System

Abstract

A system is provided.SOLUTION: A system including a means for inputting a post content, a means for transmitting the inputted post content to a server, a means for receiving the transmitted post content by the server and transmitting it to a generation AI, a means for analyzing the post content by the generation AI and generating a reaction by using a pseudo-personality, a means for evaluating a buzz level and flammability on the basis of the generated reaction, a means for returning an evaluation result to a user terminal, and a means for displaying the returned evaluation result to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, the spread of social media has enabled users to freely disseminate information, but on the other hand, the content of posts can spread instantly, increasing the risk of unintended buzz and flame wars. As a result, users are looking for ways to predict the influence and reactions to their posts, but current systems have the problem of making it difficult to simulate the likelihood of buzz and flame wars in advance. Therefore, there is a need for a system that allows users to predict the content of their social media posts and check the reactions in advance. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: a means for inputting content to be posted; a means for transmitting the input content to a server; a means for the server to receive the transmitted content and pass it to a generative AI; a means for the generative AI to analyze the content and generate reactions using pseudo-personalities; a means for evaluating the buzz level and likelihood of a post becoming a controversy based on the generated reactions; a means for returning the evaluation results to a user terminal; and a means for displaying the returned evaluation results to the user. This system allows users to simulate the impact of the content they post in advance and receive feedback in real time on the buzz level and likelihood of a post becoming a controversy, thereby avoiding unintended buzz and controversy and enabling more effective SNS posting.

[0006] "Means for entering content to post" refers to the interface that allows users to enter content they wish to post on SNS.

[0007] The "means for transmitting the input posting content to the server" is a function for transmitting the posting content input by the user to the server via the Internet.

[0008] "Means for the server to receive the posted content and pass it on to the generative AI" refers to the process by which the server receives the posted content sent by the user and provides it to the generative AI for analysis.

[0009] "Means for generative AI to analyze the content of posts and generate responses using pseudo-personalities" refers to the process by which generative AI evaluates the content of posts and generates positive, negative, or neutral responses based on the characteristics of the programmed pseudo-personalities.

[0010] "Method for evaluating the buzz level and likelihood of a post becoming a controversy based on the generated reactions" refers to the process of analyzing the reactions generated by the generative AI and quantifying the buzz level and likelihood of a post becoming a controversy based on the trends of each reaction.

[0011] The "means for returning the evaluation results to the user terminal" is a function by which the server transmits the evaluation results to the user terminal and provides them to the user.

[0012] The "means for displaying the returned evaluation results to the user" is an interface for visually displaying the evaluation results received by the user terminal from the server to the user. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a system that simulates the content that a user intends to post on social media in advance and provides real-time evaluation results of the content's buzz and potential for flaming. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, and a generative AI for generating and evaluating reactions.

[0035] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0036] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. An example of this transmission is when the user terminal sends the post content using a "POST" request.

[0037] The server has a means to receive the posted content sent from the user's device. The server analyzes the received posted content and passes it to the generative AI. This process is used to analyze the posted content and provide it to the generative AI.

[0038] Generative AI uses pseudo-personalities to generate social media responses based on the content of posts. Generative AI generates positive, negative, and neutral responses based on the characteristics of the programmed pseudo-personalities. For example, it generates responses such as, "I want to try that new cafe!" (positive response) or "It's a shame it didn't live up to your expectations!" (negative response).

[0039] The server has a means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions. The generated reactions are analyzed, and the buzz level and likelihood of a post becoming a hot topic are quantified based on the trends of each reaction. This process makes it possible to evaluate how much of a post will become a hot topic or how likely it is to become a hot topic.

[0040] The server has a means to return the evaluation results to the user terminal. The evaluation results are sent to the user terminal in JSON format, etc. The user terminal has an interface to receive the returned evaluation results and visually display them to the user.

[0041] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to a generative AI, which generates simulated reactions. The generative AI generates positive, negative, and neutral reactions, and the server then evaluates the buzz level and likelihood of causing a stir based on these. The resulting score, for example, "buzz level: 10, likelihood of causing a stir: 3," is received by the user's device and displayed to the user. In this way, the user can know in advance how the post will be received on social media.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0045] Step 2:

[0046] The user terminal sends the entered post content to the server via an HTTP POST request. At this time, the post content is sent to the server as data.

[0047] Step 3:

[0048] The server receives a POST request sent from the user's device, extracts the post content from the request, and passes it to the generative AI for analysis.

[0049] Step 4:

[0050] The generative AI analyzes the content of the post sent to it. During the analysis, it uses a pseudo-personality to simulate social media reactions to the post. The reactions generated here can be positive, negative, or neutral.

[0051] Step 5:

[0052] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0053] Step 6:

[0054] The server analyzes the generated reactions and quantifies the buzz level and flaming potential based on the tendency of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the flaming potential.

[0055] Step 7:

[0056] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0057] Step 8:

[0058] The user terminal receives the evaluation results returned from the server. The evaluation results are displayed to the user via a display interface to visually display them to the user. The user can confirm the score, for example, "Buzz level: 10, Flaming potential: 3."

[0059] Example 1

[0060] 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."

[0061] In recent years, the risk of posts on social media spreading in unexpected ways or causing outrage has increased because the content can be shared instantly by a large number of users. This has made it increasingly important for individuals and companies to evaluate posts in advance and understand their potential for spreading and causing outrage. However, current systems lack the means to evaluate posts before they are posted, and furthermore, it is difficult to evaluate them in real time.

[0062] 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.

[0063] In this invention, the server includes means for inputting post content, means for transmitting the input post content to a network device, means for the network device to receive the transmitted post content and pass it to a generative artificial intelligence, means for the generative artificial intelligence to analyze the post content and generate reactions using pseudo-personalities, means for evaluating topicality and potential for flaming based on the generated reactions, means for returning the evaluation results to a terminal device, and means for displaying the returned evaluation results to a user. This allows a user to evaluate in real time how content will be received on SNS before posting, and to grasp in advance the risk of topicality and potential for flaming.

[0064] "Post content" refers to the message or information that a user intends to post on a social networking site.

[0065] "Network device" refers to the computer system and communications infrastructure used to receive and analyze posted content.

[0066] "Generative AI" refers to an AI system that analyzes posted content and generates responses using pseudo-personalities.

[0067] "Pseudo-personality" refers to a model used by generative AI to simulate the characteristics and behavioral patterns of a virtual human.

[0068] "Topicality" refers to an indicator of how much a post becomes a hot topic on social media.

[0069] "Flame potential" refers to an indicator of the extent to which a post provokes a negative reaction on social media.

[0070] "Evaluation results" refer to indicators and numerical values ​​calculated based on the responses generated by generative artificial intelligence.

[0071] "Terminal device" refers to a device used by a user to input content to be posted.

[0072] "Reaction" refers to pseudo-feedback such as positive, negative, or neutral that generative artificial intelligence generates in response to a post.

[0073] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its topicality and potential to cause a stir. This system includes a terminal device for users to input the content to be posted, a network device for processing the content, and a generative artificial intelligence (AI) for generating and evaluating reactions.

[0074] A user uses a terminal device such as a smartphone or PC to input content they want to post on an SNS. For example, they might input content such as, "A new cafe opened, but it was a bit disappointing." The terminal device can then send the input content to a network device as an HTTP request.

[0075] The network device has a means for receiving and analyzing posts sent from user terminals. Specifically, it uses a text analysis module to analyze the posts and extract necessary information. The analysis results are formatted in a format that can be used by generative artificial intelligence (e.g., OpenAI's GPT-4).

[0076] The network device then passes the analyzed post content to the generative AI as a prompt. An example of a prompt when using a generative AI model is, "A user is about to post on social media that a new cafe has opened, but it was a bit disappointing. Please generate a prompt that classifies the general reactions to this post on social media into positive, negative, and neutral."

[0077] The generative AI generates a response to the post based on this prompt. The generated responses are classified into three types: positive, negative, and neutral. For example, responses such as "I want to try that new cafe!" (positive response), "Sorry that it didn't meet your expectations" (negative response), and "Hmm, that's just average" (neutral response) could be generated.

[0078] The network device evaluates the topicality and potential for controversy of the post based on the generated reactions. Topicality and potential for controversy are calculated based on a specific formula, analyzing the proportion and strength of the generated reactions. For example, on a 10-point scale, a score such as "Topicality: 8, Potential for controversy: 2" can be obtained.

[0079] Finally, the network device returns the evaluation results in JSON format to the terminal device. The terminal device has an interface that visually displays the received evaluation results to the user, allowing the user to check the evaluation results. For example, the evaluation results may be displayed as "Topicality: 8, Flaming Potential: 2." This allows users to know in advance how their post will be received on SNS.

[0080] Through the above steps, this system helps users reduce the risks associated with posting on social media and disseminate information more safely.

[0081] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0082] System program processing flow

[0083] Step 1:

[0084] The user enters the content to post.

[0085] The user uses a terminal device to input the content of the post in text format. Specifically, the user opens the SNS app and writes in the input form, "A new cafe opened, but it was a bit disappointing."

[0086] Input: The text of the post entered by the user.

[0087] Output: Text data of the input post content.

[0088] Step 2:

[0089] The device sends the post content to the server.

[0090] The device sends the entered post content to the server via the network as an HTTP request (POST request). This operation uses a communication module.

[0091] Input: The text data of the post entered by the user.

[0092] Output: The HTTP request sent to the server.

[0093] Step 3:

[0094] The server receives and analyzes the posted content.

[0095] The server processes the received posts through a text analysis module to extract keywords and important context, which then translates the data into a format that is easier for generative AI to process.

[0096] Input: The text data sent in the HTTP request.

[0097] Data processing: Text analysis (keyword extraction, context analysis).

[0098] Output: Analyzed data fed into a generative artificial intelligence.

[0099] Step 4:

[0100] The server passes the post content to the generative artificial intelligence.

[0101] The analyzed post content is input to the generative AI as a prompt. This action generates a prompt and sends it to the AI ​​engine. An example of a prompt: "A user is about to post on social media that, 'A new cafe has opened, but it was a bit disappointing.' Please generate a general response to this post on social media, categorizing it as positive, negative, or neutral."

[0102] Input: Parsed data.

[0103] Data processing: Prompt sentence generation.

[0104] Output: A prompt to the generative AI.

[0105] Step 5:

[0106] Generative artificial intelligence generates reactions on social media.

[0107] Based on the prompt, the generative AI generates positive, negative, or neutral responses based on the characteristics of the virtual person. Specifically, it generates responses such as "I want to try that new cafe!" (positive response) or "Sorry, it didn't meet your expectations!" (negative response).

[0108] Input: The prompt statement.

[0109] Data processing: generating positive, negative, and neutral responses.

[0110] Output: The generated reaction data.

[0111] Step 6:

[0112] The server analyzes the generated responses and evaluates their topicality and likelihood of causing a stir.

[0113] The type and proportion of reactions generated are analyzed to calculate a score for topicality and inflammatoryness. For example, a high number of positive reactions indicates a high topicality, while a high number of negative reactions indicates a high inflammatoryness.

[0114] Input: Generated reaction data.

[0115] Data processing: Analysis of responses and calculation of scores.

[0116] Output: Evaluation results of topicality and inflammatoryness.

[0117] Step 7:

[0118] The server returns the evaluation results to the user terminal.

[0119] The evaluation results are sent to the user terminal in JSON format using a communication module.

[0120] Input: Topical and inflammatory evaluation results.

[0121] Output: JSON data sent to the user device.

[0122] Step 8:

[0123] The terminal displays the evaluation results to the user.

[0124] The device visually displays the received evaluation results, providing an interface that allows users to easily check them. For example, the evaluation results might be displayed on the screen as "Topicality: 8, Flaming Potential: 2."

[0125] Input: JSON data sent from the server.

[0126] Output: The evaluation result that is displayed to the user.

[0127] By following these steps, users can see in advance how their posts will be received on social media, which is an important indicator for users to adjust their posts appropriately.

[0128] (Application example 1)

[0129] 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."

[0130] In traditional advertising campaigns, there was no appropriate way to assess in advance how social media and online advertising posts would be received, i.e., their effectiveness (buzz level) and risk (flaming potential), making it difficult to maximize the effectiveness of advertising strategies while minimizing the risks. In particular, there was a lack of a system for simulating the impact of advertising, making it difficult to predict the success rate of marketing campaigns.

[0131] 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.

[0132] In this invention, the server includes means for inputting the content of posts, means for returning evaluation results to the user terminal, means for displaying the returned evaluation results to the user, means for evaluating the risk and effectiveness of the advertising campaign, and means for visually displaying the evaluated results of the advertising campaign. This makes it possible to simulate in advance the degree of buzz and potential for an advertising campaign to cause a stir, and to optimize advertising strategies based on the evaluation results.

[0133] "Posted content" refers to content such as text, images, and videos posted by users on social media or online platforms.

[0134] A "server" is a computer system that receives data sent by a user, processes, analyzes, and returns results.

[0135] "Generative AI" is an artificial intelligence system that analyzes the content of posts entered by users and generates responses based on that content.

[0136] A "pseudo-personality" is a virtual personality programmed by a generative AI to generate various reactions.

[0137] "Reactions" are positive, negative, or neutral opinions and comments that the generative AI generates in response to a post.

[0138] "Buzz level" is an evaluation score that indicates how much of a topic a post will become on social media or online platforms.

[0139] "Flame potential" is a rating score that indicates how likely a post is to provoke a negative reaction on social media or online platforms.

[0140] The "evaluation results" are scores of buzz and flame potential calculated based on the generated reactions.

[0141] A "user terminal" is a device used by a user to input post content and receive evaluation results, and includes smartphones, tablets, desktop computers, etc.

[0142] An "advertising campaign" is a series of advertising activities designed to promote a product or service.

[0143] The "risk" is the possibility that the advertising campaign will cause negative reactions on social media or online platforms.

[0144] "Effectiveness" is a measure of how much positive response an advertising campaign generates on social media and online platforms.

[0145] "Visually displaying" means presenting the evaluation results to the user as visual data such as graphs and charts.

[0146] The embodiment of this invention is a system that inputs the content of posts and provides evaluation results for them, with the aim of evaluating the buzz and potential for an advertising campaign in particular. This system consists of three main components: a user terminal, a server, and a generative AI.

[0147] The user terminal provides an interface for entering post content. This includes a text entry field, the ability to upload images and videos, and a button to start the simulation. Users enter or upload the ad copy they want to post and related images or videos. This interface is built using front-end frameworks such as React, Vue.js, and Angular.

[0148] The entered post content is sent to the server. The server is built using a server-side framework such as Node.js or Django. The sent data is in JSON format and is sent using an HTTP POST request. The server receives the input data and processes it to pass it to the generative AI.

[0149] The generative AI analyzes the content of posts entered by users and generates responses using pseudo-personalities. These responses are generated in three categories: positive, negative, and neutral. For example, generative AI models such as OpenAI GPT-3 (registered trademark) and Hugging Face Transformers are used. The generative AI generates responses based on prompts such as the following:

[0150] Example prompt sentence:

[0151] "New product! Amazing results!"

[0152] Based on the generated reactions, the server evaluates the buzz level and likelihood of the post becoming a viral sensation. The evaluation uses an algorithm that aggregates the positive, negative, and neutral tendencies of each generated reaction and calculates a numerical score. The evaluation results are then returned to the user's device in JSON format.

[0153] The user device visually displays the returned evaluation results. The evaluation results are displayed in the form of graphs or charts. For example, a high buzz score indicates a lot of positive reactions, while a high flame war potential indicates a lot of negative reactions. For this visual display, a data visualization library such as D3.js is used.

[0154] For example, if a user enters the ad copy "New product! Experience amazing results!" and uploads an image to accompany it, the generative AI will generate a response, and the server will evaluate the buzz and potential for virality based on that response. For example, a score of 8 for buzz and 3 for potential virality will be displayed, and the user can adjust their advertising strategy based on this.

[0155] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0156] Step 1:

[0157] The user inputs the content of the post from the device. The user enters or uploads the ad copy, related images, and videos they want to post on social media into the input fields. For example, a user might enter a text ad such as "New product! Experience amazing results!" This information is collected by the device interface and converted into JSON format. The input is in text format and image / video file format, and is input from the user to the device.

[0158] Step 2:

[0159] The device sends the entered data to the server. The entered post content is sent to the server via an HTTP POST request. The device converts this data into JSON format and sends it to the server. Input is text and image / video files entered by the user into the device, and output is performed from the device to the server.

[0160] Step 3:

[0161] The server receives the submitted post and passes it to the generative AI. The server analyzes the received input data and generates a prompt to pass the content to the generative AI model (e.g., GPT-3) in an appropriate format. The input is JSON data sent from the device, and the server outputs a prompt to pass the analyzed data to the generative AI model.

[0162] Step 4:

[0163] The generative AI analyzes the content of the post and generates a response using a pseudo-personality. The generative AI generates positive, negative, or neutral responses based on the provided prompt. For example, in response to the ad copy "New product! Experience amazing results!", it generates responses such as "Amazing! I'll buy it right away! (Positive)" or "Is it true? Suspicious (Negative)." The input is the prompt provided by the server, and the generated response is output.

[0164] Step 5:

[0165] The server evaluates the buzz level and likelihood of a viral outbreak based on the generated reactions. It analyzes each generated reaction and calculates a buzz level and likelihood of a viral outbreak score based on the number of positive, negative, and neutral reactions. For example, if there are more positive reactions, the buzz level will be higher, and if there are more negative reactions, the likelihood of a viral outbreak will be higher. The input is reaction data from the generative AI model, and the output is the evaluated buzz level and likelihood of a viral outbreak score.

[0166] Step 6:

[0167] The server returns the evaluation results to the user's device. The evaluation results (buzz level and inflammatory potential scores) are sent to the user's device in JSON format. The input is the score data of the evaluation results, which is output to be sent to the user's device.

[0168] Step 7:

[0169] The user device visually displays the returned evaluation results to the user. The user device analyzes the received evaluation results and presents them to the user in visualizations such as graphs and charts. The input is the JSON format evaluation results received from the server, and the analyzed visual data is output. This allows the user to obtain specific feedback to adjust their advertising strategy.

[0170] 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.

[0171] This invention is a system that simulates content that a user intends to post on social media in advance and provides real-time evaluation results of its buzz potential and potential for flame wars, and also combines it with an emotion engine that recognizes the user's emotions. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, a generative AI for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[0172] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0173] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. When the user clicks the post button, the post content is sent to the server.

[0174] The server has a means to receive posts sent from user devices. The server analyzes the received posts and passes them to the generative AI and emotion engine. This process also includes analyzing the posts and providing them to the emotion engine.

[0175] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of the posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[0176] The generative AI uses emotional data from the emotion engine to simulate reactions on social media to the content of a post. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0177] The server receives the simulated responses from the generative AI and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0178] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post being ignited based on the trends of each reaction. By taking emotional data into account, a more accurate assessment of likelihood of a post that reflects users' negative emotions can be obtained. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as likelihood of a post being ignited.

[0179] The server returns the calculated buzz and inflammatory ratings to the user's device as a response in JSON format.

[0180] The user terminal receives the evaluation results returned from the server. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "Buzz Level: 10, Flaming Potential: 3." This allows the user to know in advance how the post will be received on the SNS.

[0181] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI generates pseudo-reactions based on the recognized emotion. The generative AI generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" or "That's unfortunate (negative reaction)." The server evaluates these reactions and calculates a score, for example, "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[0182] The processing flow will be explained below.

[0183] Step 1:

[0184] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0185] Step 2:

[0186] The user terminal sends the entered post content to the server via an HTTP POST request, and the post content is sent to the server as data.

[0187] Step 3:

[0188] The server receives a POST request sent from the user's device. The server extracts the post content from the request and passes it to the emotion engine.

[0189] Step 4:

[0190] The emotion engine recognizes the user's emotions based on the content of the posts it receives. It uses natural language processing technology to analyze the emotions (joy, anger, sadness, etc.) expressed in the posts. For example, it recognizes the emotion "disappointment" based on the phrase "it was disappointing."

[0191] Step 5:

[0192] The server receives the recognized emotion data from the emotion engine, which influences the reaction generation by the generative AI.

[0193] Step 6:

[0194] The generative AI uses emotional data from the emotion engine to simulate social media reactions to the content of a post. Specifically, it generates positive, negative, and neutral reactions that take into account the user's emotions. For example, it generates reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0195] Step 7:

[0196] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0197] Step 8:

[0198] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post becoming a viral sensation based on the trends of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the likelihood of a post becoming a viral sensation.

[0199] Step 9:

[0200] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent to the user's device as a response in JSON format or similar.

[0201] Step 10:

[0202] The user device receives the evaluation results returned from the server and visually displays them to the user. The evaluation results are displayed on the screen of the user device as a score, such as "Buzz Level: 10, Flaming Potential: 3." This allows users to know in advance how their post will be received on the SNS.

[0203] Through these concrete steps, users can simulate the impact of their posts in advance and receive real-time feedback on the degree of buzz and potential for controversy. The introduction of an emotion engine allows for more accurate evaluations that reflect the user's emotions.

[0204] Example 2

[0205] 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."

[0206] In today's social networking environment, the content users post is likely to provoke widespread reactions, potentially leading to unexpected trouble or outrage. Therefore, users need a way to know in advance how their posts will be received. Furthermore, since there is no system for assessing whether a post will go viral or spark outrage, it is difficult for users to receive appropriate feedback before posting. This has led to a demand for ways to reduce the risks of using social networking sites and provide a safer environment.

[0207] 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.

[0208] In this invention, the server includes means for receiving the posted content and passing it to an emotion engine, means for the emotion engine to analyze the posted content and generate emotion data, means for a generation AI model to generate reactions based on the generated emotion data, and means for evaluating the buzz level and likelihood of a post based on the generated reactions. This allows users to simulate reactions to their posted content on SNS in advance and provides evaluation results of the buzz level and likelihood of a post being a controversy in real time. Furthermore, since more accurate evaluations reflecting the user's emotions are obtained, users can use SNS with peace of mind.

[0209] "Posted content" is text data that indicates the content that a user intends to post on the SNS.

[0210] The "central processing unit" is a server that analyzes the content of posts and passes the data to the emotion engine and generative AI model.

[0211] The "emotion engine" is an algorithm that analyzes users' emotions from the content of their posts and generates emotional data such as joy, anger, and sadness.

[0212] A "generative AI model" is an artificial intelligence model that simulates reactions on social media based on emotional data from an emotion engine.

[0213] "Reactions" are feedback from users on social media simulated by the generative AI model, and can be positive, negative, or neutral.

[0214] "Buzz level" is a number that indicates how much attention a post receives on social media.

[0215] "Flame potential" is a number that indicates the degree of negative reaction a post garners on social media.

[0216] The "user interface" is an interface for visually displaying the evaluation results to the user.

[0217] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its buzz potential and potential for flaming. This system includes a terminal for users to input the content to be posted, a central processing unit for processing the content, a generative AI model for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[0218] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0219] The user terminal has a means for sending the entered post content to the central processing unit. The submitted post content is sent to the central processing unit as an HTTP request. When the user clicks the post button, the post content is sent to the central processing unit.

[0220] The central processing unit has a means for receiving posted content sent from a user terminal. The central processing unit analyzes the received posted content and passes it to the emotion engine. This process also includes processing for analyzing the posted content and providing it to the emotion engine.

[0221] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[0222] The generative AI model uses emotional data from the emotion engine to simulate social media reactions to posts. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0223] The central processing unit receives the simulated responses returned by the generative AI model, and based on these responses, the central processing unit processes the content to assess its virality and potential for flaming.

[0224] The central processing unit analyzes the generated reactions and emotional data, and quantifies the buzz level and inflammatory potential based on the tendency of each reaction. By taking the emotional data into consideration, a more accurate assessment of inflammatory potential can be obtained for posts that reflect users' negative emotions. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the inflammatory potential.

[0225] The central processing unit returns the calculated evaluation results of buzz level and inflammatory potential to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0226] The user terminal receives the evaluation results returned from the central processing unit. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "buzz level: 10, potential for controversy: 3." This allows the user to know in advance how the post will be received on the SNS.

[0227] Example

[0228] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the central processing unit. The central processing unit passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI model generates pseudo-reactions based on the recognized emotion. The generative AI model generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" and "That's unfortunate (negative reaction)." The central processing unit evaluates these reactions and calculates a score: "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[0229] Prompt Sentence Examples

[0230] An example of a prompt for a generative AI model might look like this:

[0231] "Simulate the social media reaction when a user posts, 'A new cafe just opened, but it was a bit disappointing,' and generate both positive and negative reactions."

[0232] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0233] Step 1:

[0234] The user enters the content to post.

[0235] A user inputs the content they want to post on SNS into their device. For example, they might input, "A new cafe opened, but it was a bit disappointing." This input data is text data that will be used in subsequent processing steps.

[0236] Step 2:

[0237] The device sends the post content to the server.

[0238] When a user clicks the post button, the terminal sends the post content to the central processing unit as an HTTP request. Specifically, this request is packaged in JSON format and sent to the central processing unit using the HTTP POST method. The input is the text data entered by the user, and the output is the HTTP request data received by the server.

[0239] Step 3:

[0240] The server receives the post.

[0241] The central processing unit receives the HTTP request sent from the terminal and extracts the posted content. Web server software (e.g., Apache (registered trademark), Nginx) performs this process. The input is the HTTP request data, and the output is the text data of the posted content.

[0242] Step 4:

[0243] The server analyzes the content of the post and passes it to the emotion engine.

[0244] The central processing unit analyzes the received posts and passes them to the emotion engine. This analysis includes text preprocessing (e.g., tokenization, stop word removal). The input is the text data of the posts, and the output is the preprocessed post data.

[0245] Step 5:

[0246] The emotion engine recognizes the user's emotions.

[0247] The emotion engine recognizes user emotions based on the content of the posts it receives. It uses natural language processing technology (e.g., BERT, RoBERTa) to analyze emotions and generate emotion data such as "joy," "anger," and "sadness." For example, it recognizes the phrase "It was a bit disappointing" as "disappointment." The input is preprocessed post content data, and the output is emotion data.

[0248] Step 6:

[0249] The server passes the emotion data to the generative AI.

[0250] The central processing unit passes the emotion data obtained from the emotion engine to the generative AI model. This data becomes the prompt for the generative AI model. The input is emotion data, and the output is prompt data used by the generative AI model.

[0251] Step 7:

[0252] Generative AI simulates social media reactions.

[0253] Generative AI models (e.g., GPT-3, T5) simulate social media reactions based on emotional data and post content. For example, they generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction). The input is prompt data, and the output is simulated reaction data.

[0254] Step 8:

[0255] The server evaluates the simulation results.

[0256] The central processing unit evaluates the buzz level and likelihood of a post being ignited based on the responses returned by the generative AI model. Specifically, it counts the number of positive responses to determine the buzz level, and counts the number of negative responses to determine the likelihood of a post being ignited. The input is simulated response data, and the output is evaluation result data.

[0257] Step 9:

[0258] The server returns the evaluation results to the user terminal.

[0259] The central processing unit returns the calculated evaluation results of buzz and inflammatory potential to the user device in JSON format. The input is the evaluation result data, and the output is the response data sent to the user device.

[0260] Step 10:

[0261] The user checks the evaluation results.

[0262] The user checks the evaluation results returned from the central processing unit on the terminal. The buzz level and controversy scores are visually displayed via the display interface. For example, the scores might be "buzz level: 10, controversy level: 3." The input is the response data received by the terminal, and the output is the evaluation results visually displayed to the user.

[0263] (Application example 2)

[0264] 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."

[0265] In recent years, social networking sites and content distribution services have required users to evaluate the content of their posts in advance and predict the reactions. However, if the content of a post is inappropriate or there is a risk of it causing a controversy, the costs and risks that users must anticipate are high. For this reason, content distributors and influencers need a system that can simulate the impact of a post before it is made and take appropriate action.

[0266] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0267] In this invention, the server includes means for a generative AI to analyze the content of a post and generate reactions using an emotion engine, means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions, and means for generating reactions based on the content of the post using prompt text and providing the evaluation results in a content distribution service. This allows users to simulate the impact of their posts in real time before posting and take appropriate action.

[0268] "Posted content" refers to information such as text, images, and videos that a user intends to post on a social networking site or content distribution service.

[0269] "Server" refers to a computer system that receives, analyzes, and processes posted content sent from user devices.

[0270] "Generative AI" refers to artificial intelligence that generates responses based on user posts.

[0271] An "emotion engine" refers to a program or algorithm that analyzes the emotions in a post and generates a response based on those emotions.

[0272] "Reactions" refer to positive, negative, or neutral comments and ratings generated by generative AI based on the content of a post.

[0273] "Buzz level" refers to a score that evaluates the degree to which a post attracts attention on social media.

[0274] "Flame potential" refers to a score that assesses the likelihood that a post will provoke a negative reaction on social media.

[0275] A "prompt" refers to an instruction entered into a generative AI to generate the optimal response.

[0276] "Content distribution service" refers to an online platform that enables users to distribute content, such as text, images, and videos, created by users to other users.

[0277] "Evaluation results" refer to the scores for the buzz level and potential for controversy of the post content, analyzed by the server using generative AI and an emotion engine.

[0278] To implement this invention, the following system must be constructed. The system allows users to input content to post on social media or content distribution services and simulate the impact of that content in advance. This system consists of a user terminal, a server, a generative AI, an emotion engine, and communication means connecting them.

[0279] First, the user terminal provides an interface for the user to input the content of their post. For example, the user may input the content of their post, "A new cafe opened, but it was a bit disappointing." This content of their post is sent from the user terminal to the server as an HTTP request.

[0280] The server receives posts sent from user devices. The received posts are passed to the emotion engine and generative AI. The emotion engine uses natural language processing technology to analyze the emotions in the posts. For example, if the post contains a negative expression such as "it was a bit disappointing," the emotion engine will recognize this as "disappointment."

[0281] The generative AI simulates social media reactions to posts based on emotional data from the emotion engine. The generative AI generates reactions using the following prompts:

[0282] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[0283] Simulate what the reaction on social media would be like.

[0284] Based on this prompt, the generative AI generates positive, negative, or neutral responses, such as "That was disappointing, but let's hope for the next one!" (positive response) or "That's unfortunate!" (negative response).

[0285] The server evaluates the buzz level and potential for flaming based on the generated reactions. The evaluation is based on the emotional tendencies of the reactions generated by the generative AI. The number of positive reactions is calculated as the buzz level, and the number of negative reactions as the potential for flaming. For example, the server calculates a score of "buzz level: 10, potential for flaming: 3."

[0286] Finally, the server returns the calculated buzz and flame potential evaluation results to the user's device. The evaluation results are visually displayed on the user's device. By checking the scores, users can know in advance how their post will be received on the SNS.

[0287] The following hardware and software are required to realize this system: OpenAI's GPT-3 as the generative AI, TextBlob as the emotion engine, and a web browser and HTTP communication method as the user interface. This allows users to simulate the impact of their posts in real time and take appropriate action before posting.

[0288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0289] Step 1:

[0290] The user inputs the content of the post into the device. The user inputs the content into the input interface. For example, the user inputs a post such as "A new cafe opened, but it was a bit disappointing." This is the input data. The input data is temporarily stored in the built-in memory.

[0291] Step 2:

[0292] The device sends the entered post content to the server as an HTTP request. Specifically, it generates an HTTP POST request and sends the post content to the server in JSON format or similar. The output is the request data sent to the server. The server receives this POST request.

[0293] Step 3:

[0294] The server analyzes the received post content and passes it to an emotion engine. The analysis program on the server extracts the post content as text and performs emotion analysis using an emotion engine such as TextBlob. Specifically, it obtains an emotion tag: positive, negative, or neutral. This emotion tag is the output data.

[0295] Step 4:

[0296] The server provides emotion data from the emotion engine to the generative AI. The server generates prompts and sends them to GPT-3, a valued-based AI. The generative AI generates responses based on the following prompts:

[0297] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[0298] Simulate what the reaction on social media would be like.

[0299] The output is the generated response data.

[0300] Step 5:

[0301] The server evaluates the buzz level and likelihood of a reaction based on the generated reactions. Specifically, it performs sentiment analysis on each reaction sentence and tallies the number of positive and negative reactions. The number of positive reactions is quantified as buzz level, and the number of negative reactions is quantified as likelihood of a reaction. The output is an evaluation score for buzz level and likelihood of a reaction.

[0302] Step 6:

[0303] The server returns the calculated evaluation results of buzz level and flame potential to the user's device. The evaluation results are sent from the server to the device as an HTTP response in a data format such as JSON. The output is the evaluation result data sent to the user's device.

[0304] Step 7:

[0305] The user device receives the evaluation results returned from the server and visually displays them via a display interface. Specifically, scores such as "Buzz Level: 10, Flaming Potential: 3" are displayed on the user interface. By checking this, users can know in advance how their post will be received on the SNS. The output is the evaluation score displayed to the user.

[0306] 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.

[0307] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0308] 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.

[0309] [Second embodiment]

[0310] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0311] 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.

[0312] 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).

[0313] 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.

[0314] 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.

[0315] 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).

[0316] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0317] 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.

[0318] 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.

[0319] 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.

[0320] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0321] 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."

[0322] This invention is a system that simulates the content that a user intends to post on social media in advance and provides real-time evaluation results of the content's buzz and potential for flaming. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, and a generative AI for generating and evaluating reactions.

[0323] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0324] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. An example of this transmission is when the user terminal sends the post content using a "POST" request.

[0325] The server has a means to receive the posted content sent from the user's device. The server analyzes the received posted content and passes it to the generative AI. This process is used to analyze the posted content and provide it to the generative AI.

[0326] Generative AI uses pseudo-personalities to generate social media responses based on the content of posts. Generative AI generates positive, negative, and neutral responses based on the characteristics of the programmed pseudo-personalities. For example, it generates responses such as, "I want to try that new cafe!" (positive response) or "It's a shame it didn't live up to your expectations!" (negative response).

[0327] The server has a means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions. The generated reactions are analyzed, and the buzz level and likelihood of a post becoming a hot topic are quantified based on the trends of each reaction. This process makes it possible to evaluate how much of a post will become a hot topic or how likely it is to become a hot topic.

[0328] The server has a means to return the evaluation results to the user terminal. The evaluation results are sent to the user terminal in JSON format, etc. The user terminal has an interface to receive the returned evaluation results and visually display them to the user.

[0329] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to a generative AI, which generates simulated reactions. The generative AI generates positive, negative, and neutral reactions, and the server then evaluates the buzz level and likelihood of causing a stir based on these. The resulting score, for example, "buzz level: 10, likelihood of causing a stir: 3," is received by the user's device and displayed to the user. In this way, the user can know in advance how the post will be received on social media.

[0330] The processing flow will be explained below.

[0331] Step 1:

[0332] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0333] Step 2:

[0334] The user terminal sends the entered post content to the server via an HTTP POST request. At this time, the post content is sent to the server as data.

[0335] Step 3:

[0336] The server receives a POST request sent from the user's device, extracts the post content from the request, and passes it to the generative AI for analysis.

[0337] Step 4:

[0338] The generative AI analyzes the content of the post sent to it. During the analysis, it uses a pseudo-personality to simulate social media reactions to the post. The reactions generated here can be positive, negative, or neutral.

[0339] Step 5:

[0340] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0341] Step 6:

[0342] The server analyzes the generated reactions and quantifies the buzz level and flaming potential based on the tendency of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the flaming potential.

[0343] Step 7:

[0344] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0345] Step 8:

[0346] The user terminal receives the evaluation results returned from the server. The evaluation results are displayed to the user via a display interface to visually display them to the user. The user can confirm the score, for example, "Buzz level: 10, Flaming potential: 3."

[0347] Example 1

[0348] 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."

[0349] In recent years, the risk of posts on social media spreading in unexpected ways or causing outrage has increased because the content can be shared instantly by a large number of users. This has made it increasingly important for individuals and companies to evaluate posts in advance and understand their potential for spreading and causing outrage. However, current systems lack the means to evaluate posts before they are posted, and furthermore, it is difficult to evaluate them in real time.

[0350] 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.

[0351] In this invention, the server includes means for inputting post content, means for transmitting the input post content to a network device, means for the network device to receive the transmitted post content and pass it to a generative artificial intelligence, means for the generative artificial intelligence to analyze the post content and generate reactions using pseudo-personalities, means for evaluating topicality and potential for flaming based on the generated reactions, means for returning the evaluation results to a terminal device, and means for displaying the returned evaluation results to a user. This allows a user to evaluate in real time how content will be received on SNS before posting, and to grasp in advance the risk of topicality and potential for flaming.

[0352] "Post content" refers to the message or information that a user intends to post on a social networking site.

[0353] "Network device" refers to the computer system and communications infrastructure used to receive and analyze posted content.

[0354] "Generative AI" refers to an AI system that analyzes posted content and generates responses using pseudo-personalities.

[0355] "Pseudo-personality" refers to a model used by generative AI to simulate the characteristics and behavioral patterns of a virtual human.

[0356] "Topicality" refers to an indicator of how much a post becomes a hot topic on social media.

[0357] "Flame potential" refers to an indicator of the extent to which a post provokes a negative reaction on social media.

[0358] "Evaluation results" refer to indicators and numerical values ​​calculated based on the responses generated by generative artificial intelligence.

[0359] "Terminal device" refers to a device used by a user to input content to be posted.

[0360] "Reaction" refers to pseudo-feedback such as positive, negative, or neutral that generative artificial intelligence generates in response to a post.

[0361] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its topicality and potential to cause a stir. This system includes a terminal device for users to input the content to be posted, a network device for processing the content, and a generative artificial intelligence (AI) for generating and evaluating reactions.

[0362] A user uses a terminal device such as a smartphone or PC to input content they want to post on an SNS. For example, they might input content such as, "A new cafe opened, but it was a bit disappointing." The terminal device can then send the input content to a network device as an HTTP request.

[0363] The network device has a means to receive and analyze the posted content sent from the user terminal. Specifically, it uses a text analysis module to break down the posted content and extract the necessary information. The analysis results are formatted in a format that can be used by generative artificial intelligence (e.g., OpenAI's GPT-4).

[0364] The network device then passes the analyzed post content to the generative AI as a prompt. An example of a prompt when using a generative AI model is, "A user is about to post on social media that a new cafe has opened, but it was a bit disappointing. Please generate a prompt that classifies the general reactions to this post on social media into positive, negative, and neutral."

[0365] The generative AI generates a response to the post based on this prompt. The generated responses are classified into three types: positive, negative, and neutral. For example, responses such as "I want to try that new cafe!" (positive response), "Sorry that it didn't meet your expectations" (negative response), and "Hmm, that's just average" (neutral response) could be generated.

[0366] The network device evaluates the topicality and potential for controversy of the post based on the generated reactions. Topicality and potential for controversy are calculated based on a specific formula, analyzing the proportion and strength of the generated reactions. For example, on a 10-point scale, a score such as "Topicality: 8, Potential for controversy: 2" can be obtained.

[0367] Finally, the network device returns the evaluation results in JSON format to the terminal device. The terminal device has an interface that visually displays the received evaluation results to the user, allowing the user to check the evaluation results. For example, the evaluation results may be displayed as "Topicality: 8, Flaming Potential: 2." This allows users to know in advance how their post will be received on SNS.

[0368] Through the above steps, this system helps users reduce the risks associated with posting on social media and disseminate information more safely.

[0369] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0370] System program processing flow

[0371] Step 1:

[0372] The user enters the content to post.

[0373] The user uses a terminal device to input the content of the post in text format. Specifically, the user opens the SNS app and writes in the input form, "A new cafe opened, but it was a bit disappointing."

[0374] Input: The text of the post entered by the user.

[0375] Output: Text data of the input post content.

[0376] Step 2:

[0377] The device sends the post content to the server.

[0378] The device sends the entered post content to the server via the network as an HTTP request (POST request). This operation uses a communication module.

[0379] Input: The text data of the post entered by the user.

[0380] Output: The HTTP request sent to the server.

[0381] Step 3:

[0382] The server receives and analyzes the posted content.

[0383] The server processes the received posts through a text analysis module to extract keywords and important context, which then translates the data into a format that is easier for generative AI to process.

[0384] Input: The text data sent in the HTTP request.

[0385] Data processing: Text analysis (keyword extraction, context analysis).

[0386] Output: Analyzed data fed into a generative artificial intelligence.

[0387] Step 4:

[0388] The server passes the post content to the generative artificial intelligence.

[0389] The analyzed post content is input to the generative AI as a prompt. This action generates a prompt and sends it to the AI ​​engine. An example of a prompt: "A user is about to post on social media that, 'A new cafe has opened, but it was a bit disappointing.' Please generate a general response to this post on social media, categorizing it as positive, negative, or neutral."

[0390] Input: Parsed data.

[0391] Data processing: Prompt sentence generation.

[0392] Output: A prompt to the generative AI.

[0393] Step 5:

[0394] Generative artificial intelligence generates reactions on social media.

[0395] Based on the prompt, the generative AI generates positive, negative, or neutral responses based on the characteristics of the virtual person. Specifically, it generates responses such as "I want to try that new cafe!" (positive response) or "Sorry, it didn't meet your expectations!" (negative response).

[0396] Input: The prompt statement.

[0397] Data processing: generating positive, negative, and neutral responses.

[0398] Output: The generated reaction data.

[0399] Step 6:

[0400] The server analyzes the generated responses and evaluates their topicality and likelihood of causing a stir.

[0401] The type and proportion of reactions generated are analyzed to calculate a score for topicality and inflammatoryness. For example, a high number of positive reactions indicates a high topicality, while a high number of negative reactions indicates a high inflammatoryness.

[0402] Input: Generated reaction data.

[0403] Data processing: Analysis of responses and calculation of scores.

[0404] Output: Evaluation results of topicality and inflammatoryness.

[0405] Step 7:

[0406] The server returns the evaluation results to the user terminal.

[0407] The evaluation results are sent to the user terminal in JSON format using a communication module.

[0408] Input: Topical and inflammatory evaluation results.

[0409] Output: JSON data sent to the user device.

[0410] Step 8:

[0411] The terminal displays the evaluation results to the user.

[0412] The device visually displays the received evaluation results, providing an interface that allows users to easily check them. For example, the evaluation results might be displayed on the screen as "Topicality: 8, Flaming Potential: 2."

[0413] Input: JSON data sent from the server.

[0414] Output: The evaluation result that is displayed to the user.

[0415] By following these steps, users can see in advance how their posts will be received on social media, which is an important indicator for users to adjust their posts appropriately.

[0416] (Application example 1)

[0417] 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."

[0418] In traditional advertising campaigns, there was no appropriate way to assess in advance how social media and online advertising posts would be received, i.e., their effectiveness (buzz level) and risk (flaming potential), making it difficult to maximize the effectiveness of advertising strategies while minimizing the risks. In particular, there was a lack of a system for simulating the impact of advertising, making it difficult to predict the success rate of marketing campaigns.

[0419] 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.

[0420] In this invention, the server includes means for inputting the content of posts, means for returning evaluation results to the user terminal, means for displaying the returned evaluation results to the user, means for evaluating the risk and effectiveness of the advertising campaign, and means for visually displaying the evaluated results of the advertising campaign. This makes it possible to simulate in advance the degree of buzz and potential for an advertising campaign to cause a stir, and to optimize advertising strategies based on the evaluation results.

[0421] "Posted content" refers to content such as text, images, and videos posted by users on social media or online platforms.

[0422] A "server" is a computer system that receives data sent by a user, processes, analyzes, and returns results.

[0423] "Generative AI" is an artificial intelligence system that analyzes the content of posts entered by users and generates responses based on that content.

[0424] A "pseudo-personality" is a virtual personality programmed by a generative AI to generate various reactions.

[0425] "Reactions" are positive, negative, or neutral opinions and comments that the generative AI generates in response to a post.

[0426] "Buzz level" is an evaluation score that indicates how much of a topic a post will become on social media or online platforms.

[0427] "Flame potential" is a rating score that indicates how likely a post is to provoke a negative reaction on social media or online platforms.

[0428] The "evaluation results" are scores of buzz and flame potential calculated based on the generated reactions.

[0429] A "user terminal" is a device used by a user to input post content and receive evaluation results, and includes smartphones, tablets, desktop computers, etc.

[0430] An "advertising campaign" is a series of advertising activities designed to promote a product or service.

[0431] The "risk" is the possibility that the advertising campaign will cause negative reactions on social media or online platforms.

[0432] "Effectiveness" is a measure of how much positive response an advertising campaign generates on social media and online platforms.

[0433] "Visually displaying" means presenting the evaluation results to the user as visual data such as graphs and charts.

[0434] The embodiment of this invention is a system that inputs the content of posts and provides evaluation results for them, with the aim of evaluating the buzz and potential for an advertising campaign in particular. This system consists of three main components: a user terminal, a server, and a generative AI.

[0435] The user terminal provides an interface for entering post content. This includes a text entry field, the ability to upload images and videos, and a button to start the simulation. Users enter or upload the ad copy they want to post and related images or videos. This interface is built using front-end frameworks such as React, Vue.js, and Angular.

[0436] The entered post content is sent to the server. The server is built using a server-side framework such as Node.js or Django. The sent data is in JSON format and is sent using an HTTP POST request. The server receives the input data and processes it to pass it to the generative AI.

[0437] Generative AI analyzes the content of posts entered by users and generates responses using pseudo-personalities. These responses are generated in three categories: positive, negative, and neutral. For example, generative AI models such as OpenAI GPT-3 and Hugging Face Transformers are used. Generative AI generates responses based on prompts such as the following:

[0438] Example prompt sentence:

[0439] "New product! Amazing results!"

[0440] Based on the generated reactions, the server evaluates the buzz level and likelihood of the post becoming a viral sensation. The evaluation uses an algorithm that aggregates the positive, negative, and neutral tendencies of each generated reaction and calculates a numerical score. The evaluation results are then returned to the user's device in JSON format.

[0441] The user device visually displays the returned evaluation results. The evaluation results are displayed in the form of graphs or charts. For example, a high buzz score indicates a lot of positive reactions, while a high flame war potential indicates a lot of negative reactions. For this visual display, a data visualization library such as D3.js is used.

[0442] For example, if a user enters the ad copy "New product! Experience amazing results!" and uploads an image to accompany it, the generative AI will generate a response, and the server will evaluate the buzz and potential for virality based on that response. For example, a score of 8 for buzz and 3 for potential virality will be displayed, and the user can adjust their advertising strategy based on this.

[0443] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0444] Step 1:

[0445] The user inputs the content of the post from the device. The user enters or uploads the ad copy, related images, and videos they want to post on social media into the input fields. For example, a user might enter a text ad such as "New product! Experience amazing results!" This information is collected by the device interface and converted into JSON format. The input is in text format and image / video file format, and is input from the user to the device.

[0446] Step 2:

[0447] The device sends the entered data to the server. The entered post content is sent to the server via an HTTP POST request. The device converts this data into JSON format and sends it to the server. Input is text and image / video files entered by the user into the device, and output is performed from the device to the server.

[0448] Step 3:

[0449] The server receives the submitted post and passes it to the generative AI. The server analyzes the received input data and generates a prompt to pass the content to the generative AI model (e.g., GPT-3) in an appropriate format. The input is JSON data sent from the device, and the server outputs a prompt to pass the analyzed data to the generative AI model.

[0450] Step 4:

[0451] The generative AI analyzes the content of the post and generates a response using a pseudo-personality. The generative AI generates positive, negative, or neutral responses based on the provided prompt. For example, in response to the ad copy "New product! Experience amazing results!", it generates responses such as "Amazing! I'll buy it right away! (Positive)" or "Is it true? Suspicious (Negative)." The input is the prompt provided by the server, and the generated response is output.

[0452] Step 5:

[0453] The server evaluates the buzz level and likelihood of a viral outbreak based on the generated reactions. It analyzes each generated reaction and calculates a buzz level and likelihood of a viral outbreak score based on the number of positive, negative, and neutral reactions. For example, if there are more positive reactions, the buzz level will be higher, and if there are more negative reactions, the likelihood of a viral outbreak will be higher. The input is reaction data from the generative AI model, and the output is the evaluated buzz level and likelihood of a viral outbreak score.

[0454] Step 6:

[0455] The server returns the evaluation results to the user's device. The evaluation results (buzz level and inflammatory potential scores) are sent to the user's device in JSON format. The input is the score data of the evaluation results, which is output to be sent to the user's device.

[0456] Step 7:

[0457] The user device visually displays the returned evaluation results to the user. The user device analyzes the received evaluation results and presents them to the user in visualizations such as graphs and charts. The input is the JSON format evaluation results received from the server, and the analyzed visual data is output. This allows the user to obtain specific feedback to adjust their advertising strategy.

[0458] 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.

[0459] This invention is a system that simulates content that a user intends to post on social media in advance and provides real-time evaluation results of its buzz potential and potential for flame wars, and also combines it with an emotion engine that recognizes the user's emotions. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, a generative AI for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[0460] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0461] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. When the user clicks the post button, the post content is sent to the server.

[0462] The server has a means to receive posts sent from user devices. The server analyzes the received posts and passes them to the generative AI and emotion engine. This process also includes analyzing the posts and providing them to the emotion engine.

[0463] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of the posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[0464] The generative AI uses emotional data from the emotion engine to simulate reactions on social media to the content of a post. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0465] The server receives the simulated responses from the generative AI and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0466] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post being ignited based on the trends of each reaction. By taking emotional data into account, a more accurate assessment of likelihood of a post that reflects users' negative emotions can be obtained. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as likelihood of a post being ignited.

[0467] The server returns the calculated buzz and inflammatory ratings to the user's device as a response in JSON format.

[0468] The user terminal receives the evaluation results returned from the server. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "Buzz Level: 10, Flaming Potential: 3." This allows the user to know in advance how the post will be received on the SNS.

[0469] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI generates pseudo-reactions based on the recognized emotion. The generative AI generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" or "That's unfortunate (negative reaction)." The server evaluates these reactions and calculates a score, for example, "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[0470] The processing flow will be explained below.

[0471] Step 1:

[0472] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0473] Step 2:

[0474] The user terminal sends the entered post content to the server via an HTTP POST request, and the post content is sent to the server as data.

[0475] Step 3:

[0476] The server receives a POST request sent from the user's device. The server extracts the post content from the request and passes it to the emotion engine.

[0477] Step 4:

[0478] The emotion engine recognizes the user's emotions based on the content of the posts it receives. It uses natural language processing technology to analyze the emotions (joy, anger, sadness, etc.) expressed in the posts. For example, it recognizes the emotion "disappointment" based on the phrase "it was disappointing."

[0479] Step 5:

[0480] The server receives the recognized emotion data from the emotion engine, which influences the reaction generation by the generative AI.

[0481] Step 6:

[0482] The generative AI uses emotional data from the emotion engine to simulate social media reactions to the content of a post. Specifically, it generates positive, negative, and neutral reactions that take into account the user's emotions. For example, it generates reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0483] Step 7:

[0484] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0485] Step 8:

[0486] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post becoming a viral sensation based on the trends of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the likelihood of a post becoming a viral sensation.

[0487] Step 9:

[0488] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent to the user's device as a response in JSON format or similar.

[0489] Step 10:

[0490] The user device receives the evaluation results returned from the server and visually displays them to the user. The evaluation results are displayed on the screen of the user device as a score, such as "Buzz Level: 10, Flaming Potential: 3." This allows users to know in advance how their post will be received on the SNS.

[0491] Through these concrete steps, users can simulate the impact of their posts in advance and receive real-time feedback on the degree of buzz and potential for controversy. The introduction of an emotion engine allows for more accurate evaluations that reflect the user's emotions.

[0492] Example 2

[0493] 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."

[0494] In today's social networking environment, the content users post is likely to provoke widespread reactions, potentially leading to unexpected trouble or outrage. Therefore, users need a way to know in advance how their posts will be received. Furthermore, since there is no system for assessing whether a post will go viral or spark outrage, it is difficult for users to receive appropriate feedback before posting. This has led to a demand for ways to reduce the risks of using social networking sites and provide a safer environment.

[0495] 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.

[0496] In this invention, the server includes means for receiving the posted content and passing it to an emotion engine, means for the emotion engine to analyze the posted content and generate emotion data, means for a generation AI model to generate reactions based on the generated emotion data, and means for evaluating the buzz level and likelihood of a post based on the generated reactions. This allows users to simulate reactions to their posted content on SNS in advance and provides evaluation results of the buzz level and likelihood of a post being a controversy in real time. Furthermore, since more accurate evaluations reflecting the user's emotions are obtained, users can use SNS with peace of mind.

[0497] "Posted content" is text data that indicates the content that a user intends to post on the SNS.

[0498] The "central processing unit" is a server that analyzes the content of posts and passes the data to the emotion engine and generative AI model.

[0499] The "emotion engine" is an algorithm that analyzes users' emotions from the content of their posts and generates emotional data such as joy, anger, and sadness.

[0500] A "generative AI model" is an artificial intelligence model that simulates reactions on social media based on emotional data from an emotion engine.

[0501] "Reactions" are feedback from users on social media simulated by the generative AI model, and can be positive, negative, or neutral.

[0502] "Buzz level" is a number that indicates how much attention a post receives on social media.

[0503] "Flame potential" is a number that indicates the degree of negative reaction a post garners on social media.

[0504] The "user interface" is an interface for visually displaying the evaluation results to the user.

[0505] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its buzz potential and potential for flaming. This system includes a terminal for users to input the content to be posted, a central processing unit for processing the content, a generative AI model for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[0506] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0507] The user terminal has a means for sending the entered post content to the central processing unit. The submitted post content is sent to the central processing unit as an HTTP request. When the user clicks the post button, the post content is sent to the central processing unit.

[0508] The central processing unit has a means for receiving posted content sent from a user terminal. The central processing unit analyzes the received posted content and passes it to the emotion engine. This process also includes processing for analyzing the posted content and providing it to the emotion engine.

[0509] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[0510] The generative AI model uses emotional data from the emotion engine to simulate social media reactions to posts. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0511] The central processing unit receives the simulated responses returned by the generative AI model, and based on these responses, the central processing unit processes the content to assess its virality and potential for flaming.

[0512] The central processing unit analyzes the generated reactions and emotional data, and quantifies the buzz level and inflammatory potential based on the tendency of each reaction. By taking the emotional data into consideration, a more accurate assessment of inflammatory potential can be obtained for posts that reflect users' negative emotions. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the inflammatory potential.

[0513] The central processing unit returns the calculated evaluation results of buzz level and inflammatory potential to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0514] The user terminal receives the evaluation results returned from the central processing unit. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "buzz level: 10, potential for controversy: 3." This allows the user to know in advance how the post will be received on the SNS.

[0515] Example

[0516] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the central processing unit. The central processing unit passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI model generates pseudo-reactions based on the recognized emotion. The generative AI model generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" and "That's unfortunate (negative reaction)." The central processing unit evaluates these reactions and calculates a score: "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[0517] Prompt Sentence Examples

[0518] An example of a prompt for a generative AI model might look like this:

[0519] "Simulate the social media reaction when a user posts, 'A new cafe just opened, but it was a bit disappointing,' and generate both positive and negative reactions."

[0520] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0521] Step 1:

[0522] The user enters the content to post.

[0523] A user inputs the content they want to post on SNS into their device. For example, they might input, "A new cafe opened, but it was a bit disappointing." This input data is text data that will be used in subsequent processing steps.

[0524] Step 2:

[0525] The device sends the post content to the server.

[0526] When a user clicks the post button, the terminal sends the post content to the central processing unit as an HTTP request. Specifically, this request is packaged in JSON format and sent to the central processing unit using the HTTP POST method. The input is the text data entered by the user, and the output is the HTTP request data received by the server.

[0527] Step 3:

[0528] The server receives the post.

[0529] The central processing unit receives the HTTP request sent from the terminal and extracts the posted content. Web server software (e.g., Apache, Nginx) performs this process. The input is the HTTP request data, and the output is the text data of the posted content.

[0530] Step 4:

[0531] The server analyzes the content of the post and passes it to the emotion engine.

[0532] The central processing unit analyzes the received posts and passes them to the emotion engine. This analysis includes text preprocessing (e.g., tokenization, stop word removal). The input is the text data of the posts, and the output is the preprocessed post data.

[0533] Step 5:

[0534] The emotion engine recognizes the user's emotions.

[0535] The emotion engine recognizes user emotions based on the content of the posts it receives. It uses natural language processing technology (e.g., BERT, RoBERTa) to analyze emotions and generate emotion data such as "joy," "anger," and "sadness." For example, it recognizes the phrase "It was a bit disappointing" as "disappointment." The input is preprocessed post content data, and the output is emotion data.

[0536] Step 6:

[0537] The server passes the emotion data to the generative AI.

[0538] The central processing unit passes the emotion data obtained from the emotion engine to the generative AI model. This data becomes the prompt for the generative AI model. The input is emotion data, and the output is prompt data used by the generative AI model.

[0539] Step 7:

[0540] Generative AI simulates social media reactions.

[0541] Generative AI models (e.g., GPT-3, T5) simulate social media reactions based on emotional data and post content. For example, they generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction). The input is prompt data, and the output is simulated reaction data.

[0542] Step 8:

[0543] The server evaluates the simulation results.

[0544] The central processing unit evaluates the buzz level and likelihood of a post being ignited based on the responses returned by the generative AI model. Specifically, it counts the number of positive responses to determine the buzz level, and counts the number of negative responses to determine the likelihood of a post being ignited. The input is simulated response data, and the output is evaluation result data.

[0545] Step 9:

[0546] The server returns the evaluation results to the user terminal.

[0547] The central processing unit returns the calculated evaluation results of buzz and inflammatory potential to the user device in JSON format. The input is the evaluation result data, and the output is the response data sent to the user device.

[0548] Step 10:

[0549] The user checks the evaluation results.

[0550] The user checks the evaluation results returned from the central processing unit on the terminal. The buzz level and controversy scores are visually displayed via the display interface. For example, the scores might be "buzz level: 10, controversy level: 3." The input is the response data received by the terminal, and the output is the evaluation results visually displayed to the user.

[0551] (Application example 2)

[0552] 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."

[0553] In recent years, social networking sites and content distribution services have required users to evaluate the content of their posts in advance and predict the reactions. However, if the content of a post is inappropriate or there is a risk of it causing a controversy, the costs and risks that users must anticipate are high. For this reason, content distributors and influencers need a system that can simulate the impact of a post before it is made and take appropriate action.

[0554] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0555] In this invention, the server includes means for a generative AI to analyze the content of a post and generate reactions using an emotion engine, means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions, and means for generating reactions based on the content of the post using prompt text and providing the evaluation results in a content distribution service. This allows users to simulate the impact of their posts in real time before posting and take appropriate action.

[0556] "Posted content" refers to information such as text, images, and videos that a user intends to post on a social networking site or content distribution service.

[0557] "Server" refers to a computer system that receives, analyzes, and processes posted content sent from user devices.

[0558] "Generative AI" refers to artificial intelligence that generates responses based on user posts.

[0559] An "emotion engine" refers to a program or algorithm that analyzes the emotions in a post and generates a response based on those emotions.

[0560] "Reactions" refer to positive, negative, or neutral comments and ratings generated by generative AI based on the content of a post.

[0561] "Buzz level" refers to a score that evaluates the degree to which a post attracts attention on social media.

[0562] "Flame potential" refers to a score that assesses the likelihood that a post will provoke a negative reaction on social media.

[0563] A "prompt" refers to an instruction entered into a generative AI to generate the optimal response.

[0564] "Content distribution service" refers to an online platform that enables users to distribute content, such as text, images, and videos, created by users to other users.

[0565] "Evaluation results" refer to the scores for the buzz level and potential for controversy of the post content, analyzed by the server using generative AI and an emotion engine.

[0566] To implement this invention, the following system must be constructed. The system allows users to input content to post on social media or content distribution services and simulate the impact of that content in advance. This system consists of a user terminal, a server, a generative AI, an emotion engine, and communication means connecting them.

[0567] First, the user terminal provides an interface for the user to input the content of their post. For example, the user may input the content of their post, "A new cafe opened, but it was a bit disappointing." This content of their post is sent from the user terminal to the server as an HTTP request.

[0568] The server receives posts sent from user devices. The received posts are passed to the emotion engine and generative AI. The emotion engine uses natural language processing technology to analyze the emotions in the posts. For example, if the post contains a negative expression such as "it was a bit disappointing," the emotion engine will recognize this as "disappointment."

[0569] The generative AI simulates social media reactions to posts based on emotional data from the emotion engine. The generative AI generates reactions using the following prompts:

[0570] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[0571] Simulate what the reaction on social media would be like.

[0572] Based on this prompt, the generative AI generates positive, negative, or neutral responses, such as "That was disappointing, but let's hope for the next one!" (positive response) or "That's unfortunate!" (negative response).

[0573] The server evaluates the buzz level and potential for flaming based on the generated reactions. The evaluation is based on the emotional tendencies of the reactions generated by the generative AI. The number of positive reactions is calculated as the buzz level, and the number of negative reactions as the potential for flaming. For example, the server calculates a score of "buzz level: 10, potential for flaming: 3."

[0574] Finally, the server returns the calculated buzz and flame potential evaluation results to the user's device. The evaluation results are visually displayed on the user's device. By checking the scores, users can know in advance how their post will be received on the SNS.

[0575] The following hardware and software are required to realize this system: OpenAI's GPT-3 as the generative AI, TextBlob as the emotion engine, and a web browser and HTTP communication method as the user interface. This allows users to simulate the impact of their posts in real time and take appropriate action before posting.

[0576] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0577] Step 1:

[0578] The user inputs the content of the post into the device. The user inputs the content into the input interface. For example, the user inputs a post such as "A new cafe opened, but it was a bit disappointing." This is the input data. The input data is temporarily stored in the built-in memory.

[0579] Step 2:

[0580] The device sends the entered post content to the server as an HTTP request. Specifically, it generates an HTTP POST request and sends the post content to the server in JSON format or similar. The output is the request data sent to the server. The server receives this POST request.

[0581] Step 3:

[0582] The server analyzes the received post content and passes it to an emotion engine. The analysis program on the server extracts the post content as text and performs emotion analysis using an emotion engine such as TextBlob. Specifically, it obtains an emotion tag: positive, negative, or neutral. This emotion tag is the output data.

[0583] Step 4:

[0584] The server provides emotion data from the emotion engine to the generative AI. The server generates prompts and sends them to GPT-3, a valued-based AI. The generative AI generates responses based on the following prompts:

[0585] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[0586] Simulate what the reaction on social media would be like.

[0587] The output is the generated response data.

[0588] Step 5:

[0589] The server evaluates the buzz level and likelihood of a reaction based on the generated reactions. Specifically, it performs sentiment analysis on each reaction sentence and tallies the number of positive and negative reactions. The number of positive reactions is quantified as buzz level, and the number of negative reactions is quantified as likelihood of a reaction. The output is an evaluation score for buzz level and likelihood of a reaction.

[0590] Step 6:

[0591] The server returns the calculated evaluation results of buzz level and flame potential to the user's device. The evaluation results are sent from the server to the device as an HTTP response in a data format such as JSON. The output is the evaluation result data sent to the user's device.

[0592] Step 7:

[0593] The user device receives the evaluation results returned from the server and visually displays them via a display interface. Specifically, scores such as "Buzz Level: 10, Flaming Potential: 3" are displayed on the user interface. By checking this, users can know in advance how their post will be received on the SNS. The output is the evaluation score displayed to the user.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] [Third embodiment]

[0598] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0599] 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.

[0600] 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).

[0601] 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.

[0602] 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.

[0603] 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).

[0604] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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."

[0610] This invention is a system that simulates the content that a user intends to post on social media in advance and provides real-time evaluation results of the content's buzz and potential for flaming. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, and a generative AI for generating and evaluating reactions.

[0611] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0612] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. An example of this transmission is when the user terminal sends the post content using a "POST" request.

[0613] The server has a means to receive the posted content sent from the user's device. The server analyzes the received posted content and passes it to the generative AI. This process is used to analyze the posted content and provide it to the generative AI.

[0614] Generative AI uses pseudo-personalities to generate social media responses based on the content of posts. Generative AI generates positive, negative, and neutral responses based on the characteristics of the programmed pseudo-personalities. For example, it generates responses such as, "I want to try that new cafe!" (positive response) or "It's a shame it didn't live up to your expectations!" (negative response).

[0615] The server has a means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions. The generated reactions are analyzed, and the buzz level and likelihood of a post becoming a hot topic are quantified based on the trends of each reaction. This process makes it possible to evaluate how much of a post will become a hot topic or how likely it is to become a hot topic.

[0616] The server has a means to return the evaluation results to the user terminal. The evaluation results are sent to the user terminal in JSON format, etc. The user terminal has an interface to receive the returned evaluation results and visually display them to the user.

[0617] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to a generative AI, which generates simulated reactions. The generative AI generates positive, negative, and neutral reactions, and the server then evaluates the buzz level and likelihood of causing a stir based on these. The resulting score, for example, "buzz level: 10, likelihood of causing a stir: 3," is received by the user's device and displayed to the user. In this way, the user can know in advance how the post will be received on social media.

[0618] The processing flow will be explained below.

[0619] Step 1:

[0620] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0621] Step 2:

[0622] The user terminal sends the entered post content to the server via an HTTP POST request. At this time, the post content is sent to the server as data.

[0623] Step 3:

[0624] The server receives a POST request sent from the user's device, extracts the post content from the request, and passes it to the generative AI for analysis.

[0625] Step 4:

[0626] The generative AI analyzes the content of the post sent to it. During the analysis, it uses a pseudo-personality to simulate social media reactions to the post. The reactions generated here can be positive, negative, or neutral.

[0627] Step 5:

[0628] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0629] Step 6:

[0630] The server analyzes the generated reactions and quantifies the buzz level and flaming potential based on the tendency of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the flaming potential.

[0631] Step 7:

[0632] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0633] Step 8:

[0634] The user terminal receives the evaluation results returned from the server. The evaluation results are displayed to the user via a display interface to visually display them to the user. The user can confirm the score, for example, "Buzz level: 10, Flaming potential: 3."

[0635] Example 1

[0636] 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."

[0637] In recent years, the risk of posts on social media spreading in unexpected ways or causing outrage has increased because the content can be shared instantly by a large number of users. This has made it increasingly important for individuals and companies to evaluate posts in advance and understand their potential for spreading and causing outrage. However, current systems lack the means to evaluate posts before they are posted, and furthermore, it is difficult to evaluate them in real time.

[0638] 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.

[0639] In this invention, the server includes means for inputting post content, means for transmitting the input post content to a network device, means for the network device to receive the transmitted post content and pass it to a generative artificial intelligence, means for the generative artificial intelligence to analyze the post content and generate reactions using pseudo-personalities, means for evaluating topicality and potential for flaming based on the generated reactions, means for returning the evaluation results to a terminal device, and means for displaying the returned evaluation results to a user. This allows a user to evaluate in real time how content will be received on SNS before posting, and to grasp in advance the risk of topicality and potential for flaming.

[0640] "Post content" refers to the message or information that a user intends to post on a social networking site.

[0641] "Network device" refers to the computer system and communications infrastructure used to receive and analyze posted content.

[0642] "Generative AI" refers to an AI system that analyzes posted content and generates responses using pseudo-personalities.

[0643] "Pseudo-personality" refers to a model used by generative AI to simulate the characteristics and behavioral patterns of a virtual human.

[0644] "Topicality" refers to an indicator of how much a post becomes a hot topic on social media.

[0645] "Flame potential" refers to an indicator of the extent to which a post provokes a negative reaction on social media.

[0646] "Evaluation results" refer to indicators and numerical values ​​calculated based on the responses generated by generative artificial intelligence.

[0647] "Terminal device" refers to a device used by a user to input content to be posted.

[0648] "Reaction" refers to pseudo-feedback such as positive, negative, or neutral that generative artificial intelligence generates in response to a post.

[0649] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its topicality and potential to cause a stir. This system includes a terminal device for users to input the content to be posted, a network device for processing the content, and a generative artificial intelligence (AI) for generating and evaluating reactions.

[0650] A user uses a terminal device such as a smartphone or PC to input content they want to post on an SNS. For example, they might input content such as, "A new cafe opened, but it was a bit disappointing." The terminal device can then send the input content to a network device as an HTTP request.

[0651] The network device has a means to receive and analyze the posted content sent from the user terminal. Specifically, it uses a text analysis module to break down the posted content and extract the necessary information. The analysis results are formatted in a format that can be used by generative artificial intelligence (e.g., OpenAI's GPT-4).

[0652] The network device then passes the analyzed post content to the generative AI as a prompt. An example of a prompt when using a generative AI model is, "A user is about to post on social media that a new cafe has opened, but it was a bit disappointing. Please generate a prompt that classifies the general reactions to this post on social media into positive, negative, and neutral."

[0653] The generative AI generates a response to the post based on this prompt. The generated responses are classified into three types: positive, negative, and neutral. For example, responses such as "I want to try that new cafe!" (positive response), "Sorry that it didn't meet your expectations" (negative response), and "Hmm, that's just average" (neutral response) could be generated.

[0654] The network device evaluates the topicality and potential for controversy of the post based on the generated reactions. Topicality and potential for controversy are calculated based on a specific formula, analyzing the proportion and strength of the generated reactions. For example, on a 10-point scale, a score such as "Topicality: 8, Potential for controversy: 2" can be obtained.

[0655] Finally, the network device returns the evaluation results in JSON format to the terminal device. The terminal device has an interface that visually displays the received evaluation results to the user, allowing the user to check the evaluation results. For example, the evaluation results may be displayed as "Topicality: 8, Flaming Potential: 2." This allows users to know in advance how their post will be received on SNS.

[0656] Through the above steps, this system helps users reduce the risks associated with posting on social media and disseminate information more safely.

[0657] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0658] System program processing flow

[0659] Step 1:

[0660] The user enters the content to post.

[0661] The user uses a terminal device to input the content of the post in text format. Specifically, the user opens the SNS app and writes in the input form, "A new cafe opened, but it was a bit disappointing."

[0662] Input: The text of the post entered by the user.

[0663] Output: Text data of the input post content.

[0664] Step 2:

[0665] The device sends the post content to the server.

[0666] The device sends the entered post content to the server via the network as an HTTP request (POST request). This operation uses a communication module.

[0667] Input: The text data of the post entered by the user.

[0668] Output: The HTTP request sent to the server.

[0669] Step 3:

[0670] The server receives and analyzes the posted content.

[0671] The server processes the received posts through a text analysis module to extract keywords and important context, which then translates the data into a format that is easier for generative AI to process.

[0672] Input: The text data sent in the HTTP request.

[0673] Data processing: Text analysis (keyword extraction, context analysis).

[0674] Output: Analyzed data fed into a generative artificial intelligence.

[0675] Step 4:

[0676] The server passes the post content to the generative artificial intelligence.

[0677] The analyzed post content is input to the generative AI as a prompt. This action generates a prompt and sends it to the AI ​​engine. An example of a prompt: "A user is about to post on social media that, 'A new cafe has opened, but it was a bit disappointing.' Please generate a general response to this post on social media, categorizing it as positive, negative, or neutral."

[0678] Input: Parsed data.

[0679] Data processing: Prompt sentence generation.

[0680] Output: A prompt to the generative AI.

[0681] Step 5:

[0682] Generative artificial intelligence generates reactions on social media.

[0683] Based on the prompt, the generative AI generates positive, negative, or neutral responses based on the characteristics of the virtual person. Specifically, it generates responses such as "I want to try that new cafe!" (positive response) or "Sorry, it didn't meet your expectations!" (negative response).

[0684] Input: The prompt statement.

[0685] Data processing: generating positive, negative, and neutral responses.

[0686] Output: The generated reaction data.

[0687] Step 6:

[0688] The server analyzes the generated responses and evaluates their topicality and likelihood of causing a stir.

[0689] The type and proportion of reactions generated are analyzed to calculate a score for topicality and inflammatoryness. For example, a high number of positive reactions indicates a high topicality, while a high number of negative reactions indicates a high inflammatoryness.

[0690] Input: Generated reaction data.

[0691] Data processing: Analysis of responses and calculation of scores.

[0692] Output: Evaluation results of topicality and inflammatoryness.

[0693] Step 7:

[0694] The server returns the evaluation results to the user terminal.

[0695] The evaluation results are sent to the user terminal in JSON format using a communication module.

[0696] Input: Topical and inflammatory evaluation results.

[0697] Output: JSON data sent to the user device.

[0698] Step 8:

[0699] The terminal displays the evaluation results to the user.

[0700] The device visually displays the received evaluation results, providing an interface that allows users to easily check them. For example, the evaluation results might be displayed on the screen as "Topicality: 8, Flaming Potential: 2."

[0701] Input: JSON data sent from the server.

[0702] Output: The evaluation result that is displayed to the user.

[0703] By following these steps, users can see in advance how their posts will be received on social media, which is an important indicator for users to adjust their posts appropriately.

[0704] (Application example 1)

[0705] 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."

[0706] In traditional advertising campaigns, there was no appropriate way to assess in advance how social media and online advertising posts would be received, i.e., their effectiveness (buzz level) and risk (flaming potential), making it difficult to maximize the effectiveness of advertising strategies while minimizing the risks. In particular, there was a lack of a system for simulating the impact of advertising, making it difficult to predict the success rate of marketing campaigns.

[0707] 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.

[0708] In this invention, the server includes means for inputting the content of posts, means for returning evaluation results to the user terminal, means for displaying the returned evaluation results to the user, means for evaluating the risk and effectiveness of the advertising campaign, and means for visually displaying the evaluated results of the advertising campaign. This makes it possible to simulate in advance the degree of buzz and potential for an advertising campaign to cause a stir, and to optimize advertising strategies based on the evaluation results.

[0709] "Posted content" refers to content such as text, images, and videos posted by users on social media or online platforms.

[0710] A "server" is a computer system that receives data sent by a user, processes, analyzes, and returns results.

[0711] "Generative AI" is an artificial intelligence system that analyzes the content of posts entered by users and generates responses based on that content.

[0712] A "pseudo-personality" is a virtual personality programmed by a generative AI to generate various reactions.

[0713] "Reactions" are positive, negative, or neutral opinions and comments that the generative AI generates in response to a post.

[0714] "Buzz level" is an evaluation score that indicates how much of a topic a post will become on social media or online platforms.

[0715] "Flame potential" is a rating score that indicates how likely a post is to provoke a negative reaction on social media or online platforms.

[0716] The "evaluation results" are scores of buzz and flame potential calculated based on the generated reactions.

[0717] A "user terminal" is a device used by a user to input post content and receive evaluation results, and includes smartphones, tablets, desktop computers, etc.

[0718] An "advertising campaign" is a series of advertising activities designed to promote a product or service.

[0719] The "risk" is the possibility that the advertising campaign will cause negative reactions on social media or online platforms.

[0720] "Effectiveness" is a measure of how much positive response an advertising campaign generates on social media and online platforms.

[0721] "Visually displaying" means presenting the evaluation results to the user as visual data such as graphs and charts.

[0722] The embodiment of this invention is a system that inputs the content of posts and provides evaluation results for them, with the aim of evaluating the buzz and potential for an advertising campaign in particular. This system consists of three main components: a user terminal, a server, and a generative AI.

[0723] The user terminal provides an interface for entering post content. This includes a text entry field, the ability to upload images and videos, and a button to start the simulation. Users enter or upload the ad copy they want to post and related images or videos. This interface is built using front-end frameworks such as React, Vue.js, and Angular.

[0724] The entered post content is sent to the server. The server is built using a server-side framework such as Node.js or Django. The sent data is in JSON format and is sent using an HTTP POST request. The server receives the input data and processes it to pass it to the generative AI.

[0725] Generative AI analyzes the content of posts entered by users and generates responses using pseudo-personalities. These responses are generated in three categories: positive, negative, and neutral. For example, generative AI models such as OpenAI GPT-3 and Hugging Face Transformers are used. Generative AI generates responses based on prompts such as the following:

[0726] Example prompt sentence:

[0727] "New product! Amazing results!"

[0728] Based on the generated reactions, the server evaluates the buzz level and likelihood of the post becoming a viral sensation. The evaluation uses an algorithm that aggregates the positive, negative, and neutral tendencies of each generated reaction and calculates a numerical score. The evaluation results are then returned to the user's device in JSON format.

[0729] The user device visually displays the returned evaluation results. The evaluation results are displayed in the form of graphs or charts. For example, a high buzz score indicates a lot of positive reactions, while a high flame war potential indicates a lot of negative reactions. For this visual display, a data visualization library such as D3.js is used.

[0730] For example, if a user enters the ad copy "New product! Experience amazing results!" and uploads an image to accompany it, the generative AI will generate a response, and the server will evaluate the buzz and potential for virality based on that response. For example, a score of 8 for buzz and 3 for potential virality will be displayed, and the user can adjust their advertising strategy based on this.

[0731] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0732] Step 1:

[0733] The user inputs the content of the post from the device. The user enters or uploads the ad copy, related images, and videos they want to post on social media into the input fields. For example, a user might enter a text ad such as "New product! Experience amazing results!" This information is collected by the device interface and converted into JSON format. The input is in text format and image / video file format, and is input from the user to the device.

[0734] Step 2:

[0735] The device sends the entered data to the server. The entered post content is sent to the server via an HTTP POST request. The device converts this data into JSON format and sends it to the server. Input is text and image / video files entered by the user into the device, and output is performed from the device to the server.

[0736] Step 3:

[0737] The server receives the submitted post and passes it to the generative AI. The server analyzes the received input data and generates a prompt to pass the content to the generative AI model (e.g., GPT-3) in an appropriate format. The input is JSON data sent from the device, and the server outputs a prompt to pass the analyzed data to the generative AI model.

[0738] Step 4:

[0739] The generative AI analyzes the content of the post and generates a response using a pseudo-personality. The generative AI generates positive, negative, or neutral responses based on the provided prompt. For example, in response to the ad copy "New product! Experience amazing results!", it generates responses such as "Amazing! I'll buy it right away! (Positive)" or "Is it true? Suspicious (Negative)." The input is the prompt provided by the server, and the generated response is output.

[0740] Step 5:

[0741] The server evaluates the buzz level and likelihood of a viral outbreak based on the generated reactions. It analyzes each generated reaction and calculates a buzz level and likelihood of a viral outbreak score based on the number of positive, negative, and neutral reactions. For example, if there are more positive reactions, the buzz level will be higher, and if there are more negative reactions, the likelihood of a viral outbreak will be higher. The input is reaction data from the generative AI model, and the output is the evaluated buzz level and likelihood of a viral outbreak score.

[0742] Step 6:

[0743] The server returns the evaluation results to the user's device. The evaluation results (buzz level and inflammatory potential scores) are sent to the user's device in JSON format. The input is the score data of the evaluation results, which is output to be sent to the user's device.

[0744] Step 7:

[0745] The user device visually displays the returned evaluation results to the user. The user device analyzes the received evaluation results and presents them to the user in visualizations such as graphs and charts. The input is the JSON format evaluation results received from the server, and the analyzed visual data is output. This allows the user to obtain specific feedback to adjust their advertising strategy.

[0746] 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.

[0747] This invention is a system that simulates content that a user intends to post on social media in advance and provides real-time evaluation results of its buzz potential and potential for flame wars, and also combines it with an emotion engine that recognizes the user's emotions. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, a generative AI for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[0748] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0749] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. When the user clicks the post button, the post content is sent to the server.

[0750] The server has a means to receive posts sent from user devices. The server analyzes the received posts and passes them to the generative AI and emotion engine. This process also includes analyzing the posts and providing them to the emotion engine.

[0751] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of the posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[0752] The generative AI uses emotional data from the emotion engine to simulate reactions on social media to the content of a post. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0753] The server receives the simulated responses from the generative AI and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0754] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post being ignited based on the trends of each reaction. By taking emotional data into account, a more accurate assessment of likelihood of a post that reflects users' negative emotions can be obtained. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as likelihood of a post being ignited.

[0755] The server returns the calculated buzz and inflammatory ratings to the user's device as a response in JSON format.

[0756] The user terminal receives the evaluation results returned from the server. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "Buzz Level: 10, Flaming Potential: 3." This allows the user to know in advance how the post will be received on the SNS.

[0757] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI generates pseudo-reactions based on the recognized emotion. The generative AI generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" or "That's unfortunate (negative reaction)." The server evaluates these reactions and calculates a score, for example, "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[0758] The processing flow will be explained below.

[0759] Step 1:

[0760] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0761] Step 2:

[0762] The user terminal sends the entered post content to the server via an HTTP POST request, and the post content is sent to the server as data.

[0763] Step 3:

[0764] The server receives a POST request sent from the user's device. The server extracts the post content from the request and passes it to the emotion engine.

[0765] Step 4:

[0766] The emotion engine recognizes the user's emotions based on the content of the posts it receives. It uses natural language processing technology to analyze the emotions (joy, anger, sadness, etc.) expressed in the posts. For example, it recognizes the emotion "disappointment" based on the phrase "it was disappointing."

[0767] Step 5:

[0768] The server receives the recognized emotion data from the emotion engine, which influences the reaction generation by the generative AI.

[0769] Step 6:

[0770] The generative AI uses emotional data from the emotion engine to simulate social media reactions to the content of a post. Specifically, it generates positive, negative, and neutral reactions that take into account the user's emotions. For example, it generates reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0771] Step 7:

[0772] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0773] Step 8:

[0774] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post becoming a viral sensation based on the trends of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the likelihood of a post becoming a viral sensation.

[0775] Step 9:

[0776] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent to the user's device as a response in JSON format or similar.

[0777] Step 10:

[0778] The user device receives the evaluation results returned from the server and visually displays them to the user. The evaluation results are displayed on the screen of the user device as a score, such as "Buzz Level: 10, Flaming Potential: 3." This allows users to know in advance how their post will be received on the SNS.

[0779] Through these concrete steps, users can simulate the impact of their posts in advance and receive real-time feedback on the degree of buzz and potential for controversy. The introduction of an emotion engine allows for more accurate evaluations that reflect the user's emotions.

[0780] Example 2

[0781] 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."

[0782] In today's social networking environment, the content users post is likely to provoke widespread reactions, potentially leading to unexpected trouble or outrage. Therefore, users need a way to know in advance how their posts will be received. Furthermore, since there is no system for assessing whether a post will go viral or spark outrage, it is difficult for users to receive appropriate feedback before posting. This has led to a demand for ways to reduce the risks of using social networking sites and provide a safer environment.

[0783] 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.

[0784] In this invention, the server includes means for receiving the posted content and passing it to an emotion engine, means for the emotion engine to analyze the posted content and generate emotion data, means for a generation AI model to generate reactions based on the generated emotion data, and means for evaluating the buzz level and likelihood of a post based on the generated reactions. This allows users to simulate reactions to their posted content on SNS in advance and provides evaluation results of the buzz level and likelihood of a post being a controversy in real time. Furthermore, since more accurate evaluations reflecting the user's emotions are obtained, users can use SNS with peace of mind.

[0785] "Posted content" is text data that indicates the content that a user intends to post on the SNS.

[0786] The "central processing unit" is a server that analyzes the content of posts and passes the data to the emotion engine and generative AI model.

[0787] The "emotion engine" is an algorithm that analyzes users' emotions from the content of their posts and generates emotional data such as joy, anger, and sadness.

[0788] A "generative AI model" is an artificial intelligence model that simulates reactions on social media based on emotional data from an emotion engine.

[0789] "Reactions" are feedback from users on social media simulated by the generative AI model, and can be positive, negative, or neutral.

[0790] "Buzz level" is a number that indicates how much attention a post receives on social media.

[0791] "Flame potential" is a number that indicates the degree of negative reaction a post garners on social media.

[0792] The "user interface" is an interface for visually displaying the evaluation results to the user.

[0793] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its buzz potential and potential for flaming. This system includes a terminal for users to input the content to be posted, a central processing unit for processing the content, a generative AI model for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[0794] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0795] The user terminal has a means for sending the entered post content to the central processing unit. The submitted post content is sent to the central processing unit as an HTTP request. When the user clicks the post button, the post content is sent to the central processing unit.

[0796] The central processing unit has a means for receiving posted content sent from a user terminal. The central processing unit analyzes the received posted content and passes it to the emotion engine. This process also includes processing for analyzing the posted content and providing it to the emotion engine.

[0797] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[0798] The generative AI model uses emotional data from the emotion engine to simulate social media reactions to posts. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[0799] The central processing unit receives the simulated responses returned by the generative AI model, and based on these responses, the central processing unit processes the content to assess its virality and potential for flaming.

[0800] The central processing unit analyzes the generated reactions and emotional data, and quantifies the buzz level and inflammatory potential based on the tendency of each reaction. By taking the emotional data into consideration, a more accurate assessment of inflammatory potential can be obtained for posts that reflect users' negative emotions. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the inflammatory potential.

[0801] The central processing unit returns the calculated evaluation results of buzz level and inflammatory potential to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0802] The user terminal receives the evaluation results returned from the central processing unit. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "buzz level: 10, potential for controversy: 3." This allows the user to know in advance how the post will be received on the SNS.

[0803] Example

[0804] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the central processing unit. The central processing unit passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI model generates pseudo-reactions based on the recognized emotion. The generative AI model generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" and "That's unfortunate (negative reaction)." The central processing unit evaluates these reactions and calculates a score: "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[0805] Prompt Sentence Examples

[0806] An example of a prompt for a generative AI model might look like this:

[0807] "Simulate the social media reaction when a user posts, 'A new cafe just opened, but it was a bit disappointing,' and generate both positive and negative reactions."

[0808] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0809] Step 1:

[0810] The user enters the content to post.

[0811] A user inputs the content they want to post on SNS into their device. For example, they might input, "A new cafe opened, but it was a bit disappointing." This input data is text data that will be used in subsequent processing steps.

[0812] Step 2:

[0813] The device sends the post content to the server.

[0814] When a user clicks the post button, the terminal sends the post content to the central processing unit as an HTTP request. Specifically, this request is packaged in JSON format and sent to the central processing unit using the HTTP POST method. The input is the text data entered by the user, and the output is the HTTP request data received by the server.

[0815] Step 3:

[0816] The server receives the post.

[0817] The central processing unit receives the HTTP request sent from the terminal and extracts the posted content. Web server software (e.g., Apache, Nginx) performs this process. The input is the HTTP request data, and the output is the text data of the posted content.

[0818] Step 4:

[0819] The server analyzes the content of the post and passes it to the emotion engine.

[0820] The central processing unit analyzes the received posts and passes them to the emotion engine. This analysis includes text preprocessing (e.g., tokenization, stop word removal). The input is the text data of the posts, and the output is the preprocessed post data.

[0821] Step 5:

[0822] The emotion engine recognizes the user's emotions.

[0823] The emotion engine recognizes user emotions based on the content of the posts it receives. It uses natural language processing technology (e.g., BERT, RoBERTa) to analyze emotions and generate emotion data such as "joy," "anger," and "sadness." For example, it recognizes the phrase "It was a bit disappointing" as "disappointment." The input is preprocessed post content data, and the output is emotion data.

[0824] Step 6:

[0825] The server passes the emotion data to the generative AI.

[0826] The central processing unit passes the emotion data obtained from the emotion engine to the generative AI model. This data becomes the prompt for the generative AI model. The input is emotion data, and the output is prompt data used by the generative AI model.

[0827] Step 7:

[0828] Generative AI simulates social media reactions.

[0829] Generative AI models (e.g., GPT-3, T5) simulate social media reactions based on emotional data and post content. For example, they generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction). The input is prompt data, and the output is simulated reaction data.

[0830] Step 8:

[0831] The server evaluates the simulation results.

[0832] The central processing unit evaluates the buzz level and likelihood of a post being ignited based on the responses returned by the generative AI model. Specifically, it counts the number of positive responses to determine the buzz level, and counts the number of negative responses to determine the likelihood of a post being ignited. The input is simulated response data, and the output is evaluation result data.

[0833] Step 9:

[0834] The server returns the evaluation results to the user terminal.

[0835] The central processing unit returns the calculated evaluation results of buzz and inflammatory potential to the user device in JSON format. The input is the evaluation result data, and the output is the response data sent to the user device.

[0836] Step 10:

[0837] The user checks the evaluation results.

[0838] The user checks the evaluation results returned from the central processing unit on the terminal. The buzz level and controversy scores are visually displayed via the display interface. For example, the scores might be "buzz level: 10, controversy level: 3." The input is the response data received by the terminal, and the output is the evaluation results visually displayed to the user.

[0839] (Application example 2)

[0840] 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."

[0841] In recent years, social networking sites and content distribution services have required users to evaluate the content of their posts in advance and predict the reactions. However, if the content of a post is inappropriate or there is a risk of it causing a controversy, the costs and risks that users must anticipate are high. For this reason, content distributors and influencers need a system that can simulate the impact of a post before it is made and take appropriate action.

[0842] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0843] In this invention, the server includes means for a generative AI to analyze the content of a post and generate reactions using an emotion engine, means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions, and means for generating reactions based on the content of the post using prompt text and providing the evaluation results in a content distribution service. This allows users to simulate the impact of their posts in real time before posting and take appropriate action.

[0844] "Posted content" refers to information such as text, images, and videos that a user intends to post on a social networking site or content distribution service.

[0845] "Server" refers to a computer system that receives, analyzes, and processes posted content sent from user devices.

[0846] "Generative AI" refers to artificial intelligence that generates responses based on user posts.

[0847] An "emotion engine" refers to a program or algorithm that analyzes the emotions in a post and generates a response based on those emotions.

[0848] "Reactions" refer to positive, negative, or neutral comments and ratings generated by generative AI based on the content of a post.

[0849] "Buzz level" refers to a score that evaluates the degree to which a post attracts attention on social media.

[0850] "Flame potential" refers to a score that assesses the likelihood that a post will provoke a negative reaction on social media.

[0851] A "prompt" refers to an instruction entered into a generative AI to generate the optimal response.

[0852] "Content distribution service" refers to an online platform that enables users to distribute content, such as text, images, and videos, created by users to other users.

[0853] "Evaluation results" refer to the scores for the buzz level and potential for controversy of the post content, analyzed by the server using generative AI and an emotion engine.

[0854] To implement this invention, the following system must be constructed. The system allows users to input content to post on social media or content distribution services and simulate the impact of that content in advance. This system consists of a user terminal, a server, a generative AI, an emotion engine, and communication means connecting them.

[0855] First, the user terminal provides an interface for the user to input the content of their post. For example, the user may input the content of their post, "A new cafe opened, but it was a bit disappointing." This content of their post is sent from the user terminal to the server as an HTTP request.

[0856] The server receives posts sent from user devices. The received posts are passed to the emotion engine and generative AI. The emotion engine uses natural language processing technology to analyze the emotions in the posts. For example, if the post contains a negative expression such as "it was a bit disappointing," the emotion engine will recognize this as "disappointment."

[0857] The generative AI simulates social media reactions to posts based on emotional data from the emotion engine. The generative AI generates reactions using the following prompts:

[0858] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[0859] Simulate what the reaction on social media would be like.

[0860] Based on this prompt, the generative AI generates positive, negative, or neutral responses, such as "That was disappointing, but let's hope for the next one!" (positive response) or "That's unfortunate!" (negative response).

[0861] The server evaluates the buzz level and potential for flaming based on the generated reactions. The evaluation is based on the emotional tendencies of the reactions generated by the generative AI. The number of positive reactions is calculated as the buzz level, and the number of negative reactions as the potential for flaming. For example, the server calculates a score of "buzz level: 10, potential for flaming: 3."

[0862] Finally, the server returns the calculated buzz and flame potential evaluation results to the user's device. The evaluation results are visually displayed on the user's device. By checking the scores, users can know in advance how their post will be received on the SNS.

[0863] The following hardware and software are required to realize this system: OpenAI's GPT-3 as the generative AI, TextBlob as the emotion engine, and a web browser and HTTP communication method as the user interface. This allows users to simulate the impact of their posts in real time and take appropriate action before posting.

[0864] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0865] Step 1:

[0866] The user inputs the content of the post into the device. The user inputs the content into the input interface. For example, the user inputs a post such as "A new cafe opened, but it was a bit disappointing." This is the input data. The input data is temporarily stored in the built-in memory.

[0867] Step 2:

[0868] The device sends the entered post content to the server as an HTTP request. Specifically, it generates an HTTP POST request and sends the post content to the server in JSON format or similar. The output is the request data sent to the server. The server receives this POST request.

[0869] Step 3:

[0870] The server analyzes the received post content and passes it to an emotion engine. The analysis program on the server extracts the post content as text and performs emotion analysis using an emotion engine such as TextBlob. Specifically, it obtains an emotion tag: positive, negative, or neutral. This emotion tag is the output data.

[0871] Step 4:

[0872] The server provides emotion data from the emotion engine to the generative AI. The server generates prompts and sends them to GPT-3, a valued-based AI. The generative AI generates responses based on the following prompts:

[0873] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[0874] Simulate what the reaction on social media would be like.

[0875] The output is the generated response data.

[0876] Step 5:

[0877] The server evaluates the buzz level and likelihood of a reaction based on the generated reactions. Specifically, it performs sentiment analysis on each reaction sentence and tallies the number of positive and negative reactions. The number of positive reactions is quantified as buzz level, and the number of negative reactions is quantified as likelihood of a reaction. The output is an evaluation score for buzz level and likelihood of a reaction.

[0878] Step 6:

[0879] The server returns the calculated evaluation results of buzz level and flame potential to the user's device. The evaluation results are sent from the server to the device as an HTTP response in a data format such as JSON. The output is the evaluation result data sent to the user's device.

[0880] Step 7:

[0881] The user device receives the evaluation results returned from the server and visually displays them via a display interface. Specifically, scores such as "Buzz Level: 10, Flaming Potential: 3" are displayed on the user interface. By checking this, users can know in advance how their post will be received on the SNS. The output is the evaluation score displayed to the user.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] [Fourth embodiment]

[0886] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0887] 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.

[0888] 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).

[0889] 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.

[0890] 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.

[0891] 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).

[0892] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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."

[0899] This invention is a system that simulates the content that a user intends to post on social media in advance and provides real-time evaluation results of the content's buzz and potential for flaming. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, and a generative AI for generating and evaluating reactions.

[0900] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[0901] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. An example of this transmission is when the user terminal sends the post content using a "POST" request.

[0902] The server has a means to receive the posted content sent from the user's device. The server analyzes the received posted content and passes it to the generative AI. This process is used to analyze the posted content and provide it to the generative AI.

[0903] Generative AI uses pseudo-personalities to generate social media responses based on the content of posts. Generative AI generates positive, negative, and neutral responses based on the characteristics of the programmed pseudo-personalities. For example, it generates responses such as, "I want to try that new cafe!" (positive response) or "It's a shame it didn't live up to your expectations!" (negative response).

[0904] The server has a means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions. The generated reactions are analyzed, and the buzz level and likelihood of a post becoming a hot topic are quantified based on the trends of each reaction. This process makes it possible to evaluate how much of a post will become a hot topic or how likely it is to become a hot topic.

[0905] The server has a means to return the evaluation results to the user terminal. The evaluation results are sent to the user terminal in JSON format, etc. The user terminal has an interface to receive the returned evaluation results and visually display them to the user.

[0906] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to a generative AI, which generates simulated reactions. The generative AI generates positive, negative, and neutral reactions, and the server then evaluates the buzz level and likelihood of causing a stir based on these. The resulting score, for example, "buzz level: 10, likelihood of causing a stir: 3," is received by the user's device and displayed to the user. In this way, the user can know in advance how the post will be received on social media.

[0907] The processing flow will be explained below.

[0908] Step 1:

[0909] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[0910] Step 2:

[0911] The user terminal sends the entered post content to the server via an HTTP POST request. At this time, the post content is sent to the server as data.

[0912] Step 3:

[0913] The server receives a POST request sent from the user's device, extracts the post content from the request, and passes it to the generative AI for analysis.

[0914] Step 4:

[0915] The generative AI analyzes the content of the post sent to it. During the analysis, it uses a pseudo-personality to simulate social media reactions to the post. The reactions generated here can be positive, negative, or neutral.

[0916] Step 5:

[0917] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[0918] Step 6:

[0919] The server analyzes the generated reactions and quantifies the buzz level and flaming potential based on the tendency of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the flaming potential.

[0920] Step 7:

[0921] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[0922] Step 8:

[0923] The user terminal receives the evaluation results returned from the server. The evaluation results are displayed to the user via a display interface to visually display them to the user. The user can confirm the score, for example, "Buzz level: 10, Flaming potential: 3."

[0924] Example 1

[0925] 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."

[0926] In recent years, the risk of posts on social media spreading in unexpected ways or causing outrage has increased because the content can be shared instantly by a large number of users. This has made it increasingly important for individuals and companies to evaluate posts in advance and understand their potential for spreading and causing outrage. However, current systems lack the means to evaluate posts before they are posted, and furthermore, it is difficult to evaluate them in real time.

[0927] 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.

[0928] In this invention, the server includes means for inputting post content, means for transmitting the input post content to a network device, means for the network device to receive the transmitted post content and pass it to a generative artificial intelligence, means for the generative artificial intelligence to analyze the post content and generate reactions using pseudo-personalities, means for evaluating topicality and potential for flaming based on the generated reactions, means for returning the evaluation results to a terminal device, and means for displaying the returned evaluation results to a user. This allows a user to evaluate in real time how content will be received on SNS before posting, and to grasp in advance the risk of topicality and potential for flaming.

[0929] "Post content" refers to the message or information that a user intends to post on a social networking site.

[0930] "Network device" refers to the computer system and communications infrastructure used to receive and analyze posted content.

[0931] "Generative AI" refers to an AI system that analyzes posted content and generates responses using pseudo-personalities.

[0932] "Pseudo-personality" refers to a model used by generative AI to simulate the characteristics and behavioral patterns of a virtual human.

[0933] "Topicality" refers to an indicator of how much a post becomes a hot topic on social media.

[0934] "Flame potential" refers to an indicator of the extent to which a post provokes a negative reaction on social media.

[0935] "Evaluation results" refer to indicators and numerical values ​​calculated based on the responses generated by generative artificial intelligence.

[0936] "Terminal device" refers to a device used by a user to input content to be posted.

[0937] "Reaction" refers to pseudo-feedback such as positive, negative, or neutral that generative artificial intelligence generates in response to a post.

[0938] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its topicality and potential to cause a stir. This system includes a terminal device for users to input the content to be posted, a network device for processing the content, and a generative artificial intelligence (AI) for generating and evaluating reactions.

[0939] A user uses a terminal device such as a smartphone or PC to input content they want to post on an SNS. For example, they might input content such as, "A new cafe opened, but it was a bit disappointing." The terminal device can then send the input content to a network device as an HTTP request.

[0940] The network device has a means to receive and analyze the posted content sent from the user terminal. Specifically, it uses a text analysis module to break down the posted content and extract the necessary information. The analysis results are formatted in a format that can be used by generative artificial intelligence (e.g., OpenAI's GPT-4).

[0941] The network device then passes the analyzed post content to the generative AI as a prompt. An example of a prompt when using a generative AI model is, "A user is about to post on social media that a new cafe has opened, but it was a bit disappointing. Please generate a prompt that classifies the general reactions to this post on social media into positive, negative, and neutral."

[0942] The generative AI generates a response to the post based on this prompt. The generated responses are classified into three types: positive, negative, and neutral. For example, responses such as "I want to try that new cafe!" (positive response), "Sorry that it didn't meet your expectations" (negative response), and "Hmm, that's just average" (neutral response) could be generated.

[0943] The network device evaluates the topicality and potential for controversy of the post based on the generated reactions. Topicality and potential for controversy are calculated based on a specific formula, analyzing the proportion and strength of the generated reactions. For example, on a 10-point scale, a score such as "Topicality: 8, Potential for controversy: 2" can be obtained.

[0944] Finally, the network device returns the evaluation results in JSON format to the terminal device. The terminal device has an interface that visually displays the received evaluation results to the user, allowing the user to check the evaluation results. For example, the evaluation results may be displayed as "Topicality: 8, Flaming Potential: 2." This allows users to know in advance how their post will be received on SNS.

[0945] Through the above steps, this system helps users reduce the risks associated with posting on social media and disseminate information more safely.

[0946] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0947] System program processing flow

[0948] Step 1:

[0949] The user enters the content to post.

[0950] The user uses a terminal device to input the content of the post in text format. Specifically, the user opens the SNS app and writes in the input form, "A new cafe opened, but it was a bit disappointing."

[0951] Input: The text of the post entered by the user.

[0952] Output: Text data of the input post content.

[0953] Step 2:

[0954] The device sends the post content to the server.

[0955] The device sends the entered post content to the server via the network as an HTTP request (POST request). This operation uses a communication module.

[0956] Input: The text data of the post entered by the user.

[0957] Output: The HTTP request sent to the server.

[0958] Step 3:

[0959] The server receives and analyzes the posted content.

[0960] The server processes the received posts through a text analysis module to extract keywords and important context, which then translates the data into a format that is easier for generative AI to process.

[0961] Input: The text data sent in the HTTP request.

[0962] Data processing: Text analysis (keyword extraction, context analysis).

[0963] Output: Analyzed data fed into a generative artificial intelligence.

[0964] Step 4:

[0965] The server passes the post content to the generative artificial intelligence.

[0966] The analyzed post content is input to the generative AI as a prompt. This action generates a prompt and sends it to the AI ​​engine. An example of a prompt: "A user is about to post on social media that, 'A new cafe has opened, but it was a bit disappointing.' Please generate a general response to this post on social media, categorizing it as positive, negative, or neutral."

[0967] Input: Parsed data.

[0968] Data processing: Prompt sentence generation.

[0969] Output: A prompt to the generative AI.

[0970] Step 5:

[0971] Generative artificial intelligence generates reactions on social media.

[0972] Based on the prompt, the generative AI generates positive, negative, or neutral responses based on the characteristics of the virtual person. Specifically, it generates responses such as "I want to try that new cafe!" (positive response) or "Sorry, it didn't meet your expectations!" (negative response).

[0973] Input: The prompt statement.

[0974] Data processing: generating positive, negative, and neutral responses.

[0975] Output: The generated reaction data.

[0976] Step 6:

[0977] The server analyzes the generated responses and evaluates their topicality and likelihood of causing a stir.

[0978] The type and proportion of reactions generated are analyzed to calculate a score for topicality and inflammatoryness. For example, a high number of positive reactions indicates a high topicality, while a high number of negative reactions indicates a high inflammatoryness.

[0979] Input: Generated reaction data.

[0980] Data processing: Analysis of responses and calculation of scores.

[0981] Output: Evaluation results of topicality and inflammatoryness.

[0982] Step 7:

[0983] The server returns the evaluation results to the user terminal.

[0984] The evaluation results are sent to the user terminal in JSON format using a communication module.

[0985] Input: Topical and inflammatory evaluation results.

[0986] Output: JSON data sent to the user device.

[0987] Step 8:

[0988] The terminal displays the evaluation results to the user.

[0989] The device visually displays the received evaluation results, providing an interface that allows users to easily check them. For example, the evaluation results might be displayed on the screen as "Topicality: 8, Flaming Potential: 2."

[0990] Input: JSON data sent from the server.

[0991] Output: The evaluation result that is displayed to the user.

[0992] By following these steps, users can see in advance how their posts will be received on social media, which is an important indicator for users to adjust their posts appropriately.

[0993] (Application example 1)

[0994] 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."

[0995] In traditional advertising campaigns, there was no appropriate way to assess in advance how social media and online advertising posts would be received, i.e., their effectiveness (buzz level) and risk (flaming potential), making it difficult to maximize the effectiveness of advertising strategies while minimizing the risks. In particular, there was a lack of a system for simulating the impact of advertising, making it difficult to predict the success rate of marketing campaigns.

[0996] 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.

[0997] In this invention, the server includes means for inputting the content of posts, means for returning evaluation results to the user terminal, means for displaying the returned evaluation results to the user, means for evaluating the risk and effectiveness of the advertising campaign, and means for visually displaying the evaluated results of the advertising campaign. This makes it possible to simulate in advance the degree of buzz and potential for an advertising campaign to cause a stir, and to optimize advertising strategies based on the evaluation results.

[0998] "Posted content" refers to content such as text, images, and videos posted by users on social media or online platforms.

[0999] A "server" is a computer system that receives data sent by a user, processes, analyzes, and returns results.

[1000] "Generative AI" is an artificial intelligence system that analyzes the content of posts entered by users and generates responses based on that content.

[1001] A "pseudo-personality" is a virtual personality programmed by a generative AI to generate various reactions.

[1002] "Reactions" are positive, negative, or neutral opinions and comments that the generative AI generates in response to a post.

[1003] "Buzz level" is an evaluation score that indicates how much of a topic a post will become on social media or online platforms.

[1004] "Flame potential" is a rating score that indicates how likely a post is to provoke a negative reaction on social media or online platforms.

[1005] The "evaluation results" are scores of buzz and flame potential calculated based on the generated reactions.

[1006] A "user terminal" is a device used by a user to input post content and receive evaluation results, and includes smartphones, tablets, desktop computers, etc.

[1007] An "advertising campaign" is a series of advertising activities designed to promote a product or service.

[1008] The "risk" is the possibility that the advertising campaign will cause negative reactions on social media or online platforms.

[1009] "Effectiveness" is a measure of how much positive response an advertising campaign generates on social media and online platforms.

[1010] "Visually displaying" means presenting the evaluation results to the user as visual data such as graphs and charts.

[1011] The embodiment of this invention is a system that inputs the content of posts and provides evaluation results for them, with the aim of evaluating the buzz and potential for an advertising campaign in particular. This system consists of three main components: a user terminal, a server, and a generative AI.

[1012] The user terminal provides an interface for entering post content. This includes a text entry field, the ability to upload images and videos, and a button to start the simulation. Users enter or upload the ad copy they want to post and related images or videos. This interface is built using front-end frameworks such as React, Vue.js, and Angular.

[1013] The entered post content is sent to the server. The server is built using a server-side framework such as Node.js or Django. The sent data is in JSON format and is sent using an HTTP POST request. The server receives the input data and processes it to pass it to the generative AI.

[1014] Generative AI analyzes the content of posts entered by users and generates responses using pseudo-personalities. These responses are generated in three categories: positive, negative, and neutral. For example, generative AI models such as OpenAI GPT-3 and Hugging Face Transformers are used. Generative AI generates responses based on prompts such as the following:

[1015] Example prompt sentence:

[1016] "New product! Amazing results!"

[1017] Based on the generated reactions, the server evaluates the buzz level and likelihood of the post becoming a viral sensation. The evaluation uses an algorithm that aggregates the positive, negative, and neutral tendencies of each generated reaction and calculates a numerical score. The evaluation results are then returned to the user's device in JSON format.

[1018] The user device visually displays the returned evaluation results. The evaluation results are displayed in the form of graphs or charts. For example, a high buzz score indicates a lot of positive reactions, while a high flame war potential indicates a lot of negative reactions. For this visual display, a data visualization library such as D3.js is used.

[1019] For example, if a user enters the ad copy "New product! Experience amazing results!" and uploads an image to accompany it, the generative AI will generate a response, and the server will evaluate the buzz and potential for virality based on that response. For example, a score of 8 for buzz and 3 for potential virality will be displayed, and the user can adjust their advertising strategy based on this.

[1020] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1021] Step 1:

[1022] The user inputs the content of the post from the device. The user enters or uploads the ad copy, related images, and videos they want to post on social media into the input fields. For example, a user might enter a text ad such as "New product! Experience amazing results!" This information is collected by the device interface and converted into JSON format. The input is in text format and image / video file format, and is input from the user to the device.

[1023] Step 2:

[1024] The device sends the entered data to the server. The entered post content is sent to the server via an HTTP POST request. The device converts this data into JSON format and sends it to the server. Input is text and image / video files entered by the user into the device, and output is performed from the device to the server.

[1025] Step 3:

[1026] The server receives the submitted post and passes it to the generative AI. The server analyzes the received input data and generates a prompt to pass the content to the generative AI model (e.g., GPT-3) in an appropriate format. The input is JSON data sent from the device, and the server outputs a prompt to pass the analyzed data to the generative AI model.

[1027] Step 4:

[1028] The generative AI analyzes the content of the post and generates a response using a pseudo-personality. The generative AI generates positive, negative, or neutral responses based on the provided prompt. For example, in response to the ad copy "New product! Experience amazing results!", it generates responses such as "Amazing! I'll buy it right away! (Positive)" or "Is it true? Suspicious (Negative)." The input is the prompt provided by the server, and the generated response is output.

[1029] Step 5:

[1030] The server evaluates the buzz level and likelihood of a viral outbreak based on the generated reactions. It analyzes each generated reaction and calculates a buzz level and likelihood of a viral outbreak score based on the number of positive, negative, and neutral reactions. For example, if there are more positive reactions, the buzz level will be higher, and if there are more negative reactions, the likelihood of a viral outbreak will be higher. The input is reaction data from the generative AI model, and the output is the evaluated buzz level and likelihood of a viral outbreak score.

[1031] Step 6:

[1032] The server returns the evaluation results to the user's device. The evaluation results (buzz level and inflammatory potential scores) are sent to the user's device in JSON format. The input is the score data of the evaluation results, which is output to be sent to the user's device.

[1033] Step 7:

[1034] The user device visually displays the returned evaluation results to the user. The user device analyzes the received evaluation results and presents them to the user in visualizations such as graphs and charts. The input is the JSON format evaluation results received from the server, and the analyzed visual data is output. This allows the user to obtain specific feedback to adjust their advertising strategy.

[1035] 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.

[1036] This invention is a system that simulates content that a user intends to post on social media in advance and provides real-time evaluation results of its buzz potential and potential for flame wars, and also combines it with an emotion engine that recognizes the user's emotions. This system includes a terminal where the user inputs the content to be posted, a server for processing the content, a generative AI for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[1037] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[1038] The user terminal has a means to send the entered post content to the server. The submitted post content is sent to the server as an HTTP request. When the user clicks the post button, the post content is sent to the server.

[1039] The server has a means to receive posts sent from user devices. The server analyzes the received posts and passes them to the generative AI and emotion engine. This process also includes analyzing the posts and providing them to the emotion engine.

[1040] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of the posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[1041] The generative AI uses emotional data from the emotion engine to simulate reactions on social media to the content of a post. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[1042] The server receives the simulated responses from the generative AI and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[1043] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post being ignited based on the trends of each reaction. By taking emotional data into account, a more accurate assessment of likelihood of a post that reflects users' negative emotions can be obtained. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as likelihood of a post being ignited.

[1044] The server returns the calculated buzz and inflammatory ratings to the user's device as a response in JSON format.

[1045] The user terminal receives the evaluation results returned from the server. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "Buzz Level: 10, Flaming Potential: 3." This allows the user to know in advance how the post will be received on the SNS.

[1046] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the server. The server then passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI generates pseudo-reactions based on the recognized emotion. The generative AI generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" or "That's unfortunate (negative reaction)." The server evaluates these reactions and calculates a score, for example, "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[1047] The processing flow will be explained below.

[1048] Step 1:

[1049] The user inputs the content they want to post on the SNS. For example, they might input the content of a post like, "A new cafe opened, but it was a bit disappointing."

[1050] Step 2:

[1051] The user terminal sends the entered post content to the server via an HTTP POST request, and the post content is sent to the server as data.

[1052] Step 3:

[1053] The server receives a POST request sent from the user's device. The server extracts the post content from the request and passes it to the emotion engine.

[1054] Step 4:

[1055] The emotion engine recognizes the user's emotions based on the content of the posts it receives. It uses natural language processing technology to analyze the emotions (joy, anger, sadness, etc.) expressed in the posts. For example, it recognizes the emotion "disappointment" based on the phrase "it was disappointing."

[1056] Step 5:

[1057] The server receives the recognized emotion data from the emotion engine, which influences the reaction generation by the generative AI.

[1058] Step 6:

[1059] The generative AI uses emotional data from the emotion engine to simulate social media reactions to the content of a post. Specifically, it generates positive, negative, and neutral reactions that take into account the user's emotions. For example, it generates reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[1060] Step 7:

[1061] The server receives the simulated responses from the generative AI, and performs processing to evaluate the buzz level and potential for flaming based on these responses.

[1062] Step 8:

[1063] The server analyzes the generated reactions and emotional data, and quantifies the buzz level and likelihood of a post becoming a viral sensation based on the trends of each reaction. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the likelihood of a post becoming a viral sensation.

[1064] Step 9:

[1065] The server returns the calculated buzz and inflammatory evaluation results to the user's device. The evaluation results are sent to the user's device as a response in JSON format or similar.

[1066] Step 10:

[1067] The user device receives the evaluation results returned from the server and visually displays them to the user. The evaluation results are displayed on the screen of the user device as a score, such as "Buzz Level: 10, Flaming Potential: 3." This allows users to know in advance how their post will be received on the SNS.

[1068] Through these concrete steps, users can simulate the impact of their posts in advance and receive real-time feedback on the degree of buzz and potential for controversy. The introduction of an emotion engine allows for more accurate evaluations that reflect the user's emotions.

[1069] Example 2

[1070] 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."

[1071] In today's social networking environment, the content users post is likely to provoke widespread reactions, potentially leading to unexpected trouble or outrage. Therefore, users need a way to know in advance how their posts will be received. Furthermore, since there is no system for assessing whether a post will go viral or spark outrage, it is difficult for users to receive appropriate feedback before posting. This has led to a demand for ways to reduce the risks of using social networking sites and provide a safer environment.

[1072] 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.

[1073] In this invention, the server includes means for receiving the posted content and passing it to an emotion engine, means for the emotion engine to analyze the posted content and generate emotion data, means for a generation AI model to generate reactions based on the generated emotion data, and means for evaluating the buzz level and likelihood of a post based on the generated reactions. This allows users to simulate reactions to their posted content on SNS in advance and provides evaluation results of the buzz level and likelihood of a post being a controversy in real time. Furthermore, since more accurate evaluations reflecting the user's emotions are obtained, users can use SNS with peace of mind.

[1074] "Posted content" is text data that indicates the content that a user intends to post on the SNS.

[1075] The "central processing unit" is a server that analyzes the content of posts and passes the data to the emotion engine and generative AI model.

[1076] The "emotion engine" is an algorithm that analyzes users' emotions from the content of their posts and generates emotional data such as joy, anger, and sadness.

[1077] A "generative AI model" is an artificial intelligence model that simulates reactions on social media based on emotional data from an emotion engine.

[1078] "Reactions" are feedback from users on social media simulated by the generative AI model, and can be positive, negative, or neutral.

[1079] "Buzz level" is a number that indicates how much attention a post receives on social media.

[1080] "Flame potential" is a number that indicates the degree of negative reaction a post garners on social media.

[1081] The "user interface" is an interface for visually displaying the evaluation results to the user.

[1082] This invention is a system that simulates content that a user intends to post on a social networking site in advance and provides real-time evaluation results of its buzz potential and potential for flaming. This system includes a terminal for users to input the content to be posted, a central processing unit for processing the content, a generative AI model for generating and evaluating reactions, and an emotion engine that recognizes the user's emotions and influences the generation of reactions.

[1083] The user terminal provides an interface for the user to input content that they want to post on the SNS. For example, the user may input content such as "A new cafe opened, but it was a bit disappointing."

[1084] The user terminal has a means for sending the entered post content to the central processing unit. The submitted post content is sent to the central processing unit as an HTTP request. When the user clicks the post button, the post content is sent to the central processing unit.

[1085] The central processing unit has a means for receiving posted content sent from a user terminal. The central processing unit analyzes the received posted content and passes it to the emotion engine. This process also includes processing for analyzing the posted content and providing it to the emotion engine.

[1086] The emotion engine has a means of recognizing the user's emotions based on the content of the posts sent. Emotion recognition uses natural language processing technology to analyze the content of posts to determine what emotions, such as joy, anger, or sadness, are expressed in the posts. For example, if the post contains a negative expression such as "It was a bit disappointing," the emotion engine will recognize it as "disappointment."

[1087] The generative AI model uses emotional data from the emotion engine to simulate social media reactions to posts. The reactions generated here are either positive, negative, or neutral, taking into account the user's emotions. For example, it could generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction).

[1088] The central processing unit receives the simulated responses returned by the generative AI model, and based on these responses, the central processing unit processes the content to assess its virality and potential for flaming.

[1089] The central processing unit analyzes the generated reactions and emotional data, and quantifies the buzz level and inflammatory potential based on the tendency of each reaction. By taking the emotional data into consideration, a more accurate assessment of inflammatory potential can be obtained for posts that reflect users' negative emotions. Specifically, the number of positive reactions is calculated as the buzz level, and the number of negative reactions is calculated as the inflammatory potential.

[1090] The central processing unit returns the calculated evaluation results of buzz level and inflammatory potential to the user's device. The evaluation results are sent back as a response in JSON format or similar.

[1091] The user terminal receives the evaluation results returned from the central processing unit. The evaluation results are visually displayed to the user via a display interface. The user can check the score, for example, "buzz level: 10, potential for controversy: 3." This allows the user to know in advance how the post will be received on the SNS.

[1092] Example

[1093] For example, suppose a user simulates a post saying, "A new cafe opened, but it was a bit disappointing." The user's device inputs the post content and sends it to the central processing unit. The central processing unit passes the received post content to the emotion engine, which recognizes the emotion "disappointment." The generative AI model generates pseudo-reactions based on the recognized emotion. The generative AI model generates reactions such as "It was disappointing, but let's hope for the next one! (positive reaction)" and "That's unfortunate (negative reaction)." The central processing unit evaluates these reactions and calculates a score: "Buzz level: 10, Flaming potential: 3." This evaluation result is returned to the user's device, where the user can check the score. This process allows the user to simulate the impact of the post in advance.

[1094] Prompt Sentence Examples

[1095] An example of a prompt for a generative AI model might look like this:

[1096] "Simulate the social media reaction when a user posts, 'A new cafe just opened, but it was a bit disappointing,' and generate both positive and negative reactions."

[1097] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1098] Step 1:

[1099] The user enters the content to post.

[1100] A user inputs the content they want to post on SNS into their device. For example, they might input, "A new cafe opened, but it was a bit disappointing." This input data is text data that will be used in subsequent processing steps.

[1101] Step 2:

[1102] The device sends the post content to the server.

[1103] When a user clicks the post button, the terminal sends the post content to the central processing unit as an HTTP request. Specifically, this request is packaged in JSON format and sent to the central processing unit using the HTTP POST method. The input is the text data entered by the user, and the output is the HTTP request data received by the server.

[1104] Step 3:

[1105] The server receives the post.

[1106] The central processing unit receives the HTTP request sent from the terminal and extracts the posted content. Web server software (e.g., Apache, Nginx) performs this process. The input is the HTTP request data, and the output is the text data of the posted content.

[1107] Step 4:

[1108] The server analyzes the content of the post and passes it to the emotion engine.

[1109] The central processing unit analyzes the received posts and passes them to the emotion engine. This analysis includes text preprocessing (e.g., tokenization, stop word removal). The input is the text data of the posts, and the output is the preprocessed post data.

[1110] Step 5:

[1111] The emotion engine recognizes the user's emotions.

[1112] The emotion engine recognizes user emotions based on the content of the posts it receives. It uses natural language processing technology (e.g., BERT, RoBERTa) to analyze emotions and generate emotion data such as "joy," "anger," and "sadness." For example, it recognizes the phrase "It was a bit disappointing" as "disappointment." The input is preprocessed post content data, and the output is emotion data.

[1113] Step 6:

[1114] The server passes the emotion data to the generative AI.

[1115] The central processing unit passes the emotion data obtained from the emotion engine to the generative AI model. This data becomes the prompt for the generative AI model. The input is emotion data, and the output is prompt data used by the generative AI model.

[1116] Step 7:

[1117] Generative AI simulates social media reactions.

[1118] Generative AI models (e.g., GPT-3, T5) simulate social media reactions based on emotional data and post content. For example, they generate reactions such as "That was disappointing, but let's hope for the next one!" (positive reaction) or "That's unfortunate!" (negative reaction). The input is prompt data, and the output is simulated reaction data.

[1119] Step 8:

[1120] The server evaluates the simulation results.

[1121] The central processing unit evaluates the buzz level and likelihood of a post being ignited based on the responses returned by the generative AI model. Specifically, it counts the number of positive responses to determine the buzz level, and counts the number of negative responses to determine the likelihood of a post being ignited. The input is simulated response data, and the output is evaluation result data.

[1122] Step 9:

[1123] The server returns the evaluation results to the user terminal.

[1124] The central processing unit returns the calculated evaluation results of buzz and inflammatory potential to the user device in JSON format. The input is the evaluation result data, and the output is the response data sent to the user device.

[1125] Step 10:

[1126] The user checks the evaluation results.

[1127] The user checks the evaluation results returned from the central processing unit on the terminal. The buzz level and controversy scores are visually displayed via the display interface. For example, the scores might be "buzz level: 10, controversy level: 3." The input is the response data received by the terminal, and the output is the evaluation results visually displayed to the user.

[1128] (Application example 2)

[1129] 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."

[1130] In recent years, social networking sites and content distribution services have required users to evaluate the content of their posts in advance and predict the reactions. However, if the content of a post is inappropriate or there is a risk of it causing a controversy, the costs and risks that users must anticipate are high. For this reason, content distributors and influencers need a system that can simulate the impact of a post before it is made and take appropriate action.

[1131] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1132] In this invention, the server includes means for a generative AI to analyze the content of a post and generate reactions using an emotion engine, means for evaluating the buzz level and likelihood of a post becoming a hot topic based on the generated reactions, and means for generating reactions based on the content of the post using prompt text and providing the evaluation results in a content distribution service. This allows users to simulate the impact of their posts in real time before posting and take appropriate action.

[1133] "Posted content" refers to information such as text, images, and videos that a user intends to post on a social networking site or content distribution service.

[1134] "Server" refers to a computer system that receives, analyzes, and processes posted content sent from user devices.

[1135] "Generative AI" refers to artificial intelligence that generates responses based on user posts.

[1136] An "emotion engine" refers to a program or algorithm that analyzes the emotions in a post and generates a response based on those emotions.

[1137] "Reactions" refer to positive, negative, or neutral comments and ratings generated by generative AI based on the content of a post.

[1138] "Buzz level" refers to a score that evaluates the degree to which a post attracts attention on social media.

[1139] "Flame potential" refers to a score that assesses the likelihood that a post will provoke a negative reaction on social media.

[1140] A "prompt" refers to an instruction entered into a generative AI to generate the optimal response.

[1141] "Content distribution service" refers to an online platform that enables users to distribute content, such as text, images, and videos, created by users to other users.

[1142] "Evaluation results" refer to the scores for the buzz level and potential for controversy of the post content, analyzed by the server using generative AI and an emotion engine.

[1143] To implement this invention, the following system must be constructed. The system allows users to input content to post on social media or content distribution services and simulate the impact of that content in advance. This system consists of a user terminal, a server, a generative AI, an emotion engine, and communication means connecting them.

[1144] First, the user terminal provides an interface for the user to input the content of their post. For example, the user may input the content of their post, "A new cafe opened, but it was a bit disappointing." This content of their post is sent from the user terminal to the server as an HTTP request.

[1145] The server receives posts sent from user devices. The received posts are passed to the emotion engine and generative AI. The emotion engine uses natural language processing technology to analyze the emotions in the posts. For example, if the post contains a negative expression such as "it was a bit disappointing," the emotion engine will recognize this as "disappointment."

[1146] The generative AI simulates social media reactions to posts based on emotional data from the emotion engine. The generative AI generates reactions using the following prompts:

[1147] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[1148] Simulate what the reaction on social media would be like.

[1149] Based on this prompt, the generative AI generates positive, negative, or neutral responses, such as "That was disappointing, but let's hope for the next one!" (positive response) or "That's unfortunate!" (negative response).

[1150] The server evaluates the buzz level and potential for flaming based on the generated reactions. The evaluation is based on the emotional tendencies of the reactions generated by the generative AI. The number of positive reactions is calculated as the buzz level, and the number of negative reactions as the potential for flaming. For example, the server calculates a score of "buzz level: 10, potential for flaming: 3."

[1151] Finally, the server returns the calculated buzz and flame potential evaluation results to the user's device. The evaluation results are visually displayed on the user's device. By checking the scores, users can know in advance how their post will be received on the SNS.

[1152] The following hardware and software are required to realize this system: OpenAI's GPT-3 as the generative AI, TextBlob as the emotion engine, and a web browser and HTTP communication method as the user interface. This allows users to simulate the impact of their posts in real time and take appropriate action before posting.

[1153] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1154] Step 1:

[1155] The user inputs the content of the post into the device. The user inputs the content into the input interface. For example, the user inputs a post such as "A new cafe opened, but it was a bit disappointing." This is the input data. The input data is temporarily stored in the built-in memory.

[1156] Step 2:

[1157] The device sends the entered post content to the server as an HTTP request. Specifically, it generates an HTTP POST request and sends the post content to the server in JSON format or similar. The output is the request data sent to the server. The server receives this POST request.

[1158] Step 3:

[1159] The server analyzes the received post content and passes it to an emotion engine. The analysis program on the server extracts the post content as text and performs emotion analysis using an emotion engine such as TextBlob. Specifically, it obtains an emotion tag: positive, negative, or neutral. This emotion tag is the output data.

[1160] Step 4:

[1161] The server provides emotion data from the emotion engine to the generative AI. The server generates prompts and sends them to GPT-3, a valued-based AI. The generative AI generates responses based on the following prompts:

[1162] User Post: A new cafe opened, but it was a bit disappointing. Sentiment: Negative.

[1163] Simulate what the reaction on social media would be like.

[1164] The output is the generated response data.

[1165] Step 5:

[1166] The server evaluates the buzz level and likelihood of a reaction based on the generated reactions. Specifically, it performs sentiment analysis on each reaction sentence and tallies the number of positive and negative reactions. The number of positive reactions is quantified as buzz level, and the number of negative reactions is quantified as likelihood of a reaction. The output is an evaluation score for buzz level and likelihood of a reaction.

[1167] Step 6:

[1168] The server returns the calculated evaluation results of buzz level and flame potential to the user's device. The evaluation results are sent from the server to the device as an HTTP response in a data format such as JSON. The output is the evaluation result data sent to the user's device.

[1169] Step 7:

[1170] The user device receives the evaluation results returned from the server and visually displays them via a display interface. Specifically, scores such as "Buzz Level: 10, Flaming Potential: 3" are displayed on the user interface. By checking this, users can know in advance how their post will be received on the SNS. The output is the evaluation score displayed to the user.

[1171] 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.

[1172] 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.

[1173] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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).

[1178] 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.

[1179] 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."

[1180] 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.

[1181] 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).

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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.

[1192] The following is further disclosed regarding the above embodiment.

[1193] (Claim 1)

[1194] A means for inputting the content of the post;

[1195] A means for transmitting the inputted post content to a server;

[1196] The server receives the submitted content and passes it to the generative AI.

[1197] A generative AI analyzes the content of posts and generates responses using pseudo-personalities.

[1198] A means for evaluating the degree of buzz and the likelihood of it becoming a hot topic based on the generated reactions;

[1199] means for returning the evaluation result to the user terminal;

[1200] The system includes means for displaying the returned evaluation results to a user.

[1201] (Claim 2)

[1202] The system of claim 1, wherein the evaluation results are provided as scores of buzz and inflammatory potential.

[1203] (Claim 3)

[1204] 10. The system of claim 1, wherein the pseudo-personality generates positive, negative, and neutral responses.

[1205] "Example 1"

[1206] (Claim 1)

[1207] A means for inputting the content of the post;

[1208] means for transmitting the input posting content to a network device;

[1209] A means for the network device to receive the posted content and pass it to the generative artificial intelligence;

[1210] A generative AI analyzes the content of posts and generates responses using pseudo-personalities;

[1211] A means for evaluating topicality and inflammatory potential based on the generated reactions;

[1212] means for returning the evaluation result to the terminal device;

[1213] The system includes means for displaying the returned evaluation results to a user.

[1214] (Claim 2)

[1215] The system of claim 1, wherein the evaluation results are provided as scores for topicality and inflammatoryness.

[1216] (Claim 3)

[1217] 10. The system of claim 1, wherein the pseudo-personality generates positive, negative, and neutral responses.

[1218] "Application Example 1"

[1219] (Claim 1)

[1220] A means for inputting the content of the post;

[1221] A means for transmitting the inputted post content to a server;

[1222] The server receives the submitted content and passes it to the generative AI.

[1223] A generative AI analyzes the content of posts and generates responses using pseudo-personalities.

[1224] A means for evaluating the degree of buzz and the likelihood of it becoming a hot topic based on the generated reactions;

[1225] means for returning the evaluation result to the user terminal;

[1226] means for displaying the returned evaluation results to the user;

[1227] a means of assessing the risk and effectiveness of advertising campaigns;

[1228] The system includes a means for visually displaying evaluated advertising campaign results.

[1229] (Claim 2)

[1230] The system of claim 1, wherein the evaluation results are provided as scores of buzz and inflammatory potential.

[1231] (Claim 3)

[1232] 10. The system of claim 1, wherein the pseudo-personality generates positive, negative, and neutral responses.

[1233] "Example 2: Combining Emotion Engines"

[1234] (Claim 1)

[1235] A means for inputting the content of the post;

[1236] means for transmitting the inputted posting content to a central processing unit;

[1237] A means for a central processing unit to receive the posted content and pass it to an emotion engine;

[1238] A means for the emotion engine to analyze the content of posts and generate emotion data;

[1239] A means for the generative AI model to generate a response based on the generated emotion data; and

[1240] A means for evaluating the degree of buzz and the likelihood of it becoming a hot topic based on the generated reactions;

[1241] means for returning the evaluation results to a user interface;

[1242] The system includes means for displaying the returned evaluation results to a user.

[1243] (Claim 2)

[1244] The system according to claim 1, wherein the evaluation results are provided as numerical values ​​of buzz level and inflammatory potential.

[1245] (Claim 3)

[1246] 10. The system of claim 1, wherein the emotion engine identifies joy, anger, sadness, and the like.

[1247] "Application example 2 when combining emotion engines"

[1248] (Claim 1)

[1249] A means for inputting the content of the post;

[1250] A means for transmitting the inputted post content to a server;

[1251] The server receives the submitted content and passes it to the generative AI.

[1252] A generative AI analyzes the content of posts and generates responses using an emotion engine.

[1253] A means for evaluating the degree of buzz and the likelihood of it becoming a hot topic based on the generated reactions;

[1254] means for returning the evaluation result to the user terminal;

[1255] means for displaying the returned evaluation results to the user;

[1256] In particular, the system uses prompt sentences to generate responses based on posted content and provides evaluation results in a content distribution service.

[1257] (Claim 2)

[1258] The system of claim 1, wherein the evaluation results are provided as scores for buzz and inflammatoryness, and further wherein a generative AI generates expressions to analyze the emotional data.

[1259] (Claim 3)

[1260] 2. The system of claim 1, wherein the pseudo-personality generates positive, negative, and neutral responses, and further uses prompt sentences to generate the responses. [Explanation of symbols]

[1261] 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 for inputting the content of the post; A means for transmitting the inputted post content to a server; The server receives the submitted content and passes it to the generative AI. A generative AI analyzes the content of posts and generates responses using pseudo-personalities. A means for evaluating the degree of buzz and the likelihood of it becoming a hot topic based on the generated reactions; means for returning the evaluation result to the user terminal; The system includes means for displaying the returned evaluation results to a user.

2. The system according to claim 1, wherein the evaluation results are provided as scores of buzz and inflammatory potential.

3. 10. The system of claim 1, wherein the pseudo-personality generates positive, negative, and neutral responses.

Images