputs this information through the interface, and the terminal receives it and sends it to the server. The input consists of the search terms and the search period, which are then output as a request to the server.

[1255] Step 3:

[1256] The server generates a request to the online platform API based on the search terms and research period received from the terminal. The generated request is constructed to include the search terms and research period as query parameters. This is output as an API request and sent to the online platform.

[1257] Step 4:

[1258] The server receives communication information collected from the online platform API. This communication information includes metadata such as the post text, author, and posting date and time. The response from the API is used as input data, and this is output as communication information.

[1259] Step 5:

[1260] The server converts the collected communication information into a structured data format (e.g., JSON). This improves the efficiency of data structuring and analysis. The input is unstructured communication information, and the output is JSON formatted data.

[1261] Step 6:

[1262] The server generates prompt messages to pass to the analysis device based on structured communication information. These prompt messages include specific analysis requirements (e.g., "Analyze the following messages and extract trend information. Identify the latest topics related to 'ClimateChange'."). The input is communication information in JSON format, and the output is prompt messages.

[1263] Step 7:

[1264] The server sends the generated prompt message and JSON data to the analysis device, requesting analysis of trend information. The input is the prompt message and JSON data, and the output is the analysis request.

[1265] Step 8:

[1266] The analysis device extracts trend information using natural language processing techniques based on prompt messages received from the server. For example, it generates information such as "interest in policy changes is increasing." The input is prompt messages and JSON data, and the output is trend information.

[1267] Step 9:

[1268] The server retrieves trend information returned from the analysis device. Simultaneously, it passes communication information to the emotion analysis device and requests it to analyze the emotion data. The inputs are trend information and communication information, and the output is a request for emotion data analysis.

[1269] Step 10:

[1270] The emotion analysis device analyzes the text of communication information and classifies the type of emotion (e.g., joy, sadness, anger). For example, it might generate information such as "Many users are expressing anger towards the policy change." The input is the text of the communication information, and the output is emotion data.

[1271] Step 11:

[1272] The server integrates trend information returned from the analysis device and sentiment data acquired from the sentiment analysis device. The input is trend information and sentiment data, and the output is the integrated information.

[1273] Step 12:

[1274] The server provides integrated information to users through dashboards and dedicated application interfaces. The information is displayed visually, making it easily accessible to users. The input is integrated information, and the output is data displayed to the user.

[1275] Step 13:

[1276] The server distributes trend information and sentiment data to news organizations and research institutions that have subscribed to it. Information is distributed via dedicated APIs, email notifications, and file uploads to an FTP server. The input is integrated information, and the output is distributed data.

[1277] (Application Example 2)

[1278] 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".

[1279] Traditional advertising delivery systems have struggled to grasp user interests and emotions in real time, making it difficult to deliver effective advertisements. Furthermore, advertising based on trend information and sentiment data is rarely used, highlighting the need for methods that maximize advertising effectiveness.

[1280] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing a social media API using authentication information and collecting message information based on specified keywords and time periods; means for inputting the collected message information into an analysis engine and generating prompts for identifying trend information; and means for obtaining the trend information and sentiment data returned from the analysis engine and displaying advertising information using that data. This enables real-time advertising delivery based on trend information and sentiment data.

[1281] "Authentication information" refers to information such as API keys, API secrets, access tokens, and access token secrets required to access social media APIs.

[1282] A "social media API" refers to a programmatic interface provided by a social media platform, which allows external applications to access data on social media.

[1283] A "keyword" is a term used to refer to a specific topic or subject that is gaining attention on social media.

[1284] "Period" refers to any past date range for which data will be collected.

[1285] "Message information" refers to data such as posts on social media, the poster, and the date and time of posting.

[1286] An "analysis engine" is a system that uses natural language processing technology to identify trend information based on collected message data.

[1287] A "prompt" is a set of instructions that tells the analysis engine which data to analyze and how to analyze it.

[1288] "Trend information" refers to information that indicates frequently occurring themes and topics extracted from collected social media posts.

[1289] "Emotional data" refers to information extracted from social media messages that indicates a user's emotional state (e.g., joy, sadness, anger, etc.).

[1290] "Advertising information" refers to the content of advertisements displayed to users, and is generated based on trend information and sentiment data.

[1291] This invention relates to a system that utilizes social media APIs to collect message information based on specified keywords and time periods, analyzes trend information and user sentiment data using an analysis engine, and uses that data to display optimal advertisements.

[1292] First, the server configures the authentication credentials (API key, API secret, access token, and access token secret) for accessing the social media API. These credentials are crucial for successful authentication to the social media platform.

[1293] Next, the device receives specific keywords and a search period from the user. For example, if the user sets the keyword "ClimateChange" and the time period to the past day, this information will indicate specific topics that are trending on social media.

[1294] Based on its configuration, the server uses social media APIs to collect relevant message information. This step includes information such as the post text, the poster, and the date and time of posting.

[1295] Next, the server converts the collected message information into JSON format. Because JSON format is suitable for structuring and efficiently analyzing data, it is used to pass the data to the analysis engine and sentiment engine.

[1296] The server generates a prompt to pass to the analysis engine based on the message information converted into JSON format. This prompt instructs the analysis engine on which data to analyze and how. For example, it might say, "Analyze the following messages and extract trend information."

[1297] The analysis engine uses natural language processing techniques to analyze trend information based on prompts received from the server. In this process, it identifies frequently occurring themes and topics from the collected social media posts.

[1298] Next, the server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the message text and generates emotion data.

[1299] The server then integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine and provides it to the user. It also includes means of displaying optimal advertisements using this data. For example, it might display an advertisement using trend information such as "A major topic regarding recent ClimateChange is the growing public interest in policy changes" and sentiment data such as "Many users are expressing anger towards policy changes."

[1300] Examples of prompt statements used include the following:

[1301] "Please analyze the following text data to extract trend information and sentiment."

[1302] [

[1303] {"text": "Climate change is real and urgent!", "user": "user1", "date": "2023-10-01 12:00:00"},

[1304] ...

[1305] ]

[1306] This system enables the rapid and accurate acquisition of trending information and user sentiment data from social media, allowing for real-time information delivery. Furthermore, by displaying advertising information based on the analysis results, it maximizes advertising effectiveness.

[1307] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1308] Step 1:

[1309] The server configures the credentials for accessing the social media API. Specifically, it uses credentials including the API key, API secret, access token, and access token secret to successfully authenticate to the social media platform. The input for this step is the credentials, and the output is a state where the social media API is accessible.

[1310] Step 2:

[1311] The terminal receives specific keywords and a survey period from the user. The user enters keywords (e.g., ClimateChange) and a period (e.g., the past day) through the terminal's interface. This information is used as the basis for data collection. The input for this step is the keywords and period entered by the user, and the output is the keyword and period settings.

[1312] Step 3:

[1313] The server collects relevant message information using social media APIs based on the configured keywords and time period. It retrieves metadata such as post text, author, and posting date and time from social media platforms. The input for this step is the keyword and time period settings, and the output is the collected message information.

[1314] Step 4:

[1315] The server converts the collected message information into JSON format. Using JSON format streamlines data structuring and analysis. The input for this step is the collected message information, and the output is data in JSON format.

[1316] Step 5:

[1317] The server generates a prompt to pass to the analysis engine based on the message information converted to JSON format. It creates a prompt statement and prepares it for passing to the analysis engine. Specifically, it generates an instruction statement in the format of "Analyze the following message and extract trend information." The input for this step is data in JSON format, and the output is the generated prompt statement.

[1318] Step 6:

[1319] The server passes the prompt message to the analysis engine, which then analyzes the trend information. The analysis engine uses natural language processing techniques to identify frequently occurring themes and topics from the collected social media posts. The input for this step is the generated prompt message, and the output is the identified trend information.

[1320] Step 7:

[1321] The server passes the collected message information to the emotion engine, which analyzes the user's emotion data. The emotion engine classifies the type of emotion (e.g., joy, sadness, anger, etc.) from the text and generates emotion data. The input for this step is message information, and the output is emotion data.

[1322] Step 8:

[1323] The server integrates trend information returned from the analysis engine and sentiment data obtained from the sentiment engine. It then provides this information to the user through a means of displaying advertising information. For example, it selects and displays the most suitable advertisement based on the trend information and sentiment data. The input for this step is trend information and sentiment data, and the output is the display of the most suitable advertising information.

[1324] 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.

[1325] 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.

[1326] 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 robot 414.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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.

[1332] 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."

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1345] The following is further disclosed regarding the embodiments described above.

[1346] (Claim 1)

[1347] A means of accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods,

[1348] A means for inputting collected message information into an analysis engine and generating prompts to identify trend information,

[1349] A means of obtaining trend information returned from the analysis engine and outputting that trend information,

[1350] A system that includes this.

[1351] (Claim 2)

[1352] A means of converting collected message information into JSON format,

[1353] The system according to claim 1, further comprising means for passing prompts to an analysis engine and analyzing trend information.

[1354] (Claim 3)

[1355] The system according to claim 1, wherein the analysis engine performs natural language processing.

[1356] "Example 1"

[1357] (Claim 1)

[1358] A means of accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods,

[1359] A means of converting collected message information into JSON format,

[1360] A means for generating a prompt for the parsing engine using message information converted to JSON format,

[1361] A means of passing the generated prompt to the analysis engine and analyzing trend information,

[1362] A means of obtaining trend information returned from the analysis engine and outputting that trend information,

[1363] A system that includes this.

[1364] (Claim 2)

[1365] The system according to claim 1, which converts collected message information into a structured data format and generates prompts for an analysis engine.

[1366] (Claim 3)

[1367] The system according to claim 1, wherein the analysis engine performs natural language processing.

[1368] "Application Example 1"

[1369] (Claim 1)

[1370] A means of accessing a social networking service API using authentication information and collecting text information based on specified search words and time period,

[1371] A means for inputting collected text information into an analysis device and generating a generative AI model prompt for identifying trend information,

[1372] A means for acquiring trend information returned from an analysis device and outputting that trend information,

[1373] A means to understand market reactions in real time and optimize advertising content,

[1374] A system that includes this.

[1375] (Claim 2)

[1376] A means of converting collected text information into JSON format,

[1377] The system according to claim 1, further comprising means for passing a generated AI model prompt to an analysis device and analyzing trend information.

[1378] (Claim 3)

[1379] The system according to claim 1, wherein the analysis device performs natural language processing.

[1380] "Example 2 of combining an emotion engine"

[1381] (Claim 1)

[1382] A means of accessing an online platform API using authentication information and collecting communication information based on specified search terms and time ranges,

[1383] A means for inputting collected communication information into an analysis device and generating instruction sentences to identify trend information,

[1384] A means for acquiring trend information returned from an analysis device and outputting that trend information,

[1385] A means of inputting collected communication information into an emotion analysis device and analyzing the user's emotional data,

[1386] A means for integrating trend information and emotional data acquired from an analysis device and an emotion analysis device,

[1387] A means of providing integrated information to users and distributing it to information recipients,

[1388] A system that includes this.

[1389] (Claim 2)

[1390] A means for converting collected communication information into a structured data format,

[1391] The system according to claim 1, further comprising means for passing instructions to an analysis device and analyzing trend information.

[1392] (Claim 3)

[1393] The system according to claim 1, wherein the analysis device performs natural language processing.

[1394] "Application example 2 when combining with an emotional engine"

[1395] (Claim 1)

[1396] A means of accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods,

[1397] A means for inputting collected message information into an analysis engine and generating prompts to identify trend information,

[1398] A means of obtaining trend information and sentiment data returned from an analysis engine and using that data to display advertising information,

[1399] A system that includes this.

[1400] (Claim 2)

[1401] A means of converting collected message information into JSON format,

[1402] The system according to claim 1, further comprising means for passing prompts to an analysis engine and analyzing trend information and sentiment data.

[1403] (Claim 3)

[1404] The system according to claim 1, wherein the analysis engine performs natural language processing. [Explanation of Symbols]

[1405] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of accessing social media APIs using authentication information and collecting message information based on specified keywords and time periods, A means for inputting collected message information into an analysis engine and generating prompts to identify trend information, A means of obtaining trend information returned from the analysis engine and outputting that trend information, A system that includes this.

2. A means of converting collected message information into JSON format, The system according to claim 1, further comprising means for passing a prompt to an analysis engine and analyzing trend information.

3. The system according to claim 1, wherein the analysis engine performs natural language processing.

Images