system

Abstract

The system according to this embodiment aims to automatically generate content that resonates with the target audience in order to increase the probability of success in viral marketing. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, a generation unit, and a distribution unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes new ideas based on the analysis results obtained by the analysis unit. The generation unit automatically generates content tailored to the target based on the ideas proposed by the proposal unit. The distribution unit distributes the content generated by the generation unit at an appropriate time.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the success of viral marketing is easily influenced by luck and it is difficult to generate effective content.

[0005] The system according to the embodiment aims to automatically generate content that resonates with the target in order to increase the success probability of viral marketing.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, a generation unit, and a distribution unit. The collection unit collects data. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes new ideas based on the analysis results obtained by the analysis unit. The generation unit automatically generates content tailored to the target based on the ideas proposed by the proposal unit. The distribution unit distributes the content generated by the generation unit at an appropriate time. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate content that resonates with the target audience in order to increase the probability of success in viral marketing. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The viral marketing support system according to an embodiment of the present invention is a system that uses AI to increase the success rate of viral marketing. This viral marketing support system addresses the problem that conventional viral marketing is highly dependent on luck and has a low success rate. It increases the probability of success by using AI to evaluate the shareability of content, suggest themes and formats with a high potential for virality, and automatically generate content that resonates with the target audience. For example, the viral marketing support system collects data in real time from various social media platforms. For example, the AI ​​analyzes the collected data to detect trends and engagement elements. Furthermore, the viral marketing support system proposes new ideas based on past success stories, automatically generates content tailored to the target audience, and distributes it at the appropriate time. This enables the design of efficient campaigns, leading to resource concentration and waste reduction. Specific application scenarios include promotional campaigns, target analysis, and response analysis and optimization. For example, the AI ​​generates unique promotional formats based on past campaign data, analyzes social media usage patterns to identify optimal content themes and distribution times. The viral marketing support system also monitors campaign effectiveness in real time, and the AI ​​automatically suggests improvement measures. This system enables highly efficient marketing and precise targeting. Furthermore, the viral marketing support system allows for rapid response to changing trends and enables market anticipation. Success stories include an overseas fashion brand that increased its social media followers by 20% using automatically generated content, and a fitness app that increased its number of registered users by 30% through target analysis. In short, the viral marketing support system can increase the probability of success in viral marketing.

[0029] The viral marketing support system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, a generation unit, and a distribution unit. The collection unit collects data. The collection unit can collect data in real time from various social networking services (SNS), for example. The collection unit can obtain data from SNS using APIs, for example. The collection unit can also collect data from websites using scraping technology. Furthermore, the collection unit can collect user posts and engagement data. For example, the collection unit can obtain user posts and engagement data in real time using SNS APIs. When using scraping technology, the collection unit analyzes the HTML structure of the website and extracts the necessary data. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit can analyze the collected data and detect trends and engagement elements. The analysis unit can analyze text data using natural language processing technology, for example. The analysis unit can also analyze image data using image recognition technology. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, the analysis unit uses natural language processing technology to extract trending words from collected text data. When using image recognition technology, the analysis unit detects engagement elements from collected image data. When using speech recognition technology, the analysis unit analyzes emotions from collected speech data. The proposal unit proposes new ideas based on the analysis results obtained by the analysis unit. The proposal unit can, for example, propose new ideas based on past success stories. For example, the proposal unit uses AI to analyze past success stories and generate new ideas. The proposal unit can also propose new ideas based on user attributes and behavioral patterns. Furthermore, the proposal unit can propose new ideas based on trends and engagement elements. For example, the proposal unit uses AI to analyze past success stories and propose similar campaigns. When based on user attributes and behavioral patterns, the proposal unit proposes content that is optimal for the target user. The generation unit automatically generates target-appropriate content based on the ideas proposed by the proposal unit.The generation unit can, for example, automatically generate targeted content using AI. The generation unit can generate text using text generation AI. It can also generate images using image generation AI. Furthermore, it can generate videos using video generation AI. For example, the generation unit can generate catchy slogans that resonate with target users using text generation AI. When using image generation AI, the generation unit generates visual content that resonates with target users. When using video generation AI, the generation unit generates promotional videos that resonate with target users. The distribution unit distributes the content generated by the generation unit at the appropriate time. The distribution unit can, for example, distribute content at the appropriate time using AI. The distribution unit can determine the distribution timing based on user behavior patterns and time of day, for example. The distribution unit can also monitor user reactions in real time and adjust the distribution timing accordingly. Furthermore, the distribution unit can distribute content through multiple channels. For example, the distribution unit determines the optimal distribution timing based on user behavior patterns and time of day. When monitoring user reactions in real time, the distribution unit adjusts the distribution timing based on user engagement data. When distributing content through multiple channels, the distribution unit distributes content via social media, email, websites, etc. This allows the viral marketing support system according to this embodiment to efficiently collect, analyze, propose, generate, and distribute data.

[0030] The data collection unit collects data. For example, the data collection unit can collect data in real time from various social networking services (SNS). Specifically, the data collection unit obtains data from SNS using APIs. For example, it uses SNS APIs to collect user posts, comments, likes, shares, and other engagement data in real time. The data collection unit can also collect data from websites using scraping technology. When using scraping technology, the data collection unit analyzes the HTML structure of the website and extracts the necessary data. For example, it collects blog posts and news articles related to specific keywords and uses this data for analysis. Furthermore, the data collection unit can also collect user posts and engagement data. For example, the data collection unit uses SNS APIs to obtain user posts and engagement data in real time. This allows the data collection unit to quickly grasp trends and user interests on SNS. The data collection unit centrally manages this data and makes it accessible to the analysis and proposal units. By adjusting the frequency and accuracy of data collection, flexible responses can be made according to specific situations and conditions. For example, the frequency of data collection can be increased during specific campaign periods to gain real-time insights into the situation. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit can analyze the collected data to detect trends and engagement elements. Specifically, the analysis unit uses natural language processing technology to analyze text data. For example, it can extract trending words from the collected text data to understand user interests and changes in topics. The analysis unit can also analyze image data using image recognition technology. For example, it can detect engagement elements from the collected image data to analyze what kind of visual content resonates with users. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, it can analyze emotions from the collected audio data to understand changes in users' emotions and reactions. By combining these technologies, the analysis unit can analyze the collected data from multiple angles and obtain more accurate insights. In addition, the analysis unit can utilize historical data and statistical information to predict long-term trends and fluctuations in engagement. For example, it can predict user reactions at specific times or events based on past campaign data and formulate future marketing strategies. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, enabling it to issue warnings early. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term trend analysis and anomaly detection, thereby improving the reliability and effectiveness of the entire system.

[0032] The proposal department proposes new ideas based on the analysis results obtained by the analysis department. For example, the proposal department can propose new ideas based on past success stories. Specifically, the proposal department uses AI to analyze past success stories and generate new ideas. For example, it can extract elements of campaigns that have achieved high engagement in the past and propose similar campaigns. The proposal department can also propose new ideas based on user attributes and behavioral patterns. For example, it can propose optimal content and campaigns based on attribute data such as the target user's age, gender, and interests. Furthermore, the proposal department can propose new ideas based on trends and engagement factors. For example, it can propose content that incorporates current trending words and popular visual styles. The proposal department can comprehensively analyze this information and propose the optimal marketing strategy for the target user. Furthermore, the proposal department can use AI to simulate the effectiveness of the proposed content and select the most effective idea. For example, it can simulate multiple ideas and predict engagement rates and conversion rates to select the optimal idea. In this way, the proposal department can propose effective marketing strategies based on analysis results and maximize the overall effectiveness of the system.

[0033] The generation unit automatically generates target-specific content based on ideas proposed by the proposal unit. For example, the generation unit can use AI to automatically generate target-specific content. Specifically, it can use text generation AI to generate text, such as catchy slogans and advertisements that resonate with target users. It can also use image generation AI to generate images, such as visual content and advertising banners that appeal to target users. Furthermore, it can use video generation AI to generate videos, such as promotional videos and product introduction videos that appeal to target users. By combining these technologies, the generation unit can automatically generate content optimized for target users. In addition, the generation unit can evaluate the quality of the generated content and make corrections or improvements as needed. For example, it can simulate the effect of generated slogans and select the most appropriate expression. The generation unit can also improve content based on user feedback, such as collecting user reactions to the generated content and incorporating them into future generation. This allows the generation unit to consistently provide high-quality content and maximize target user engagement.

[0034] The distribution unit delivers content generated by the generation unit at the appropriate time. The distribution unit can, for example, use AI to deliver content at the optimal time. Specifically, the distribution unit determines delivery timing based on user behavior patterns and time of day. For example, it can deliver content during the user's most active time to maximize engagement. The distribution unit can also monitor user reactions in real time and adjust delivery timing accordingly. For example, it can optimize the next delivery timing based on post-delivery engagement data. Furthermore, the distribution unit can deliver content through multiple channels. For example, it can deliver content via social media, email, and websites to maximize reach to users. The distribution unit can effectively combine these channels to deliver content to target users in the most optimal way. Additionally, the distribution unit can analyze delivery results and reflect them in the next delivery strategy. For example, it can review delivery content and timing based on post-delivery engagement data to optimize the next delivery strategy. This allows the distribution unit to consistently deliver content at the optimal time and in the optimal way, maximizing engagement with target users.

[0035] The data collection unit can collect data in real time from various social networking services (SNS). For example, the data collection unit can obtain data in real time using the APIs of various SNS. The data collection unit can also obtain data from SNS using APIs. Furthermore, the data collection unit can collect data from websites using scraping technology. In addition, the data collection unit can collect user posts and engagement data. For example, the data collection unit can obtain user posts and engagement data in real time using SNS APIs. When using scraping technology, the data collection unit analyzes the HTML structure of the website and extracts the necessary data. This allows for the acquisition of the latest information by collecting data in real time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data obtained using the APIs of various SNS into a generating AI and have the generating AI perform the data collection.

[0036] The analysis unit can analyze collected data and detect trends and engagement elements. For example, the analysis unit can analyze collected data and detect trends and engagement elements. The analysis unit can analyze text data using natural language processing technology. The analysis unit can also analyze image data using image recognition technology. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, the analysis unit can extract trend words from collected text data using natural language processing technology. When using image recognition technology, the analysis unit detects engagement elements from collected image data. When using speech recognition technology, the analysis unit analyzes emotions from collected audio data. This enables effective marketing by detecting trends and engagement elements. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input collected data into a generating AI and have the generating AI perform the detection of trends and engagement elements.

[0037] The proposal department can propose new ideas based on past success stories. For example, the proposal department can propose new ideas based on past success stories. For example, the proposal department can use AI to analyze past success stories and generate new ideas. The proposal department can also propose new ideas based on user attributes and behavioral patterns. Furthermore, the proposal department can propose new ideas based on trends and engagement factors. For example, the proposal department can use AI to analyze past success stories and propose similar campaigns. When based on user attributes and behavioral patterns, the proposal department proposes content that is optimal for the target user. This increases the probability of success by proposing new ideas based on past success stories. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input past success stories into a generation AI and have the generation AI execute the proposal of new ideas.

[0038] The generation unit can automatically generate content tailored to the target audience. For example, the generation unit can use AI to automatically generate content tailored to the target audience. For example, the generation unit can use text generation AI to generate text. The generation unit can also generate images using image generation AI. Furthermore, the generation unit can generate videos using video generation AI. For example, the generation unit can use text generation AI to generate catchy slogans that resonate with the target user. When using image generation AI, the generation unit generates visual content that resonates with the target user. When using video generation AI, the generation unit generates promotional videos that resonate with the target user. This enables effective marketing by automatically generating content tailored to the target audience. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can have the generation AI perform the generation of content tailored to the target audience.

[0039] The distribution unit can deliver generated content at the appropriate time. For example, the distribution unit can use AI to deliver content at the appropriate time. The distribution unit can determine the delivery timing based on user behavior patterns and time of day. Furthermore, the distribution unit can monitor user reactions in real time and adjust the delivery timing accordingly. In addition, the distribution unit can deliver content through multiple channels. For example, the distribution unit determines the optimal delivery timing based on user behavior patterns and time of day. When monitoring user reactions in real time, the distribution unit adjusts the delivery timing based on user engagement data. When delivering through multiple channels, the distribution unit delivers content via social media, email, websites, etc. This enables effective marketing by delivering content at the appropriate time. Some or all of the above processes in the distribution unit may be performed using AI, or not. For example, the distribution unit can have a generation AI deliver the generated content.

[0040] The improvement suggestion department can automatically propose improvement measures. For example, the improvement suggestion department can automatically propose improvement measures using AI. For example, the improvement suggestion department can propose improvement measures based on data collected in real time. The improvement suggestion department can also propose improvement measures based on past campaign data. Furthermore, the improvement suggestion department can propose improvement measures based on user response data. For example, the improvement suggestion department can analyze data collected in real time using AI and propose improvement measures. When based on past campaign data, the improvement suggestion department analyzes data from successful campaigns and proposes similar improvement measures. When based on user response data, the improvement suggestion department analyzes engagement data and proposes effective improvement measures. This maximizes the effectiveness of campaigns by automatically proposing improvement measures. Some or all of the above processes in the improvement suggestion department may be performed using AI, for example, or without AI. For example, the improvement suggestion department can input collected data into a generating AI and have the generating AI execute the proposal of improvement measures.

[0041] The data collection unit can analyze usage patterns of various social media platforms and select the optimal data collection method. For example, the data collection unit can use AI to analyze usage patterns of various social media platforms. For example, the data collection unit can analyze user posting frequency and engagement rates. Furthermore, the data collection unit can analyze the usage of specific hashtags. In addition, the data collection unit can analyze users' follower counts and influence. For example, the data collection unit uses AI to analyze user posting frequency and engagement rates and select the optimal data collection method. When analyzing the usage of specific hashtags, the data collection unit prioritizes collecting posts related to trending hashtags. When analyzing user follower counts and influence, the data collection unit prioritizes collecting posts from influential users. This allows the optimal data collection method to be selected by analyzing social media usage patterns. Some or all of the above-described processes in the data collection unit may be performed using AI, or not. For example, the data collection unit can input usage patterns of various social media platforms into a generating AI and have the generating AI select the optimal data collection method.

[0042] The data collection unit can filter data based on specific keywords or hashtags during the data collection process. For example, the data collection unit can use AI to filter based on specific keywords or hashtags. For example, the data collection unit can prioritize collecting posts containing keywords that are likely to go viral. The data collection unit can also collect posts containing hashtags related to a specific campaign. Furthermore, the data collection unit can exclude posts containing negative keywords and collect only positive posts. For example, the data collection unit can use AI to prioritize collecting posts containing keywords that are likely to go viral. When collecting posts containing hashtags related to a specific campaign, the data collection unit prioritizes collecting posts containing campaign-related hashtags. When excluding posts containing negative keywords, the data collection unit collects only posts containing positive keywords. This allows for the collection of highly relevant data by filtering based on specific keywords or hashtags. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have a generating AI perform filtering based on specific keywords or hashtags.

[0043] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can use AI to consider the user's geographical location information. For example, the data collection unit can obtain the user's location information using GPS data. The data collection unit can also estimate the user's location information using IP addresses. Furthermore, the data collection unit can extract location information from the user's posts. For example, the data collection unit can analyze GPS data using AI to obtain the user's location information. When using IP addresses, the data collection unit estimates the user's location information from the IP address. When extracting location information from posts, the data collection unit analyzes place names and location information contained in the user's posts. The data collection unit prioritizes the collection of highly relevant data by considering the user's geographical location information. For example, if the user is in a specific region, the data collection unit prioritizes collecting posts related to that region. The data collection unit prioritizes collecting posts from users who are geographically close. The data collection unit prioritizes collecting posts from regions where specific events are being held. In this way, by considering the user's geographical location information, highly relevant data can be prioritized for collection. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI collect highly relevant data.

[0044] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can use AI to analyze a user's social media activity. For example, the data collection unit can analyze a user's posting frequency and engagement rate. The data collection unit can also analyze the content of posts from accounts the user follows. Furthermore, the data collection unit can analyze the content of posts from groups and communities the user participates in. For example, the data collection unit uses AI to analyze a user's posting frequency and engagement rate and collects relevant data. When analyzing the content of posts from accounts the user follows, the data collection unit prioritizes collecting the content of those accounts. When analyzing the content of posts from groups and communities the user participates in, the data collection unit prioritizes collecting the content of those groups and communities. This allows for the collection of relevant data by analyzing the user's social media activity. Some or all of the above-described processes in the data collection unit may be performed using AI, or not. For example, the data collection unit can input the user's social media activity into a generating AI and have the generating AI collect the relevant data.

[0045] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during the analysis. For example, the analysis unit can use AI to evaluate the importance of the data. For example, the analysis unit can evaluate the importance of the data based on business impact. The analysis unit can also evaluate the importance of the data based on user interest. Furthermore, the analysis unit can evaluate the importance of the data based on engagement data. For example, the analysis unit can use AI to evaluate business impact and perform a detailed analysis on data with high importance. If based on user interest, the analysis unit performs a detailed analysis on data of high user interest. If based on engagement data, the analysis unit performs a detailed analysis on data with high engagement. This allows for effective analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for evaluating data importance into a generating AI and have the generating AI perform the importance evaluation.

[0046] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can classify data categories using AI. For example, the analysis unit can apply natural language processing algorithms to text data. The analysis unit can also apply image recognition algorithms to image data. Furthermore, the analysis unit can apply video analysis algorithms to video data. For example, the analysis unit can classify text data using AI and apply natural language processing algorithms. For image data, it can apply image recognition algorithms. For video data, it can apply video analysis algorithms. This enables effective analysis by applying different analysis algorithms depending on the data category. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for classifying data categories into a generating AI and have the generating AI perform the category classification.

[0047] The analysis unit can determine the priority of analysis based on the data collection timing during analysis. For example, the analysis unit can use AI to evaluate the data collection timing. For example, the analysis unit can prioritize the analysis of the most recent data. The analysis unit can also analyze the most recent data while referring to past data. Furthermore, the analysis unit can prioritize the analysis of data collected during a specific period. For example, the analysis unit uses AI to prioritize the analysis of the most recent data. When referring to past data, the analysis unit analyzes the most recent data based on past data. When prioritizing the analysis of data collected during a specific period, the analysis unit prioritizes the analysis of data collected during that specific period. This enables effective analysis by determining the priority of analysis based on the data collection timing. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for evaluating the data collection timing into a generating AI and have the generating AI perform the evaluation of the collection timing.

[0048] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. For example, the analysis unit can use AI to evaluate the relevance of the data. For example, the analysis unit can evaluate the relevance of the data based on co-occurrence relationships. The analysis unit can also evaluate the relevance of the data based on correlation relationships. Furthermore, the analysis unit can also evaluate the relevance of the data based on user behavior patterns. For example, the analysis unit can use AI to evaluate co-occurrence relationships and prioritize the analysis of highly relevant data. When based on correlation relationships, the analysis unit prioritizes the analysis of data with high correlation relationships. When based on user behavior patterns, the analysis unit prioritizes the analysis of data with high relevance based on user behavior patterns. This allows for effective analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for evaluating the relevance of the data into a generating AI and have the generating AI perform the relevance evaluation.

[0049] The proposal department can adjust the level of detail of a proposal based on the importance of the idea. For example, the proposal department can use AI to evaluate the importance of an idea. For example, the proposal department can evaluate the importance of an idea based on its business impact. The proposal department can also evaluate the importance of an idea based on user interest. Furthermore, the proposal department can evaluate the importance of an idea based on engagement data. For example, the proposal department can use AI to evaluate the business impact and make detailed proposals for ideas with high importance. If based on user interest, the proposal department will make detailed proposals for ideas that users are interested in. If based on engagement data, the proposal department will make detailed proposals for ideas that have high engagement. This allows for effective proposals by adjusting the level of detail of the proposal based on the importance of the idea. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input data for evaluating the importance of an idea into a generating AI and have the generating AI perform the importance evaluation.

[0050] The proposal unit can apply different proposal algorithms depending on the category of the idea during the proposal process. For example, the proposal unit can use AI to classify the category of the idea. For example, the proposal unit can apply a marketing algorithm to a marketing idea. The proposal unit can also apply a product development algorithm to a product idea. Furthermore, the proposal unit can apply a service design algorithm to a service idea. For example, the proposal unit can use AI to classify a marketing idea and apply a marketing algorithm. For a product idea, it can apply a product development algorithm. For a service idea, it can apply a service design algorithm. This allows for effective proposals by applying different proposal algorithms depending on the category of the idea. Some or all of the above processes in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input data for classifying the category of the idea into a generating AI and have the generating AI perform the category classification.

[0051] The proposal department can determine the priority of proposals based on when the ideas were submitted. For example, the proposal department can use AI to evaluate the submission timing of ideas. For example, the proposal department can prioritize proposing the latest ideas. The proposal department can also propose the latest ideas while referring to past ideas. Furthermore, the proposal department can prioritize proposing ideas submitted within a specific period. For example, the proposal department can use AI to prioritize proposing the latest ideas. When referring to past ideas, the proposal department proposes the latest ideas based on past ideas. When prioritizing ideas submitted within a specific period, the proposal department prioritizes ideas submitted within that period. This allows for effective proposals by determining the priority of proposals based on the submission timing of ideas. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input data for evaluating the submission timing of ideas into a generating AI and have the generating AI perform the evaluation of submission timing.

[0052] The proposal unit can adjust the order of proposals based on the relevance of the ideas during the proposal process. For example, the proposal unit can use AI to evaluate the relevance of ideas. For example, the proposal unit can evaluate the relevance of ideas based on co-occurrence relationships. The proposal unit can also evaluate the relevance of ideas based on correlation relationships. Furthermore, the proposal unit can evaluate the relevance of ideas based on user behavior patterns. For example, the proposal unit can use AI to evaluate co-occurrence relationships and prioritize suggesting highly relevant ideas. If based on correlation, the proposal unit prioritizes suggesting ideas with high correlation. If based on user behavior patterns, the proposal unit prioritizes suggesting highly relevant ideas based on user behavior patterns. This allows for effective proposals by adjusting the order of proposals based on the relevance of ideas. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input data for evaluating the relevance of ideas into a generating AI and have the generating AI perform the relevance evaluation.

[0053] The generation unit can analyze users' past reactions to select the optimal generation method when generating content. For example, the generation unit can use AI to analyze users' past reactions. The generation unit can analyze click-through rates and engagement rates, for example. The generation unit can also analyze the number of shares and comments. Furthermore, the generation unit can analyze the number of followers and influence of users. For example, the generation unit uses AI to analyze users' click-through rates and engagement rates to select the optimal generation method. When analyzing the number of shares and comments, the generation unit generates new content based on content with a high number of shares and comments. When analyzing the number of followers and influence of users, the generation unit generates new content based on the reactions of highly influential users. In this way, the optimal content generation method can be selected by analyzing users' past reactions. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data for analyzing users' past reactions into a generation AI and have the generation AI perform the reaction analysis.

[0054] The generation unit can customize the generated content based on the user's current areas of interest during content creation. For example, the generation unit can use AI to evaluate the user's current areas of interest. The generation unit can evaluate the user's areas of interest based on search history and browsing history, for example. The generation unit can also evaluate the user's areas of interest based on the content posted by accounts that the user follows. Furthermore, the generation unit can evaluate the user's areas of interest based on the content posted by the user. For example, the generation unit uses AI to analyze the user's search history and browsing history to evaluate areas of interest. When based on the content posted by accounts that the user follows, the generation unit analyzes the content posted by those accounts to evaluate areas of interest. When based on the content posted by the user, the generation unit analyzes the content posted by the user to evaluate areas of interest. The generation unit customizes the generated content based on the user's current areas of interest. For example, the generation unit generates content related to topics that the user is currently interested in. The generation unit generates content based on keywords that the user has recently searched for. The generation unit generates content based on the content posted by accounts that the user follows. This allows for effective content creation by customizing the generated content based on the user's current areas of interest. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data for evaluating the user's areas of interest into a generation AI and have the generation AI perform the evaluation of the areas of interest.

[0055] The generation unit can select the optimal generation method when generating content, taking into account the user's geographical location information. For example, the generation unit can use AI to consider the user's geographical location information. For example, the generation unit can obtain the user's location information using GPS data. Furthermore, the generation unit can estimate the user's location information using an IP address. In addition, the generation unit can extract location information from the user's posted content. For example, the generation unit can analyze GPS data using AI to obtain the user's location information. When using an IP address, the generation unit estimates the user's location information from the IP address. When extracting location information from posted content, the generation unit analyzes place names and location information contained in the user's posted content. The generation unit can select the optimal generation method, taking into account the user's geographical location information. For example, the generation unit can use AI to consider the user's geographical location information. For example, the generation unit can obtain the user's location information using GPS data. Furthermore, the generation unit can estimate the user's location information using an IP address. Furthermore, the generation unit can extract location information from the user's posted content. For example, the generation unit can analyze GPS data using AI to obtain the user's location information. When using an IP address, the generation unit estimates the user's location information from the IP address. When extracting location information from posted content, the generation unit analyzes place names and location information contained in the user's posted content. The generation unit selects the optimal generation method considering the user's geographical location information. For example, if the user is in a specific region, the generation unit generates content related to that region. The generation unit generates content that will attract the interest of users who are geographically close. The generation unit generates content related to the region where a specific event is being held. In this way, the optimal content generation method can be selected by considering the user's geographical location information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's geographical location information into a generation AI and have the generation AI select the optimal generation method.

[0056] The generation unit can analyze a user's social media activity and propose content to generate when generating content. For example, the generation unit can use AI to analyze a user's social media activity. For example, the generation unit can analyze a user's posting frequency and engagement rate. The generation unit can also analyze the content of posts from accounts that the user follows. Furthermore, the generation unit can analyze the content of posts from groups and communities that the user participates in. For example, the generation unit uses AI to analyze a user's posting frequency and engagement rate and proposes content to generate. When analyzing the content of posts from accounts that the user follows, the generation unit proposes new content based on the content of those accounts. When analyzing the content of posts from groups and communities that the user participates in, the generation unit proposes new content based on the content of those groups and communities. This makes it possible to generate effective content by analyzing the user's social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's social media activity into a generation AI and have the generation AI propose content to generate.

[0057] The distribution department can analyze users' past reactions to select the optimal distribution method at the time of distribution. For example, the distribution department can use AI to analyze users' past reactions. The distribution department can analyze click-through rates and engagement rates, for example. The distribution department can also analyze the number of shares and comments. Furthermore, the distribution department can analyze the number of followers and influence of users. For example, the distribution department uses AI to analyze users' click-through rates and engagement rates to select the optimal distribution method. When analyzing the number of shares and comments, the distribution department distributes new content based on content with a high number of shares and comments. When analyzing the number of followers and influence of users, the distribution department distributes new content based on the reactions of highly influential users. In this way, the optimal distribution method can be selected by analyzing users' past reactions. Some or all of the above processing in the distribution department may be performed using AI, for example, or without AI. For example, the distribution department distributes new content based on distribution methods that users have shown a favorable reaction to in the past. The distribution department distributes new content by incorporating distribution methods that users have shown high engagement to in the past. The distribution unit analyzes the characteristics of content previously shared by users and distributes content with similar characteristics. This allows for the selection of the optimal distribution method by analyzing users' past reactions. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input data for analyzing users' past reactions into a generating AI and have the generating AI perform the reaction analysis.

[0058] The distribution team can customize the content delivered based on the user's current areas of interest at the time of delivery. For example, the distribution team can use AI to evaluate the user's current areas of interest. For example, the distribution team can evaluate the user's areas of interest based on search history and browsing history. The distribution team can also evaluate the user's areas of interest based on the content posted by accounts that the user follows. Furthermore, the distribution team can evaluate the user's areas of interest based on the content posted by the user. For example, the distribution team can use AI to analyze the user's search history and browsing history to evaluate areas of interest. When basing it on the content posted by accounts that the user follows, the distribution team analyzes the content posted by those accounts to evaluate areas of interest. When basing it on the content posted by the user, the distribution team analyzes the content posted by the user to evaluate areas of interest. The distribution team customizes the content delivered based on the user's current areas of interest. For example, the distribution team delivers content related to topics that the user is currently interested in. The distribution team delivers content based on keywords that the user has recently searched for. The distribution team delivers content based on the content posted by accounts that the user follows. This allows for effective content delivery by customizing the content delivered based on the user's current areas of interest. Some or all of the above-described processes in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input data for evaluating the user's areas of interest into a generating AI and have the generating AI perform the evaluation of the areas of interest.

[0059] The distribution unit can select the optimal distribution method at the time of distribution, taking into account the user's geographical location information. For example, the distribution unit can use AI to consider the user's geographical location information. For example, the distribution unit can obtain the user's location information using GPS data. The distribution unit can also estimate the user's location information using IP addresses. Furthermore, the distribution unit can extract location information from the user's posted content. For example, the distribution unit can use AI to analyze GPS data and obtain the user's location information. When using IP addresses, the distribution unit estimates the user's location information from the IP address. When extracting location information from posted content, the distribution unit analyzes place names and location information contained in the user's posted content. The distribution unit selects the optimal distribution method considering the user's geographical location information. For example, if the distribution unit is in a specific region, it will distribute content related to that region. The distribution unit will distribute content that will attract the interest of users who are geographically close. The distribution unit will distribute content related to the region where a specific event is being held. In this way, the optimal distribution method can be selected by taking into account the user's geographical location information. Some or all of the above-described processes in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal distribution method.

[0060] The distribution unit can analyze users' social media activity and suggest content for distribution at the time of distribution. For example, the distribution unit can use AI to analyze users' social media activity. For example, the distribution unit can analyze users' posting frequency and engagement rate. The distribution unit can also analyze the content of posts from accounts that users follow. Furthermore, the distribution unit can analyze the content of posts from groups and communities that users participate in. For example, the distribution unit uses AI to analyze users' posting frequency and engagement rate and suggests content for distribution. When analyzing the content of posts from accounts that users follow, the distribution unit suggests new content based on the content of those accounts. When analyzing the content of posts from groups and communities that users participate in, the distribution unit suggests new content based on the content of those groups and communities. This enables effective content distribution by analyzing users' social media activity. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input users' social media activity into a generating AI and have the generating AI suggest content for distribution.

[0061] The monitoring unit can select the optimal monitoring method by referring to past campaign data during monitoring. For example, the monitoring unit can analyze past campaign data using AI. For example, the monitoring unit can select a monitoring method based on data from successful campaigns. The monitoring unit can also select an improved monitoring method based on data from unsuccessful campaigns. Furthermore, the monitoring unit can determine the optimal monitoring timing based on past campaign data. For example, the monitoring unit can analyze data from successful campaigns using AI and apply a similar monitoring method. If based on data from unsuccessful campaigns, the monitoring unit applies an improved monitoring method. If based on past campaign data, the monitoring unit determines the optimal monitoring timing. This allows the optimal monitoring method to be selected by referring to past campaign data. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past campaign data into a generating AI and have the generating AI select the optimal monitoring method.

[0062] The monitoring unit can improve the accuracy of monitoring by analyzing real-time responses during monitoring. For example, the monitoring unit can use AI to analyze real-time responses. For example, the monitoring unit can analyze real-time user click-through rates and engagement rates. The monitoring unit can also analyze real-time trend data. Furthermore, the monitoring unit can improve the accuracy of monitoring based on real-time user response data. For example, the monitoring unit can use AI to analyze real-time user responses and improve the accuracy of monitoring. When based on real-time click-through rates and engagement rates, the monitoring unit improves the accuracy of monitoring based on real-time data. When based on real-time trend data, the monitoring unit improves the accuracy of monitoring based on trend data. In this way, the accuracy of monitoring can be improved by analyzing real-time responses. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input real-time response data into a generating AI and have the generating AI perform the response analysis.

[0063] The monitoring unit can select the optimal monitoring method by considering the user's geographical location information during monitoring. For example, the monitoring unit can use AI to consider the user's geographical location information. For example, the monitoring unit can obtain the user's location information using GPS data. The monitoring unit can also estimate the user's location information using IP addresses. Furthermore, the monitoring unit can extract location information from the user's posts. For example, the monitoring unit can use AI to analyze GPS data and obtain the user's location information. When using IP addresses, the monitoring unit estimates the user's location information from the IP address. When extracting location information from posts, the monitoring unit analyzes place names and location information contained in the user's posts. The monitoring unit selects the optimal monitoring method by considering the user's geographical location information. For example, if the user is in a specific region, the monitoring unit prioritizes monitoring posts related to that region. The monitoring unit prioritizes monitoring posts from geographically close users. The monitoring unit prioritizes monitoring posts from regions where specific events are being held. In this way, the optimal monitoring method can be selected by considering the user's geographical location information. Some or all of the above-described processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal monitoring method.

[0064] The monitoring unit can analyze a user's social media activity during monitoring and propose monitoring content. For example, the monitoring unit can use AI to analyze a user's social media activity. For example, it can analyze a user's posting frequency and engagement rate. The monitoring unit can also analyze the content of posts from accounts the user follows. Furthermore, the monitoring unit can analyze the content of posts from groups and communities the user participates in. For example, the monitoring unit uses AI to analyze a user's posting frequency and engagement rate and proposes monitoring content. When analyzing the content of posts from accounts the user follows, the monitoring unit proposes new monitoring content based on the content of those accounts. When analyzing the content of posts from groups and communities the user participates in, the monitoring unit proposes new monitoring content based on the content of those groups and communities. This enables effective monitoring by analyzing the user's social media activity. Some or all of the above-described processes in the monitoring unit may be performed using AI, or not. For example, the monitoring unit can input the user's social media activity into a generating AI and have the generating AI propose monitoring content.

[0065] The improvement proposal unit can select the optimal improvement proposal method by referring to past campaign data when making improvement proposals. For example, the improvement proposal unit can analyze past campaign data using AI. For example, the improvement proposal unit can select an improvement proposal method based on data from successful campaigns. The improvement proposal unit can also select an improved proposal method based on data from unsuccessful campaigns. Furthermore, the improvement proposal unit can determine the optimal timing for improvement proposals based on past campaign data. For example, the improvement proposal unit can analyze data from successful campaigns using AI and apply a similar improvement proposal method. If based on data from unsuccessful campaigns, the improvement proposal unit applies an improved proposal method. If based on past campaign data, the improvement proposal unit determines the optimal timing for improvement proposals. In this way, the optimal improvement proposal method can be selected by referring to past campaign data. Some or all of the above processing in the improvement proposal unit may be performed using AI, for example, or without AI. For example, the improvement proposal unit can input past campaign data into a generating AI and have the generating AI select the optimal improvement proposal method.

[0066] The improvement suggestion unit can improve the accuracy of improvement suggestions by analyzing real-time responses when making suggestions. For example, the improvement suggestion unit can use AI to analyze real-time responses. For example, the improvement suggestion unit can analyze real-time user click-through rates and engagement rates. Furthermore, the improvement suggestion unit can also analyze real-time trend data. In addition, the improvement suggestion unit can improve the accuracy of improvement suggestions based on real-time user response data. For example, the improvement suggestion unit can use AI to analyze real-time user responses and improve the accuracy of improvement suggestions. When based on real-time click-through rates and engagement rates, the improvement suggestion unit improves the accuracy of improvement suggestions based on real-time data. When based on real-time trend data, the improvement suggestion unit improves the accuracy of improvement suggestions based on trend data. Thus, by analyzing real-time responses, the accuracy of improvement suggestions can be improved. Some or all of the above-described processes in the improvement suggestion unit may be performed using AI, or not. For example, the improvement suggestion unit can input real-time response data into a generating AI and have the generating AI perform the response analysis.

[0067] The improvement suggestion department can select the optimal improvement suggestion method when making improvement suggestions, taking into account the user's geographical location information. For example, the improvement suggestion department can use AI to consider the user's geographical location information. For example, the improvement suggestion department can obtain the user's location information using GPS data. The improvement suggestion department can also estimate the user's location information using IP addresses. Furthermore, the improvement suggestion department can extract location information from the user's posted content. For example, the improvement suggestion department can use AI to analyze GPS data and obtain the user's location information. When using IP addresses, the improvement suggestion department estimates the user's location information from the IP address. When extracting location information from posted content, the improvement suggestion department analyzes place names and location information contained in the user's posted content. The improvement suggestion department selects the optimal improvement suggestion method, taking into account the user's geographical location information. For example, if the user is in a specific region, the improvement suggestion department will make improvement suggestions related to that region. The improvement suggestion department will make improvement suggestions that will attract the interest of users who are geographically close. The improvement suggestion department will make improvement suggestions related to regions where specific events are being held. In this way, the optimal improvement suggestion method can be selected by taking into account the user's geographical location information. Some or all of the above-described processes in the improvement suggestion unit may be performed using AI, for example, or without AI. For example, the improvement suggestion unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal improvement suggestion method.

[0068] The Improvement Proposal Department can propose improvement suggestions by analyzing the user's social media activity. For example, the Improvement Proposal Department can use AI to analyze the user's social media activity. For example, it can analyze the user's posting frequency and engagement rate. Furthermore, the Improvement Proposal Department can analyze the content of posts from accounts the user follows. In addition, it can analyze the content of posts from groups and communities the user participates in. For example, the Improvement Proposal Department uses AI to analyze the user's posting frequency and engagement rate and proposes improvement suggestions. When analyzing the content of posts from accounts the user follows, the Improvement Proposal Department proposes new improvement suggestions based on the content of those accounts. When analyzing the content of posts from groups and communities the user participates in, the Improvement Proposal Department proposes new improvement suggestions based on the content of those groups and communities. This enables effective improvement suggestions by analyzing the user's social media activity. Some or all of the above-described processes in the Improvement Proposal Department may be performed using AI, or not. For example, the improvement suggestion unit can input the user's social media activity into a generating AI and have the AI ​​execute suggestions for improvement.

[0069] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0070] The viral marketing support system can prioritize the collection of highly relevant data by considering the user's geographical location. For example, if a user is in a specific region, the data collection unit can prioritize collecting posts related to that region. It can also prioritize collecting posts from users who are geographically close. It can prioritize collecting posts from regions where a specific event is being held. In this way, by considering the user's geographical location, it can prioritize the collection of highly relevant data.

[0071] A viral marketing support system can analyze a user's social media activity and suggest content to generate. For example, the generation unit can analyze a user's posting frequency and engagement rate and suggest content. It can also suggest new content based on the content of accounts the user follows. It can also suggest new content based on the content of groups and communities the user participates in. This enables effective content generation by analyzing the user's social media activity.

[0072] A viral marketing support system can analyze past user reactions and select the optimal generation method. For example, the generation unit can analyze user click-through rates and engagement rates to select the most suitable generation method. It can generate new content based on content with a high number of shares and comments. It can also generate new content based on reactions from highly influential users. In this way, by analyzing past user reactions, the system can select the most suitable content generation method.

[0073] The viral marketing support system can customize generated content based on the user's current areas of interest. For example, the generation unit can analyze the user's search and browsing history to evaluate their areas of interest. It can also analyze the content of accounts the user follows to evaluate their areas of interest. It can analyze the user's own posts to evaluate their areas of interest. This allows for the creation of effective content by customizing the generated content based on the user's current areas of interest.

[0074] A viral marketing support system can analyze users' social media activity and suggest content to distribute. For example, the distribution department can analyze users' posting frequency and engagement rates to suggest content. It can also suggest new content based on the content of accounts that users follow. It can also suggest new content based on the content of groups and communities that users participate in. This enables effective content distribution by analyzing users' social media activity.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The data collection unit collects data. The data collection unit can collect data in real time from various social networking services (SNS), for example. The data collection unit can obtain data from SNS using APIs, for example. The data collection unit can also collect data from websites using scraping techniques. Furthermore, the data collection unit can collect user posts and engagement data. For example, the data collection unit can obtain user posts and engagement data in real time using SNS APIs. When using scraping techniques, the data collection unit analyzes the HTML structure of the website and extracts the necessary data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit can, for example, analyze the collected data and detect trends and engagement elements. The analysis unit can, for example, analyze text data using natural language processing technology. The analysis unit can also analyze image data using image recognition technology. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, the analysis unit extracts trending words from the collected text data using natural language processing technology. When using image recognition technology, the analysis unit detects engagement elements from the collected image data. When using speech recognition technology, the analysis unit analyzes emotions from the collected audio data. Step 3: The proposal team proposes new ideas based on the analysis results obtained by the analysis team. For example, the proposal team can propose new ideas based on past success stories. For example, the proposal team can use AI to analyze past success stories and generate new ideas. The proposal team can also propose new ideas based on user attributes and behavioral patterns. Furthermore, the proposal team can propose new ideas based on trends and engagement factors. For example, the proposal team can use AI to analyze past success stories and propose similar campaigns. When based on user attributes and behavioral patterns, the proposal team proposes content that is optimal for the target users. Step 4: The generation unit automatically generates target-specific content based on the ideas proposed by the proposal unit. The generation unit can, for example, use AI to automatically generate target-specific content. For example, the generation unit can generate text using text generation AI. The generation unit can also generate images using image generation AI. Furthermore, the generation unit can generate videos using video generation AI. For example, the generation unit can use text generation AI to generate catchy slogans that resonate with the target users. When using image generation AI, the generation unit generates visual content that resonates with the target users. When using video generation AI, the generation unit generates promotional videos that resonate with the target users. Step 5: The distribution unit distributes the content generated by the generation unit at the appropriate time. The distribution unit can, for example, use AI to distribute content at the appropriate time. The distribution unit determines the distribution timing based on, for example, user behavior patterns and time of day. The distribution unit can also monitor user reactions in real time and adjust the distribution timing accordingly. Furthermore, the distribution unit can distribute content through multiple channels. For example, the distribution unit determines the optimal distribution timing based on user behavior patterns and time of day. When monitoring user reactions in real time, the distribution unit adjusts the distribution timing based on user engagement data. When distributing through multiple channels, the distribution unit distributes content through social media, email, websites, etc.

[0077] (Example of form 2) The viral marketing support system according to an embodiment of the present invention is a system that uses AI to increase the success rate of viral marketing. This viral marketing support system addresses the problem that conventional viral marketing is highly dependent on luck and has a low success rate. It increases the probability of success by using AI to evaluate the shareability of content, suggest themes and formats with a high potential for virality, and automatically generate content that resonates with the target audience. For example, the viral marketing support system collects data in real time from various social media platforms. For example, the AI ​​analyzes the collected data to detect trends and engagement elements. Furthermore, the viral marketing support system proposes new ideas based on past success stories, automatically generates content tailored to the target audience, and distributes it at the appropriate time. This enables the design of efficient campaigns, leading to resource concentration and waste reduction. Specific application scenarios include promotional campaigns, target analysis, and response analysis and optimization. For example, the AI ​​generates unique promotional formats based on past campaign data, analyzes social media usage patterns to identify optimal content themes and distribution times. The viral marketing support system also monitors campaign effectiveness in real time, and the AI ​​automatically suggests improvement measures. This system enables highly efficient marketing and precise targeting. Furthermore, the viral marketing support system allows for rapid response to changing trends and enables market anticipation. Success stories include an overseas fashion brand that increased its social media followers by 20% using automatically generated content, and a fitness app that increased its number of registered users by 30% through target analysis. In short, the viral marketing support system can increase the probability of success in viral marketing.

[0078] The viral marketing support system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, a generation unit, and a distribution unit. The collection unit collects data. The collection unit can collect data in real time from various social networking services (SNS), for example. The collection unit can obtain data from SNS using APIs, for example. The collection unit can also collect data from websites using scraping technology. Furthermore, the collection unit can collect user posts and engagement data. For example, the collection unit can obtain user posts and engagement data in real time using SNS APIs. When using scraping technology, the collection unit analyzes the HTML structure of the website and extracts the necessary data. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit can analyze the collected data and detect trends and engagement elements. The analysis unit can analyze text data using natural language processing technology, for example. The analysis unit can also analyze image data using image recognition technology. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, the analysis unit uses natural language processing technology to extract trending words from collected text data. When using image recognition technology, the analysis unit detects engagement elements from collected image data. When using speech recognition technology, the analysis unit analyzes emotions from collected speech data. The proposal unit proposes new ideas based on the analysis results obtained by the analysis unit. The proposal unit can, for example, propose new ideas based on past success stories. For example, the proposal unit uses AI to analyze past success stories and generate new ideas. The proposal unit can also propose new ideas based on user attributes and behavioral patterns. Furthermore, the proposal unit can propose new ideas based on trends and engagement elements. For example, the proposal unit uses AI to analyze past success stories and propose similar campaigns. When based on user attributes and behavioral patterns, the proposal unit proposes content that is optimal for the target user. The generation unit automatically generates target-appropriate content based on the ideas proposed by the proposal unit.The generation unit can, for example, automatically generate targeted content using AI. The generation unit can generate text using text generation AI. It can also generate images using image generation AI. Furthermore, it can generate videos using video generation AI. For example, the generation unit can generate catchy slogans that resonate with target users using text generation AI. When using image generation AI, the generation unit generates visual content that resonates with target users. When using video generation AI, the generation unit generates promotional videos that resonate with target users. The distribution unit distributes the content generated by the generation unit at the appropriate time. The distribution unit can, for example, distribute content at the appropriate time using AI. The distribution unit can determine the distribution timing based on user behavior patterns and time of day, for example. The distribution unit can also monitor user reactions in real time and adjust the distribution timing accordingly. Furthermore, the distribution unit can distribute content through multiple channels. For example, the distribution unit determines the optimal distribution timing based on user behavior patterns and time of day. When monitoring user reactions in real time, the distribution unit adjusts the distribution timing based on user engagement data. When distributing content through multiple channels, the distribution unit distributes content via social media, email, websites, etc. This allows the viral marketing support system according to this embodiment to efficiently collect, analyze, propose, generate, and distribute data.

[0079] The data collection unit collects data. For example, the data collection unit can collect data in real time from various social networking services (SNS). Specifically, the data collection unit obtains data from SNS using APIs. For example, it uses SNS APIs to collect user posts, comments, likes, shares, and other engagement data in real time. The data collection unit can also collect data from websites using scraping technology. When using scraping technology, the data collection unit analyzes the HTML structure of the website and extracts the necessary data. For example, it collects blog posts and news articles related to specific keywords and uses this data for analysis. Furthermore, the data collection unit can also collect user posts and engagement data. For example, the data collection unit uses SNS APIs to obtain user posts and engagement data in real time. This allows the data collection unit to quickly grasp trends and user interests on SNS. The data collection unit centrally manages this data and makes it accessible to the analysis and proposal units. By adjusting the frequency and accuracy of data collection, flexible responses can be made according to specific situations and conditions. For example, the frequency of data collection can be increased during specific campaign periods to gain real-time insights into the situation. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0080] The analysis unit analyzes the data collected by the data collection unit. For example, the analysis unit can analyze the collected data to detect trends and engagement elements. Specifically, the analysis unit uses natural language processing technology to analyze text data. For example, it can extract trending words from the collected text data to understand user interests and changes in topics. The analysis unit can also analyze image data using image recognition technology. For example, it can detect engagement elements from the collected image data to analyze what kind of visual content resonates with users. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, it can analyze emotions from the collected audio data to understand changes in users' emotions and reactions. By combining these technologies, the analysis unit can analyze the collected data from multiple angles and obtain more accurate insights. In addition, the analysis unit can utilize historical data and statistical information to predict long-term trends and fluctuations in engagement. For example, it can predict user reactions at specific times or events based on past campaign data and formulate future marketing strategies. Furthermore, the analysis unit can use anomaly detection algorithms to detect unusual patterns and abnormal data, enabling it to issue warnings early. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term trend analysis and anomaly detection, thereby improving the reliability and effectiveness of the entire system.

[0081] The proposal department proposes new ideas based on the analysis results obtained by the analysis department. For example, the proposal department can propose new ideas based on past success stories. Specifically, the proposal department uses AI to analyze past success stories and generate new ideas. For example, it can extract elements of campaigns that have achieved high engagement in the past and propose similar campaigns. The proposal department can also propose new ideas based on user attributes and behavioral patterns. For example, it can propose optimal content and campaigns based on attribute data such as the target user's age, gender, and interests. Furthermore, the proposal department can propose new ideas based on trends and engagement factors. For example, it can propose content that incorporates current trending words and popular visual styles. The proposal department can comprehensively analyze this information and propose the optimal marketing strategy for the target user. Furthermore, the proposal department can use AI to simulate the effectiveness of the proposed content and select the most effective idea. For example, it can simulate multiple ideas and predict engagement rates and conversion rates to select the optimal idea. In this way, the proposal department can propose effective marketing strategies based on analysis results and maximize the overall effectiveness of the system.

[0082] The generation unit automatically generates target-specific content based on ideas proposed by the proposal unit. For example, the generation unit can use AI to automatically generate target-specific content. Specifically, it can use text generation AI to generate text, such as catchy slogans and advertisements that resonate with target users. It can also use image generation AI to generate images, such as visual content and advertising banners that appeal to target users. Furthermore, it can use video generation AI to generate videos, such as promotional videos and product introduction videos that appeal to target users. By combining these technologies, the generation unit can automatically generate content optimized for target users. In addition, the generation unit can evaluate the quality of the generated content and make corrections or improvements as needed. For example, it can simulate the effect of generated slogans and select the most appropriate expression. The generation unit can also improve content based on user feedback, such as collecting user reactions to the generated content and incorporating them into future generation. This allows the generation unit to consistently provide high-quality content and maximize target user engagement.

[0083] The distribution unit delivers content generated by the generation unit at the appropriate time. The distribution unit can, for example, use AI to deliver content at the optimal time. Specifically, the distribution unit determines delivery timing based on user behavior patterns and time of day. For example, it can deliver content during the user's most active time to maximize engagement. The distribution unit can also monitor user reactions in real time and adjust delivery timing accordingly. For example, it can optimize the next delivery timing based on post-delivery engagement data. Furthermore, the distribution unit can deliver content through multiple channels. For example, it can deliver content via social media, email, and websites to maximize reach to users. The distribution unit can effectively combine these channels to deliver content to target users in the most optimal way. Additionally, the distribution unit can analyze delivery results and reflect them in the next delivery strategy. For example, it can review delivery content and timing based on post-delivery engagement data to optimize the next delivery strategy. This allows the distribution unit to consistently deliver content at the optimal time and in the optimal way, maximizing engagement with target users.

[0084] The data collection unit can collect data in real time from various social networking services (SNS). For example, the data collection unit can obtain data in real time using the APIs of various SNS. The data collection unit can also obtain data from SNS using APIs. Furthermore, the data collection unit can collect data from websites using scraping technology. In addition, the data collection unit can collect user posts and engagement data. For example, the data collection unit can obtain user posts and engagement data in real time using SNS APIs. When using scraping technology, the data collection unit analyzes the HTML structure of the website and extracts the necessary data. This allows for the acquisition of the latest information by collecting data in real time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input data obtained using the APIs of various SNS into a generating AI and have the generating AI perform the data collection.

[0085] The analysis unit can analyze collected data and detect trends and engagement elements. For example, the analysis unit can analyze collected data and detect trends and engagement elements. The analysis unit can analyze text data using natural language processing technology. The analysis unit can also analyze image data using image recognition technology. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, the analysis unit can extract trend words from collected text data using natural language processing technology. When using image recognition technology, the analysis unit detects engagement elements from collected image data. When using speech recognition technology, the analysis unit analyzes emotions from collected audio data. This enables effective marketing by detecting trends and engagement elements. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input collected data into a generating AI and have the generating AI perform the detection of trends and engagement elements.

[0086] The proposal department can propose new ideas based on past success stories. For example, the proposal department can propose new ideas based on past success stories. For example, the proposal department can use AI to analyze past success stories and generate new ideas. The proposal department can also propose new ideas based on user attributes and behavioral patterns. Furthermore, the proposal department can propose new ideas based on trends and engagement factors. For example, the proposal department can use AI to analyze past success stories and propose similar campaigns. When based on user attributes and behavioral patterns, the proposal department proposes content that is optimal for the target user. This increases the probability of success by proposing new ideas based on past success stories. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input past success stories into a generation AI and have the generation AI execute the proposal of new ideas.

[0087] The generation unit can automatically generate content tailored to the target audience. For example, the generation unit can use AI to automatically generate content tailored to the target audience. For example, the generation unit can use text generation AI to generate text. The generation unit can also generate images using image generation AI. Furthermore, the generation unit can generate videos using video generation AI. For example, the generation unit can use text generation AI to generate catchy slogans that resonate with the target user. When using image generation AI, the generation unit generates visual content that resonates with the target user. When using video generation AI, the generation unit generates promotional videos that resonate with the target user. This enables effective marketing by automatically generating content tailored to the target audience. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can have the generation AI perform the generation of content tailored to the target audience.

[0088] The distribution unit can deliver generated content at the appropriate time. For example, the distribution unit can use AI to deliver content at the appropriate time. The distribution unit can determine the delivery timing based on user behavior patterns and time of day. Furthermore, the distribution unit can monitor user reactions in real time and adjust the delivery timing accordingly. In addition, the distribution unit can deliver content through multiple channels. For example, the distribution unit determines the optimal delivery timing based on user behavior patterns and time of day. When monitoring user reactions in real time, the distribution unit adjusts the delivery timing based on user engagement data. When delivering through multiple channels, the distribution unit delivers content via social media, email, websites, etc. This enables effective marketing by delivering content at the appropriate time. Some or all of the above processes in the distribution unit may be performed using AI, or not. For example, the distribution unit can have a generation AI deliver the generated content.

[0089] The monitoring unit can monitor the effectiveness of a campaign in real time. For example, the monitoring unit monitors the effectiveness of a campaign in real time. For example, the monitoring unit monitors the effectiveness of a campaign in real time using AI. The monitoring unit can also evaluate the effectiveness of a campaign based on user engagement data. Furthermore, the monitoring unit can evaluate the effectiveness of a campaign based on trend data. For example, the monitoring unit uses AI to monitor user reactions in real time and evaluate the effectiveness of the campaign. When based on user engagement data, the monitoring unit collects data such as the number of likes, comments, and shares to evaluate the effectiveness of the campaign. When based on trend data, the monitoring unit analyzes trending words and popular topics to evaluate the effectiveness of the campaign. This enables rapid response by monitoring the effectiveness of a campaign in real time. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the data collected in real time into a generating AI and have the generating AI perform the monitoring of the effectiveness of the campaign.

[0090] The improvement suggestion department can automatically propose improvement measures. For example, the improvement suggestion department can automatically propose improvement measures using AI. For example, the improvement suggestion department can propose improvement measures based on data collected in real time. The improvement suggestion department can also propose improvement measures based on past campaign data. Furthermore, the improvement suggestion department can propose improvement measures based on user response data. For example, the improvement suggestion department can analyze data collected in real time using AI and propose improvement measures. When based on past campaign data, the improvement suggestion department analyzes data from successful campaigns and proposes similar improvement measures. When based on user response data, the improvement suggestion department analyzes engagement data and proposes effective improvement measures. This maximizes the effectiveness of campaigns by automatically proposing improvement measures. Some or all of the above processes in the improvement suggestion department may be performed using AI, for example, or without AI. For example, the improvement suggestion department can input collected data into a generating AI and have the generating AI execute the proposal of improvement measures.

[0091] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. The data collection unit can estimate the user's emotions using, for example, AI. The data collection unit can estimate the user's emotions using, for example, facial recognition technology. The data collection unit can also estimate the user's emotions using text analysis technology. Furthermore, the data collection unit can also estimate the user's emotions using voice analysis technology. For example, the data collection unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the data collection unit estimates emotions from the content of the user's posts. When using voice analysis technology, the data collection unit estimates emotions from the user's voice. The data collection unit adjusts the timing of data collection based on the estimated emotions of the user. For example, if the user is excited, the data collection unit will collect data at the time when the frequency of SNS posts increases. If the user is relaxed, the data collection unit will collect data during the nighttime. If the user is stressed, the data collection unit will collect data during the time when posts for stress relief increase. This enables effective data collection by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using AI or not using AI. For example, the collection unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0092] The data collection unit can analyze usage patterns of various social media platforms and select the optimal data collection method. For example, the data collection unit can use AI to analyze usage patterns of various social media platforms. For example, the data collection unit can analyze user posting frequency and engagement rates. Furthermore, the data collection unit can analyze the usage of specific hashtags. In addition, the data collection unit can analyze users' follower counts and influence. For example, the data collection unit uses AI to analyze user posting frequency and engagement rates and select the optimal data collection method. When analyzing the usage of specific hashtags, the data collection unit prioritizes collecting posts related to trending hashtags. When analyzing user follower counts and influence, the data collection unit prioritizes collecting posts from influential users. This allows the optimal data collection method to be selected by analyzing social media usage patterns. Some or all of the above-described processes in the data collection unit may be performed using AI, or not. For example, the data collection unit can input usage patterns of various social media platforms into a generating AI and have the generating AI select the optimal data collection method.

[0093] The data collection unit can filter data based on specific keywords or hashtags during the data collection process. For example, the data collection unit can use AI to filter based on specific keywords or hashtags. For example, the data collection unit can prioritize collecting posts containing keywords that are likely to go viral. The data collection unit can also collect posts containing hashtags related to a specific campaign. Furthermore, the data collection unit can exclude posts containing negative keywords and collect only positive posts. For example, the data collection unit can use AI to prioritize collecting posts containing keywords that are likely to go viral. When collecting posts containing hashtags related to a specific campaign, the data collection unit prioritizes collecting posts containing campaign-related hashtags. When excluding posts containing negative keywords, the data collection unit collects only posts containing positive keywords. This allows for the collection of highly relevant data by filtering based on specific keywords or hashtags. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can have a generating AI perform filtering based on specific keywords or hashtags.

[0094] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated user emotions. For example, the data collection unit can estimate the user's emotions using AI. For example, the data collection unit can estimate the user's emotions using facial recognition technology. The data collection unit can also estimate the user's emotions using text analysis technology. Furthermore, the data collection unit can also estimate the user's emotions using voice analysis technology. For example, the data collection unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the data collection unit estimates emotions from the content of the user's posts. When using voice analysis technology, the data collection unit estimates emotions from the user's voice. The data collection unit determines the priority of data to collect based on the estimated user emotions. For example, if the user is excited, the data collection unit will prioritize collecting posts with high engagement. If the user is relaxed, the data collection unit will prioritize collecting long posts. If the user is stressed, the data collection unit will prioritize collecting posts related to stress relief. This enables effective data collection by prioritizing data based on user emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input data for estimating user emotions into a generative AI and have the generative AI perform the emotion estimation.

[0095] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, the data collection unit can use AI to consider the user's geographical location information. For example, the data collection unit can obtain the user's location information using GPS data. The data collection unit can also estimate the user's location information using IP addresses. Furthermore, the data collection unit can extract location information from the user's posts. For example, the data collection unit can analyze GPS data using AI to obtain the user's location information. When using IP addresses, the data collection unit estimates the user's location information from the IP address. When extracting location information from posts, the data collection unit analyzes place names and location information contained in the user's posts. The data collection unit prioritizes the collection of highly relevant data by considering the user's geographical location information. For example, if the user is in a specific region, the data collection unit prioritizes collecting posts related to that region. The data collection unit prioritizes collecting posts from users who are geographically close. The data collection unit prioritizes collecting posts from regions where specific events are being held. In this way, by considering the user's geographical location information, highly relevant data can be prioritized for collection. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and have the generating AI collect highly relevant data.

[0096] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can use AI to analyze a user's social media activity. For example, the data collection unit can analyze a user's posting frequency and engagement rate. The data collection unit can also analyze the content of posts from accounts the user follows. Furthermore, the data collection unit can analyze the content of posts from groups and communities the user participates in. For example, the data collection unit uses AI to analyze a user's posting frequency and engagement rate and collects relevant data. When analyzing the content of posts from accounts the user follows, the data collection unit prioritizes collecting the content of those accounts. When analyzing the content of posts from groups and communities the user participates in, the data collection unit prioritizes collecting the content of those groups and communities. This allows for the collection of relevant data by analyzing the user's social media activity. Some or all of the above-described processes in the data collection unit may be performed using AI, or not. For example, the data collection unit can input the user's social media activity into a generating AI and have the generating AI collect the relevant data.

[0097] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using AI. For example, the analysis unit can estimate the user's emotions using facial recognition technology. The analysis unit can also estimate the user's emotions using text analysis technology. Furthermore, the analysis unit can also estimate the user's emotions using voice analysis technology. For example, the analysis unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the analysis unit estimates emotions from the content of the user's posts. When using voice analysis technology, the analysis unit estimates emotions from the user's voice. The analysis unit adjusts the presentation of the analysis based on the estimated emotions of the user. For example, if the user is excited, the analysis unit displays the analysis results using visually stimulating graphs and charts. If the user is relaxed, the analysis unit provides analysis results with detailed text explanations. If the user is stressed, the analysis unit provides simple and to-the-point analysis results. This allows for the provision of effective analysis results by adjusting the presentation of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0098] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during the analysis. For example, the analysis unit can use AI to evaluate the importance of the data. For example, the analysis unit can evaluate the importance of the data based on business impact. The analysis unit can also evaluate the importance of the data based on user interest. Furthermore, the analysis unit can evaluate the importance of the data based on engagement data. For example, the analysis unit can use AI to evaluate business impact and perform a detailed analysis on data with high importance. If based on user interest, the analysis unit performs a detailed analysis on data of high user interest. If based on engagement data, the analysis unit performs a detailed analysis on data with high engagement. This allows for effective analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for evaluating data importance into a generating AI and have the generating AI perform the importance evaluation.

[0099] The analysis unit can apply different analysis algorithms depending on the data category during analysis. For example, the analysis unit can classify data categories using AI. For example, the analysis unit can apply natural language processing algorithms to text data. The analysis unit can also apply image recognition algorithms to image data. Furthermore, the analysis unit can apply video analysis algorithms to video data. For example, the analysis unit can classify text data using AI and apply natural language processing algorithms. For image data, it can apply image recognition algorithms. For video data, it can apply video analysis algorithms. This enables effective analysis by applying different analysis algorithms depending on the data category. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for classifying data categories into a generating AI and have the generating AI perform the category classification.

[0100] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using AI. Alternatively, it can estimate the user's emotions using facial recognition technology. Furthermore, the analysis unit can estimate the user's emotions using text analysis technology. In addition, it can estimate the user's emotions using voice analysis technology. For example, the analysis unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the analysis unit estimates emotions from the user's posts. When using voice analysis technology, the analysis unit estimates emotions from the user's voice. The analysis unit adjusts the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit provides a short, concise analysis. If the user is relaxed, the analysis unit provides a detailed analysis. If the user is excited, the analysis unit provides a visually stimulating analysis. This allows for the provision of effective analysis results by adjusting the length of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0101] The analysis unit can determine the priority of analysis based on the data collection timing during analysis. For example, the analysis unit can use AI to evaluate the data collection timing. For example, the analysis unit can prioritize the analysis of the most recent data. The analysis unit can also analyze the most recent data while referring to past data. Furthermore, the analysis unit can prioritize the analysis of data collected during a specific period. For example, the analysis unit uses AI to prioritize the analysis of the most recent data. When referring to past data, the analysis unit analyzes the most recent data based on past data. When prioritizing the analysis of data collected during a specific period, the analysis unit prioritizes the analysis of data collected during that specific period. This enables effective analysis by determining the priority of analysis based on the data collection timing. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for evaluating the data collection timing into a generating AI and have the generating AI perform the evaluation of the collection timing.

[0102] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. For example, the analysis unit can use AI to evaluate the relevance of the data. For example, the analysis unit can evaluate the relevance of the data based on co-occurrence relationships. The analysis unit can also evaluate the relevance of the data based on correlation relationships. Furthermore, the analysis unit can also evaluate the relevance of the data based on user behavior patterns. For example, the analysis unit can use AI to evaluate co-occurrence relationships and prioritize the analysis of highly relevant data. When based on correlation relationships, the analysis unit prioritizes the analysis of data with high correlation relationships. When based on user behavior patterns, the analysis unit prioritizes the analysis of data with high relevance based on user behavior patterns. This allows for effective analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data for evaluating the relevance of the data into a generating AI and have the generating AI perform the relevance evaluation.

[0103] The suggestion function can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, the suggestion function can estimate the user's emotions using AI. For example, the suggestion function can estimate the user's emotions using facial recognition technology. The suggestion function can also estimate the user's emotions using text analysis technology. Furthermore, the suggestion function can also estimate the user's emotions using voice analysis technology. For example, the suggestion function can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the suggestion function estimates emotions from the content of the user's posts. When using voice analysis technology, the suggestion function estimates emotions from the user's voice. The suggestion function adjusts the way it presents suggestions based on the estimated user emotions. For example, if the user is excited, the suggestion function will present visually stimulating suggestions. If the user is relaxed, the suggestion function will present suggestions that include detailed explanations. If the user is stressed, the suggestion function will present simple, to-the-point suggestions. By adjusting the way suggestions are presented based on the user's emotions, effective suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the proposed unit may be performed using AI, or not using AI. For example, the proposed unit can input data for estimating the user's emotions into a generative AI and have the generative AI perform the emotion estimation.

[0104] The proposal department can adjust the level of detail of a proposal based on the importance of the idea. For example, the proposal department can use AI to evaluate the importance of an idea. For example, the proposal department can evaluate the importance of an idea based on its business impact. The proposal department can also evaluate the importance of an idea based on user interest. Furthermore, the proposal department can evaluate the importance of an idea based on engagement data. For example, the proposal department can use AI to evaluate the business impact and make detailed proposals for ideas with high importance. If based on user interest, the proposal department will make detailed proposals for ideas that users are interested in. If based on engagement data, the proposal department will make detailed proposals for ideas that have high engagement. This allows for effective proposals by adjusting the level of detail of the proposal based on the importance of the idea. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input data for evaluating the importance of an idea into a generating AI and have the generating AI perform the importance evaluation.

[0105] The proposal unit can apply different proposal algorithms depending on the category of the idea during the proposal process. For example, the proposal unit can use AI to classify the category of the idea. For example, the proposal unit can apply a marketing algorithm to a marketing idea. The proposal unit can also apply a product development algorithm to a product idea. Furthermore, the proposal unit can apply a service design algorithm to a service idea. For example, the proposal unit can use AI to classify a marketing idea and apply a marketing algorithm. For a product idea, it can apply a product development algorithm. For a service idea, it can apply a service design algorithm. This allows for effective proposals by applying different proposal algorithms depending on the category of the idea. Some or all of the above processes in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input data for classifying the category of the idea into a generating AI and have the generating AI perform the category classification.

[0106] The suggestion function can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, the suggestion function can estimate the user's emotions using AI. It can also estimate the user's emotions using facial recognition technology. Furthermore, it can estimate the user's emotions using text analysis technology. Additionally, it can estimate the user's emotions using voice analysis technology. For example, the suggestion function can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the suggestion function estimates emotions from the user's posts. When using voice analysis technology, the suggestion function estimates emotions from the user's voice. The suggestion function adjusts the length of the suggestion based on the estimated emotions. For example, if the user is in a hurry, the suggestion function will provide a short, concise suggestion. If the user is relaxed, the suggestion function will provide a detailed suggestion. If the user is excited, the suggestion function will provide a visually stimulating suggestion. This allows for more effective suggestions by adjusting the length of the suggestion based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the proposed unit may be performed using AI, or not using AI. For example, the proposed unit can input data for estimating the user's emotions into a generative AI and have the generative AI perform the emotion estimation.

[0107] The proposal department can determine the priority of proposals based on when the ideas were submitted. For example, the proposal department can use AI to evaluate the submission timing of ideas. For example, the proposal department can prioritize proposing the latest ideas. The proposal department can also propose the latest ideas while referring to past ideas. Furthermore, the proposal department can prioritize proposing ideas submitted within a specific period. For example, the proposal department can use AI to prioritize proposing the latest ideas. When referring to past ideas, the proposal department proposes the latest ideas based on past ideas. When prioritizing ideas submitted within a specific period, the proposal department prioritizes ideas submitted within that period. This allows for effective proposals by determining the priority of proposals based on the submission timing of ideas. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input data for evaluating the submission timing of ideas into a generating AI and have the generating AI perform the evaluation of submission timing.

[0108] The proposal unit can adjust the order of proposals based on the relevance of the ideas during the proposal process. For example, the proposal unit can use AI to evaluate the relevance of ideas. For example, the proposal unit can evaluate the relevance of ideas based on co-occurrence relationships. The proposal unit can also evaluate the relevance of ideas based on correlation relationships. Furthermore, the proposal unit can evaluate the relevance of ideas based on user behavior patterns. For example, the proposal unit can use AI to evaluate co-occurrence relationships and prioritize suggesting highly relevant ideas. If based on correlation, the proposal unit prioritizes suggesting ideas with high correlation. If based on user behavior patterns, the proposal unit prioritizes suggesting highly relevant ideas based on user behavior patterns. This allows for effective proposals by adjusting the order of proposals based on the relevance of ideas. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input data for evaluating the relevance of ideas into a generating AI and have the generating AI perform the relevance evaluation.

[0109] The generation unit can estimate the user's emotions and adjust the content generation method based on the estimated user emotions. For example, the generation unit can estimate the user's emotions using AI. For example, the generation unit can estimate the user's emotions using facial recognition technology. The generation unit can also estimate the user's emotions using text analysis technology. Furthermore, the generation unit can also estimate the user's emotions using voice analysis technology. For example, the generation unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the generation unit estimates emotions from the user's posted content. When using voice analysis technology, the generation unit estimates emotions from the user's voice. The generation unit adjusts the content generation method based on the estimated user emotions. For example, if the user is excited, the generation unit generates visually stimulating content. If the user is relaxed, the generation unit generates content in a calm tone. If the user is stressed, the generation unit generates simple, to-the-point content. This allows for effective content generation by adjusting the content generation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0110] The generation unit can analyze users' past reactions to select the optimal generation method when generating content. For example, the generation unit can use AI to analyze users' past reactions. The generation unit can analyze click-through rates and engagement rates, for example. The generation unit can also analyze the number of shares and comments. Furthermore, the generation unit can analyze the number of followers and influence of users. For example, the generation unit uses AI to analyze users' click-through rates and engagement rates to select the optimal generation method. When analyzing the number of shares and comments, the generation unit generates new content based on content with a high number of shares and comments. When analyzing the number of followers and influence of users, the generation unit generates new content based on the reactions of highly influential users. In this way, the optimal content generation method can be selected by analyzing users' past reactions. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data for analyzing users' past reactions into a generation AI and have the generation AI perform the reaction analysis.

[0111] The generation unit can customize the generated content based on the user's current areas of interest during content creation. For example, the generation unit can use AI to evaluate the user's current areas of interest. The generation unit can evaluate the user's areas of interest based on search history and browsing history, for example. The generation unit can also evaluate the user's areas of interest based on the content posted by accounts that the user follows. Furthermore, the generation unit can evaluate the user's areas of interest based on the content posted by the user. For example, the generation unit uses AI to analyze the user's search history and browsing history to evaluate areas of interest. When based on the content posted by accounts that the user follows, the generation unit analyzes the content posted by those accounts to evaluate areas of interest. When based on the content posted by the user, the generation unit analyzes the content posted by the user to evaluate areas of interest. The generation unit customizes the generated content based on the user's current areas of interest. For example, the generation unit generates content related to topics that the user is currently interested in. The generation unit generates content based on keywords that the user has recently searched for. The generation unit generates content based on the content posted by accounts that the user follows. This allows for effective content creation by customizing the generated content based on the user's current areas of interest. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data for evaluating the user's areas of interest into a generation AI and have the generation AI perform the evaluation of the areas of interest.

[0112] The generation unit can estimate the user's emotions and determine the priority of content to generate based on the estimated user emotions. The generation unit can estimate the user's emotions using, for example, AI. The generation unit can estimate the user's emotions using, for example, facial recognition technology. The generation unit can also estimate the user's emotions using text analysis technology. Furthermore, the generation unit can also estimate the user's emotions using voice analysis technology. For example, the generation unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the generation unit estimates emotions from the user's posts. When using voice analysis technology, the generation unit estimates emotions from the user's voice. The generation unit determines the priority of content to generate based on the estimated user emotions. For example, if the user is excited, the generation unit will prioritize generating visually stimulating content. If the user is relaxed, the generation unit will prioritize generating content with a calm tone. The generation unit prioritizes generating simple, concise content when the user is experiencing stress. This enables effective content generation by determining the priority of content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input data for estimating the user's emotions into the generation AI and have the generation AI perform the emotion estimation.

[0113] The generation unit can select the optimal generation method when generating content, taking into account the user's geographical location information. For example, the generation unit can use AI to consider the user's geographical location information. For example, the generation unit can obtain the user's location information using GPS data. Furthermore, the generation unit can estimate the user's location information using an IP address. In addition, the generation unit can extract location information from the user's posted content. For example, the generation unit can analyze GPS data using AI to obtain the user's location information. When using an IP address, the generation unit estimates the user's location information from the IP address. When extracting location information from posted content, the generation unit analyzes place names and location information contained in the user's posted content. The generation unit can select the optimal generation method, taking into account the user's geographical location information. For example, the generation unit can use AI to consider the user's geographical location information. For example, the generation unit can obtain the user's location information using GPS data. Furthermore, the generation unit can estimate the user's location information using an IP address. Furthermore, the generation unit can extract location information from the user's posted content. For example, the generation unit can analyze GPS data using AI to obtain the user's location information. When using an IP address, the generation unit estimates the user's location information from the IP address. When extracting location information from posted content, the generation unit analyzes place names and location information contained in the user's posted content. The generation unit selects the optimal generation method considering the user's geographical location information. For example, if the user is in a specific region, the generation unit generates content related to that region. The generation unit generates content that will attract the interest of users who are geographically close. The generation unit generates content related to the region where a specific event is being held. In this way, the optimal content generation method can be selected by considering the user's geographical location information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's geographical location information into a generation AI and have the generation AI select the optimal generation method.

[0114] The generation unit can analyze a user's social media activity and propose content to generate when generating content. For example, the generation unit can use AI to analyze a user's social media activity. For example, the generation unit can analyze a user's posting frequency and engagement rate. The generation unit can also analyze the content of posts from accounts that the user follows. Furthermore, the generation unit can analyze the content of posts from groups and communities that the user participates in. For example, the generation unit uses AI to analyze a user's posting frequency and engagement rate and proposes content to generate. When analyzing the content of posts from accounts that the user follows, the generation unit proposes new content based on the content of those accounts. When analyzing the content of posts from groups and communities that the user participates in, the generation unit proposes new content based on the content of those groups and communities. This makes it possible to generate effective content by analyzing the user's social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's social media activity into a generation AI and have the generation AI propose content to generate.

[0115] The distribution unit can estimate the user's emotions and adjust the timing of distribution based on the estimated emotions. The distribution unit can estimate the user's emotions using, for example, AI. The distribution unit can estimate the user's emotions using, for example, facial recognition technology. The distribution unit can also estimate the user's emotions using text analysis technology. Furthermore, the distribution unit can also estimate the user's emotions using voice analysis technology. For example, the distribution unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the distribution unit estimates emotions from the content of the user's posts. When using voice analysis technology, the distribution unit estimates emotions from the user's voice. The distribution unit adjusts the timing of distribution based on the estimated emotions of the user. For example, if the distribution unit is excited, it will distribute content at a time when the frequency of SNS posts increases. If the distribution unit is relaxed, it will distribute content at night. If the distribution unit is stressed, it will distribute content during times when posts for stress relief increase. This enables effective content delivery by adjusting the timing of delivery based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI or not using AI. For example, the delivery unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0116] The distribution department can analyze users' past reactions to select the optimal distribution method at the time of distribution. For example, the distribution department can use AI to analyze users' past reactions. The distribution department can analyze click-through rates and engagement rates, for example. The distribution department can also analyze the number of shares and comments. Furthermore, the distribution department can analyze the number of followers and influence of users. For example, the distribution department uses AI to analyze users' click-through rates and engagement rates to select the optimal distribution method. When analyzing the number of shares and comments, the distribution department distributes new content based on content with a high number of shares and comments. When analyzing the number of followers and influence of users, the distribution department distributes new content based on the reactions of highly influential users. In this way, the optimal distribution method can be selected by analyzing users' past reactions. Some or all of the above processing in the distribution department may be performed using AI, for example, or without AI. For example, the distribution department distributes new content based on distribution methods that users have shown a favorable reaction to in the past. The distribution department distributes new content by incorporating distribution methods that users have shown high engagement to in the past. The distribution unit analyzes the characteristics of content previously shared by users and distributes content with similar characteristics. This allows for the selection of the optimal distribution method by analyzing users' past reactions. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input data for analyzing users' past reactions into a generating AI and have the generating AI perform the reaction analysis.

[0117] The distribution team can customize the content delivered based on the user's current areas of interest at the time of delivery. For example, the distribution team can use AI to evaluate the user's current areas of interest. For example, the distribution team can evaluate the user's areas of interest based on search history and browsing history. The distribution team can also evaluate the user's areas of interest based on the content posted by accounts that the user follows. Furthermore, the distribution team can evaluate the user's areas of interest based on the content posted by the user. For example, the distribution team can use AI to analyze the user's search history and browsing history to evaluate areas of interest. When basing it on the content posted by accounts that the user follows, the distribution team analyzes the content posted by those accounts to evaluate areas of interest. When basing it on the content posted by the user, the distribution team analyzes the content posted by the user to evaluate areas of interest. The distribution team customizes the content delivered based on the user's current areas of interest. For example, the distribution team delivers content related to topics that the user is currently interested in. The distribution team delivers content based on keywords that the user has recently searched for. The distribution team delivers content based on the content posted by accounts that the user follows. This allows for effective content delivery by customizing the content delivered based on the user's current areas of interest. Some or all of the above-described processes in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input data for evaluating the user's areas of interest into a generating AI and have the generating AI perform the evaluation of the areas of interest.

[0118] The distribution team can estimate the user's emotions and determine the priority of content to deliver based on the estimated emotions. For example, the distribution team can estimate the user's emotions using AI. For example, the distribution team can estimate the user's emotions using facial recognition technology. The distribution team can also estimate the user's emotions using text analysis technology. Furthermore, the distribution team can estimate the user's emotions using voice analysis technology. For example, the distribution team can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the distribution team can estimate emotions from the user's posts. When using voice analysis technology, the distribution team can estimate emotions from the user's voice. The distribution team determines the priority of content to deliver based on the estimated emotions of the user. For example, if the user is excited, the distribution team will prioritize delivering visually stimulating content. If the user is relaxed, the distribution team will prioritize delivering content with a calm tone. If the user is stressed, the distribution team will prioritize delivering simple, to-the-point content. This enables effective content delivery by prioritizing content based on user emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input data for estimating user emotions into a generative AI and have the generative AI perform the emotion estimation.

[0119] The distribution unit can select the optimal distribution method at the time of distribution, taking into account the user's geographical location information. For example, the distribution unit can use AI to consider the user's geographical location information. For example, the distribution unit can obtain the user's location information using GPS data. The distribution unit can also estimate the user's location information using IP addresses. Furthermore, the distribution unit can extract location information from the user's posted content. For example, the distribution unit can use AI to analyze GPS data and obtain the user's location information. When using IP addresses, the distribution unit estimates the user's location information from the IP address. When extracting location information from posted content, the distribution unit analyzes place names and location information contained in the user's posted content. The distribution unit selects the optimal distribution method considering the user's geographical location information. For example, if the distribution unit is in a specific region, it will distribute content related to that region. The distribution unit will distribute content that will attract the interest of users who are geographically close. The distribution unit will distribute content related to the region where a specific event is being held. In this way, the optimal distribution method can be selected by taking into account the user's geographical location information. Some or all of the above-described processes in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal distribution method.

[0120] The distribution unit can analyze users' social media activity and suggest content for distribution at the time of distribution. For example, the distribution unit can use AI to analyze users' social media activity. For example, the distribution unit can analyze users' posting frequency and engagement rate. The distribution unit can also analyze the content of posts from accounts that users follow. Furthermore, the distribution unit can analyze the content of posts from groups and communities that users participate in. For example, the distribution unit uses AI to analyze users' posting frequency and engagement rate and suggests content for distribution. When analyzing the content of posts from accounts that users follow, the distribution unit suggests new content based on the content of those accounts. When analyzing the content of posts from groups and communities that users participate in, the distribution unit suggests new content based on the content of those groups and communities. This enables effective content distribution by analyzing users' social media activity. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input users' social media activity into a generating AI and have the generating AI suggest content for distribution.

[0121] The monitoring unit can estimate the user's emotions and adjust the monitoring method based on the estimated emotions. For example, the monitoring unit can estimate the user's emotions using AI. For example, the monitoring unit can estimate the user's emotions using facial recognition technology. The monitoring unit can also estimate the user's emotions using text analysis technology. Furthermore, the monitoring unit can also estimate the user's emotions using voice analysis technology. For example, the monitoring unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the monitoring unit estimates emotions from the content of the user's posts. When using voice analysis technology, the monitoring unit estimates emotions from the user's voice. The monitoring unit adjusts the monitoring method based on the estimated emotions of the user. For example, if the user is excited, the monitoring unit will enhance real-time monitoring. If the user is relaxed, the monitoring unit will perform periodic monitoring. If the user is stressed, the monitoring unit will prioritize monitoring posts related to stress relief. This allows for effective monitoring by adjusting the monitoring method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI or not using AI. For example, the monitoring unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0122] The monitoring unit can select the optimal monitoring method by referring to past campaign data during monitoring. For example, the monitoring unit can analyze past campaign data using AI. For example, the monitoring unit can select a monitoring method based on data from successful campaigns. The monitoring unit can also select an improved monitoring method based on data from unsuccessful campaigns. Furthermore, the monitoring unit can determine the optimal monitoring timing based on past campaign data. For example, the monitoring unit can analyze data from successful campaigns using AI and apply a similar monitoring method. If based on data from unsuccessful campaigns, the monitoring unit applies an improved monitoring method. If based on past campaign data, the monitoring unit determines the optimal monitoring timing. This allows the optimal monitoring method to be selected by referring to past campaign data. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past campaign data into a generating AI and have the generating AI select the optimal monitoring method.

[0123] The monitoring unit can improve the accuracy of monitoring by analyzing real-time responses during monitoring. For example, the monitoring unit can use AI to analyze real-time responses. For example, the monitoring unit can analyze real-time user click-through rates and engagement rates. The monitoring unit can also analyze real-time trend data. Furthermore, the monitoring unit can improve the accuracy of monitoring based on real-time user response data. For example, the monitoring unit can use AI to analyze real-time user responses and improve the accuracy of monitoring. When based on real-time click-through rates and engagement rates, the monitoring unit improves the accuracy of monitoring based on real-time data. When based on real-time trend data, the monitoring unit improves the accuracy of monitoring based on trend data. In this way, the accuracy of monitoring can be improved by analyzing real-time responses. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input real-time response data into a generating AI and have the generating AI perform the response analysis.

[0124] The monitoring unit can estimate the user's emotions and determine monitoring priorities based on the estimated emotions. For example, the monitoring unit can estimate user emotions using AI, facial recognition technology, text analysis technology, or voice analysis technology. For instance, the monitoring unit can estimate emotions from a user's facial expressions using facial recognition technology. When using text analysis technology, the monitoring unit estimates emotions from the user's posts. When using voice analysis technology, the monitoring unit estimates emotions from the user's voice. The monitoring unit determines monitoring priorities based on the estimated emotions. For example, if the user is excited, the monitoring unit prioritizes monitoring posts with high engagement. If the user is relaxed, the monitoring unit prioritizes monitoring longer posts. If the user is stressed, the monitoring unit prioritizes monitoring posts related to stress relief. This allows for effective monitoring by determining monitoring priorities based on user emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI or not using AI. For example, the monitoring unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0125] The monitoring unit can select the optimal monitoring method by considering the user's geographical location information during monitoring. For example, the monitoring unit can use AI to consider the user's geographical location information. For example, the monitoring unit can obtain the user's location information using GPS data. The monitoring unit can also estimate the user's location information using IP addresses. Furthermore, the monitoring unit can extract location information from the user's posts. For example, the monitoring unit can use AI to analyze GPS data and obtain the user's location information. When using IP addresses, the monitoring unit estimates the user's location information from the IP address. When extracting location information from posts, the monitoring unit analyzes place names and location information contained in the user's posts. The monitoring unit selects the optimal monitoring method by considering the user's geographical location information. For example, if the user is in a specific region, the monitoring unit prioritizes monitoring posts related to that region. The monitoring unit prioritizes monitoring posts from geographically close users. The monitoring unit prioritizes monitoring posts from regions where specific events are being held. In this way, the optimal monitoring method can be selected by considering the user's geographical location information. Some or all of the above-described processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal monitoring method.

[0126] The monitoring unit can analyze a user's social media activity during monitoring and propose monitoring content. For example, the monitoring unit can use AI to analyze a user's social media activity. For example, it can analyze a user's posting frequency and engagement rate. The monitoring unit can also analyze the content of posts from accounts the user follows. Furthermore, the monitoring unit can analyze the content of posts from groups and communities the user participates in. For example, the monitoring unit uses AI to analyze a user's posting frequency and engagement rate and proposes monitoring content. When analyzing the content of posts from accounts the user follows, the monitoring unit proposes new monitoring content based on the content of those accounts. When analyzing the content of posts from groups and communities the user participates in, the monitoring unit proposes new monitoring content based on the content of those groups and communities. This enables effective monitoring by analyzing the user's social media activity. Some or all of the above-described processes in the monitoring unit may be performed using AI, or not. For example, the monitoring unit can input the user's social media activity into a generating AI and have the generating AI propose monitoring content.

[0127] The improvement suggestion unit can estimate the user's emotions and adjust the method of improvement suggestions based on the estimated user emotions. For example, the improvement suggestion unit can estimate the user's emotions using AI. For example, the improvement suggestion unit can estimate the user's emotions using facial recognition technology. The improvement suggestion unit can also estimate the user's emotions using text analysis technology. Furthermore, the improvement suggestion unit can also estimate the user's emotions using voice analysis technology. For example, the improvement suggestion unit can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the improvement suggestion unit estimates emotions from the content of the user's posts. When using voice analysis technology, the improvement suggestion unit estimates emotions from the user's voice. The improvement suggestion unit adjusts the method of improvement suggestions based on the estimated user emotions. For example, if the user is excited, the improvement suggestion unit will make visually stimulating improvement suggestions. If the user is relaxed, the improvement suggestion unit will make improvement suggestions that include detailed explanations. If the user is stressed, the improvement suggestion unit will make simple, to-the-point improvement suggestions. This allows for more effective improvement suggestions by adjusting the method of suggestion based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the improvement suggestion unit may be performed using AI or not. For example, the improvement suggestion unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0128] The improvement proposal unit can select the optimal improvement proposal method by referring to past campaign data when making improvement proposals. For example, the improvement proposal unit can analyze past campaign data using AI. For example, the improvement proposal unit can select an improvement proposal method based on data from successful campaigns. The improvement proposal unit can also select an improved proposal method based on data from unsuccessful campaigns. Furthermore, the improvement proposal unit can determine the optimal timing for improvement proposals based on past campaign data. For example, the improvement proposal unit can analyze data from successful campaigns using AI and apply a similar improvement proposal method. If based on data from unsuccessful campaigns, the improvement proposal unit applies an improved proposal method. If based on past campaign data, the improvement proposal unit determines the optimal timing for improvement proposals. In this way, the optimal improvement proposal method can be selected by referring to past campaign data. Some or all of the above processing in the improvement proposal unit may be performed using AI, for example, or without AI. For example, the improvement proposal unit can input past campaign data into a generating AI and have the generating AI select the optimal improvement proposal method.

[0129] The improvement suggestion unit can improve the accuracy of improvement suggestions by analyzing real-time responses when making suggestions. For example, the improvement suggestion unit can use AI to analyze real-time responses. For example, the improvement suggestion unit can analyze real-time user click-through rates and engagement rates. Furthermore, the improvement suggestion unit can also analyze real-time trend data. In addition, the improvement suggestion unit can improve the accuracy of improvement suggestions based on real-time user response data. For example, the improvement suggestion unit can use AI to analyze real-time user responses and improve the accuracy of improvement suggestions. When based on real-time click-through rates and engagement rates, the improvement suggestion unit improves the accuracy of improvement suggestions based on real-time data. When based on real-time trend data, the improvement suggestion unit improves the accuracy of improvement suggestions based on trend data. Thus, by analyzing real-time responses, the accuracy of improvement suggestions can be improved. Some or all of the above-described processes in the improvement suggestion unit may be performed using AI, or not. For example, the improvement suggestion unit can input real-time response data into a generating AI and have the generating AI perform the response analysis.

[0130] The improvement suggestion department can estimate the user's emotions and determine the priority of improvement suggestions based on those estimated emotions. For example, the improvement suggestion department can estimate the user's emotions using AI. For example, the improvement suggestion department can estimate the user's emotions using facial recognition technology. The improvement suggestion department can also estimate the user's emotions using text analysis technology. Furthermore, the improvement suggestion department can also estimate the user's emotions using voice analysis technology. For example, the improvement suggestion department can estimate emotions from the user's facial expressions using facial recognition technology. When using text analysis technology, the improvement suggestion department can estimate emotions from the user's posts. When using voice analysis technology, the improvement suggestion department can estimate emotions from the user's voice. The improvement suggestion department determines the priority of improvement suggestions based on the estimated user emotions. For example, if the user is excited, the improvement suggestion department will prioritize improvement suggestions with high engagement. If the user is relaxed, the improvement suggestion department will prioritize detailed improvement suggestions. If the user is stressed, the improvement suggestion department will prioritize simple, to-the-point improvement suggestions. This enables effective improvement suggestions by prioritizing improvement suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the improvement suggestion unit may be performed using AI or not. For example, the improvement suggestion unit can input data for estimating the user's emotions into the generative AI and have the generative AI perform the emotion estimation.

[0131] The improvement suggestion department can select the optimal improvement suggestion method when making improvement suggestions, taking into account the user's geographical location information. For example, the improvement suggestion department can use AI to consider the user's geographical location information. For example, the improvement suggestion department can obtain the user's location information using GPS data. The improvement suggestion department can also estimate the user's location information using IP addresses. Furthermore, the improvement suggestion department can extract location information from the user's posted content. For example, the improvement suggestion department can use AI to analyze GPS data and obtain the user's location information. When using IP addresses, the improvement suggestion department estimates the user's location information from the IP address. When extracting location information from posted content, the improvement suggestion department analyzes place names and location information contained in the user's posted content. The improvement suggestion department selects the optimal improvement suggestion method, taking into account the user's geographical location information. For example, if the user is in a specific region, the improvement suggestion department will make improvement suggestions related to that region. The improvement suggestion department will make improvement suggestions that will attract the interest of users who are geographically close. The improvement suggestion department will make improvement suggestions related to regions where specific events are being held. In this way, the optimal improvement suggestion method can be selected by taking into account the user's geographical location information. Some or all of the above-described processes in the improvement suggestion unit may be performed using AI, for example, or without AI. For example, the improvement suggestion unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal improvement suggestion method.

[0132] The Improvement Proposal Department can propose improvement suggestions by analyzing the user's social media activity. For example, the Improvement Proposal Department can use AI to analyze the user's social media activity. For example, it can analyze the user's posting frequency and engagement rate. Furthermore, the Improvement Proposal Department can analyze the content of posts from accounts the user follows. In addition, it can analyze the content of posts from groups and communities the user participates in. For example, the Improvement Proposal Department uses AI to analyze the user's posting frequency and engagement rate and proposes improvement suggestions. When analyzing the content of posts from accounts the user follows, the Improvement Proposal Department proposes new improvement suggestions based on the content of those accounts. When analyzing the content of posts from groups and communities the user participates in, the Improvement Proposal Department proposes new improvement suggestions based on the content of those groups and communities. This enables effective improvement suggestions by analyzing the user's social media activity. Some or all of the above-described processes in the Improvement Proposal Department may be performed using AI, or not. For example, the improvement suggestion unit can input the user's social media activity into a generating AI and have the AI ​​execute suggestions for improvement.

[0133] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0134] A viral marketing support system can estimate a user's emotions and adjust the content generation method based on those emotions. For example, if a user is excited, the generation unit can create visually stimulating content. If a user is relaxed, it can create content with a calm tone. If a user is stressed, it can create simple, to-the-point content. This allows for effective content creation by adjusting the content generation method based on the user's emotions.

[0135] The viral marketing support system can prioritize the collection of highly relevant data by considering the user's geographical location. For example, if a user is in a specific region, the data collection unit can prioritize collecting posts related to that region. It can also prioritize collecting posts from users who are geographically close. It can prioritize collecting posts from regions where a specific event is being held. In this way, by considering the user's geographical location, it can prioritize the collection of highly relevant data.

[0136] The viral marketing support system can estimate user emotions and adjust the timing of data collection based on those emotions. For example, if a user is excited, the data collection unit can collect data at that time because their frequency of posting on social media increases. If a user is relaxed, data can be collected during nighttime hours. If a user is stressed, data can be collected during times when stress-relieving posts increase. By adjusting the timing of data collection based on user emotions, effective data collection becomes possible.

[0137] A viral marketing support system can analyze a user's social media activity and suggest content to generate. For example, the generation unit can analyze a user's posting frequency and engagement rate and suggest content. It can also suggest new content based on the content of accounts the user follows. It can also suggest new content based on the content of groups and communities the user participates in. This enables effective content generation by analyzing the user's social media activity.

[0138] Viral marketing support systems can estimate a user's emotions and adjust the way they present suggestions based on those emotions. For example, if a user is excited, the suggestion section can present visually stimulating suggestions. If a user is relaxed, it can present suggestions with detailed explanations. If a user is stressed, it can present simple, to-the-point suggestions. By adjusting the presentation of suggestions based on the user's emotions, more effective suggestions become possible.

[0139] A viral marketing support system can analyze past user reactions and select the optimal generation method. For example, the generation unit can analyze user click-through rates and engagement rates to select the most suitable generation method. It can generate new content based on content with a high number of shares and comments. It can also generate new content based on reactions from highly influential users. In this way, by analyzing past user reactions, the system can select the most suitable content generation method.

[0140] A viral marketing support system can estimate user emotions and adjust the timing of content delivery based on those emotions. For example, if a user is excited, the delivery unit can deliver content at a time when their social media posting frequency is higher. If a user is relaxed, content can be delivered during nighttime hours. If a user is stressed, content can be delivered during times when stress-relieving posts are more likely to occur. By adjusting the timing of content delivery based on user emotions, effective content delivery becomes possible.

[0141] The viral marketing support system can customize generated content based on the user's current areas of interest. For example, the generation unit can analyze the user's search and browsing history to evaluate their areas of interest. It can also analyze the content of accounts the user follows to evaluate their areas of interest. It can analyze the user's own posts to evaluate their areas of interest. This allows for the creation of effective content by customizing the generated content based on the user's current areas of interest.

[0142] A viral marketing support system can estimate user emotions and adjust monitoring methods based on those emotions. For example, the monitoring unit can enhance real-time monitoring when a user is excited, perform periodic monitoring when a user is relaxed, and prioritize monitoring posts related to stress relief when a user is stressed. This allows for more effective monitoring by adjusting monitoring methods based on user emotions.

[0143] A viral marketing support system can analyze users' social media activity and suggest content to distribute. For example, the distribution department can analyze users' posting frequency and engagement rates to suggest content. It can also suggest new content based on the content of accounts that users follow. It can also suggest new content based on the content of groups and communities that users participate in. This enables effective content distribution by analyzing users' social media activity.

[0144] The following briefly describes the processing flow for example form 2.

[0145] Step 1: The data collection unit collects data. The data collection unit can collect data in real time from various social networking services (SNS), for example. The data collection unit can obtain data from SNS using APIs, for example. The data collection unit can also collect data from websites using scraping techniques. Furthermore, the data collection unit can collect user posts and engagement data. For example, the data collection unit can obtain user posts and engagement data in real time using SNS APIs. When using scraping techniques, the data collection unit analyzes the HTML structure of the website and extracts the necessary data. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit can, for example, analyze the collected data and detect trends and engagement elements. The analysis unit can, for example, analyze text data using natural language processing technology. The analysis unit can also analyze image data using image recognition technology. Furthermore, the analysis unit can analyze audio data using speech recognition technology. For example, the analysis unit extracts trending words from the collected text data using natural language processing technology. When using image recognition technology, the analysis unit detects engagement elements from the collected image data. When using speech recognition technology, the analysis unit analyzes emotions from the collected audio data. Step 3: The proposal team proposes new ideas based on the analysis results obtained by the analysis team. For example, the proposal team can propose new ideas based on past success stories. For example, the proposal team can use AI to analyze past success stories and generate new ideas. The proposal team can also propose new ideas based on user attributes and behavioral patterns. Furthermore, the proposal team can propose new ideas based on trends and engagement factors. For example, the proposal team can use AI to analyze past success stories and propose similar campaigns. When based on user attributes and behavioral patterns, the proposal team proposes content that is optimal for the target users. Step 4: The generation unit automatically generates target-specific content based on the ideas proposed by the proposal unit. The generation unit can, for example, use AI to automatically generate target-specific content. For example, the generation unit can generate text using text generation AI. The generation unit can also generate images using image generation AI. Furthermore, the generation unit can generate videos using video generation AI. For example, the generation unit can use text generation AI to generate catchy slogans that resonate with the target users. When using image generation AI, the generation unit generates visual content that resonates with the target users. When using video generation AI, the generation unit generates promotional videos that resonate with the target users. Step 5: The distribution unit distributes the content generated by the generation unit at the appropriate time. The distribution unit can, for example, use AI to distribute content at the appropriate time. The distribution unit determines the distribution timing based on, for example, user behavior patterns and time of day. The distribution unit can also monitor user reactions in real time and adjust the distribution timing accordingly. Furthermore, the distribution unit can distribute content through multiple channels. For example, the distribution unit determines the optimal distribution timing based on user behavior patterns and time of day. When monitoring user reactions in real time, the distribution unit adjusts the distribution timing based on user engagement data. When distributing through multiple channels, the distribution unit distributes content through social media, email, websites, etc.

[0146] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0147] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0148] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, generation unit, and distribution unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit can collect data in real time from various SNS using the communication I / F 44 of the smart device 14. The analysis unit analyzes the collected data using the specific processing unit 290 of the data processing unit 12 to detect trends and engagement elements. The proposal unit proposes new ideas based on past success stories using the specific processing unit 290 of the data processing unit 12. The generation unit automatically generates target-specific content using the control unit 46A of the smart device 14. The distribution unit distributes content at the appropriate time using the communication I / F 44 of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0150] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0151] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0152] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0153] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0154] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0156] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0157] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, generation unit, and distribution unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit can collect data in real time from various SNS using the communication I / F 44 of the smart glasses 214. The analysis unit analyzes the collected data using the specific processing unit 290 of the data processing unit 12 to detect trends and engagement elements. The proposal unit proposes new ideas based on past success stories using the specific processing unit 290 of the data processing unit 12. The generation unit automatically generates target-specific content using the control unit 46A of the smart glasses 214. The distribution unit distributes content at the appropriate time using the communication I / F 44 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0166] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0167] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0168] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0169] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0170] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0172] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0173] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0174] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, generation unit, and distribution unit, is implemented in at least one of the following: the headset terminal 314 and the data processing unit 12. For example, the collection unit can collect data in real time from various SNSs using the communication I / F 44 of the headset terminal 314. The analysis unit analyzes the collected data using the specific processing unit 290 of the data processing unit 12 to detect trends and engagement elements. The proposal unit proposes new ideas based on past success stories using the specific processing unit 290 of the data processing unit 12. The generation unit automatically generates target-specific content using the control unit 46A of the headset terminal 314. The distribution unit distributes content at the appropriate time using the communication I / F 44 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0182] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0183] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0184] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0185] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0186] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0187] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0188] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0189] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0190] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0191] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0192] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0193] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0194] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0195] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0196] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0197] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0198] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, generation unit, and distribution unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit can collect data in real time from various social networking services (SNS) using the robot 414's communication interface 44. The analysis unit analyzes the collected data using the specific processing unit 290 of the data processing unit 12 to detect trends and engagement elements. The proposal unit proposes new ideas based on past success stories using the specific processing unit 290 of the data processing unit 12. The generation unit automatically generates target-specific content using the control unit 46A of the robot 414. The distribution unit distributes content at the appropriate time using the robot 414's communication interface 44. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0199] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0200] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0201] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0202] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0203] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0204] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0205] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0206] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0207] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0208] 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.

[0209] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0210] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0211] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0212] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0213] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0214] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0215] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0216] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0217] (Note 1) A data collection unit that collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, Based on the analysis results obtained by the aforementioned analysis unit, a proposal unit proposes new ideas. A generation unit that automatically generates content tailored to the target based on the ideas proposed by the aforementioned proposal unit, The system includes a distribution unit that delivers the content generated by the generation unit at an appropriate time. A system characterized by the following features. (Note 2) The aforementioned collection unit is We collect data in real time from various social media platforms. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The collected data is analyzed to detect trends and engagement factors. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, We propose new ideas based on past success stories. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Automatically generate content tailored to the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned distribution unit, Deliver the generated content at the appropriate time. The system described in Appendix 1, characterized by the features described herein. (Note 7) It includes a monitoring unit that monitors the effectiveness of campaigns in real time. The system described in Appendix 1, characterized by the features described herein. (Note 8) It is equipped with an improvement suggestion unit that automatically proposes improvement measures. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We will analyze usage patterns across various social media platforms and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting data, filter it based on specific keywords or hashtags. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the data was collected. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, adjust the order of analysis based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, When making a proposal, adjust the level of detail based on the importance of the idea. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, When submitting a proposal, a different proposal algorithm is applied depending on the category of the idea. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, When submitting proposals, prioritize them based on when the ideas were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, When making proposals, adjust the order of the proposals based on the relevance of the ideas. The system described in Appendix 1, characterized by the features described herein. (Note 27) The generating unit is It estimates user sentiment and adjusts content generation methods based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The generating unit is When generating content, the system analyzes past user reactions to select the optimal generation method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The generating unit is When generating content, customize the generated content based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 30) The generating unit is It estimates user sentiment and determines the priority of content to generate based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 31) The generating unit is When generating content, the optimal generation method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 32) The generating unit is When generating content, we analyze the user's social media activity and suggest content to be generated. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned distribution unit, It estimates the user's emotions and adjusts the delivery timing based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned distribution unit, During distribution, the system analyzes past user reactions to select the optimal distribution method. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned distribution unit, During delivery, customize the content based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned distribution unit, It estimates user sentiment and prioritizes the content delivered based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned distribution unit, During delivery, the optimal delivery method is selected considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned distribution unit, During distribution, we analyze users' social media activity and suggest content for the broadcast. The system described in Appendix 1, characterized by the features described herein. (Note 39) The monitoring unit, We estimate the user's emotions and adjust the monitoring method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 40) The monitoring unit, During monitoring, past campaign data is referenced to select the optimal monitoring method. The system described in Appendix 1, characterized by the features described herein. (Note 41) The monitoring unit, During monitoring, analyze real-time responses to improve monitoring accuracy. The system according to appended note 1, characterized in that... (Appended note 42) The monitoring unit estimates the user's emotion and determines the priority of monitoring based on the estimated user emotion The system according to appended note 1, characterized in that... (Appended note 43) The monitoring unit selects an optimal monitoring method in consideration of the user's geographical location information during monitoring The system according to appended note 1, characterized in that... (Appended note 44) The monitoring unit analyzes the user's social media activities during monitoring and proposes monitoring content The system according to appended note 1, characterized in that... (Appended note 45) The improvement proposal unit estimates the user's emotion and adjusts the improvement proposal method based on the estimated user emotion The system according to appended note 1, characterized in that... (Appended note 46) The improvement proposal unit selects an optimal improvement proposal method by referring to past campaign data during improvement proposal The system according to appended note 1, characterized in that... (Appended note 47) The improvement proposal unit analyzes the real-time reaction during improvement proposal to improve the accuracy of improvement proposal The system according to appended note , characterized in that... (Appended note 48) The improvement proposal unit s estimates the user's emotion and determines the priority of improvement proposal based on the estimated user emotion The system according to appended note 1, characterized in that... (Appended note 49) (Appended note 49) The improvement proposal unit When making improvement proposals, select the optimal improvement proposal method considering the user's geographical location information The system according to appended note 1, characterized in that it does so (Appended note 50) The improvement proposal department When making improvement proposals, analyze the user's social media activities and propose the content of the improvement proposals The system according to appended note 1, characterized in that it does so

Explanation of symbols

[0218] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. A data collection unit that collects data, An analysis unit analyzes the data collected by the aforementioned collection unit, Based on the analysis results obtained by the aforementioned analysis unit, a proposal unit proposes new ideas. A generation unit that automatically generates content tailored to the target based on the ideas proposed by the aforementioned proposal unit, The system includes a distribution unit that delivers the content generated by the generation unit at an appropriate time. A system characterized by the following features.

2. The aforementioned collection unit is We collect data in real time from various social media platforms. The system according to feature 1.

3. The aforementioned analysis unit, The collected data is analyzed to detect trends and engagement factors. The system according to feature 1.

4. The aforementioned proposal section is, We propose new ideas based on past success stories. The system according to feature 1.

5. The generating unit is Automatically generate content tailored to the target audience. The system according to feature 1.

6. The aforementioned distribution unit, Deliver the generated content at the appropriate time. The system according to feature 1.

7. It includes a monitoring unit that monitors the effectiveness of campaigns in real time. The system according to feature 1.

8. It is equipped with an improvement suggestion unit that automatically proposes improvement measures. The system according to feature 1.

9. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

10. The aforementioned collection unit is We will analyze usage patterns across various social media platforms and select the optimal data collection method. The system according to feature 1.

Images