System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting trend information; means for analyzing and presenting the collected trend information to a user; means for generating a post related to a trend selected by the user; means for presenting the generated post to the user and providing an opportunity for editing; means for posting to a social networking service after the post has been reviewed and edited by the user; and means for collecting and displaying engagement data of the posted content to the user as feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Creating attention-grabbing posts on modern social networking services (SNS) is important for many users. Many users want to create buzzworthy posts, but at the same time, they risk posting inappropriate content in an attempt to gain attention, leading to backlash and criticism. Furthermore, many users find it difficult to grasp constantly changing trend information and generate effective posts based on that information. In these circumstances, a system that helps users effectively and safely create attention-grabbing posts is needed. [Means for solving the problem]

[0005] The present invention relates to a system for safely and effectively posting attention-grabbing content on a social networking service, and includes the following means. First, a means for collecting trend information is provided to constantly obtain the latest trend data. Then, a means for analyzing the collected trend information and presenting it to the user is provided. Furthermore, a natural language generation model is used as a means for generating a post related to a trend selected by the user. This generated post is presented to the user, who is given the opportunity to edit it. Finally, a means for posting the edited post to the social networking service is provided. The system also includes a means for collecting engagement data on the posted content and displaying it to the user as feedback, allowing users to post content that will go viral with peace of mind.

[0006] "Trending information" refers to topics or hashtags that are rapidly gaining popularity on social networking services.

[0007] "Means of collection" refers to a mechanism for obtaining trend information in real time using APIs of social networking services and other data acquisition methods.

[0008] "Means for analyzing and presenting to the user" refers to a mechanism for analyzing collected trend information and presenting the results to the user in visual or text format.

[0009] "Means for generation" refers to a mechanism that uses a natural language generation model to automatically create related posts based on trends selected by users.

[0010] "Means for providing editing opportunities" refers to a mechanism that provides an interface for users to review the generated posts and make corrections or additions as necessary.

[0011] "Means for posting" refers to a mechanism for automatically sending a user-confirmed and edited post to a social networking service.

[0012] "Engagement Data" refers to data that includes reactions and interactions with posted content (e.g., likes, comments, shares).

[0013] "Means for displaying to the user as feedback" refers to a mechanism for analyzing the collected engagement data and visually displaying the results to the user.

[0014] A "natural language generation model" refers to an artificial intelligence model that generates text in natural language that humans can understand based on input information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0036] The present invention relates to a system that collects and analyzes trend information, generates, edits, and posts posts, and provides feedback on engagement data, in order to safely and effectively post attention-grabbing content on social networking services (SNS). This system is composed of server, terminal, and user components.

[0037] 1. Collecting trend information

[0038] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. This ensures that the latest trend information is always kept in the system. For example, trending hashtags such as "WorldCup" and "Oscars" are collected.

[0039] 2. Analysis and presentation of trend information

[0040] The server analyzes the collected trend data and organizes it for presentation to the user. The analysis results are displayed on the device in visual or text format for easy understanding by the user. Specifically, the message displayed is, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0041] 3. Post Generation

[0042] When a user selects a trend they are interested in, the server uses a natural language generation model (e.g., GPT-4) to generate a post related to the selected trend. For example, a request to "generate a post about the World Cup" generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[0043] 4. Check and edit the generated text

[0044] The generated post is displayed on the device for the user to review. An editing interface is also provided on the device, allowing the user to modify or add to the generated post as needed. For example, the user can insert an additional hashtag such as "I want to connect with soccer fans."

[0045] 5. Submitting a post

[0046] Once the post is finalized, the device sends it to the social networking platform's API via the post button, which publishes the post to the actual social networking platform. For example, this can be done using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[0047] 6. Engagement Data Collection and Feedback

[0048] After a post is published, the server periodically collects engagement data (number of likes, retweets, comments, etc.) using social media APIs. This data is analyzed by the server and displayed as feedback on the device, allowing users to see how their post is performing. For example, it might say, "Your post has received the following responses: 200 likes, 50 retweets, 10 comments."

[0049] For example, if a user selects the trend "WorldCup" and posts the generated message "Last night's WorldCup game was amazing! Who was your best player?", the post will generate a lot of reactions on social media, and the reactions will be collected as engagement data. This data will be provided to the user as feedback and used to improve future posts.

[0050] This system allows users to safely and effectively create buzzworthy posts, and attract attention on social media with trending posts.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] The server sends a request to the social networking service's API (e.g., Twitter API) to retrieve trend information. Specifically, it uses the GET / trends / place endpoint to collect the current trending hashtags and their associated data.

[0054] Step 2:

[0055] The server analyzes the collected trend information and converts it into an appropriate format for presentation to users. Specifically, it parses the JSON format data and extracts trending hashtags and their summaries.

[0056] Step 3:

[0057] The server then transmits the analyzed trend information to the device, which then displays the information on a user interface, prompting the user with a message such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0058] Step 4:

[0059] The user selects the trend they are interested in. For example, the user selects "WorldCup."

[0060] Step 5:

[0061] The device receives the user's selection and sends that information to the server, which then uses a natural language generation model (e.g., GPT-4) to generate a post.

[0062] Step 6:

[0063] The server sends a request to the natural language generation model with the instruction, "Generate a post about the WorldCup." The generation model generates text based on this instruction.

[0064] Step 7:

[0065] The server receives the generated message and sends it to the terminal. The terminal displays the generated message on its user interface and displays a message such as, "A message suggestion has been created: 'Last night's World Cup game was amazing! Who was your best player?' Would you like to post it?"

[0066] Step 8:

[0067] The user can review the generated post and edit it as needed, for example, adding a hashtag such as "I want to connect with soccer fans."

[0068] Step 9:

[0069] After the user has finished editing and confirmed the post, the device sends the confirmed post to the server, which then sends a request to post it to the SNS API.

[0070] Step 10:

[0071] The server publishes the post using the POST / 1.1 / statuses / update.json endpoint of the social networking service's API (e.g., Twitter API).

[0072] Step 11:

[0073] The server periodically calls the social media API after a post is published to collect engagement data (likes, retweets, comments, etc.), for example, to get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[0074] Step 12:

[0075] The server analyzes the collected engagement data and sends it to the device as feedback, generating a message such as, "Your post received the following responses: 200 likes, 50 retweets, and 10 comments."

[0076] Step 13:

[0077] The device displays the collected feedback on a user interface to inform the user about the performance of their post, which can help the user improve their future posts.

[0078] Example 1

[0079] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0080] Currently, effectively posting attention-grabbing content on social networking services (SNS) requires a lot of time and effort. Furthermore, efficiently collecting and analyzing trend information to generate appropriate posts is technically complex and difficult for average users. Therefore, there is a demand for a system that allows users to easily post content based on trends.

[0081] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0082] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posts related to trends selected by users, means for presenting the generated posts to users and providing an opportunity for editing, means for the users to check and edit the posts and then post them to the social networking service, means for collecting engagement data on the posted content and displaying it to the users as feedback, and means for analyzing the engagement data and providing feedback to be used in future posts by the users, thereby enabling users to easily make effective posts based on trends.

[0083] "Trending information" refers to topics or hashtags that are popular on social networking services at a particular time.

[0084] "Means of collection" refers to the function of obtaining trend information using the API of a social networking service.

[0085] "Means of analysis" refers to the algorithms that classify collected trend information and evaluate its popularity and relevance.

[0086] "Presentation means" refers to an interface that displays the analysis results to the user in visual or textual form.

[0087] "Means for generating" refers to the function of generating posts using a natural language generation model based on trends selected by the user.

[0088] "Means for providing editing opportunities" refers to an editing interface that allows users to correct or complete generated posts.

[0089] "Means of posting" refers to the function of publishing the final confirmed post through the API of the social networking service.

[0090] "Engagement data" refers to responses to a post, such as the number of likes, retweets, and comments.

[0091] "Means for displaying as feedback" refers to an interface that displays the collected engagement data in an easy-to-understand manner for users.

[0092] "Natural language generation model" refers to AI technology that generates relevant text based on trending information.

[0093] MODE FOR CARRYING OUT THE INVENTION

[0094] The present invention is a system for safely and effectively posting attention-grabbing content on social networking services (SNS), collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data. The program processing of this system is described in detail below.

[0095] Hardware and software used

[0096] Server: A central processing unit that collects, analyzes, and generates data. The server is equipped with a client library for accessing SNS APIs, a database management system, and a natural language generation model (e.g., GPT-4).

[0097] Terminal: A device operated by a user. This includes mobile devices and personal computers. Terminals are equipped with web apps and mobile apps that provide a user interface.

[0098] SNS API: An access point provided by a social networking platform. An example is the Twitter API.

[0099] Specific system processing and data processing

[0100] 1. Collecting trend information

[0101] The server periodically sends a request to the social networking service's API (e.g., Twitter API) to obtain trend information. The server collects trend data using the GET / 1.1 / trends / place.json endpoint and stores it in a database.

[0102] 2. Analysis and presentation of trend information

[0103] The server runs algorithms to analyze the collected trend information and evaluate the popularity and relevance of the data. The analysis results are displayed on the device in a visual or text format that is easy for the user to understand. For example, a message might say, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0104] 3. Post Generation

[0105] When a user selects a topic of interest from the trends, the server sends a prompt to a generative AI model (e.g., GPT-4) to generate a post. An example of a prompt is "Generate a post about the World Cup." The generative AI model generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[0106] 4. Check and edit the generated text

[0107] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the text and insert additional hashtags. For example, the user can add the hashtag "I want to connect with soccer fans."

[0108] 5. Submitting a post

[0109] After confirming and editing the post, the user sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) from their device to execute the post. The server confirms the post was successful and notifies the user.

[0110] 6. Engagement Data Collection and Feedback

[0111] After a post is published, the server periodically uses the SNS API to collect engagement data (number of likes, retweets, comments, etc.). The collected data is analyzed by the server, and the results are displayed as feedback on the device. For example, it might say, "Your post received the following response: 200 likes, 50 retweets, 10 comments." This allows users to check the performance of their post and use it to improve their future posts.

[0112] Specific examples

[0113] For example, if a user selects the trend "WorldCup," the server sends a prompt to the generative AI model saying, "Generate a post about the WorldCup," which generates a post saying, "Last night's WorldCup match was amazing! Who was your best player?" The user adds the hashtag "I want to connect with soccer fans" to this post and presses the post button to post it directly to a social media platform. The server then collects engagement data and provides feedback such as, "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[0114] The above is a specific embodiment for carrying out the present invention. This system allows users to easily post effective content based on trends, thereby attracting attention on social media.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: Gather trend information

[0117] The server periodically sends requests to the social networking service's API (e.g., Twitter API) to obtain the latest trend information. This is done using the GET / 1.1 / trends / place.json endpoint. Trend information for a specific region or globally is specified as input, and trend data is returned in JSON format in response to the request. The server analyzes this data and stores it in a database. Specifically, the server sends a request to the API, formats the returned data, and stores it in the database.

[0118] Step 2: Analyze and present trend information

[0119] The server retrieves the collected trend information from the database and runs an analysis algorithm to evaluate the popularity and relevance of hashtags. As input, it takes trend data, analyzes it, and converts it into a visually understandable format. As output, the analysis results are sent to the device to be presented to the user. Specifically, the server retrieves data from the database, runs the analysis algorithm, and converts the results into text or graph format and sends them to the device.

[0120] Step 3: Generate a post

[0121] When a user selects a trend of interest on their device, the device sends that information to the server. The server then sends a prompt to a generative AI model (e.g., GPT-4) to generate a related post. The input is the trend information selected by the user and the prompt. If a prompt such as "Generate a post about the WorldCup" is sent, the generative AI model generates the text. The generated post is sent from the server to the device as output. In concrete terms, the user selects a trend on their device and sends that information to the server, and then the server sends a prompt to the generative AI model and receives the generated text.

[0122] Step 4: Review and edit the generated text

[0123] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the generated text or add new information. The input is the generated text and the edited content. The output is the final post confirmed by the user. In concrete terms, the device displays the generated post, the user edits it through the interface, and the final confirmed text is saved.

[0124] Step 5: Execute the post

[0125] After the user completes the edit, the device sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) to post the post to the SNS. The input is the finalized post. The output is the completion of the post on the SNS. Specifically, the device sends a request to the API to post and receives a success response.

[0126] Step 6: Collect engagement data and feedback

[0127] After a post is published, the server periodically uses the SNS API to collect engagement data for the post. This data includes the number of likes, retweets, comments, etc. The post ID and other information are required as input. The server analyzes this data and sends the results as feedback to the device. The output is the analyzed engagement data, which is displayed to the user. Specifically, the server retrieves the engagement data from the SNS API, analyzes it, and displays it on the device.

[0128] The above is the processing flow of this system. The input and output of data required at each step, as well as the specific operations involved, are described in detail.

[0129] (Application example 1)

[0130] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0131] In conventional social networking services (SNS), users have to identify trends on their own and create posts accordingly, making it difficult to efficiently attract attention. In particular, the advertising industry is required to generate effective advertising copy that follows trends and post it to gain a lot of engagement. A system is needed to streamline this process and enable users to easily create effective advertising posts.

[0132] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0133] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posted text and advertisement copy related to trends selected by users, means for presenting the generated posted text and advertisement copy to users and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, means for collecting engagement data on the posted content and displaying it to users as feedback, and means for generating advertisement copy based on the collected engagement data and posting it as an advertisement. This allows users to efficiently generate and post effective advertisements based on trends and increase engagement on the SNS.

[0134] "Trending information" refers to topics and hashtags that are trending on social networking services (SNS) at a particular time.

[0135] "Analysis" refers to the process of analyzing the content of collected data and extracting valuable information.

[0136] "Posts" refer to text content that users publish on social media.

[0137] "Engagement data" refers to data that shows reactions to posts on social media (number of likes, retweets, comments, etc.).

[0138] "Advertising copy" refers to text content posted by users or companies on social media for the purpose of promoting products or marketing their brands.

[0139] "Feedback" refers to information provided to users based on engagement data.

[0140] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate natural language text.

[0141] This invention relates to a system that supports effective advertisement posting on social networking sites in the advertising industry. This system is composed of the following main components: a server, a terminal, and a user.

[0142] Collecting trend information

[0143] The server periodically collects trend information using the API of the social networking service. This uses the API of an existing social networking platform, such as the Twitter API. By calling the API from the server, the server obtains current trend data (for example, popular hashtags and keywords).

[0144] Analysis and presentation of trend information

[0145] The server analyzes the collected trend information and presents it in a format that is easy for users to understand. The analysis results are displayed on the device in visual graphs and text format. Users can use this information to decide the direction of their advertising posts.

[0146] Post generation

[0147] When a user selects a trend that interests them, the server automatically generates relevant post and ad copy using a generative AI model (e.g., GPT-3 or GPT-4). For example, if the user enters the prompt "Generate effective ad copy related to Black Friday," the AI ​​generates the ad copy "Black Friday Super Sale Starts! All items are 30% off now. Don't miss out!"

[0148] Review and edit the generated text

[0149] The generated post and ad copy is displayed on the device for the user to review. The device also provides an editing interface, allowing the user to modify or edit the generated copy as needed. For example, they can add additional hashtags or specific product names.

[0150] Executing the post

[0151] Once the user has confirmed and edited the ad copy, it is actually posted from the device via the social networking service's API. The post is published on the social networking service by using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[0152] Engagement data collection and feedback

[0153] After the ad copy is published on the social networking site, the server periodically collects engagement data using the social networking site's API. The collected engagement data (number of likes, retweets, comments, etc.) is analyzed and the results are displayed as feedback on the device. Users can use this feedback to improve future ad posts.

[0154] Specific examples

[0155] For example, if "Black Friday" is collected as a current trend and the user selects this trend to generate ad copy, the user enters the prompt "Generate effective ad copy related to Black Friday," and the AI ​​model generates ad copy such as "Black Friday Super Sale Starts! All products are 30% off now. Don't miss out!" This ad copy can be posted directly to social media to garner a large response.

[0156] In this way, the system of the present invention can efficiently generate and post trend-based advertisements and increase engagement on social media. This system is extremely useful in the advertising industry, especially for marketing activities using social media.

[0157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0158] Detailed process steps for carrying out the invention

[0159] Step 1:

[0160] The server calls the API of the SNS (e.g., Twitter API) and collects trend information.

[0161] Input: SNS API endpoint URL and authentication token.

[0162] Data processing: Analyze the JSON format trend data obtained from the API.

[0163] Output: Collected trending information (e.g. hashtag list).

[0164] Step 2:

[0165] The server analyzes the collected trend information and transmits it to the terminal for presentation to the user.

[0166] Input: Trend information.

[0167] Data Calculation: Organize trend data and convert it into visual or text format.

[0168] Output: Analysis results (e.g., list of top trends).

[0169] Step 3:

[0170] The device displays the analysis results to the user, who can then select trends to post based on this information.

[0171] Input: Analysis results.

[0172] Operation: The analysis results are displayed in the user interface in graph and list format.

[0173] Output: User selection (e.g. selected trending hashtags).

[0174] Step 4:

[0175] The server generates post and ad copy using a generative AI model (e.g., GPT-4) based on the trends selected by the user.

[0176] Input: Selected trending hashtag and prompt statement (e.g., "Generate effective ad copy related to Black Friday.").

[0177] Data calculation: Call the generative AI model and receive the generated text based on the prompt.

[0178] Output: The generated post and ad copy (e.g., "Black Friday Sale Has Started! 30% Off Everything Right Now. Don't Miss Out!").

[0179] Step 5:

[0180] The terminal presents the generated posting and advertising copy to the user, and provides an opportunity for editing.

[0181] Input: Generated post and ad copy.

[0182] What it does: Provides a text editing interface that allows the user to edit.

[0183] Output: The final post, reviewed and edited by the user.

[0184] Step 6:

[0185] The device actually posts the post that the user has confirmed and edited to the SNS via the SNS API.

[0186] Input: Final edited post.

[0187] Data processing: Convert the post into a format that complies with the SNS API specifications.

[0188] Output: Posting result on social media (success / failure status).

[0189] Step 7:

[0190] The server periodically collects post engagement data using the SNS API.

[0191] Input: The ID or URL of the posted content.

[0192] Data calculation: Analyzes engagement data obtained from the API.

[0193] Output: Parsed engagement data (likes, retweets, comments, etc.).

[0194] Step 8:

[0195] The server generates ad copy based on the collected engagement data and uses it for the next ad posting.

[0196] Input: Engagement data.

[0197] Data calculation: The results of data analysis are passed as prompts to the generative AI model to generate new ad copy.

[0198] Output: The following ad copy. This is also sent to the device and presented to the user as feedback.

[0199] Through this process, users can generate and post effective ad copy based on trends, check the effectiveness of the post based on data, and use the data to improve future ad postings. The hardware and software used in this process include Twitter API, OpenAI's generative AI model, and Python libraries (requests, openai).

[0200] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0201] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[0202] 1. Collecting and analyzing trend information

[0203] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. The collected trend information is analyzed, sent to the device, and displayed to the user. For example, it displays a message such as, "Current trends are: World Cup Oscars. What topic would you like to post about?"

[0204] 2. Emotion Recognition by Emotion Engine

[0205] The device is equipped with an emotion engine for recognizing the user's emotions. This emotion engine analyzes the user's current emotional state using facial or voice recognition technology. For example, it uses a camera and microphone to determine emotions such as joy, sadness, and surprise from the user's facial expressions and voice.

[0206] 3. Generating posts based on emotion data

[0207] Based on the trends selected by the user, the server uses a natural language generation model (e.g., GPT-4) and emotional data obtained from the emotion engine to generate posts. The tone and content are adjusted to match the user's emotions. For example, if the user expresses joy, the post will be adjusted to a more positive tone, such as "Last night's World Cup game was so exciting! What did you all think was the best scene?"

[0208] 4. Check and edit the generated text

[0209] The device displays the generated post on the user interface and gives the user the opportunity to review and edit it. For example, it might present a message like, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can edit the text and add additional hashtags or comments as needed.

[0210] 5. Submitting a post

[0211] Once the post is confirmed, the device sends the confirmed post to the server and executes the post via the social networking API (e.g., Twitter API), for example, by using the POST / 1.1 / statuses / update.json endpoint to publish the post to the social networking platform.

[0212] 6. Engagement Data Collection and Feedback

[0213] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the SNS API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post has received the following responses: 200 likes, 50 retweets, and 10 comments" may be generated and provided to the user.

[0214] For example, if a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated: "Last night's WorldCup game was so exciting! What did you think was the best part?" This post will garner a lot of attention on social media, and engagement data such as 200 likes, 50 retweets, and 10 comments will be collected. Based on this, feedback will be provided to the user to help them improve their future posts.

[0215] This system allows users to make effective posts based on their emotions, and to attract attention on social media by posting posts that combine trends with their own emotions.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] The server calls the API of the social networking service (e.g., Twitter API) to collect trend information. Specifically, it uses the GET / trends / place endpoint to retrieve the current trending hashtags and their associated data.

[0219] Step 2:

[0220] The server analyzes the collected trend information and extracts important meta-information about each trend (e.g., trend score, number of related tweets, etc.), and sends the analyzed data to the device.

[0221] Step 3:

[0222] The terminal displays the analysis results on a user interface and presents trend information to the user, such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0223] Step 4:

[0224] The user selects from the presented trend information a trend that he or she is interested in. For example, the user selects "WorldCup."

[0225] Step 5:

[0226] The device sends trend selection information to the server, and at the same time, the device's built-in emotion engine uses a camera and microphone to collect the user's facial expressions and voice in order to recognize the user's emotions.

[0227] Step 6:

[0228] The device's emotion engine analyzes the collected data and determines the user's current emotional state (e.g., joy, sadness, surprise, etc.). Once the emotion data is determined, it is sent to the server.

[0229] Step 7:

[0230] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information selected by the user and the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server generates a post with a positive tone such as, "Last night's World Cup game was so exciting! Which scene did you like best?"

[0231] Step 8:

[0232] The server sends the generated message to the device. The device displays the message on the user interface and asks the user, "Here's a message suggestion: 'Last night's World Cup game was so exciting! Which scene did you think was the best?' Would you like to post it?"

[0233] Step 9:

[0234] The user can review the generated post and edit it as needed, for example adding an additional hashtag such as "I want to connect with soccer fans."

[0235] Step 10:

[0236] After the user has finished editing the post, they confirm the post. The device then sends the confirmed post to the server.

[0237] Step 11:

[0238] The server posts the confirmed post to the API of the social networking service (e.g., Twitter API) using the POST / 1.1 / statuses / update.json endpoint.

[0239] Step 12:

[0240] After the post is completed, the server periodically calls the SNS API to collect engagement data (e.g., number of likes, retweets, comments, etc.). For example, get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[0241] Step 13:

[0242] The server analyzes the collected engagement data and sends the results to the device, which displays the data on a user interface and provides feedback to the user, such as "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[0243] This process allows users to create effective posts that combine their emotions with the latest trending information, attracting attention on social media, and providing feedback on engagement data to help them improve their next posts.

[0244] Example 2

[0245] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0246] In conventional social networking services, the content of posts may not reflect the user's emotional state, making it difficult to gain empathy. Furthermore, it is difficult to post effectively using trending information, which can lead to a decline in user engagement. This creates the challenge of making it difficult for users to gain the response and recognition they desire.

[0247] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0248] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for recognizing the user's emotional state, means for generating a post related to a trend selected by the user and based on the recognized emotion, means for presenting the generated post to the user and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting tailored to the user's emotional state and makes it possible to achieve high engagement by utilizing trend information.

[0249] "Trending information" refers to topics and keywords that are attracting attention on social networking services.

[0250] "Emotional state" refers to a psychological state recognized through facial expression and voice analysis of a user, such as joy, sadness, surprise, etc.

[0251] A "post" is a text message that a user posts to a social networking service.

[0252] "Engagement data" refers to data that shows users' reactions to posts, and specifically includes the number of likes, retweets, comments, etc.

[0253] A "natural language generation model" is a program or algorithm that generates natural language sentences that humans can understand based on input data.

[0254] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating and editing posts, and providing feedback on posting and engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[0255] Collecting trend information

[0256] The server periodically calls the API of the social networking site (e.g., the API of the social networking site) to collect current trending information. The collected data includes hashtags, related keywords, and trending topics. This data is analyzed and sorted in order of interest to the user. It is then formatted optimally and sent to the device, where it is displayed in the user interface. For example, the server might ask the user, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[0257] emotion recognition

[0258] The device collects the user's face and voice through a camera and microphone and runs an emotion recognition algorithm. The device analyzes the user's current emotions using facial recognition technology (e.g., general facial recognition software) and voice recognition technology (e.g., general voice recognition software). It recognizes emotions such as joy, sadness, and surprise from the user's facial expressions and generates emotion data based on this.

[0259] Post generation

[0260] The server uses a natural language generation model (e.g., a generative AI model) to generate posts based on the trends and emotional data selected by the user. The server is programmed to incorporate tone and content that reflects the user's emotions. If the user expresses joy, a cheerful post such as "Last night's World Cup game was so exciting! What did you all think was the best scene?" will be generated.

[0261] Review and edit your post

[0262] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. For example, a message might appear saying, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can easily edit the text and add additional hashtags or comments.

[0263] Executing the post

[0264] After the user confirms and edits the post, the device sends the confirmed text to the server. The server then uses the SNS API (e.g., SNS API) to execute the post, for example, by using the POST / 1.1 / statuses / update.json endpoint to send the confirmed post to the SNS platform.

[0265] Engagement data collection and feedback

[0266] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the social media API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post received the following engagement: 200 likes, 50 retweets, and 10 comments" is generated.

[0267] Specific examples

[0268] If a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated, such as "Last night's WorldCup game was so exciting! What did you think was the best part?" The post then generates a significant response on social media, collecting engagement data such as 200 likes, 50 retweets, and 10 comments. Based on this, the user will be provided with feedback to help them improve their future posts.

[0269] Prompt Sentence Examples

[0270] "Since users are expressing joy, generate positive WorldCup-related posts."

[0271] "The user is expressing sadness, so please generate a comforting post related to the Oscars."

[0272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0273] Step 1: Gather trend information

[0274] The server periodically calls the API of a social networking service (e.g., the API of a social networking service) to collect current trend information. As input, it sends a request to the API endpoint of the social networking service. As output, it obtains trend information (hashtags, keywords, trending topics) obtained from the API. Specifically, the server sends a request of GET / 1.1 / trends / place.json?id=1 to obtain trend data in JSON format.

[0275] Step 2: Analyze and present trend information

[0276] The server analyzes the collected trend information and sorts it in order of the user's interest. It receives the collected trend data as input and obtains organized trend information as output. Specifically, the server analyzes the collected trend data and generates a trend list sorted based on interest. It then sends it to the terminal and displays on the user interface, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[0277] Step 3: Emotion Recognition

[0278] The device uses a camera and microphone to collect the user's face and voice in order to recognize the user's emotional state. As input, it acquires real-time data from the camera and microphone. As output, it generates the user's emotional data (happiness, sadness, surprise, etc.). Specifically, the device activates the camera, captures the user's facial expression data, and passes it to facial recognition software (e.g., general facial recognition software). Similarly, for voice input, it collects voice using the microphone and passes it to voice recognition software (e.g., general voice recognition software).

[0279] Step 4: Generate a post

[0280] The server generates a post using a generative AI model (e.g., a generative AI model) based on the user-selected trend and emotion data. It receives the user-selected trend and emotion data as input. It obtains the generated post as output. Specifically, the server creates a prompt, such as "The user is expressing joy, so please generate a post related to the WorldCup with positive content," and inputs it into the generative AI model, then receives the generated text.

[0281] Step 5: Review and edit your post

[0282] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. The generated post is received as input. The text that the user has reviewed and edited is obtained as output. Specifically, an editing screen displaying the generated text pops up for the user, and a confirmation message such as "A post suggestion has been created: 'Last night's World Cup game was so exciting! Which scene did you all like best?' Would you like to post it here?" is displayed.

[0283] Step 6: Execute the post

[0284] The device sends the confirmed and edited post to the server, and the server uses the SNS API to execute the post. As input, it receives the text confirmed and edited by the user. As output, it obtains the text actually posted to the SNS. Specifically, the server sends an HTTP POST request including the confirmed text to the POST / 1.1 / statuses / update.json endpoint and publishes the post to the SNS platform.

[0285] Step 7: Collect engagement data and feedback

[0286] The server periodically collects engagement data using the SNS API and sends the analyzed results to the device. As input, it receives engagement data for posted content (e.g., number of likes, retweets, and comments). As output, it obtains engagement data that is displayed to the user as feedback. Specifically, the server sends a GET / 1.1 / statuses / show.json?id=post ID request to obtain the engagement data. It then generates a feedback message such as "Your post received the following responses: 200 likes, 50 retweets, and 10 comments," and provides it to the user.

[0287] (Application example 2)

[0288] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0289] Conventional online shopping sites and social networking services have faced the issue of declining user engagement and satisfaction because they make uniform posts and product recommendations without considering the user's emotions or state. In particular, effective posts and product recommendations that reflect the user's emotions have not been realized, and there is a demand for improving the user experience.

[0290] The identification process 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 collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for generating a prompt sentence corresponding to the emotional state based on emotional information recognized by an emotion engine, means for generating a post based on the emotional data and trend information using a natural language generation model, means for presenting the generated post to the user and offering an opportunity for editing, means for the user to check and edit the post and then post it to a digital networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting and product recommendations that reflect the user's emotions and trend information.

[0291] "Trending information" is information about topics and keywords that many people are interested in on the Internet during a specific period of time.

[0292] An "emotion engine" is an engine that analyzes the user's emotional state and processes data based on that.

[0293] A "natural language generation model" is an algorithm or software that allows a computer to generate human language.

[0294] A "prompt sentence" is an input sentence for generating a post sentence that is generated by a natural language generation model.

[0295] "Engagement data" is data that shows reactions and evaluations of posts and content, and examples include "likes," "retweets," and "comments."

[0296] A "digital networking service" is an online platform that allows users to share information and interact with each other via the Internet.

[0297] "Collection methods" are the methods or techniques used to obtain specific information.

[0298] "Analytical means" refers to methods and techniques for analyzing collected data and discovering its meaning and trends.

[0299] "Presentation means" refers to the method or technology used to display information to the user and allow them to make a selection or confirmation.

[0300] A "generation means" is a method or technology for producing specific data or information.

[0301] "Editing means" refers to methods or techniques that allow users to modify or add to the generated data or information.

[0302] "Verification means" refers to methods or techniques that allow users to check the content of generated data or information.

[0303] "Posting means" refers to the method or technology for publishing the generated information on an external platform.

[0304] "Feedback means" refers to methods or techniques for presenting collected engagement data to users and reflecting it in their next actions.

[0305] MODE FOR CARRYING OUT THE INVENTION

[0306] The present invention relates to a posting system for social networking services (SNS) that incorporates an emotion engine. This system can be used particularly for posting and product recommendations on online shopping sites. An embodiment of the system is described below.

[0307] 1. Collecting and analyzing trend information

[0308] The server periodically collects trend information using the API. This trend information includes currently popular topics and keywords on the Internet. The collected trend information is analyzed by the server and sent to the user's device, allowing the user to check the current trend information.

[0309] 2. Emotion Recognition by Emotion Engine

[0310] The device is equipped with an emotion engine that uses a camera and microphone to recognize the user's emotions. For example, the device recognizes the user's emotional state (happiness, sadness, surprise, etc.) by reading the user's facial expressions with the camera and analyzing the user's voice with the microphone. This emotion data is sent to the server.

[0311] 3. Generating posts based on emotion data

[0312] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information and emotion data selected by the user. The tone and content of the posts are adjusted to match the user's emotions. For example, if the user expresses joy, the post will have a positive message such as, "The summer sale was amazing! I especially loved my new sunglasses."

[0313] 4. Check and edit the generated text

[0314] The device displays the generated post on the user interface and provides the user with an opportunity to review and edit it. The user can review the generated post and make edits or add comments as needed. This process allows the user to add their own intentions and information to the post.

[0315] 5. Submitting a post

[0316] After the user confirms and edits the post, the finalized post is sent to the server and posted to the digital networking service (SNS or online shopping site). This allows the post to be published in a way that reflects the user's sentiment and trend information.

[0317] 6. Engagement Data Collection and Feedback

[0318] After a post is published, the server periodically collects engagement data (e.g., number of likes, comments, and shares) using the API of the social networking site or online shopping site. This data is analyzed by the server and sent to the user's device as feedback, allowing the user to see how their post has been received.

[0319] Specific examples

[0320] For example, if a user selects the trend "SummerSale" and the emotion engine recognizes the emotion of joy, the generated post might look like this:

[0321] "This summer sale is amazing! I especially love the new sunglasses. SummerSale"

[0322] This post will then be published on social media and online shopping sites, potentially eliciting many helpful comments and likes.

[0323] As described above, this system integrates user emotions with current trend information, providing a concrete form for realizing effective posting and product recommendations.

[0324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0325] Step 1:

[0326] The server uses an API to collect trend information on the Internet. Specifically, it periodically calls the API of a social media platform (e.g., Twitter API) to obtain the latest trend information. The input of this step is the API endpoint, and the output is the collected trend information. The server stores the collected trend information in a database.

[0327] Step 2:

[0328] The server analyzes the collected trend information and sends it to the user's terminal for presentation to the user. The analysis involves evaluating the ranking and relevance of the trend information and extracting the most relevant trends. The input to this step is the collected trend information, and the output is the analyzed trend information. The analysis results are displayed on the user interface.

[0329] Step 3:

[0330] The device uses a camera and microphone to recognize the user's emotions. The emotion engine analyzes emotions (happiness, sadness, surprise, etc.) from facial expressions and voice in real time. The input is the user's facial image and voice data, and the output is the recognized emotion data. The recognized emotion data is sent to the server.

[0331] Step 4:

[0332] The server generates a prompt sentence based on the trend information selected by the user and the recognized emotion data. The prompt sentence contains information about the user's emotional state and the selected trend. The input of this step is the trend information and emotion data, and the output is the generated prompt sentence. As a specific example, the generated prompt sentence is "User is feeling happy. Write a review for a product considering the trend SummerSale."

[0333] Step 5:

[0334] The server inputs the generated prompt into a natural language generation model (e.g., GPT-4) to generate a post. The generative AI model creates a post with an appropriate tone and content based on the prompt. The input for this step is the prompt, and the output is the generated post. The generated post is sent to the device.

[0335] Step 6:

[0336] The terminal displays the generated post on a user interface, providing the user with an opportunity to review and edit it. The user can review the post, modify the text as needed, and add additional comments. The input of this step is the generated post, and the output is the post reviewed and edited by the user.

[0337] Step 7:

[0338] The device sends the user's confirmed and edited post to the server, which then posts it via the API of the social networking site or shopping site. The input of this step is the confirmed and edited post, and the output is a message that the post was successful. This makes the post publicly available on the digital networking service.

[0339] Step 8:

[0340] The server periodically collects engagement data (e.g., number of likes, comments, and shares) for posted content using the API of the social networking site or online shopping site. The input for this step is the URL or ID of the post, and the output is the collected engagement data. The collected data is sent to the user's device and displayed as feedback.

[0341] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0342] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0343] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0344] [Second embodiment]

[0345] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0346] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0347] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0348] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0349] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0350] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0351] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0352] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0353] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0354] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0355] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0356] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0357] The present invention relates to a system that collects and analyzes trend information, generates, edits, and posts posts, and provides feedback on engagement data, in order to safely and effectively post attention-grabbing content on social networking services (SNS). This system is composed of server, terminal, and user components.

[0358] 1. Collecting trend information

[0359] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. This ensures that the latest trend information is always kept in the system. For example, trending hashtags such as "WorldCup" and "Oscars" are collected.

[0360] 2. Analysis and presentation of trend information

[0361] The server analyzes the collected trend data and organizes it for presentation to the user. The analysis results are displayed on the device in visual or text format for easy understanding by the user. Specifically, the message displayed is, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0362] 3. Post Generation

[0363] When a user selects a trend they are interested in, the server uses a natural language generation model (e.g., GPT-4) to generate a post related to the selected trend. For example, a request to "generate a post about the World Cup" generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[0364] 4. Check and edit the generated text

[0365] The generated post is displayed on the device for the user to review. An editing interface is also provided on the device, allowing the user to modify or add to the generated post as needed. For example, the user can insert an additional hashtag such as "I want to connect with soccer fans."

[0366] 5. Submitting a post

[0367] Once the post is finalized, the device sends it to the social networking platform's API via the post button, which publishes the post to the actual social networking platform. For example, this can be done using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[0368] 6. Engagement Data Collection and Feedback

[0369] After a post is published, the server periodically collects engagement data (number of likes, retweets, comments, etc.) using social media APIs. This data is analyzed by the server and displayed as feedback on the device, allowing users to see how their post is performing. For example, it might say, "Your post has received the following responses: 200 likes, 50 retweets, 10 comments."

[0370] For example, if a user selects the trend "WorldCup" and posts the generated message "Last night's WorldCup game was amazing! Who was your best player?", the post will generate a lot of reactions on social media, and the reactions will be collected as engagement data. This data will be provided to the user as feedback and used to improve future posts.

[0371] This system allows users to safely and effectively create buzzworthy posts, and attract attention on social media with trending posts.

[0372] The processing flow will be explained below.

[0373] Step 1:

[0374] The server sends a request to the social networking service's API (e.g., Twitter API) to retrieve trend information. Specifically, it uses the GET / trends / place endpoint to collect the current trending hashtags and their associated data.

[0375] Step 2:

[0376] The server analyzes the collected trend information and converts it into an appropriate format for presentation to users. Specifically, it parses the JSON format data and extracts trending hashtags and their summaries.

[0377] Step 3:

[0378] The server then transmits the analyzed trend information to the device, which then displays the information on a user interface, prompting the user with a message such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0379] Step 4:

[0380] The user selects the trend they are interested in. For example, the user selects "WorldCup."

[0381] Step 5:

[0382] The device receives the user's selection and sends that information to the server, which then uses a natural language generation model (e.g., GPT-4) to generate a post.

[0383] Step 6:

[0384] The server sends a request to the natural language generation model with the instruction, "Generate a post about the WorldCup." The generation model generates text based on this instruction.

[0385] Step 7:

[0386] The server receives the generated message and sends it to the terminal. The terminal displays the generated message on its user interface and displays a message such as, "A message suggestion has been created: 'Last night's World Cup game was amazing! Who was your best player?' Would you like to post it?"

[0387] Step 8:

[0388] The user can review the generated post and edit it as needed, for example, adding a hashtag such as "I want to connect with soccer fans."

[0389] Step 9:

[0390] After the user has finished editing and confirmed the post, the device sends the confirmed post to the server, which then sends a request to post it to the SNS API.

[0391] Step 10:

[0392] The server publishes the post using the POST / 1.1 / statuses / update.json endpoint of the social networking service's API (e.g., Twitter API).

[0393] Step 11:

[0394] The server periodically calls the social media API after a post is published to collect engagement data (likes, retweets, comments, etc.), for example, to get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[0395] Step 12:

[0396] The server analyzes the collected engagement data and sends it to the device as feedback, generating a message such as, "Your post received the following responses: 200 likes, 50 retweets, and 10 comments."

[0397] Step 13:

[0398] The device displays the collected feedback on a user interface to inform the user about the performance of their post, which can help the user improve their future posts.

[0399] Example 1

[0400] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0401] Currently, effectively posting attention-grabbing content on social networking services (SNS) requires a lot of time and effort. Furthermore, efficiently collecting and analyzing trend information to generate appropriate posts is technically complex and difficult for average users. Therefore, there is a demand for a system that allows users to easily post content based on trends.

[0402] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0403] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posts related to trends selected by users, means for presenting the generated posts to users and providing an opportunity for editing, means for the users to check and edit the posts and then post them to the social networking service, means for collecting engagement data on the posted content and displaying it to the users as feedback, and means for analyzing the engagement data and providing feedback to be used in future posts by the users, thereby enabling users to easily make effective posts based on trends.

[0404] "Trending information" refers to topics or hashtags that are popular on social networking services at a particular time.

[0405] "Means of collection" refers to the function of obtaining trend information using the API of a social networking service.

[0406] "Means of analysis" refers to the algorithms that classify collected trend information and evaluate its popularity and relevance.

[0407] "Presentation means" refers to an interface that displays the analysis results to the user in visual or textual form.

[0408] "Means for generating" refers to the function of generating posts using a natural language generation model based on trends selected by the user.

[0409] "Means for providing editing opportunities" refers to an editing interface that allows users to correct or complete generated posts.

[0410] "Means of posting" refers to the function of publishing the final confirmed post through the API of the social networking service.

[0411] "Engagement data" refers to responses to a post, such as the number of likes, retweets, and comments.

[0412] "Means for displaying as feedback" refers to an interface that displays the collected engagement data in an easy-to-understand manner for users.

[0413] "Natural language generation model" refers to AI technology that generates relevant text based on trending information.

[0414] MODE FOR CARRYING OUT THE INVENTION

[0415] The present invention is a system for safely and effectively posting attention-grabbing content on social networking services (SNS), collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data. The program processing of this system is described in detail below.

[0416] Hardware and software used

[0417] Server: A central processing unit that collects, analyzes, and generates data. The server is equipped with a client library for accessing SNS APIs, a database management system, and a natural language generation model (e.g., GPT-4).

[0418] Terminal: A device operated by a user. This includes mobile devices and personal computers. Terminals are equipped with web apps and mobile apps that provide a user interface.

[0419] SNS API: An access point provided by a social networking platform. An example is the Twitter API.

[0420] Specific system processing and data processing

[0421] 1. Collecting trend information

[0422] The server periodically sends a request to the social networking service's API (e.g., Twitter API) to obtain trend information. The server collects trend data using the GET / 1.1 / trends / place.json endpoint and stores it in a database.

[0423] 2. Analysis and presentation of trend information

[0424] The server runs algorithms to analyze the collected trend information and evaluate the popularity and relevance of the data. The analysis results are displayed on the device in a visual or text format that is easy for the user to understand. For example, a message might say, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0425] 3. Post Generation

[0426] When a user selects a topic of interest from the trends, the server sends a prompt to a generative AI model (e.g., GPT-4) to generate a post. An example of a prompt is "Generate a post about the World Cup." The generative AI model generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[0427] 4. Check and edit the generated text

[0428] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the text and insert additional hashtags. For example, the user can add the hashtag "I want to connect with soccer fans."

[0429] 5. Submitting a post

[0430] After confirming and editing the post, the user sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) from their device to execute the post. The server confirms the post was successful and notifies the user.

[0431] 6. Engagement Data Collection and Feedback

[0432] After a post is published, the server periodically uses the SNS API to collect engagement data (number of likes, retweets, comments, etc.). The collected data is analyzed by the server, and the results are displayed as feedback on the device. For example, it might say, "Your post received the following response: 200 likes, 50 retweets, 10 comments." This allows users to check the performance of their post and use it to improve their future posts.

[0433] Specific examples

[0434] For example, if a user selects the trend "WorldCup," the server sends a prompt to the generative AI model saying, "Generate a post about the WorldCup," which generates a post saying, "Last night's WorldCup match was amazing! Who was your best player?" The user adds the hashtag "I want to connect with soccer fans" to this post and presses the post button to post it directly to a social media platform. The server then collects engagement data and provides feedback such as, "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[0435] The above is a specific embodiment for carrying out the present invention. This system allows users to easily post effective content based on trends, thereby attracting attention on social media.

[0436] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0437] Step 1: Gather trend information

[0438] The server periodically sends requests to the social networking service's API (e.g., Twitter API) to obtain the latest trend information. This is done using the GET / 1.1 / trends / place.json endpoint. Trend information for a specific region or globally is specified as input, and trend data is returned in JSON format in response to the request. The server analyzes this data and stores it in a database. Specifically, the server sends a request to the API, formats the returned data, and stores it in the database.

[0439] Step 2: Analyze and present trend information

[0440] The server retrieves the collected trend information from the database and runs an analysis algorithm to evaluate the popularity and relevance of hashtags. As input, it takes trend data, analyzes it, and converts it into a visually understandable format. As output, the analysis results are sent to the device to be presented to the user. Specifically, the server retrieves data from the database, runs the analysis algorithm, and converts the results into text or graph format and sends them to the device.

[0441] Step 3: Generate a post

[0442] When a user selects a trend of interest on their device, the device sends that information to the server. The server then sends a prompt to a generative AI model (e.g., GPT-4) to generate a related post. The input is the trend information selected by the user and the prompt. If a prompt such as "Generate a post about the WorldCup" is sent, the generative AI model generates the text. The generated post is sent from the server to the device as output. In concrete terms, the user selects a trend on their device and sends that information to the server, and then the server sends a prompt to the generative AI model and receives the generated text.

[0443] Step 4: Review and edit the generated text

[0444] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the generated text or add new information. The input is the generated text and the edited content. The output is the final post confirmed by the user. In concrete terms, the device displays the generated post, the user edits it through the interface, and the final confirmed text is saved.

[0445] Step 5: Execute the post

[0446] After the user completes the edit, the device sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) to post the post to the SNS. The input is the finalized post. The output is the completion of the post on the SNS. Specifically, the device sends a request to the API to post and receives a success response.

[0447] Step 6: Collect engagement data and feedback

[0448] After a post is published, the server periodically uses the SNS API to collect engagement data for the post. This data includes the number of likes, retweets, comments, etc. The post ID and other information are required as input. The server analyzes this data and sends the results as feedback to the device. The output is the analyzed engagement data, which is displayed to the user. Specifically, the server retrieves the engagement data from the SNS API, analyzes it, and displays it on the device.

[0449] The above is the processing flow of this system. The input and output of data required at each step, as well as the specific operations involved, are described in detail.

[0450] (Application example 1)

[0451] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0452] In conventional social networking services (SNS), users have to identify trends on their own and create posts accordingly, making it difficult to efficiently attract attention. In particular, the advertising industry is required to generate effective advertising copy that follows trends and post it to gain a lot of engagement. A system is needed to streamline this process and enable users to easily create effective advertising posts.

[0453] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0454] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posted text and advertisement copy related to trends selected by users, means for presenting the generated posted text and advertisement copy to users and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, means for collecting engagement data on the posted content and displaying it to users as feedback, and means for generating advertisement copy based on the collected engagement data and posting it as an advertisement. This allows users to efficiently generate and post effective advertisements based on trends and increase engagement on the SNS.

[0455] "Trending information" refers to topics and hashtags that are trending on social networking services (SNS) at a particular time.

[0456] "Analysis" refers to the process of analyzing the content of collected data and extracting valuable information.

[0457] "Posts" refer to text content that users publish on social media.

[0458] "Engagement data" refers to data that shows reactions to posts on social media (number of likes, retweets, comments, etc.).

[0459] "Advertising copy" refers to text content posted by users or companies on social media for the purpose of promoting products or marketing their brands.

[0460] "Feedback" refers to information provided to users based on engagement data.

[0461] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate natural language text.

[0462] This invention relates to a system that supports effective advertisement posting on social networking sites in the advertising industry. This system is composed of the following main components: a server, a terminal, and a user.

[0463] Collecting trend information

[0464] The server periodically collects trend information using the API of the social networking service. This uses the API of an existing social networking platform, such as the Twitter API. By calling the API from the server, the server obtains current trend data (for example, popular hashtags and keywords).

[0465] Analysis and presentation of trend information

[0466] The server analyzes the collected trend information and presents it in a format that is easy for users to understand. The analysis results are displayed on the device in visual graphs and text format. Users can use this information to decide the direction of their advertising posts.

[0467] Post generation

[0468] When a user selects a trend that interests them, the server automatically generates relevant post and ad copy using a generative AI model (e.g., GPT-3 or GPT-4). For example, if the user enters the prompt "Generate effective ad copy related to Black Friday," the AI ​​generates the ad copy "Black Friday Super Sale Starts! All items are 30% off now. Don't miss out!"

[0469] Review and edit the generated text

[0470] The generated post and ad copy is displayed on the device for the user to review. The device also provides an editing interface, allowing the user to modify or edit the generated copy as needed. For example, they can add additional hashtags or specific product names.

[0471] Executing the post

[0472] Once the user has confirmed and edited the ad copy, it is actually posted from the device via the social networking service's API. The post is published on the social networking service by using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[0473] Engagement data collection and feedback

[0474] After the ad copy is published on the social networking site, the server periodically collects engagement data using the social networking site's API. The collected engagement data (number of likes, retweets, comments, etc.) is analyzed and the results are displayed as feedback on the device. Users can use this feedback to improve future ad posts.

[0475] Specific examples

[0476] For example, if "Black Friday" is collected as a current trend and the user selects this trend to generate ad copy, the user enters the prompt "Generate effective ad copy related to Black Friday," and the AI ​​model generates ad copy such as "Black Friday Super Sale Starts! All products are 30% off now. Don't miss out!" This ad copy can be posted directly to social media to garner a large response.

[0477] In this way, the system of the present invention can efficiently generate and post trend-based advertisements and increase engagement on social media. This system is extremely useful in the advertising industry, especially for marketing activities using social media.

[0478] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0479] Detailed process steps for carrying out the invention

[0480] Step 1:

[0481] The server calls the API of the SNS (e.g., Twitter API) and collects trend information.

[0482] Input: SNS API endpoint URL and authentication token.

[0483] Data processing: Analyze the JSON format trend data obtained from the API.

[0484] Output: Collected trending information (e.g. hashtag list).

[0485] Step 2:

[0486] The server analyzes the collected trend information and transmits it to the terminal for presentation to the user.

[0487] Input: Trend information.

[0488] Data Calculation: Organize trend data and convert it into visual or text format.

[0489] Output: Analysis results (e.g., list of top trends).

[0490] Step 3:

[0491] The device displays the analysis results to the user, who can then select trends to post based on this information.

[0492] Input: Analysis results.

[0493] Operation: The analysis results are displayed in the user interface in graph and list format.

[0494] Output: User selection (e.g. selected trending hashtags).

[0495] Step 4:

[0496] The server generates post and ad copy using a generative AI model (e.g., GPT-4) based on the trends selected by the user.

[0497] Input: Selected trending hashtag and prompt statement (e.g., "Generate effective ad copy related to Black Friday.").

[0498] Data calculation: Call the generative AI model and receive the generated text based on the prompt.

[0499] Output: The generated post and ad copy (e.g., "Black Friday Sale Has Started! 30% Off Everything Right Now. Don't Miss Out!").

[0500] Step 5:

[0501] The terminal presents the generated posting and advertising copy to the user, and provides an opportunity for editing.

[0502] Input: Generated post and ad copy.

[0503] What it does: Provides a text editing interface that allows the user to edit.

[0504] Output: The final post, reviewed and edited by the user.

[0505] Step 6:

[0506] The device actually posts the post that the user has confirmed and edited to the SNS via the SNS API.

[0507] Input: Final edited post.

[0508] Data processing: Convert the post into a format that complies with the SNS API specifications.

[0509] Output: Posting result on social media (success / failure status).

[0510] Step 7:

[0511] The server periodically collects post engagement data using the SNS API.

[0512] Input: The ID or URL of the posted content.

[0513] Data calculation: Analyzes engagement data obtained from the API.

[0514] Output: Parsed engagement data (likes, retweets, comments, etc.).

[0515] Step 8:

[0516] The server generates ad copy based on the collected engagement data and uses it for the next ad posting.

[0517] Input: Engagement data.

[0518] Data calculation: The results of data analysis are passed as prompts to the generative AI model to generate new ad copy.

[0519] Output: The following ad copy. This is also sent to the device and presented to the user as feedback.

[0520] Through this process, users can generate and post effective ad copy based on trends, check the effectiveness of the post based on data, and use the data to improve future ad postings. The hardware and software used in this process include Twitter API, OpenAI's generative AI model, and Python libraries (requests, openai).

[0521] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0522] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[0523] 1. Collecting and analyzing trend information

[0524] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. The collected trend information is analyzed, sent to the device, and displayed to the user. For example, it displays a message such as, "Current trends are: World Cup Oscars. What topic would you like to post about?"

[0525] 2. Emotion Recognition by Emotion Engine

[0526] The device is equipped with an emotion engine for recognizing the user's emotions. This emotion engine analyzes the user's current emotional state using facial or voice recognition technology. For example, it uses a camera and microphone to determine emotions such as joy, sadness, and surprise from the user's facial expressions and voice.

[0527] 3. Generating posts based on emotion data

[0528] Based on the trends selected by the user, the server uses a natural language generation model (e.g., GPT-4) and emotional data obtained from the emotion engine to generate posts. The tone and content are adjusted to match the user's emotions. For example, if the user expresses joy, the post will be adjusted to a more positive tone, such as "Last night's World Cup game was so exciting! What did you all think was the best scene?"

[0529] 4. Check and edit the generated text

[0530] The device displays the generated post on the user interface and gives the user the opportunity to review and edit it. For example, it might present a message like, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can edit the text and add additional hashtags or comments as needed.

[0531] 5. Submitting a post

[0532] Once the post is confirmed, the device sends the confirmed post to the server and executes the post via the social networking API (e.g., Twitter API), for example, by using the POST / 1.1 / statuses / update.json endpoint to publish the post to the social networking platform.

[0533] 6. Engagement Data Collection and Feedback

[0534] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the SNS API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post has received the following responses: 200 likes, 50 retweets, and 10 comments" may be generated and provided to the user.

[0535] For example, if a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated: "Last night's WorldCup game was so exciting! What did you think was the best part?" This post will garner a lot of attention on social media, and engagement data such as 200 likes, 50 retweets, and 10 comments will be collected. Based on this, feedback will be provided to the user to help them improve their future posts.

[0536] This system allows users to make effective posts based on their emotions, and to attract attention on social media by posting posts that combine trends with their own emotions.

[0537] The processing flow will be explained below.

[0538] Step 1:

[0539] The server calls the API of the social networking service (e.g., Twitter API) to collect trend information. Specifically, it uses the GET / trends / place endpoint to retrieve the current trending hashtags and their associated data.

[0540] Step 2:

[0541] The server analyzes the collected trend information and extracts important meta-information about each trend (e.g., trend score, number of related tweets, etc.), and sends the analyzed data to the device.

[0542] Step 3:

[0543] The terminal displays the analysis results on a user interface and presents trend information to the user, such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0544] Step 4:

[0545] The user selects from the presented trend information a trend that he or she is interested in. For example, the user selects "WorldCup."

[0546] Step 5:

[0547] The device sends trend selection information to the server, and at the same time, the device's built-in emotion engine uses a camera and microphone to collect the user's facial expressions and voice in order to recognize the user's emotions.

[0548] Step 6:

[0549] The device's emotion engine analyzes the collected data and determines the user's current emotional state (e.g., joy, sadness, surprise, etc.). Once the emotion data is determined, it is sent to the server.

[0550] Step 7:

[0551] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information selected by the user and the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server generates a post with a positive tone such as, "Last night's World Cup game was so exciting! Which scene did you like best?"

[0552] Step 8:

[0553] The server sends the generated message to the device. The device displays the message on the user interface and asks the user, "Here's a message suggestion: 'Last night's World Cup game was so exciting! Which scene did you think was the best?' Would you like to post it?"

[0554] Step 9:

[0555] The user can review the generated post and edit it as needed, for example adding an additional hashtag such as "I want to connect with soccer fans."

[0556] Step 10:

[0557] After the user has finished editing the post, they confirm the post. The device then sends the confirmed post to the server.

[0558] Step 11:

[0559] The server posts the confirmed post to the API of the social networking service (e.g., Twitter API) using the POST / 1.1 / statuses / update.json endpoint.

[0560] Step 12:

[0561] After the post is completed, the server periodically calls the SNS API to collect engagement data (e.g., number of likes, retweets, comments, etc.). For example, get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[0562] Step 13:

[0563] The server analyzes the collected engagement data and sends the results to the device, which displays the data on a user interface and provides feedback to the user, such as "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[0564] This process allows users to create effective posts that combine their emotions with the latest trending information, attracting attention on social media, and providing feedback on engagement data to help them improve their next posts.

[0565] Example 2

[0566] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] In conventional social networking services, the content of posts may not reflect the user's emotional state, making it difficult to gain empathy. Furthermore, it is difficult to post effectively using trending information, which can lead to a decline in user engagement. This creates the challenge of making it difficult for users to gain the response and recognition they desire.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0569] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for recognizing the user's emotional state, means for generating a post related to a trend selected by the user and based on the recognized emotion, means for presenting the generated post to the user and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting tailored to the user's emotional state and makes it possible to achieve high engagement by utilizing trend information.

[0570] "Trending information" refers to topics and keywords that are attracting attention on social networking services.

[0571] "Emotional state" refers to a psychological state recognized through facial expression and voice analysis of a user, such as joy, sadness, surprise, etc.

[0572] A "post" is a text message that a user posts to a social networking service.

[0573] "Engagement data" refers to data that shows users' reactions to posts, and specifically includes the number of likes, retweets, comments, etc.

[0574] A "natural language generation model" is a program or algorithm that generates natural language sentences that humans can understand based on input data.

[0575] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating and editing posts, and providing feedback on posting and engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[0576] Collecting trend information

[0577] The server periodically calls the API of the social networking site (e.g., the API of the social networking site) to collect current trending information. The collected data includes hashtags, related keywords, and trending topics. This data is analyzed and sorted in order of interest to the user. It is then formatted optimally and sent to the device, where it is displayed in the user interface. For example, the server might ask the user, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[0578] emotion recognition

[0579] The device collects the user's face and voice through a camera and microphone and runs an emotion recognition algorithm. The device analyzes the user's current emotions using facial recognition technology (e.g., general facial recognition software) and voice recognition technology (e.g., general voice recognition software). It recognizes emotions such as joy, sadness, and surprise from the user's facial expressions and generates emotion data based on this.

[0580] Post generation

[0581] The server uses a natural language generation model (e.g., a generative AI model) to generate posts based on the trends and emotional data selected by the user. The server is programmed to incorporate tone and content that reflects the user's emotions. If the user expresses joy, a cheerful post such as "Last night's World Cup game was so exciting! What did you all think was the best scene?" will be generated.

[0582] Review and edit your post

[0583] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. For example, a message might appear saying, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can easily edit the text and add additional hashtags or comments.

[0584] Executing the post

[0585] After the user confirms and edits the post, the device sends the confirmed text to the server. The server then uses the SNS API (e.g., SNS API) to execute the post, for example, by using the POST / 1.1 / statuses / update.json endpoint to send the confirmed post to the SNS platform.

[0586] Engagement data collection and feedback

[0587] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the social media API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post received the following engagement: 200 likes, 50 retweets, and 10 comments" is generated.

[0588] Specific examples

[0589] If a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated, such as "Last night's WorldCup game was so exciting! What did you think was the best part?" The post then generates a significant response on social media, collecting engagement data such as 200 likes, 50 retweets, and 10 comments. Based on this, the user will be provided with feedback to help them improve their future posts.

[0590] Prompt Sentence Examples

[0591] "Since users are expressing joy, generate positive WorldCup-related posts."

[0592] "The user is expressing sadness, so please generate a comforting post related to the Oscars."

[0593] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0594] Step 1: Gather trend information

[0595] The server periodically calls the API of a social networking service (e.g., the API of a social networking service) to collect current trend information. As input, it sends a request to the API endpoint of the social networking service. As output, it obtains trend information (hashtags, keywords, trending topics) obtained from the API. Specifically, the server sends a request of GET / 1.1 / trends / place.json?id=1 to obtain trend data in JSON format.

[0596] Step 2: Analyze and present trend information

[0597] The server analyzes the collected trend information and sorts it in order of the user's interest. It receives the collected trend data as input and obtains organized trend information as output. Specifically, the server analyzes the collected trend data and generates a trend list sorted based on interest. It then sends it to the terminal and displays on the user interface, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[0598] Step 3: Emotion Recognition

[0599] The device uses a camera and microphone to collect the user's face and voice in order to recognize the user's emotional state. As input, it acquires real-time data from the camera and microphone. As output, it generates the user's emotional data (happiness, sadness, surprise, etc.). Specifically, the device activates the camera, captures the user's facial expression data, and passes it to facial recognition software (e.g., general facial recognition software). Similarly, for voice input, it collects voice using the microphone and passes it to voice recognition software (e.g., general voice recognition software).

[0600] Step 4: Generate a post

[0601] The server generates a post using a generative AI model (e.g., a generative AI model) based on the user-selected trend and emotion data. It receives the user-selected trend and emotion data as input. It obtains the generated post as output. Specifically, the server creates a prompt, such as "The user is expressing joy, so please generate a post related to the WorldCup with positive content," and inputs it into the generative AI model, then receives the generated text.

[0602] Step 5: Review and edit your post

[0603] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. The generated post is received as input. The text that the user has reviewed and edited is obtained as output. Specifically, an editing screen displaying the generated text pops up for the user, and a confirmation message such as "A post suggestion has been created: 'Last night's World Cup game was so exciting! Which scene did you all like best?' Would you like to post it here?" is displayed.

[0604] Step 6: Execute the post

[0605] The device sends the confirmed and edited post to the server, and the server uses the SNS API to execute the post. As input, it receives the text confirmed and edited by the user. As output, it obtains the text actually posted to the SNS. Specifically, the server sends an HTTP POST request including the confirmed text to the POST / 1.1 / statuses / update.json endpoint and publishes the post to the SNS platform.

[0606] Step 7: Collect engagement data and feedback

[0607] The server periodically collects engagement data using the SNS API and sends the analyzed results to the device. As input, it receives engagement data for posted content (e.g., number of likes, retweets, and comments). As output, it obtains engagement data that is displayed to the user as feedback. Specifically, the server sends a GET / 1.1 / statuses / show.json?id=post ID request to obtain the engagement data. It then generates a feedback message such as "Your post received the following responses: 200 likes, 50 retweets, and 10 comments," and provides it to the user.

[0608] (Application example 2)

[0609] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0610] Conventional online shopping sites and social networking services have faced the issue of declining user engagement and satisfaction because they make uniform posts and product recommendations without considering the user's emotions or state. In particular, effective posts and product recommendations that reflect the user's emotions have not been realized, and there is a demand for improving the user experience.

[0611] The identification process 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 collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for generating a prompt sentence corresponding to the emotional state based on emotional information recognized by an emotion engine, means for generating a post based on the emotional data and trend information using a natural language generation model, means for presenting the generated post to the user and offering an opportunity for editing, means for the user to check and edit the post and then post it to a digital networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting and product recommendations that reflect the user's emotions and trend information.

[0612] "Trending information" is information about topics and keywords that many people are interested in on the Internet during a specific period of time.

[0613] An "emotion engine" is an engine that analyzes the user's emotional state and processes data based on that.

[0614] A "natural language generation model" is an algorithm or software that allows a computer to generate human language.

[0615] A "prompt sentence" is an input sentence for generating a post sentence that is generated by a natural language generation model.

[0616] "Engagement data" is data that shows reactions and evaluations of posts and content, and examples include "likes," "retweets," and "comments."

[0617] A "digital networking service" is an online platform that allows users to share information and interact with each other via the Internet.

[0618] "Collection methods" are the methods or techniques used to obtain specific information.

[0619] "Analytical means" refers to methods and techniques for analyzing collected data and discovering its meaning and trends.

[0620] "Presentation means" refers to the method or technology used to display information to the user and allow them to make a selection or confirmation.

[0621] A "generation means" is a method or technology for producing specific data or information.

[0622] "Editing means" refers to methods or techniques that allow users to modify or add to the generated data or information.

[0623] "Verification means" refers to methods or techniques that allow users to check the content of generated data or information.

[0624] "Posting means" refers to the method or technology for publishing the generated information on an external platform.

[0625] "Feedback means" refers to methods or techniques for presenting collected engagement data to users and reflecting it in their next actions.

[0626] MODE FOR CARRYING OUT THE INVENTION

[0627] The present invention relates to a posting system for social networking services (SNS) that incorporates an emotion engine. This system can be used particularly for posting and product recommendations on online shopping sites. An embodiment of the system is described below.

[0628] 1. Collecting and analyzing trend information

[0629] The server periodically collects trend information using the API. This trend information includes currently popular topics and keywords on the Internet. The collected trend information is analyzed by the server and sent to the user's device, allowing the user to check the current trend information.

[0630] 2. Emotion Recognition by Emotion Engine

[0631] The device is equipped with an emotion engine that uses a camera and microphone to recognize the user's emotions. For example, the device recognizes the user's emotional state (happiness, sadness, surprise, etc.) by reading the user's facial expressions with the camera and analyzing the user's voice with the microphone. This emotion data is sent to the server.

[0632] 3. Generating posts based on emotion data

[0633] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information and emotion data selected by the user. The tone and content of the posts are adjusted to match the user's emotions. For example, if the user expresses joy, the post will have a positive message such as, "The summer sale was amazing! I especially loved my new sunglasses."

[0634] 4. Check and edit the generated text

[0635] The device displays the generated post on the user interface and provides the user with an opportunity to review and edit it. The user can review the generated post and make edits or add comments as needed. This process allows the user to add their own intentions and information to the post.

[0636] 5. Submitting a post

[0637] After the user confirms and edits the post, the finalized post is sent to the server and posted to the digital networking service (SNS or online shopping site). This allows the post to be published in a way that reflects the user's sentiment and trend information.

[0638] 6. Engagement Data Collection and Feedback

[0639] After a post is published, the server periodically collects engagement data (e.g., number of likes, comments, and shares) using the API of the social networking site or online shopping site. This data is analyzed by the server and sent to the user's device as feedback, allowing the user to see how their post has been received.

[0640] Specific examples

[0641] For example, if a user selects the trend "SummerSale" and the emotion engine recognizes the emotion of joy, the generated post might look like this:

[0642] "This summer sale is amazing! I especially love the new sunglasses. SummerSale"

[0643] This post will then be published on social media and online shopping sites, potentially eliciting many helpful comments and likes.

[0644] As described above, this system integrates user emotions with current trend information, providing a concrete form for realizing effective posting and product recommendations.

[0645] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0646] Step 1:

[0647] The server uses an API to collect trend information on the Internet. Specifically, it periodically calls the API of a social media platform (e.g., Twitter API) to obtain the latest trend information. The input of this step is the API endpoint, and the output is the collected trend information. The server stores the collected trend information in a database.

[0648] Step 2:

[0649] The server analyzes the collected trend information and sends it to the user's terminal for presentation to the user. The analysis involves evaluating the ranking and relevance of the trend information and extracting the most relevant trends. The input to this step is the collected trend information, and the output is the analyzed trend information. The analysis results are displayed on the user interface.

[0650] Step 3:

[0651] The device uses a camera and microphone to recognize the user's emotions. The emotion engine analyzes emotions (happiness, sadness, surprise, etc.) from facial expressions and voice in real time. The input is the user's facial image and voice data, and the output is the recognized emotion data. The recognized emotion data is sent to the server.

[0652] Step 4:

[0653] The server generates a prompt sentence based on the trend information selected by the user and the recognized emotion data. The prompt sentence contains information about the user's emotional state and the selected trend. The input of this step is the trend information and emotion data, and the output is the generated prompt sentence. As a specific example, the generated prompt sentence is "User is feeling happy. Write a review for a product considering the trend SummerSale."

[0654] Step 5:

[0655] The server inputs the generated prompt into a natural language generation model (e.g., GPT-4) to generate a post. The generative AI model creates a post with an appropriate tone and content based on the prompt. The input for this step is the prompt, and the output is the generated post. The generated post is sent to the device.

[0656] Step 6:

[0657] The terminal displays the generated post on a user interface, providing the user with an opportunity to review and edit it. The user can review the post, modify the text as needed, and add additional comments. The input of this step is the generated post, and the output is the post reviewed and edited by the user.

[0658] Step 7:

[0659] The device sends the user's confirmed and edited post to the server, which then posts it via the API of the social networking site or shopping site. The input of this step is the confirmed and edited post, and the output is a message that the post was successful. This makes the post publicly available on the digital networking service.

[0660] Step 8:

[0661] The server periodically collects engagement data (e.g., number of likes, comments, and shares) for posted content using the API of the social networking site or online shopping site. The input for this step is the URL or ID of the post, and the output is the collected engagement data. The collected data is sent to the user's device and displayed as feedback.

[0662] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0663] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0664] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0665] [Third embodiment]

[0666] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0667] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0668] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0669] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0670] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0671] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0672] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0673] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0674] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0675] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0676] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0677] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0678] The present invention relates to a system that collects and analyzes trend information, generates, edits, and posts posts, and provides feedback on engagement data, in order to safely and effectively post attention-grabbing content on social networking services (SNS). This system is composed of server, terminal, and user components.

[0679] 1. Collecting trend information

[0680] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. This ensures that the latest trend information is always kept in the system. For example, trending hashtags such as "WorldCup" and "Oscars" are collected.

[0681] 2. Analysis and presentation of trend information

[0682] The server analyzes the collected trend data and organizes it for presentation to the user. The analysis results are displayed on the device in visual or text format for easy understanding by the user. Specifically, the message displayed is, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0683] 3. Post Generation

[0684] When a user selects a trend they are interested in, the server uses a natural language generation model (e.g., GPT-4) to generate a post related to the selected trend. For example, a request to "generate a post about the World Cup" generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[0685] 4. Check and edit the generated text

[0686] The generated post is displayed on the device for the user to review. An editing interface is also provided on the device, allowing the user to modify or add to the generated post as needed. For example, the user can insert an additional hashtag such as "I want to connect with soccer fans."

[0687] 5. Submitting a post

[0688] Once the post is finalized, the device sends it to the social networking platform's API via the post button, which publishes the post to the actual social networking platform. For example, this can be done using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[0689] 6. Engagement Data Collection and Feedback

[0690] After a post is published, the server periodically collects engagement data (number of likes, retweets, comments, etc.) using social media APIs. This data is analyzed by the server and displayed as feedback on the device, allowing users to see how their post is performing. For example, it might say, "Your post has received the following responses: 200 likes, 50 retweets, 10 comments."

[0691] For example, if a user selects the trend "WorldCup" and posts the generated message "Last night's WorldCup game was amazing! Who was your best player?", the post will generate a lot of reactions on social media, and the reactions will be collected as engagement data. This data will be provided to the user as feedback and used to improve future posts.

[0692] This system allows users to safely and effectively create buzzworthy posts, and attract attention on social media with trending posts.

[0693] The processing flow will be explained below.

[0694] Step 1:

[0695] The server sends a request to the social networking service's API (e.g., Twitter API) to retrieve trend information. Specifically, it uses the GET / trends / place endpoint to collect the current trending hashtags and their associated data.

[0696] Step 2:

[0697] The server analyzes the collected trend information and converts it into an appropriate format for presentation to users. Specifically, it parses the JSON format data and extracts trending hashtags and their summaries.

[0698] Step 3:

[0699] The server then transmits the analyzed trend information to the device, which then displays the information on a user interface, prompting the user with a message such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0700] Step 4:

[0701] The user selects the trend they are interested in. For example, the user selects "WorldCup."

[0702] Step 5:

[0703] The device receives the user's selection and sends that information to the server, which then uses a natural language generation model (e.g., GPT-4) to generate a post.

[0704] Step 6:

[0705] The server sends a request to the natural language generation model with the instruction, "Generate a post about the WorldCup." The generation model generates text based on this instruction.

[0706] Step 7:

[0707] The server receives the generated message and sends it to the terminal. The terminal displays the generated message on its user interface and displays a message such as, "A message suggestion has been created: 'Last night's World Cup game was amazing! Who was your best player?' Would you like to post it?"

[0708] Step 8:

[0709] The user can review the generated post and edit it as needed, for example, adding a hashtag such as "I want to connect with soccer fans."

[0710] Step 9:

[0711] After the user has finished editing and confirmed the post, the device sends the confirmed post to the server, which then sends a request to post it to the SNS API.

[0712] Step 10:

[0713] The server publishes the post using the POST / 1.1 / statuses / update.json endpoint of the social networking service's API (e.g., Twitter API).

[0714] Step 11:

[0715] The server periodically calls the social media API after a post is published to collect engagement data (likes, retweets, comments, etc.), for example, to get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[0716] Step 12:

[0717] The server analyzes the collected engagement data and sends it to the device as feedback, generating a message such as, "Your post received the following responses: 200 likes, 50 retweets, and 10 comments."

[0718] Step 13:

[0719] The device displays the collected feedback on a user interface to inform the user about the performance of their post, which can help the user improve their future posts.

[0720] Example 1

[0721] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0722] Currently, effectively posting attention-grabbing content on social networking services (SNS) requires a lot of time and effort. Furthermore, efficiently collecting and analyzing trend information to generate appropriate posts is technically complex and difficult for average users. Therefore, there is a demand for a system that allows users to easily post content based on trends.

[0723] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0724] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posts related to trends selected by users, means for presenting the generated posts to users and providing an opportunity for editing, means for the users to check and edit the posts and then post them to the social networking service, means for collecting engagement data on the posted content and displaying it to the users as feedback, and means for analyzing the engagement data and providing feedback to be used in future posts by the users, thereby enabling users to easily make effective posts based on trends.

[0725] "Trending information" refers to topics or hashtags that are popular on social networking services at a particular time.

[0726] "Means of collection" refers to the function of obtaining trend information using the API of a social networking service.

[0727] "Means of analysis" refers to the algorithms that classify collected trend information and evaluate its popularity and relevance.

[0728] "Presentation means" refers to an interface that displays the analysis results to the user in visual or textual form.

[0729] "Means for generating" refers to the function of generating posts using a natural language generation model based on trends selected by the user.

[0730] "Means for providing editing opportunities" refers to an editing interface that allows users to correct or complete generated posts.

[0731] "Means of posting" refers to the function of publishing the final confirmed post through the API of the social networking service.

[0732] "Engagement data" refers to responses to a post, such as the number of likes, retweets, and comments.

[0733] "Means for displaying as feedback" refers to an interface that displays the collected engagement data in an easy-to-understand manner for users.

[0734] "Natural language generation model" refers to AI technology that generates relevant text based on trending information.

[0735] MODE FOR CARRYING OUT THE INVENTION

[0736] The present invention is a system for safely and effectively posting attention-grabbing content on social networking services (SNS), collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data. The program processing of this system is described in detail below.

[0737] Hardware and software used

[0738] Server: A central processing unit that collects, analyzes, and generates data. The server is equipped with a client library for accessing SNS APIs, a database management system, and a natural language generation model (e.g., GPT-4).

[0739] Terminal: A device operated by a user. This includes mobile devices and personal computers. Terminals are equipped with web apps and mobile apps that provide a user interface.

[0740] SNS API: An access point provided by a social networking platform. An example is the Twitter API.

[0741] Specific system processing and data processing

[0742] 1. Collecting trend information

[0743] The server periodically sends a request to the social networking service's API (e.g., Twitter API) to obtain trend information. The server collects trend data using the GET / 1.1 / trends / place.json endpoint and stores it in a database.

[0744] 2. Analysis and presentation of trend information

[0745] The server runs algorithms to analyze the collected trend information and evaluate the popularity and relevance of the data. The analysis results are displayed on the device in a visual or text format that is easy for the user to understand. For example, a message might say, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0746] 3. Post Generation

[0747] When a user selects a topic of interest from the trends, the server sends a prompt to a generative AI model (e.g., GPT-4) to generate a post. An example of a prompt is "Generate a post about the World Cup." The generative AI model generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[0748] 4. Check and edit the generated text

[0749] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the text and insert additional hashtags. For example, the user can add the hashtag "I want to connect with soccer fans."

[0750] 5. Submitting a post

[0751] After confirming and editing the post, the user sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) from their device to execute the post. The server confirms the post was successful and notifies the user.

[0752] 6. Engagement Data Collection and Feedback

[0753] After a post is published, the server periodically uses the SNS API to collect engagement data (number of likes, retweets, comments, etc.). The collected data is analyzed by the server, and the results are displayed as feedback on the device. For example, it might say, "Your post received the following response: 200 likes, 50 retweets, 10 comments." This allows users to check the performance of their post and use it to improve their future posts.

[0754] Specific examples

[0755] For example, if a user selects the trend "WorldCup," the server sends a prompt to the generative AI model saying, "Generate a post about the WorldCup," which generates a post saying, "Last night's WorldCup match was amazing! Who was your best player?" The user adds the hashtag "I want to connect with soccer fans" to this post and presses the post button to post it directly to a social media platform. The server then collects engagement data and provides feedback such as, "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[0756] The above is a specific embodiment for carrying out the present invention. This system allows users to easily post effective content based on trends, thereby attracting attention on social media.

[0757] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0758] Step 1: Gather trend information

[0759] The server periodically sends requests to the social networking service's API (e.g., Twitter API) to obtain the latest trend information. This is done using the GET / 1.1 / trends / place.json endpoint. Trend information for a specific region or globally is specified as input, and trend data is returned in JSON format in response to the request. The server analyzes this data and stores it in a database. Specifically, the server sends a request to the API, formats the returned data, and stores it in the database.

[0760] Step 2: Analyze and present trend information

[0761] The server retrieves the collected trend information from the database and runs an analysis algorithm to evaluate the popularity and relevance of hashtags. As input, it takes trend data, analyzes it, and converts it into a visually understandable format. As output, the analysis results are sent to the device to be presented to the user. Specifically, the server retrieves data from the database, runs the analysis algorithm, and converts the results into text or graph format and sends them to the device.

[0762] Step 3: Generate a post

[0763] When a user selects a trend of interest on their device, the device sends that information to the server. The server then sends a prompt to a generative AI model (e.g., GPT-4) to generate a related post. The input is the trend information selected by the user and the prompt. If a prompt such as "Generate a post about the WorldCup" is sent, the generative AI model generates the text. The generated post is sent from the server to the device as output. In concrete terms, the user selects a trend on their device and sends that information to the server, and then the server sends a prompt to the generative AI model and receives the generated text.

[0764] Step 4: Review and edit the generated text

[0765] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the generated text or add new information. The input is the generated text and the edited content. The output is the final post confirmed by the user. In concrete terms, the device displays the generated post, the user edits it through the interface, and the final confirmed text is saved.

[0766] Step 5: Execute the post

[0767] After the user completes the edit, the device sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) to post the post to the SNS. The input is the finalized post. The output is the completion of the post on the SNS. Specifically, the device sends a request to the API to post and receives a success response.

[0768] Step 6: Collect engagement data and feedback

[0769] After a post is published, the server periodically uses the SNS API to collect engagement data for the post. This data includes the number of likes, retweets, comments, etc. The post ID and other information are required as input. The server analyzes this data and sends the results as feedback to the device. The output is the analyzed engagement data, which is displayed to the user. Specifically, the server retrieves the engagement data from the SNS API, analyzes it, and displays it on the device.

[0770] The above is the processing flow of this system. The input and output of data required at each step, as well as the specific operations involved, are described in detail.

[0771] (Application example 1)

[0772] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0773] In conventional social networking services (SNS), users have to identify trends on their own and create posts accordingly, making it difficult to efficiently attract attention. In particular, the advertising industry is required to generate effective advertising copy that follows trends and post it to gain a lot of engagement. A system is needed to streamline this process and enable users to easily create effective advertising posts.

[0774] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0775] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posted text and advertisement copy related to trends selected by users, means for presenting the generated posted text and advertisement copy to users and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, means for collecting engagement data on the posted content and displaying it to users as feedback, and means for generating advertisement copy based on the collected engagement data and posting it as an advertisement. This allows users to efficiently generate and post effective advertisements based on trends and increase engagement on the SNS.

[0776] "Trending information" refers to topics and hashtags that are trending on social networking services (SNS) at a particular time.

[0777] "Analysis" refers to the process of analyzing the content of collected data and extracting valuable information.

[0778] "Posts" refer to text content that users publish on social media.

[0779] "Engagement data" refers to data that shows reactions to posts on social media (number of likes, retweets, comments, etc.).

[0780] "Advertising copy" refers to text content posted by users or companies on social media for the purpose of promoting products or marketing their brands.

[0781] "Feedback" refers to information provided to users based on engagement data.

[0782] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate natural language text.

[0783] This invention relates to a system that supports effective advertisement posting on social networking sites in the advertising industry. This system is composed of the following main components: a server, a terminal, and a user.

[0784] Collecting trend information

[0785] The server periodically collects trend information using the API of the social networking service. This uses the API of an existing social networking platform, such as the Twitter API. By calling the API from the server, the server obtains current trend data (for example, popular hashtags and keywords).

[0786] Analysis and presentation of trend information

[0787] The server analyzes the collected trend information and presents it in a format that is easy for users to understand. The analysis results are displayed on the device in visual graphs and text format. Users can use this information to decide the direction of their advertising posts.

[0788] Post generation

[0789] When a user selects a trend that interests them, the server automatically generates relevant post and ad copy using a generative AI model (e.g., GPT-3 or GPT-4). For example, if the user enters the prompt "Generate effective ad copy related to Black Friday," the AI ​​generates the ad copy "Black Friday Super Sale Starts! All items are 30% off now. Don't miss out!"

[0790] Review and edit the generated text

[0791] The generated post and ad copy is displayed on the device for the user to review. The device also provides an editing interface, allowing the user to modify or edit the generated copy as needed. For example, they can add additional hashtags or specific product names.

[0792] Executing the post

[0793] Once the user has confirmed and edited the ad copy, it is actually posted from the device via the social networking service's API. The post is published on the social networking service by using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[0794] Engagement data collection and feedback

[0795] After the ad copy is published on the social networking site, the server periodically collects engagement data using the social networking site's API. The collected engagement data (number of likes, retweets, comments, etc.) is analyzed and the results are displayed as feedback on the device. Users can use this feedback to improve future ad posts.

[0796] Specific examples

[0797] For example, if "Black Friday" is collected as a current trend and the user selects this trend to generate ad copy, the user enters the prompt "Generate effective ad copy related to Black Friday," and the AI ​​model generates ad copy such as "Black Friday Super Sale Starts! All products are 30% off now. Don't miss out!" This ad copy can be posted directly to social media to garner a large response.

[0798] In this way, the system of the present invention can efficiently generate and post trend-based advertisements and increase engagement on social media. This system is extremely useful in the advertising industry, especially for marketing activities using social media.

[0799] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0800] Detailed process steps for carrying out the invention

[0801] Step 1:

[0802] The server calls the API of the SNS (e.g., Twitter API) and collects trend information.

[0803] Input: SNS API endpoint URL and authentication token.

[0804] Data processing: Analyze the JSON format trend data obtained from the API.

[0805] Output: Collected trending information (e.g. hashtag list).

[0806] Step 2:

[0807] The server analyzes the collected trend information and transmits it to the terminal for presentation to the user.

[0808] Input: Trend information.

[0809] Data Calculation: Organize trend data and convert it into visual or text format.

[0810] Output: Analysis results (e.g., list of top trends).

[0811] Step 3:

[0812] The device displays the analysis results to the user, who can then select trends to post based on this information.

[0813] Input: Analysis results.

[0814] Operation: The analysis results are displayed in the user interface in graph and list format.

[0815] Output: User selection (e.g. selected trending hashtags).

[0816] Step 4:

[0817] The server generates post and ad copy using a generative AI model (e.g., GPT-4) based on the trends selected by the user.

[0818] Input: Selected trending hashtag and prompt statement (e.g., "Generate effective ad copy related to Black Friday.").

[0819] Data calculation: Call the generative AI model and receive the generated text based on the prompt.

[0820] Output: The generated post and ad copy (e.g., "Black Friday Sale Has Started! 30% Off Everything Right Now. Don't Miss Out!").

[0821] Step 5:

[0822] The terminal presents the generated posting and advertising copy to the user, and provides an opportunity for editing.

[0823] Input: Generated post and ad copy.

[0824] What it does: Provides a text editing interface that allows the user to edit.

[0825] Output: The final post, reviewed and edited by the user.

[0826] Step 6:

[0827] The device actually posts the post that the user has confirmed and edited to the SNS via the SNS API.

[0828] Input: Final edited post.

[0829] Data processing: Convert the post into a format that complies with the SNS API specifications.

[0830] Output: Posting result on social media (success / failure status).

[0831] Step 7:

[0832] The server periodically collects post engagement data using the SNS API.

[0833] Input: The ID or URL of the posted content.

[0834] Data calculation: Analyzes engagement data obtained from the API.

[0835] Output: Parsed engagement data (likes, retweets, comments, etc.).

[0836] Step 8:

[0837] The server generates ad copy based on the collected engagement data and uses it for the next ad posting.

[0838] Input: Engagement data.

[0839] Data calculation: The results of data analysis are passed as prompts to the generative AI model to generate new ad copy.

[0840] Output: The following ad copy. This is also sent to the device and presented to the user as feedback.

[0841] Through this process, users can generate and post effective ad copy based on trends, check the effectiveness of the post based on data, and use the data to improve future ad postings. The hardware and software used in this process include Twitter API, OpenAI's generative AI model, and Python libraries (requests, openai).

[0842] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0843] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[0844] 1. Collecting and analyzing trend information

[0845] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. The collected trend information is analyzed, sent to the device, and displayed to the user. For example, it displays a message such as, "Current trends are: World Cup Oscars. What topic would you like to post about?"

[0846] 2. Emotion Recognition by Emotion Engine

[0847] The device is equipped with an emotion engine for recognizing the user's emotions. This emotion engine analyzes the user's current emotional state using facial or voice recognition technology. For example, it uses a camera and microphone to determine emotions such as joy, sadness, and surprise from the user's facial expressions and voice.

[0848] 3. Generating posts based on emotion data

[0849] Based on the trends selected by the user, the server uses a natural language generation model (e.g., GPT-4) and emotional data obtained from the emotion engine to generate posts. The tone and content are adjusted to match the user's emotions. For example, if the user expresses joy, the post will be adjusted to a more positive tone, such as "Last night's World Cup game was so exciting! What did you all think was the best scene?"

[0850] 4. Check and edit the generated text

[0851] The device displays the generated post on the user interface and gives the user the opportunity to review and edit it. For example, it might present a message like, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can edit the text and add additional hashtags or comments as needed.

[0852] 5. Submitting a post

[0853] Once the post is confirmed, the device sends the confirmed post to the server and executes the post via the social networking API (e.g., Twitter API), for example, by using the POST / 1.1 / statuses / update.json endpoint to publish the post to the social networking platform.

[0854] 6. Engagement Data Collection and Feedback

[0855] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the SNS API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post has received the following responses: 200 likes, 50 retweets, and 10 comments" may be generated and provided to the user.

[0856] For example, if a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated: "Last night's WorldCup game was so exciting! What did you think was the best part?" This post will garner a lot of attention on social media, and engagement data such as 200 likes, 50 retweets, and 10 comments will be collected. Based on this, feedback will be provided to the user to help them improve their future posts.

[0857] This system allows users to make effective posts based on their emotions, and to attract attention on social media by posting posts that combine trends with their own emotions.

[0858] The processing flow will be explained below.

[0859] Step 1:

[0860] The server calls the API of the social networking service (e.g., Twitter API) to collect trend information. Specifically, it uses the GET / trends / place endpoint to retrieve the current trending hashtags and their associated data.

[0861] Step 2:

[0862] The server analyzes the collected trend information and extracts important meta-information about each trend (e.g., trend score, number of related tweets, etc.), and sends the analyzed data to the device.

[0863] Step 3:

[0864] The terminal displays the analysis results on a user interface and presents trend information to the user, such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[0865] Step 4:

[0866] The user selects from the presented trend information a trend that he or she is interested in. For example, the user selects "WorldCup."

[0867] Step 5:

[0868] The device sends trend selection information to the server, and at the same time, the device's built-in emotion engine uses a camera and microphone to collect the user's facial expressions and voice in order to recognize the user's emotions.

[0869] Step 6:

[0870] The device's emotion engine analyzes the collected data and determines the user's current emotional state (e.g., joy, sadness, surprise, etc.). Once the emotion data is determined, it is sent to the server.

[0871] Step 7:

[0872] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information selected by the user and the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server generates a post with a positive tone such as, "Last night's World Cup game was so exciting! Which scene did you like best?"

[0873] Step 8:

[0874] The server sends the generated message to the device. The device displays the message on the user interface and asks the user, "Here's a message suggestion: 'Last night's World Cup game was so exciting! Which scene did you think was the best?' Would you like to post it?"

[0875] Step 9:

[0876] The user can review the generated post and edit it as needed, for example adding an additional hashtag such as "I want to connect with soccer fans."

[0877] Step 10:

[0878] After the user has finished editing the post, they confirm the post. The device then sends the confirmed post to the server.

[0879] Step 11:

[0880] The server posts the confirmed post to the API of the social networking service (e.g., Twitter API) using the POST / 1.1 / statuses / update.json endpoint.

[0881] Step 12:

[0882] After the post is completed, the server periodically calls the SNS API to collect engagement data (e.g., number of likes, retweets, comments, etc.). For example, get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[0883] Step 13:

[0884] The server analyzes the collected engagement data and sends the results to the device, which displays the data on a user interface and provides feedback to the user, such as "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[0885] This process allows users to create effective posts that combine their emotions with the latest trending information, attracting attention on social media, and providing feedback on engagement data to help them improve their next posts.

[0886] Example 2

[0887] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] In conventional social networking services, the content of posts may not reflect the user's emotional state, making it difficult to gain empathy. Furthermore, it is difficult to post effectively using trending information, which can lead to a decline in user engagement. This creates the challenge of making it difficult for users to gain the response and recognition they desire.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0890] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for recognizing the user's emotional state, means for generating a post related to a trend selected by the user and based on the recognized emotion, means for presenting the generated post to the user and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting tailored to the user's emotional state and makes it possible to achieve high engagement by utilizing trend information.

[0891] "Trending information" refers to topics and keywords that are attracting attention on social networking services.

[0892] "Emotional state" refers to a psychological state recognized through facial expression and voice analysis of a user, such as joy, sadness, surprise, etc.

[0893] A "post" is a text message that a user posts to a social networking service.

[0894] "Engagement data" refers to data that shows users' reactions to posts, and specifically includes the number of likes, retweets, comments, etc.

[0895] A "natural language generation model" is a program or algorithm that generates natural language sentences that humans can understand based on input data.

[0896] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating and editing posts, and providing feedback on posting and engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[0897] Collecting trend information

[0898] The server periodically calls the API of the social networking site (e.g., the API of the social networking site) to collect current trending information. The collected data includes hashtags, related keywords, and trending topics. This data is analyzed and sorted in order of interest to the user. It is then formatted optimally and sent to the device, where it is displayed in the user interface. For example, the server might ask the user, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[0899] emotion recognition

[0900] The device collects the user's face and voice through a camera and microphone and runs an emotion recognition algorithm. The device analyzes the user's current emotions using facial recognition technology (e.g., general facial recognition software) and voice recognition technology (e.g., general voice recognition software). It recognizes emotions such as joy, sadness, and surprise from the user's facial expressions and generates emotion data based on this.

[0901] Post generation

[0902] The server uses a natural language generation model (e.g., a generative AI model) to generate posts based on the trends and emotional data selected by the user. The server is programmed to incorporate tone and content that reflects the user's emotions. If the user expresses joy, a cheerful post such as "Last night's World Cup game was so exciting! What did you all think was the best scene?" will be generated.

[0903] Review and edit your post

[0904] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. For example, a message might appear saying, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can easily edit the text and add additional hashtags or comments.

[0905] Executing the post

[0906] After the user confirms and edits the post, the device sends the confirmed text to the server. The server then uses the SNS API (e.g., SNS API) to execute the post, for example, by using the POST / 1.1 / statuses / update.json endpoint to send the confirmed post to the SNS platform.

[0907] Engagement data collection and feedback

[0908] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the social media API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post received the following engagement: 200 likes, 50 retweets, and 10 comments" is generated.

[0909] Specific examples

[0910] If a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated, such as "Last night's WorldCup game was so exciting! What did you think was the best part?" The post then generates a significant response on social media, collecting engagement data such as 200 likes, 50 retweets, and 10 comments. Based on this, the user will be provided with feedback to help them improve their future posts.

[0911] Prompt Sentence Examples

[0912] "Since users are expressing joy, generate positive WorldCup-related posts."

[0913] "The user is expressing sadness, so please generate a comforting post related to the Oscars."

[0914] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0915] Step 1: Gather trend information

[0916] The server periodically calls the API of a social networking service (e.g., the API of a social networking service) to collect current trend information. As input, it sends a request to the API endpoint of the social networking service. As output, it obtains trend information (hashtags, keywords, trending topics) obtained from the API. Specifically, the server sends a request of GET / 1.1 / trends / place.json?id=1 to obtain trend data in JSON format.

[0917] Step 2: Analyze and present trend information

[0918] The server analyzes the collected trend information and sorts it in order of the user's interest. It receives the collected trend data as input and obtains organized trend information as output. Specifically, the server analyzes the collected trend data and generates a trend list sorted based on interest. It then sends it to the terminal and displays on the user interface, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[0919] Step 3: Emotion Recognition

[0920] The device uses a camera and microphone to collect the user's face and voice in order to recognize the user's emotional state. As input, it acquires real-time data from the camera and microphone. As output, it generates the user's emotional data (happiness, sadness, surprise, etc.). Specifically, the device activates the camera, captures the user's facial expression data, and passes it to facial recognition software (e.g., general facial recognition software). Similarly, for voice input, it collects voice using the microphone and passes it to voice recognition software (e.g., general voice recognition software).

[0921] Step 4: Generate a post

[0922] The server generates a post using a generative AI model (e.g., a generative AI model) based on the user-selected trend and emotion data. It receives the user-selected trend and emotion data as input. It obtains the generated post as output. Specifically, the server creates a prompt, such as "The user is expressing joy, so please generate a post related to the WorldCup with positive content," and inputs it into the generative AI model, then receives the generated text.

[0923] Step 5: Review and edit your post

[0924] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. The generated post is received as input. The text that the user has reviewed and edited is obtained as output. Specifically, an editing screen displaying the generated text pops up for the user, and a confirmation message such as "A post suggestion has been created: 'Last night's World Cup game was so exciting! Which scene did you all like best?' Would you like to post it here?" is displayed.

[0925] Step 6: Execute the post

[0926] The device sends the confirmed and edited post to the server, and the server uses the SNS API to execute the post. As input, it receives the text confirmed and edited by the user. As output, it obtains the text actually posted to the SNS. Specifically, the server sends an HTTP POST request including the confirmed text to the POST / 1.1 / statuses / update.json endpoint and publishes the post to the SNS platform.

[0927] Step 7: Collect engagement data and feedback

[0928] The server periodically collects engagement data using the SNS API and sends the analyzed results to the device. As input, it receives engagement data for posted content (e.g., number of likes, retweets, and comments). As output, it obtains engagement data that is displayed to the user as feedback. Specifically, the server sends a GET / 1.1 / statuses / show.json?id=post ID request to obtain the engagement data. It then generates a feedback message such as "Your post received the following responses: 200 likes, 50 retweets, and 10 comments," and provides it to the user.

[0929] (Application example 2)

[0930] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0931] Conventional online shopping sites and social networking services have faced the issue of declining user engagement and satisfaction because they make uniform posts and product recommendations without considering the user's emotions or state. In particular, effective posts and product recommendations that reflect the user's emotions have not been realized, and there is a demand for improving the user experience.

[0932] The identification process 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 collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for generating a prompt sentence corresponding to the emotional state based on emotional information recognized by an emotion engine, means for generating a post based on the emotional data and trend information using a natural language generation model, means for presenting the generated post to the user and offering an opportunity for editing, means for the user to check and edit the post and then post it to a digital networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting and product recommendations that reflect the user's emotions and trend information.

[0933] "Trending information" is information about topics and keywords that many people are interested in on the Internet during a specific period of time.

[0934] An "emotion engine" is an engine that analyzes the user's emotional state and processes data based on that.

[0935] A "natural language generation model" is an algorithm or software that allows a computer to generate human language.

[0936] A "prompt sentence" is an input sentence for generating a post sentence that is generated by a natural language generation model.

[0937] "Engagement data" is data that shows reactions and evaluations of posts and content, and examples include "likes," "retweets," and "comments."

[0938] A "digital networking service" is an online platform that allows users to share information and interact with each other via the Internet.

[0939] "Collection methods" are the methods or techniques used to obtain specific information.

[0940] "Analytical means" refers to methods and techniques for analyzing collected data and discovering its meaning and trends.

[0941] "Presentation means" refers to the method or technology used to display information to the user and allow them to make a selection or confirmation.

[0942] A "generation means" is a method or technology for producing specific data or information.

[0943] "Editing means" refers to methods or techniques that allow users to modify or add to the generated data or information.

[0944] "Verification means" refers to methods or techniques that allow users to check the content of generated data or information.

[0945] "Posting means" refers to the method or technology for publishing the generated information on an external platform.

[0946] "Feedback means" refers to methods or techniques for presenting collected engagement data to users and reflecting it in their next actions.

[0947] MODE FOR CARRYING OUT THE INVENTION

[0948] The present invention relates to a posting system for social networking services (SNS) that incorporates an emotion engine. This system can be used particularly for posting and product recommendations on online shopping sites. An embodiment of the system is described below.

[0949] 1. Collecting and analyzing trend information

[0950] The server periodically collects trend information using the API. This trend information includes currently popular topics and keywords on the Internet. The collected trend information is analyzed by the server and sent to the user's device, allowing the user to check the current trend information.

[0951] 2. Emotion Recognition by Emotion Engine

[0952] The device is equipped with an emotion engine that uses a camera and microphone to recognize the user's emotions. For example, the device recognizes the user's emotional state (happiness, sadness, surprise, etc.) by reading the user's facial expressions with the camera and analyzing the user's voice with the microphone. This emotion data is sent to the server.

[0953] 3. Generating posts based on emotion data

[0954] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information and emotion data selected by the user. The tone and content of the posts are adjusted to match the user's emotions. For example, if the user expresses joy, the post will have a positive message such as, "The summer sale was amazing! I especially loved my new sunglasses."

[0955] 4. Check and edit the generated text

[0956] The device displays the generated post on the user interface and provides the user with an opportunity to review and edit it. The user can review the generated post and make edits or add comments as needed. This process allows the user to add their own intentions and information to the post.

[0957] 5. Submitting a post

[0958] After the user confirms and edits the post, the finalized post is sent to the server and posted to the digital networking service (SNS or online shopping site). This allows the post to be published in a way that reflects the user's sentiment and trend information.

[0959] 6. Engagement Data Collection and Feedback

[0960] After a post is published, the server periodically collects engagement data (e.g., number of likes, comments, and shares) using the API of the social networking site or online shopping site. This data is analyzed by the server and sent to the user's device as feedback, allowing the user to see how their post has been received.

[0961] Specific examples

[0962] For example, if a user selects the trend "SummerSale" and the emotion engine recognizes the emotion of joy, the generated post might look like this:

[0963] "This summer sale is amazing! I especially love the new sunglasses. SummerSale"

[0964] This post will then be published on social media and online shopping sites, potentially eliciting many helpful comments and likes.

[0965] As described above, this system integrates user emotions with current trend information, providing a concrete form for realizing effective posting and product recommendations.

[0966] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0967] Step 1:

[0968] The server uses an API to collect trend information on the Internet. Specifically, it periodically calls the API of a social media platform (e.g., Twitter API) to obtain the latest trend information. The input of this step is the API endpoint, and the output is the collected trend information. The server stores the collected trend information in a database.

[0969] Step 2:

[0970] The server analyzes the collected trend information and sends it to the user's terminal for presentation to the user. The analysis involves evaluating the ranking and relevance of the trend information and extracting the most relevant trends. The input to this step is the collected trend information, and the output is the analyzed trend information. The analysis results are displayed on the user interface.

[0971] Step 3:

[0972] The device uses a camera and microphone to recognize the user's emotions. The emotion engine analyzes emotions (happiness, sadness, surprise, etc.) from facial expressions and voice in real time. The input is the user's facial image and voice data, and the output is the recognized emotion data. The recognized emotion data is sent to the server.

[0973] Step 4:

[0974] The server generates a prompt sentence based on the trend information selected by the user and the recognized emotion data. The prompt sentence contains information about the user's emotional state and the selected trend. The input of this step is the trend information and emotion data, and the output is the generated prompt sentence. As a specific example, the generated prompt sentence is "User is feeling happy. Write a review for a product considering the trend SummerSale."

[0975] Step 5:

[0976] The server inputs the generated prompt into a natural language generation model (e.g., GPT-4) to generate a post. The generative AI model creates a post with an appropriate tone and content based on the prompt. The input for this step is the prompt, and the output is the generated post. The generated post is sent to the device.

[0977] Step 6:

[0978] The terminal displays the generated post on a user interface, providing the user with an opportunity to review and edit it. The user can review the post, modify the text as needed, and add additional comments. The input of this step is the generated post, and the output is the post reviewed and edited by the user.

[0979] Step 7:

[0980] The device sends the user's confirmed and edited post to the server, which then posts it via the API of the social networking site or shopping site. The input of this step is the confirmed and edited post, and the output is a message that the post was successful. This makes the post publicly available on the digital networking service.

[0981] Step 8:

[0982] The server periodically collects engagement data (e.g., number of likes, comments, and shares) for posted content using the API of the social networking site or online shopping site. The input for this step is the URL or ID of the post, and the output is the collected engagement data. The collected data is sent to the user's device and displayed as feedback.

[0983] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0984] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0985] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0986] [Fourth embodiment]

[0987] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0988] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0989] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0990] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0991] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0992] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0993] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0994] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0995] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0996] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0997] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0998] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0999] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1000] The present invention relates to a system that collects and analyzes trend information, generates, edits, and posts posts, and provides feedback on engagement data, in order to safely and effectively post attention-grabbing content on social networking services (SNS). This system is composed of server, terminal, and user components.

[1001] 1. Collecting trend information

[1002] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. This ensures that the latest trend information is always kept in the system. For example, trending hashtags such as "WorldCup" and "Oscars" are collected.

[1003] 2. Analysis and presentation of trend information

[1004] The server analyzes the collected trend data and organizes it for presentation to the user. The analysis results are displayed on the device in visual or text format for easy understanding by the user. Specifically, the message displayed is, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[1005] 3. Post Generation

[1006] When a user selects a trend they are interested in, the server uses a natural language generation model (e.g., GPT-4) to generate a post related to the selected trend. For example, a request to "generate a post about the World Cup" generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[1007] 4. Check and edit the generated text

[1008] The generated post is displayed on the device for the user to review. An editing interface is also provided on the device, allowing the user to modify or add to the generated post as needed. For example, the user can insert an additional hashtag such as "I want to connect with soccer fans."

[1009] 5. Submitting a post

[1010] Once the post is finalized, the device sends it to the social networking platform's API via the post button, which publishes the post to the actual social networking platform. For example, this can be done using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[1011] 6. Engagement Data Collection and Feedback

[1012] After a post is published, the server periodically collects engagement data (number of likes, retweets, comments, etc.) using social media APIs. This data is analyzed by the server and displayed as feedback on the device, allowing users to see how their post is performing. For example, it might say, "Your post has received the following responses: 200 likes, 50 retweets, 10 comments."

[1013] For example, if a user selects the trend "WorldCup" and posts the generated message "Last night's WorldCup game was amazing! Who was your best player?", the post will generate a lot of reactions on social media, and the reactions will be collected as engagement data. This data will be provided to the user as feedback and used to improve future posts.

[1014] This system allows users to safely and effectively create buzzworthy posts, and attract attention on social media with trending posts.

[1015] The processing flow will be explained below.

[1016] Step 1:

[1017] The server sends a request to the social networking service's API (e.g., Twitter API) to retrieve trend information. Specifically, it uses the GET / trends / place endpoint to collect the current trending hashtags and their associated data.

[1018] Step 2:

[1019] The server analyzes the collected trend information and converts it into an appropriate format for presentation to users. Specifically, it parses the JSON format data and extracts trending hashtags and their summaries.

[1020] Step 3:

[1021] The server then transmits the analyzed trend information to the device, which then displays the information on a user interface, prompting the user with a message such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[1022] Step 4:

[1023] The user selects the trend they are interested in. For example, the user selects "WorldCup."

[1024] Step 5:

[1025] The device receives the user's selection and sends that information to the server, which then uses a natural language generation model (e.g., GPT-4) to generate a post.

[1026] Step 6:

[1027] The server sends a request to the natural language generation model with the instruction, "Generate a post about the WorldCup." The generation model generates text based on this instruction.

[1028] Step 7:

[1029] The server receives the generated message and sends it to the terminal. The terminal displays the generated message on its user interface and displays a message such as, "A message suggestion has been created: 'Last night's World Cup game was amazing! Who was your best player?' Would you like to post it?"

[1030] Step 8:

[1031] The user can review the generated post and edit it as needed, for example, adding a hashtag such as "I want to connect with soccer fans."

[1032] Step 9:

[1033] After the user has finished editing and confirmed the post, the device sends the confirmed post to the server, which then sends a request to post it to the SNS API.

[1034] Step 10:

[1035] The server publishes the post using the POST / 1.1 / statuses / update.json endpoint of the social networking service's API (e.g., Twitter API).

[1036] Step 11:

[1037] The server periodically calls the social media API after a post is published to collect engagement data (likes, retweets, comments, etc.), for example, to get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[1038] Step 12:

[1039] The server analyzes the collected engagement data and sends it to the device as feedback, generating a message such as, "Your post received the following responses: 200 likes, 50 retweets, and 10 comments."

[1040] Step 13:

[1041] The device displays the collected feedback on a user interface to inform the user about the performance of their post, which can help the user improve their future posts.

[1042] Example 1

[1043] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1044] Currently, effectively posting attention-grabbing content on social networking services (SNS) requires a lot of time and effort. Furthermore, efficiently collecting and analyzing trend information to generate appropriate posts is technically complex and difficult for average users. Therefore, there is a demand for a system that allows users to easily post content based on trends.

[1045] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1046] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posts related to trends selected by users, means for presenting the generated posts to users and providing an opportunity for editing, means for the users to check and edit the posts and then post them to the social networking service, means for collecting engagement data on the posted content and displaying it to the users as feedback, and means for analyzing the engagement data and providing feedback to be used in future posts by the users, thereby enabling users to easily make effective posts based on trends.

[1047] "Trending information" refers to topics or hashtags that are popular on social networking services at a particular time.

[1048] "Means of collection" refers to the function of obtaining trend information using the API of a social networking service.

[1049] "Means of analysis" refers to the algorithms that classify collected trend information and evaluate its popularity and relevance.

[1050] "Presentation means" refers to an interface that displays the analysis results to the user in visual or textual form.

[1051] "Means for generating" refers to the function of generating posts using a natural language generation model based on trends selected by the user.

[1052] "Means for providing editing opportunities" refers to an editing interface that allows users to correct or complete generated posts.

[1053] "Means of posting" refers to the function of publishing the final confirmed post through the API of the social networking service.

[1054] "Engagement data" refers to responses to a post, such as the number of likes, retweets, and comments.

[1055] "Means for displaying as feedback" refers to an interface that displays the collected engagement data in an easy-to-understand manner for users.

[1056] "Natural language generation model" refers to AI technology that generates relevant text based on trending information.

[1057] MODE FOR CARRYING OUT THE INVENTION

[1058] The present invention is a system for safely and effectively posting attention-grabbing content on social networking services (SNS), collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data. The program processing of this system is described in detail below.

[1059] Hardware and software used

[1060] Server: A central processing unit that collects, analyzes, and generates data. The server is equipped with a client library for accessing SNS APIs, a database management system, and a natural language generation model (e.g., GPT-4).

[1061] Terminal: A device operated by a user. This includes mobile devices and personal computers. Terminals are equipped with web apps and mobile apps that provide a user interface.

[1062] SNS API: An access point provided by a social networking platform. An example is the Twitter API.

[1063] Specific system processing and data processing

[1064] 1. Collecting trend information

[1065] The server periodically sends a request to the social networking service's API (e.g., Twitter API) to obtain trend information. The server collects trend data using the GET / 1.1 / trends / place.json endpoint and stores it in a database.

[1066] 2. Analysis and presentation of trend information

[1067] The server runs algorithms to analyze the collected trend information and evaluate the popularity and relevance of the data. The analysis results are displayed on the device in a visual or text format that is easy for the user to understand. For example, a message might say, "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[1068] 3. Post Generation

[1069] When a user selects a topic of interest from the trends, the server sends a prompt to a generative AI model (e.g., GPT-4) to generate a post. An example of a prompt is "Generate a post about the World Cup." The generative AI model generates a post such as "Last night's World Cup game was amazing! Who was your best player?"

[1070] 4. Check and edit the generated text

[1071] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the text and insert additional hashtags. For example, the user can add the hashtag "I want to connect with soccer fans."

[1072] 5. Submitting a post

[1073] After confirming and editing the post, the user sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) from their device to execute the post. The server confirms the post was successful and notifies the user.

[1074] 6. Engagement Data Collection and Feedback

[1075] After a post is published, the server periodically uses the SNS API to collect engagement data (number of likes, retweets, comments, etc.). The collected data is analyzed by the server, and the results are displayed as feedback on the device. For example, it might say, "Your post received the following response: 200 likes, 50 retweets, 10 comments." This allows users to check the performance of their post and use it to improve their future posts.

[1076] Specific examples

[1077] For example, if a user selects the trend "WorldCup," the server sends a prompt to the generative AI model saying, "Generate a post about the WorldCup," which generates a post saying, "Last night's WorldCup match was amazing! Who was your best player?" The user adds the hashtag "I want to connect with soccer fans" to this post and presses the post button to post it directly to a social media platform. The server then collects engagement data and provides feedback such as, "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[1078] The above is a specific embodiment for carrying out the present invention. This system allows users to easily post effective content based on trends, thereby attracting attention on social media.

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1: Gather trend information

[1081] The server periodically sends requests to the social networking service's API (e.g., Twitter API) to obtain the latest trend information. This is done using the GET / 1.1 / trends / place.json endpoint. Trend information for a specific region or globally is specified as input, and trend data is returned in JSON format in response to the request. The server analyzes this data and stores it in a database. Specifically, the server sends a request to the API, formats the returned data, and stores it in the database.

[1082] Step 2: Analyze and present trend information

[1083] The server retrieves the collected trend information from the database and runs an analysis algorithm to evaluate the popularity and relevance of hashtags. As input, it takes trend data, analyzes it, and converts it into a visually understandable format. As output, the analysis results are sent to the device to be presented to the user. Specifically, the server retrieves data from the database, runs the analysis algorithm, and converts the results into text or graph format and sends them to the device.

[1084] Step 3: Generate a post

[1085] When a user selects a trend of interest on their device, the device sends that information to the server. The server then sends a prompt to a generative AI model (e.g., GPT-4) to generate a related post. The input is the trend information selected by the user and the prompt. If a prompt such as "Generate a post about the WorldCup" is sent, the generative AI model generates the text. The generated post is sent from the server to the device as output. In concrete terms, the user selects a trend on their device and sends that information to the server, and then the server sends a prompt to the generative AI model and receives the generated text.

[1086] Step 4: Review and edit the generated text

[1087] The generated post is displayed on the device for the user to review. An editing interface is provided on the device, allowing the user to modify the generated text or add new information. The input is the generated text and the edited content. The output is the final post confirmed by the user. In concrete terms, the device displays the generated post, the user edits it through the interface, and the final confirmed text is saved.

[1088] Step 5: Execute the post

[1089] After the user completes the edit, the device sends a request to the POST / 1.1 / statuses / update.json endpoint of the SNS API (e.g., Twitter API) to post the post to the SNS. The input is the finalized post. The output is the completion of the post on the SNS. Specifically, the device sends a request to the API to post and receives a success response.

[1090] Step 6: Collect engagement data and feedback

[1091] After a post is published, the server periodically uses the SNS API to collect engagement data for the post. This data includes the number of likes, retweets, comments, etc. The post ID and other information are required as input. The server analyzes this data and sends the results as feedback to the device. The output is the analyzed engagement data, which is displayed to the user. Specifically, the server retrieves the engagement data from the SNS API, analyzes it, and displays it on the device.

[1092] The above is the processing flow of this system. The input and output of data required at each step, as well as the specific operations involved, are described in detail.

[1093] (Application example 1)

[1094] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1095] In conventional social networking services (SNS), users have to identify trends on their own and create posts accordingly, making it difficult to efficiently attract attention. In particular, the advertising industry is required to generate effective advertising copy that follows trends and post it to gain a lot of engagement. A system is needed to streamline this process and enable users to easily create effective advertising posts.

[1096] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1097] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to users, means for generating posted text and advertisement copy related to trends selected by users, means for presenting the generated posted text and advertisement copy to users and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, means for collecting engagement data on the posted content and displaying it to users as feedback, and means for generating advertisement copy based on the collected engagement data and posting it as an advertisement. This allows users to efficiently generate and post effective advertisements based on trends and increase engagement on the SNS.

[1098] "Trending information" refers to topics and hashtags that are trending on social networking services (SNS) at a particular time.

[1099] "Analysis" refers to the process of analyzing the content of collected data and extracting valuable information.

[1100] "Posts" refer to text content that users publish on social media.

[1101] "Engagement data" refers to data that shows reactions to posts on social media (number of likes, retweets, comments, etc.).

[1102] "Advertising copy" refers to text content posted by users or companies on social media for the purpose of promoting products or marketing their brands.

[1103] "Feedback" refers to information provided to users based on engagement data.

[1104] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate natural language text.

[1105] This invention relates to a system that supports effective advertisement posting on social networking sites in the advertising industry. This system is composed of the following main components: a server, a terminal, and a user.

[1106] Collecting trend information

[1107] The server periodically collects trend information using the API of the social networking service. This uses the API of an existing social networking platform, such as the Twitter API. By calling the API from the server, the server obtains current trend data (for example, popular hashtags and keywords).

[1108] Analysis and presentation of trend information

[1109] The server analyzes the collected trend information and presents it in a format that is easy for users to understand. The analysis results are displayed on the device in visual graphs and text format. Users can use this information to decide the direction of their advertising posts.

[1110] Post generation

[1111] When a user selects a trend that interests them, the server automatically generates relevant post and ad copy using a generative AI model (e.g., GPT-3 or GPT-4). For example, if the user enters the prompt "Generate effective ad copy related to Black Friday," the AI ​​generates the ad copy "Black Friday Super Sale Starts! All items are 30% off now. Don't miss out!"

[1112] Review and edit the generated text

[1113] The generated post and ad copy is displayed on the device for the user to review. The device also provides an editing interface, allowing the user to modify or edit the generated copy as needed. For example, they can add additional hashtags or specific product names.

[1114] Executing the post

[1115] Once the user has confirmed and edited the ad copy, it is actually posted from the device via the social networking service's API. The post is published on the social networking service by using the Twitter API's POST / 1.1 / statuses / update.json endpoint.

[1116] Engagement data collection and feedback

[1117] After the ad copy is published on the social networking site, the server periodically collects engagement data using the social networking site's API. The collected engagement data (number of likes, retweets, comments, etc.) is analyzed and the results are displayed as feedback on the device. Users can use this feedback to improve future ad posts.

[1118] Specific examples

[1119] For example, if "Black Friday" is collected as a current trend and the user selects this trend to generate ad copy, the user enters the prompt "Generate effective ad copy related to Black Friday," and the AI ​​model generates ad copy such as "Black Friday Super Sale Starts! All products are 30% off now. Don't miss out!" This ad copy can be posted directly to social media to garner a large response.

[1120] In this way, the system of the present invention can efficiently generate and post trend-based advertisements and increase engagement on social media. This system is extremely useful in the advertising industry, especially for marketing activities using social media.

[1121] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1122] Detailed process steps for carrying out the invention

[1123] Step 1:

[1124] The server calls the API of the SNS (e.g., Twitter API) and collects trend information.

[1125] Input: SNS API endpoint URL and authentication token.

[1126] Data processing: Analyze the JSON format trend data obtained from the API.

[1127] Output: Collected trending information (e.g. hashtag list).

[1128] Step 2:

[1129] The server analyzes the collected trend information and transmits it to the terminal for presentation to the user.

[1130] Input: Trend information.

[1131] Data Calculation: Organize trend data and convert it into visual or text format.

[1132] Output: Analysis results (e.g., list of top trends).

[1133] Step 3:

[1134] The device displays the analysis results to the user, who can then select trends to post based on this information.

[1135] Input: Analysis results.

[1136] Operation: The analysis results are displayed in the user interface in graph and list format.

[1137] Output: User selection (e.g. selected trending hashtags).

[1138] Step 4:

[1139] The server generates post and ad copy using a generative AI model (e.g., GPT-4) based on the trends selected by the user.

[1140] Input: Selected trending hashtag and prompt statement (e.g., "Generate effective ad copy related to Black Friday.").

[1141] Data calculation: Call the generative AI model and receive the generated text based on the prompt.

[1142] Output: The generated post and ad copy (e.g., "Black Friday Sale Has Started! 30% Off Everything Right Now. Don't Miss Out!").

[1143] Step 5:

[1144] The terminal presents the generated posting and advertising copy to the user, and provides an opportunity for editing.

[1145] Input: Generated post and ad copy.

[1146] What it does: Provides a text editing interface that allows the user to edit.

[1147] Output: The final post, reviewed and edited by the user.

[1148] Step 6:

[1149] The device actually posts the post that the user has confirmed and edited to the SNS via the SNS API.

[1150] Input: Final edited post.

[1151] Data processing: Convert the post into a format that complies with the SNS API specifications.

[1152] Output: Posting result on social media (success / failure status).

[1153] Step 7:

[1154] The server periodically collects post engagement data using the SNS API.

[1155] Input: The ID or URL of the posted content.

[1156] Data calculation: Analyzes engagement data obtained from the API.

[1157] Output: Parsed engagement data (likes, retweets, comments, etc.).

[1158] Step 8:

[1159] The server generates ad copy based on the collected engagement data and uses it for the next ad posting.

[1160] Input: Engagement data.

[1161] Data calculation: The results of data analysis are passed as prompts to the generative AI model to generate new ad copy.

[1162] Output: The following ad copy. This is also sent to the device and presented to the user as feedback.

[1163] Through this process, users can generate and post effective ad copy based on trends, check the effectiveness of the post based on data, and use the data to improve future ad postings. The hardware and software used in this process include Twitter API, OpenAI's generative AI model, and Python libraries (requests, openai).

[1164] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1165] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating, editing, and posting posts, and providing feedback on engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[1166] 1. Collecting and analyzing trend information

[1167] The server periodically calls the API of the social networking site (e.g., Twitter API) to collect current trend data. The collected trend information is analyzed, sent to the device, and displayed to the user. For example, it displays a message such as, "Current trends are: World Cup Oscars. What topic would you like to post about?"

[1168] 2. Emotion Recognition by Emotion Engine

[1169] The device is equipped with an emotion engine for recognizing the user's emotions. This emotion engine analyzes the user's current emotional state using facial or voice recognition technology. For example, it uses a camera and microphone to determine emotions such as joy, sadness, and surprise from the user's facial expressions and voice.

[1170] 3. Generating posts based on emotion data

[1171] Based on the trends selected by the user, the server uses a natural language generation model (e.g., GPT-4) and emotional data obtained from the emotion engine to generate posts. The tone and content are adjusted to match the user's emotions. For example, if the user expresses joy, the post will be adjusted to a more positive tone, such as "Last night's World Cup game was so exciting! What did you all think was the best scene?"

[1172] 4. Check and edit the generated text

[1173] The device displays the generated post on the user interface and gives the user the opportunity to review and edit it. For example, it might present a message like, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can edit the text and add additional hashtags or comments as needed.

[1174] 5. Submitting a post

[1175] Once the post is confirmed, the device sends the confirmed post to the server and executes the post via the social networking API (e.g., Twitter API), for example, by using the POST / 1.1 / statuses / update.json endpoint to publish the post to the social networking platform.

[1176] 6. Engagement Data Collection and Feedback

[1177] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the SNS API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post has received the following responses: 200 likes, 50 retweets, and 10 comments" may be generated and provided to the user.

[1178] For example, if a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated: "Last night's WorldCup game was so exciting! What did you think was the best part?" This post will garner a lot of attention on social media, and engagement data such as 200 likes, 50 retweets, and 10 comments will be collected. Based on this, feedback will be provided to the user to help them improve their future posts.

[1179] This system allows users to make effective posts based on their emotions, and to attract attention on social media by posting posts that combine trends with their own emotions.

[1180] The processing flow will be explained below.

[1181] Step 1:

[1182] The server calls the API of the social networking service (e.g., Twitter API) to collect trend information. Specifically, it uses the GET / trends / place endpoint to retrieve the current trending hashtags and their associated data.

[1183] Step 2:

[1184] The server analyzes the collected trend information and extracts important meta-information about each trend (e.g., trend score, number of related tweets, etc.), and sends the analyzed data to the device.

[1185] Step 3:

[1186] The terminal displays the analysis results on a user interface and presents trend information to the user, such as "Current trends are: WorldCup Oscars. What topic would you like to post about?"

[1187] Step 4:

[1188] The user selects from the presented trend information a trend that he or she is interested in. For example, the user selects "WorldCup."

[1189] Step 5:

[1190] The device sends trend selection information to the server, and at the same time, the device's built-in emotion engine uses a camera and microphone to collect the user's facial expressions and voice in order to recognize the user's emotions.

[1191] Step 6:

[1192] The device's emotion engine analyzes the collected data and determines the user's current emotional state (e.g., joy, sadness, surprise, etc.). Once the emotion data is determined, it is sent to the server.

[1193] Step 7:

[1194] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information selected by the user and the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server generates a post with a positive tone such as, "Last night's World Cup game was so exciting! Which scene did you like best?"

[1195] Step 8:

[1196] The server sends the generated message to the device. The device displays the message on the user interface and asks the user, "Here's a message suggestion: 'Last night's World Cup game was so exciting! Which scene did you think was the best?' Would you like to post it?"

[1197] Step 9:

[1198] The user can review the generated post and edit it as needed, for example adding an additional hashtag such as "I want to connect with soccer fans."

[1199] Step 10:

[1200] After the user has finished editing the post, they confirm the post. The device then sends the confirmed post to the server.

[1201] Step 11:

[1202] The server posts the confirmed post to the API of the social networking service (e.g., Twitter API) using the POST / 1.1 / statuses / update.json endpoint.

[1203] Step 12:

[1204] After the post is completed, the server periodically calls the SNS API to collect engagement data (e.g., number of likes, retweets, comments, etc.). For example, get the status of a specific post using GET / 1.1 / statuses / show / :id.json.

[1205] Step 13:

[1206] The server analyzes the collected engagement data and sends the results to the device, which displays the data on a user interface and provides feedback to the user, such as "Your post received the following response: 200 likes, 50 retweets, and 10 comments."

[1207] This process allows users to create effective posts that combine their emotions with the latest trending information, attracting attention on social media, and providing feedback on engagement data to help them improve their next posts.

[1208] Example 2

[1209] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1210] In conventional social networking services, the content of posts may not reflect the user's emotional state, making it difficult to gain empathy. Furthermore, it is difficult to post effectively using trending information, which can lead to a decline in user engagement. This creates the challenge of making it difficult for users to gain the response and recognition they desire.

[1211] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1212] In this invention, the server includes means for collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for recognizing the user's emotional state, means for generating a post related to a trend selected by the user and based on the recognized emotion, means for presenting the generated post to the user and providing an opportunity for editing, means for the user to check and edit the post and then post it to the social networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting tailored to the user's emotional state and makes it possible to achieve high engagement by utilizing trend information.

[1213] "Trending information" refers to topics and keywords that are attracting attention on social networking services.

[1214] "Emotional state" refers to a psychological state recognized through facial expression and voice analysis of a user, such as joy, sadness, surprise, etc.

[1215] A "post" is a text message that a user posts to a social networking service.

[1216] "Engagement data" refers to data that shows users' reactions to posts, and specifically includes the number of likes, retweets, comments, etc.

[1217] A "natural language generation model" is a program or algorithm that generates natural language sentences that humans can understand based on input data.

[1218] The present invention relates to a system that provides an effective posting method on a social networking service (SNS) by combining an emotion engine. This system includes functions for collecting and analyzing trend information, generating and editing posts, and providing feedback on posting and engagement data, as well as an emotion engine that recognizes users' emotions and adjusts posts accordingly.

[1219] Collecting trend information

[1220] The server periodically calls the API of the social networking site (e.g., the API of the social networking site) to collect current trending information. The collected data includes hashtags, related keywords, and trending topics. This data is analyzed and sorted in order of interest to the user. It is then formatted optimally and sent to the device, where it is displayed in the user interface. For example, the server might ask the user, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[1221] emotion recognition

[1222] The device collects the user's face and voice through a camera and microphone and runs an emotion recognition algorithm. The device analyzes the user's current emotions using facial recognition technology (e.g., general facial recognition software) and voice recognition technology (e.g., general voice recognition software). It recognizes emotions such as joy, sadness, and surprise from the user's facial expressions and generates emotion data based on this.

[1223] Post generation

[1224] The server uses a natural language generation model (e.g., a generative AI model) to generate posts based on the trends and emotional data selected by the user. The server is programmed to incorporate tone and content that reflects the user's emotions. If the user expresses joy, a cheerful post such as "Last night's World Cup game was so exciting! What did you all think was the best scene?" will be generated.

[1225] Review and edit your post

[1226] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. For example, a message might appear saying, "Here's a post suggestion: 'Last night's World Cup game was so exciting! What did you think was the best part?' Would you like to post it?" The user can easily edit the text and add additional hashtags or comments.

[1227] Executing the post

[1228] After the user confirms and edits the post, the device sends the confirmed text to the server. The server then uses the SNS API (e.g., SNS API) to execute the post, for example, by using the POST / 1.1 / statuses / update.json endpoint to send the confirmed post to the SNS platform.

[1229] Engagement data collection and feedback

[1230] After a post is published, the server periodically collects engagement data (e.g., number of likes, retweets, and comments) using the social media API. This data is analyzed and sent to the device, where it is displayed as feedback to the user. For example, a message such as "Your post received the following engagement: 200 likes, 50 retweets, and 10 comments" is generated.

[1231] Specific examples

[1232] If a user selects the trend "WorldCup" and the emotion engine recognizes the emotion of joy, a positive post will be generated, such as "Last night's WorldCup game was so exciting! What did you think was the best part?" The post then generates a significant response on social media, collecting engagement data such as 200 likes, 50 retweets, and 10 comments. Based on this, the user will be provided with feedback to help them improve their future posts.

[1233] Prompt Sentence Examples

[1234] "Since users are expressing joy, generate positive WorldCup-related posts."

[1235] "The user is expressing sadness, so please generate a comforting post related to the Oscars."

[1236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1237] Step 1: Gather trend information

[1238] The server periodically calls the API of a social networking service (e.g., the API of a social networking service) to collect current trend information. As input, it sends a request to the API endpoint of the social networking service. As output, it obtains trend information (hashtags, keywords, trending topics) obtained from the API. Specifically, the server sends a request of GET / 1.1 / trends / place.json?id=1 to obtain trend data in JSON format.

[1239] Step 2: Analyze and present trend information

[1240] The server analyzes the collected trend information and sorts it in order of the user's interest. It receives the collected trend data as input and obtains organized trend information as output. Specifically, the server analyzes the collected trend data and generates a trend list sorted based on interest. It then sends it to the terminal and displays on the user interface, "Current trends are: WorldCup Oscars. Which topic would you like to post about?"

[1241] Step 3: Emotion Recognition

[1242] The device uses a camera and microphone to collect the user's face and voice in order to recognize the user's emotional state. As input, it acquires real-time data from the camera and microphone. As output, it generates the user's emotional data (happiness, sadness, surprise, etc.). Specifically, the device activates the camera, captures the user's facial expression data, and passes it to facial recognition software (e.g., general facial recognition software). Similarly, for voice input, it collects voice using the microphone and passes it to voice recognition software (e.g., general voice recognition software).

[1243] Step 4: Generate a post

[1244] The server generates a post using a generative AI model (e.g., a generative AI model) based on the user-selected trend and emotion data. It receives the user-selected trend and emotion data as input. It obtains the generated post as output. Specifically, the server creates a prompt, such as "The user is expressing joy, so please generate a post related to the WorldCup with positive content," and inputs it into the generative AI model, then receives the generated text.

[1245] Step 5: Review and edit your post

[1246] The device displays the generated post on a user interface, giving the user the opportunity to review and edit it. The generated post is received as input. The text that the user has reviewed and edited is obtained as output. Specifically, an editing screen displaying the generated text pops up for the user, and a confirmation message such as "A post suggestion has been created: 'Last night's World Cup game was so exciting! Which scene did you all like best?' Would you like to post it here?" is displayed.

[1247] Step 6: Execute the post

[1248] The device sends the confirmed and edited post to the server, and the server uses the SNS API to execute the post. As input, it receives the text confirmed and edited by the user. As output, it obtains the text actually posted to the SNS. Specifically, the server sends an HTTP POST request including the confirmed text to the POST / 1.1 / statuses / update.json endpoint and publishes the post to the SNS platform.

[1249] Step 7: Collect engagement data and feedback

[1250] The server periodically collects engagement data using the SNS API and sends the analyzed results to the device. As input, it receives engagement data for posted content (e.g., number of likes, retweets, and comments). As output, it obtains engagement data that is displayed to the user as feedback. Specifically, the server sends a GET / 1.1 / statuses / show.json?id=post ID request to obtain the engagement data. It then generates a feedback message such as "Your post received the following responses: 200 likes, 50 retweets, and 10 comments," and provides it to the user.

[1251] (Application example 2)

[1252] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1253] Conventional online shopping sites and social networking services have faced the issue of declining user engagement and satisfaction because they make uniform posts and product recommendations without considering the user's emotions or state. In particular, effective posts and product recommendations that reflect the user's emotions have not been realized, and there is a demand for improving the user experience.

[1254] The identification process 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 collecting trend information, means for analyzing the collected trend information and presenting it to the user, means for generating a prompt sentence corresponding to the emotional state based on emotional information recognized by an emotion engine, means for generating a post based on the emotional data and trend information using a natural language generation model, means for presenting the generated post to the user and offering an opportunity for editing, means for the user to check and edit the post and then post it to a digital networking service, and means for collecting engagement data on the posted content and displaying it to the user as feedback. This enables effective posting and product recommendations that reflect the user's emotions and trend information.

[1255] "Trending information" is information about topics and keywords that many people are interested in on the Internet during a specific period of time.

[1256] An "emotion engine" is an engine that analyzes the user's emotional state and processes data based on that.

[1257] A "natural language generation model" is an algorithm or software that allows a computer to generate human language.

[1258] A "prompt sentence" is an input sentence for generating a post sentence that is generated by a natural language generation model.

[1259] "Engagement data" is data that shows reactions and evaluations of posts and content, and examples include "likes," "retweets," and "comments."

[1260] A "digital networking service" is an online platform that allows users to share information and interact with each other via the Internet.

[1261] "Collection methods" are the methods or techniques used to obtain specific information.

[1262] "Analytical means" refers to methods and techniques for analyzing collected data and discovering its meaning and trends.

[1263] "Presentation means" refers to the method or technology used to display information to the user and allow them to make a selection or confirmation.

[1264] A "generation means" is a method or technology for producing specific data or information.

[1265] "Editing means" refers to methods or techniques that allow users to modify or add to the generated data or information.

[1266] "Verification means" refers to methods or techniques that allow users to check the content of generated data or information.

[1267] "Posting means" refers to the method or technology for publishing the generated information on an external platform.

[1268] "Feedback means" refers to methods or techniques for presenting collected engagement data to users and reflecting it in their next actions.

[1269] MODE FOR CARRYING OUT THE INVENTION

[1270] The present invention relates to a posting system for social networking services (SNS) that incorporates an emotion engine. This system can be used particularly for posting and product recommendations on online shopping sites. An embodiment of the system is described below.

[1271] 1. Collecting and analyzing trend information

[1272] The server periodically collects trend information using the API. This trend information includes currently popular topics and keywords on the Internet. The collected trend information is analyzed by the server and sent to the user's device, allowing the user to check the current trend information.

[1273] 2. Emotion Recognition by Emotion Engine

[1274] The device is equipped with an emotion engine that uses a camera and microphone to recognize the user's emotions. For example, the device recognizes the user's emotional state (happiness, sadness, surprise, etc.) by reading the user's facial expressions with the camera and analyzing the user's voice with the microphone. This emotion data is sent to the server.

[1275] 3. Generating posts based on emotion data

[1276] The server generates posts using a natural language generation model (e.g., GPT-4) based on the trend information and emotion data selected by the user. The tone and content of the posts are adjusted to match the user's emotions. For example, if the user expresses joy, the post will have a positive message such as, "The summer sale was amazing! I especially loved my new sunglasses."

[1277] 4. Check and edit the generated text

[1278] The device displays the generated post on the user interface and provides the user with an opportunity to review and edit it. The user can review the generated post and make edits or add comments as needed. This process allows the user to add their own intentions and information to the post.

[1279] 5. Submitting a post

[1280] After the user confirms and edits the post, the finalized post is sent to the server and posted to the digital networking service (SNS or online shopping site). This allows the post to be published in a way that reflects the user's sentiment and trend information.

[1281] 6. Engagement Data Collection and Feedback

[1282] After a post is published, the server periodically collects engagement data (e.g., number of likes, comments, and shares) using the API of the social networking site or online shopping site. This data is analyzed by the server and sent to the user's device as feedback, allowing the user to see how their post has been received.

[1283] Specific examples

[1284] For example, if a user selects the trend "SummerSale" and the emotion engine recognizes the emotion of joy, the generated post might look like this:

[1285] "This summer sale is amazing! I especially love the new sunglasses. SummerSale"

[1286] This post will then be published on social media and online shopping sites, potentially eliciting many helpful comments and likes.

[1287] As described above, this system integrates user emotions with current trend information, providing a concrete form for realizing effective posting and product recommendations.

[1288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1289] Step 1:

[1290] The server uses an API to collect trend information on the Internet. Specifically, it periodically calls the API of a social media platform (e.g., Twitter API) to obtain the latest trend information. The input of this step is the API endpoint, and the output is the collected trend information. The server stores the collected trend information in a database.

[1291] Step 2:

[1292] The server analyzes the collected trend information and sends it to the user's terminal for presentation to the user. The analysis involves evaluating the ranking and relevance of the trend information and extracting the most relevant trends. The input to this step is the collected trend information, and the output is the analyzed trend information. The analysis results are displayed on the user interface.

[1293] Step 3:

[1294] The device uses a camera and microphone to recognize the user's emotions. The emotion engine analyzes emotions (happiness, sadness, surprise, etc.) from facial expressions and voice in real time. The input is the user's facial image and voice data, and the output is the recognized emotion data. The recognized emotion data is sent to the server.

[1295] Step 4:

[1296] The server generates a prompt sentence based on the trend information selected by the user and the recognized emotion data. The prompt sentence contains information about the user's emotional state and the selected trend. The input of this step is the trend information and emotion data, and the output is the generated prompt sentence. As a specific example, the generated prompt sentence is "User is feeling happy. Write a review for a product considering the trend SummerSale."

[1297] Step 5:

[1298] The server inputs the generated prompt into a natural language generation model (e.g., GPT-4) to generate a post. The generative AI model creates a post with an appropriate tone and content based on the prompt. The input for this step is the prompt, and the output is the generated post. The generated post is sent to the device.

[1299] Step 6:

[1300] The terminal displays the generated post on a user interface, providing the user with an opportunity to review and edit it. The user can review the post, modify the text as needed, and add additional comments. The input of this step is the generated post, and the output is the post reviewed and edited by the user.

[1301] Step 7:

[1302] The device sends the user's confirmed and edited post to the server, which then posts it via the API of the social networking site or shopping site. The input of this step is the confirmed and edited post, and the output is a message that the post was successful. This makes the post publicly available on the digital networking service.

[1303] Step 8:

[1304] The server periodically collects engagement data (e.g., number of likes, comments, and shares) for posted content using the API of the social networking site or online shopping site. The input for this step is the URL or ID of the post, and the output is the collected engagement data. The collected data is sent to the user's device and displayed as feedback.

[1305] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1306] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1307] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1308] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1309] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1310] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1311] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1312] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1313] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1314] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1315] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1316] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1317] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1318] 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.

[1319] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1320] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1321] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1322] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1323] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1324] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1325] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1326] The following is further disclosed regarding the above embodiment.

[1327] (Claim 1)

[1328] a means of collecting trend information;

[1329] A means for analyzing the collected trend information and presenting it to the user;

[1330] A means for generating a post related to a trend selected by a user;

[1331] A means for presenting the generated post to a user and providing an opportunity for editing;

[1332] a means for the user to review and edit the post before posting it to the social networking service;

[1333] a means for collecting engagement data on posted content and displaying it to users as feedback;

[1334] A system including:

[1335] (Claim 2)

[1336] 10. The system of claim 1, comprising means for using an API of a social networking service to ascertain trend information.

[1337] (Claim 3)

[1338] 10. The system of claim 1, further comprising: means for generating posts using a natural language generation model.

[1339] "Example 1"

[1340] (Claim 1)

[1341] a means of collecting trend information;

[1342] A means for analyzing the collected trend information and presenting it to users;

[1343] A means for generating a post related to a trend selected by a user;

[1344] A means for presenting the generated post to a user and providing an opportunity for editing;

[1345] A means for a user to review and edit the post and then post it to a social networking service;

[1346] A means for collecting engagement data on posted content and displaying it to users as feedback;

[1347] A means to analyze engagement data and provide feedback to users to help them improve their future posts; and

[1348] A system including:

[1349] (Claim 2)

[1350] 10. The system of claim 1, comprising means for using an API of a social networking service to ascertain trend information.

[1351] (Claim 3)

[1352] 10. The system of claim 1, further comprising: means for generating posts using a natural language generation model.

[1353] "Application Example 1"

[1354] (Claim 1)

[1355] a means of collecting trend information;

[1356] A means for analyzing the collected trend information and presenting it to the user;

[1357] A means for generating a post related to a trend selected by a user;

[1358] A means for presenting the generated post to a user and providing an opportunity for editing;

[1359] a means for the user to review and edit the post before posting it to the social networking service;

[1360] a means for collecting engagement data on posted content and displaying it to users as feedback;

[1361] A means to generate ad copy based on the collected engagement data and post it as an ad;

[1362] A system including:

[1363] (Claim 2)

[1364] 10. The system of claim 1, comprising means for using an API of a social networking service to ascertain trend information.

[1365] (Claim 3)

[1366] 10. The system of claim 1, comprising means for generating posts and advertisements using a natural language generation model.

[1367] "Example 2: Combining Emotion Engines"

[1368] (Claim 1)

[1369] a means of collecting trend information;

[1370] A means for analyzing the collected trend information and presenting it to the user;

[1371] means for recognizing the emotional state of a user;

[1372] means for generating posts based on the recognized sentiment associated with a trend selected by a user;

[1373] A means for presenting the generated post to a user and providing an opportunity for editing;

[1374] a means for the user to review and edit the post before posting it to the social networking service;

[1375] a means for collecting engagement data on posted content and displaying it to users as feedback;

[1376] A system including:

[1377] (Claim 2)

[1378] 10. The system of claim 1, comprising means for using an API of a social networking service to ascertain trend information.

[1379] (Claim 3)

[1380] 10. The system of claim 1, further comprising: means for generating posts using a natural language generation model.

[1381] "Application example 2 when combining emotion engines"

[1382] (Claim 1)

[1383] a means of collecting trend information;

[1384] A means for analyzing the collected trend information and presenting it to the user;

[1385] means comprising an emotion engine for recognizing an emotion of a user;

[1386] means for generating sentiment-based posts related to trends selected by a user;

[1387] A means for presenting the generated post to a user and providing an opportunity for editing;

[1388] a means for users to review and edit their posts before posting them to the digital networking service;

[1389] a means for collecting engagement data on posted content and displaying it to users as feedback;

[1390] A system including:

[1391] (Claim 2)

[1392] 10. The system of claim 1, further comprising: means for generating a prompt sentence corresponding to an emotional state based on the emotional information recognized by the emotion engine.

[1393] (Claim 3)

[1394] 10. The system of claim 1, further comprising: means for generating posts based on sentiment data and trend information using a natural language generation model. [Explanation of symbols]

[1395] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting trend information; A means for analyzing the collected trend information and presenting it to the user; A means for generating a post related to a trend selected by a user; A means for presenting the generated post to a user and providing an opportunity for editing; a means for the user to review and edit the post before posting it to the social networking service; a means for collecting engagement data on posted content and displaying it to users as feedback; A system including:

2. The system of claim 1 , further comprising means for using an API of a social networking service to grasp trend information.

3. The system of claim 1 , further comprising: means for generating posts using a natural language generation model.

Images