System

Abstract

An object of the system according to the embodiment is to select an optimum influencer and manage effective collaboration.SOLUTION: A system includes an influencer selection part, an outreach part, a collaboration management part, a user interface part, and an analysis part. An influencer selection part analyzes the profile of the influencer, past contribution and the attribute of the follower and selects the optimal influencer. The outreach section transmits the customized message to the influencer selected by the influencer selection section. The collaboration manager manages collaboration schedules with influencers and analyzes progress and feedback. The user interface unit provides a user-friendly interface. The analysis unit analyzes the performance of the influencer and the effect of the campaign.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have faced challenges in that it is difficult to select the most suitable influencers and manage effective collaborations.

[0005] The system according to the embodiment aims to select optimal influencers and manage effective collaborations. [Means for solving the problem]

[0006] The system according to the embodiment includes an influencer selection unit, an outreach unit, a collaboration management unit, a user interface unit, and an analysis unit. The influencer selection unit selects the most suitable influencer by analyzing influencer profiles, past posts, and follower attributes. The outreach unit sends customized messages to influencers selected by the influencer selection unit. The collaboration management unit manages collaboration schedules with influencers and analyzes progress and feedback. The user interface unit provides a user-friendly interface. The analysis unit analyzes influencer performance and campaign effectiveness. [Effects of the Invention]

[0007] The system according to the embodiment can select the most suitable influencer and manage effective collaboration. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The influencer assist AI system according to an embodiment of the present invention is a system that enables companies to easily find influencers who are best suited to their products and to centrally manage everything from outreach to collaboration management. This makes it possible for even those with no marketing experience to easily develop influencer marketing.

[0029] An influencer-assisted AI system according to an embodiment includes an influencer selection unit, an outreach unit, a collaboration management unit, a user interface unit, and an analysis unit. The influencer selection unit selects the most suitable influencer by analyzing influencer profiles, past posts, and follower attributes. For example, the generation AI searches a database of influencers and lists influencers who are best suited to a company's products. The outreach unit sends customized messages to the influencers selected by the influencer selection unit. For example, the generation AI sends collaboration proposals to the selected influencers. The collaboration management unit manages collaboration schedules with influencers and analyzes progress and feedback. For example, the generation AI manages collaboration schedules with influencers and tracks progress. The user interface unit provides a user-friendly interface, including, for example, drag-and-drop functionality and intuitive navigation. The analysis unit analyzes influencer performance and campaign effectiveness. For example, the generation AI analyzes the engagement rate, reach, and conversion rate of influencer posts and provides detailed reports to companies. This allows the influencer assist AI system according to the embodiment to enable companies to efficiently and effectively conduct influencer marketing.

[0030] The influencer selection unit can analyze the purchasing history and behavioral patterns of influencer followers to identify influencers with a high affinity for a product. For example, the influencer selection unit uses a generation AI to analyze the purchasing history of influencer followers and select influencers with followers who have a high purchasing intent for a specific product category. For example, it identifies influencers with followers who have a high purchasing history for fashion products. It also analyzes the behavioral patterns of followers to select influencers with followers who are highly interested in specific products or services. For example, it identifies influencers with followers who respond frequently to posts about health foods. It also comprehensively analyzes the purchasing history and behavioral patterns of followers to identify influencers with a high affinity for a product. For example, it selects influencers who frequently purchase products from a specific brand and have followers who show high engagement with posts about that brand. This identifies influencers with a high affinity for a product, thereby improving marketing effectiveness.

[0031] The influencer selection unit can analyze the time and frequency of influencer postings and propose collaborations at the most effective times. For example, the generation AI in the influencer selection unit analyzes the influencer's past posting times and engagement rates to identify the most effective posting times. For example, if content posted at a specific time period receives high engagement, that time period will be suggested. The influencer selection unit can also analyze the influencer's posting frequency and propose the optimal collaboration timing. For example, if posting several times a week is most effective, collaboration at that frequency will be suggested. The influencer selection unit can also analyze the online activity times of the influencer's followers and propose collaborations at times when the most followers are online. For example, it can suggest posting at times when follower activity is at its peak. This improves engagement rates by proposing collaborations at the most effective times.

[0032] The influencer selection unit can also include the performance of video content and live streaming in its evaluation. For example, the generation AI analyzes the number of views and engagement rates of influencers' video content to select high-performing influencers. For example, it identifies influencers with videos that have many views and many comments and shares. It also analyzes the number of viewers and real-time engagement of influencers' live streaming to select high-performing influencers. For example, it identifies influencers with a large number of viewers during live streaming and active comments and reactions. It also comprehensively evaluates the performance of video content and live streaming to select the most effective influencer. For example, it selects influencers who show high engagement in both videos and live streaming. This enables a more comprehensive evaluation of influencers by including the performance of video content and live streaming in its evaluation.

[0033] The influencer selection unit can select influencers from a global perspective, including influencers from different cultural spheres and regions. For example, the generation AI analyzes data on influencers from different cultural spheres and regions to select the most suitable influencers from a global perspective. For example, it lists the most suitable influencers for each region, such as Asia, Europe, and America. It also analyzes the attributes and behavioral patterns of followers in different cultural spheres to select influencers according to their cultural background. For example, it identifies influencers that are popular in specific cultural spheres. In addition, to select influencers from a global perspective, it compares the performance of influencers from different regions and selects the most effective influencers. For example, it selects influencers based on engagement rates and reach in each region. This enables international marketing strategies by selecting influencers from a global perspective.

[0034] The outreach unit can analyze an influencer's past collaboration history and automatically generate the most effective outreach message. In the outreach unit, for example, the generation AI analyzes an influencer's past collaboration history and extracts characteristics of successful collaborations. Based on this, the most effective outreach message is automatically generated. For example, elements of messages that have received high engagement in the past are incorporated. In addition, customized outreach messages are generated based on the influencer's past collaboration history. For example, messages tailored to the influencer's preferences and interests are created. In addition, the generation AI analyzes the influencer's past collaboration history and identifies the timing and content of the most effective message. Based on this, the optimal outreach message is automatically generated. In this way, the automatic generation of the most effective outreach message improves the success rate of collaboration with influencers.

[0035] The outreach department can analyze influencers' active hours and conduct outreach at the times when they are most likely to receive a response. For example, the generation AI in the outreach department analyzes the influencer's past posting times and engagement rates to identify the times when they are most likely to receive a response. For example, if content posted at a specific time period receives high engagement, outreach will be conducted at that time period. The outreach department can also analyze influencers' active hours and suggest the optimal outreach timing. For example, messages can be sent at the time when the influencer is most active. The outreach department can also analyze followers' online activity times and conduct outreach at the time when the most followers are online. For example, messages can be sent at the time when followers are most active. This improves the influencer's response rate by conducting outreach at the time when they are most likely to receive a response.

[0036] The outreach department can include personalized content based on the influencer's interests in the outreach message. For example, the outreach department uses a generation AI to analyze the influencer's past postings and interests, and include personalized content based on that in the outreach message. For example, the outreach department provides information related to topics that interest the influencer. The outreach message also includes customized content based on the influencer's profile and follower attributes. For example, the outreach message may introduce products or services that the influencer's followers are interested in. The outreach message may also analyze the influencer's past collaboration history, and include personalized content that incorporates elements of successful collaborations in the outreach message. This makes it easier to attract the influencer's attention by including personalized content based on the influencer's interests.

[0037] The outreach department can integrate different platforms (e.g., social media, email, messaging apps) to achieve multi-channel outreach. For example, the outreach department will build a system in which generation AI integrates different platforms and performs outreach across multiple channels, such as social media, email, and messaging apps. For example, the same message can be sent simultaneously across multiple platforms. It also generates optimal outreach messages by taking into account the characteristics of each platform. For example, it can provide short messages on social media and detailed information via email. In addition, to achieve multi-channel outreach, a system will be developed that integrates data from each platform and sends unified messages. This will enable multi-channel outreach, increasing opportunities to reach influencers.

[0038] The collaboration management unit can analyze the content of influencer posts and suggest content that is most suitable for a company's brand image. For example, the generation AI in the collaboration management unit analyzes influencer past posts and suggests content that matches the company's brand image. For example, it selects influencers whose posts match the brand's values ​​and message. It also generates content that is best suited to the company's brand image based on the influencer's posts. For example, it suggests visual content that incorporates the brand's colors and logo. The generation AI also analyzes the influencer's posts and suggests storytelling that matches the company's brand image. For example, it suggests stories related to the brand's history and mission. This maintains brand consistency by suggesting content that is most suitable for the company's brand image.

[0039] The collaboration management unit can track the progress of collaboration in real time and automatically issue alerts when problems occur. For example, the collaboration management unit uses the generation AI to track the progress of collaboration in real time and automatically issue alerts when schedule delays or uncompleted tasks occur. For example, it can send reminders for tasks with approaching deadlines. It also builds a system that analyzes the progress of collaboration and automatically issues alerts when problems occur. For example, it can send notifications if feedback from influencers is delayed. The generation AI can also monitor the progress of collaboration in real time and automatically issue alerts when problems occur. For example, it can send a request for corrections if there are any errors in the content of a post. This allows the progress of collaboration to be tracked in real time and alerts can be issued automatically when problems occur, enabling rapid response.

[0040] The collaboration management unit can monitor the reactions of influencers' followers in real time and adjust strategies as necessary. For example, in the collaboration management unit, the generation AI monitors the reactions of influencers' followers in real time and analyzes engagement rates and comment content. Based on this, the collaboration strategy is adjusted as necessary. For example, the content of posts is changed if follower reactions are low. A system is also built to adjust the progress of collaboration based on followers' real-time reactions. For example, additional posts are made if follower reactions are positive. The generation AI also monitors followers' reactions in real time and adjusts the collaboration strategy as necessary. For example, the posting schedule is changed based on follower feedback. In this way, the effectiveness of collaboration is maximized by monitoring the reactions of influencers' followers in real time and adjusting the strategy as necessary.

[0041] The collaboration management unit can integrate collaboration history with different companies and brands and suggest the most suitable collaboration partner. For example, in the collaboration management unit, the generation AI analyzes an influencer's past collaboration history and integrates collaboration data with different companies and brands. Based on this, the unit suggests the most suitable collaboration partner. For example, elements of past successful collaborations can be incorporated. A system can also be built to suggest the most suitable partner based on the collaboration history with different companies and brands. For example, collaborations with companies that have the same target demographic can be suggested. The generation AI can also integrate collaboration history with different companies and brands and suggest the most suitable collaboration partner. For example, it can analyze the factors that made past collaborations successful and suggest similar companies. In this way, effective collaborations can be achieved by integrating collaboration history with different companies and brands and suggesting the most suitable collaboration partner.

[0042] The user interface unit can provide a customization function that analyzes a user's operation history and prioritizes displaying the most frequently used functions. The user interface unit, for example, provides a customization function in which a generation AI analyzes a user's operation history and prioritizes displaying the most frequently used functions. For example, menu items frequently used by the user are displayed at the top. In addition, a system is constructed that provides a customized interface based on the user's operation history. For example, the interface is automatically adjusted according to the user's operation patterns. In addition, a customization function in which a generation AI analyzes a user's operation history and prioritizes displaying the most frequently used functions is provided. For example, pages frequently accessed by the user are placed on the home screen. This improves user operation efficiency by analyzing a user's operation history and displaying the most frequently used functions preferentially.

[0043] The user interface unit can continuously improve the interface design based on user feedback. In the user interface unit, for example, the generation AI analyzes user feedback and continuously improves the interface design. For example, it makes suggestions to correct parts that the user is dissatisfied with. In addition, a system is built to improve the interface design based on user feedback. For example, it makes design changes that reflect user opinions. In addition, the generation AI analyzes user feedback in real time and continuously improves the interface design. For example, it identifies areas for improvement in the design based on user feedback. In this way, user satisfaction is increased by continuously improving the interface design based on user feedback.

[0044] The user interface unit can add a voice operation function to the interface, enabling hands-free operation. The user interface unit, for example, adds a voice operation function to the interface, allowing the user to operate it hands-free. For example, opening a menu or performing a search using a voice command. Furthermore, using the voice operation function, a system can be built that allows the user to operate the interface without using their hands. For example, selecting and outreaching influencers by voice. Furthermore, the generation AI analyzes the voice operation function and performs operations according to the user's voice command. For example, checking the progress of a collaboration by voice. In this way, adding a voice operation function to the interface and enabling hands-free operation improves user convenience.

[0045] The user interface unit can employ a responsive design that is compatible with different devices (e.g., smartphones, tablets, and PCs). The user interface unit, for example, employs a responsive design for the interface to optimize display on different devices. For example, the display is automatically adjusted for smartphones, tablets, and PCs. A system can also be built that provides an interface compatible with different devices. For example, a design can be adopted in which the layout changes depending on the screen size of the device. A generative AI can also be employed to analyze the characteristics of the device and provide a responsive design that provides the optimal display. For example, a portrait layout can be provided for smartphones, and a landscape layout can be provided for PCs. This improves the user's operating experience by employing a responsive design that is compatible with different devices.

[0046] The analysis unit can analyze the content of influencer posts and identify the most effective posting patterns and trends. In this analysis unit, for example, the generation AI analyzes the content of influencer posts in the past and identifies the most effective posting patterns. For example, if content posted at a particular time of day or day of the week has received high engagement, the system will suggest that pattern. The system also builds a system that identifies the latest trends based on the content of influencer posts. For example, it analyzes posts that frequently use particular hashtags or keywords to identify trends. The generation AI also analyzes the content of influencer posts and identifies the most effective posting patterns and trends. For example, if a particular visual style or content format has received high engagement, the system will suggest that pattern. This allows the system to analyze the content of influencer posts and identify the most effective posting patterns and trends, thereby improving marketing strategies.

[0047] The analysis department can monitor the effectiveness of the campaign in real time and adjust the strategy as necessary. For example, the generation AI in the analysis department monitors the effectiveness of the campaign in real time and analyzes the engagement rate and reach. Based on this, the strategy can be adjusted as necessary. For example, changing the content of posts if engagement is low. A system can also be built that monitors the progress of the campaign in real time and adjusts the strategy as necessary. For example, making an additional post if a particular post is receiving more response than expected. The generation AI can also monitor the effectiveness of the campaign in real time and adjust the strategy as necessary. For example, changing the posting schedule based on the response of followers. In this way, by monitoring the effectiveness of the campaign in real time and adjusting the strategy as necessary, marketing effectiveness can be improved.

[0048] The analysis unit can visualize the analysis results so that users can understand them intuitively. For example, the generation AI analyzes the effectiveness of a campaign and visualizes the results. For example, it displays engagement rates and reach numbers in graphs and charts. The analysis unit also builds a system that visualizes the analysis results so that users can understand them intuitively. For example, it allows important indicators to be checked at a glance in dashboard format. The generation AI also visualizes the analysis results so that users can understand them intuitively. For example, it provides interactive graphs and charts so that detailed data can be checked. In this way, visualizing the analysis results so that users can understand them intuitively makes it easier to interpret the data.

[0049] The analysis unit can compare the effectiveness of different campaigns and identify the most successful strategy. For example, the generation AI in the analysis unit analyzes the effectiveness of different campaigns and compares engagement rates and reach. Based on this, the most successful strategy is identified. For example, if a particular post format has high engagement, that format is recommended. In addition, a system is built to compare the effectiveness of different campaigns and identify the most successful strategy. For example, success factors are analyzed based on past campaign data. In addition, the generation AI compares the effectiveness of different campaigns and identifies the most successful strategy. For example, if an approach to a particular target demographic has been successful, that approach is recommended. In this way, by comparing the effectiveness of different campaigns and identifying the most successful strategy, the success rate of the next campaign is improved.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The influencer selection unit can analyze the purchasing history and behavioral patterns of influencers' followers to identify influencers with a high affinity for a product. For example, the generation AI analyzes the purchasing history of influencers' followers to select influencers with followers who have a high purchasing intent for a specific product category. For example, it identifies influencers with followers who have a high purchasing history of fashion products. It also analyzes followers' behavioral patterns to select influencers with followers who are highly interested in specific products or services. For example, it identifies influencers with followers who respond frequently to posts about health foods. It also comprehensively analyzes followers' purchasing history and behavioral patterns to identify influencers with a high affinity for a product. For example, it selects influencers who frequently purchase products from a specific brand and have followers who show high engagement with posts about that brand. This identifies influencers with a high affinity for a product, thereby improving marketing effectiveness.

[0052] The influencer selection unit can analyze an influencer's posting times and frequency to suggest collaborations at the most effective times. For example, the generation AI can analyze an influencer's past posting times and engagement rates to identify the most effective posting times. For example, if content posted at a specific time period receives high engagement, that time period will be suggested. It can also analyze an influencer's posting frequency to suggest the optimal timing for collaboration. For example, if posting several times a week is most effective, it can suggest collaboration at that frequency. It can also analyze the online activity times of an influencer's followers to suggest collaborations at times when the most followers are online. For example, it can suggest posting at times when follower activity is at its peak. This improves engagement rates by suggesting collaborations at the most effective times.

[0053] The influencer selection unit can also evaluate the performance of video content and live streaming. For example, the generation AI analyzes the number of views and engagement rates of influencers' video content to select high-performing influencers. For example, it identifies influencers with videos that have many views and many comments and shares. It also analyzes the number of viewers and real-time engagement of influencers' live streaming to select high-performing influencers. For example, it identifies influencers with a large number of viewers during live streaming and active comments and reactions. It also comprehensively evaluates the performance of video content and live streaming to select the most effective influencer. For example, it selects influencers who show high engagement in both videos and live streaming. This enables a more comprehensive evaluation of influencers by including the performance of video content and live streaming in the evaluation.

[0054] The influencer selection unit can select influencers from a global perspective, including influencers from different cultural spheres and regions. For example, the generation AI analyzes data on influencers from different cultural spheres and regions to select the most suitable influencers from a global perspective. For example, it can list the most suitable influencers for each region, such as Asia, Europe, and America. It can also analyze the attributes and behavioral patterns of followers in different cultural spheres to select influencers according to their cultural background. For example, it can identify influencers who are popular in specific cultural spheres. In addition, to select influencers from a global perspective, it compares the performance of influencers from different regions and selects the most effective influencers. For example, it can select influencers based on engagement rates and reach in each region. This allows for selection from a global perspective, enabling international marketing strategies.

[0055] The outreach department can analyze an influencer's past collaboration history and automatically generate the most effective outreach message. For example, the generation AI analyzes an influencer's past collaboration history and extracts the characteristics of successful collaborations. Based on this, the most effective outreach message is automatically generated. For example, elements of messages that have previously received high engagement are incorporated. Customized outreach messages are also generated based on the influencer's past collaboration history. For example, messages tailored to the influencer's preferences and interests are created. The generation AI also analyzes the influencer's past collaboration history and identifies the timing and content of the most effective message. Based on this, the optimal outreach message is automatically generated. This automatically generates the most effective outreach message, improving the success rate of collaboration with influencers.

[0056] The outreach department analyzes influencers' active hours and can reach out to them at the times when they are most likely to receive a response. For example, the generation AI analyzes the influencer's past posting times and engagement rates to identify the times when they are most likely to receive a response. For example, if content posted at a specific time period receives high engagement, outreach will be carried out at that time period. The outreach department also analyzes the influencer's active hours and suggests the optimal outreach timing. For example, messages will be sent at the time when the influencer is most active. The outreach department also analyzes the online activity times of followers and carries out outreach at the time when the most followers are online. For example, messages will be sent at the time when follower activity is at its peak. This improves the influencer's response rate by outreach at the time when they are most likely to receive a response.

[0057] The outreach department can include personalized content based on the influencer's interests in outreach messages. For example, the generative AI can analyze the influencer's past postings and interests, and include personalized content based on that in the outreach message. For example, providing information related to topics that interest the influencer. In addition, customized content can be included in the outreach message based on the influencer's profile and follower attributes. For example, introducing products and services that the influencer's followers are interested in. In addition, the outreach message can analyze the influencer's past collaboration history, and include personalized content that incorporates elements of successful collaborations. This makes it easier to attract the influencer's attention by including personalized content based on the influencer's interests.

[0058] The outreach department can integrate different platforms (e.g., social media, email, messaging apps) to achieve multi-channel outreach. For example, a generation AI can integrate different platforms and build a system for outreach across multiple channels, such as social media, email, and messaging apps. For example, the same message can be sent simultaneously across multiple platforms. It also generates optimal outreach messages by taking into account the characteristics of each platform. For example, it can provide short messages on social media and detailed information via email. In addition, to achieve multi-channel outreach, a system can be developed that integrates data from each platform and sends unified messages. This will enable multi-channel outreach, increasing opportunities to reach influencers.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The influencer selection department selects the most suitable influencers by analyzing influencer profiles, past posts, and follower attributes. For example, the generation AI searches a database of influencers and lists the influencers who are best suited to a company's products. Step 2: The outreach department sends customized messages to the influencers selected by the influencer selection department. For example, the generation AI sends collaboration proposals to the selected influencers. Step 3: The collaboration management unit manages the collaboration schedule with influencers and analyzes progress and feedback. For example, the generative AI manages the collaboration schedule with influencers and tracks progress. Step 4: The user interface section provides a user-friendly interface, including drag-and-drop functionality and intuitive navigation. Step 5: The analytics department analyzes influencer performance and campaign effectiveness. For example, the generative AI analyzes the engagement rate, reach, and conversion rate of influencer posts and provides a detailed report to the company.

[0061] (Example 2) The influencer assist AI system according to an embodiment of the present invention is a system that enables companies to easily find influencers who are best suited to their products and to centrally manage everything from outreach to collaboration management. This makes it possible for even those with no marketing experience to easily develop influencer marketing.

[0062] An influencer-assisted AI system according to an embodiment includes an influencer selection unit, an outreach unit, a collaboration management unit, a user interface unit, and an analysis unit. The influencer selection unit selects the most suitable influencer by analyzing influencer profiles, past posts, and follower attributes. For example, the generation AI searches a database of influencers and lists influencers who are best suited to a company's products. The outreach unit sends customized messages to the influencers selected by the influencer selection unit. For example, the generation AI sends collaboration proposals to the selected influencers. The collaboration management unit manages collaboration schedules with influencers and analyzes progress and feedback. For example, the generation AI manages collaboration schedules with influencers and tracks progress. The user interface unit provides a user-friendly interface, including, for example, drag-and-drop functionality and intuitive navigation. The analysis unit analyzes influencer performance and campaign effectiveness. For example, the generation AI analyzes the engagement rate, reach, and conversion rate of influencer posts and provides detailed reports to companies. This allows the influencer assist AI system according to the embodiment to enable companies to efficiently and effectively conduct influencer marketing.

[0063] The influencer selection unit can estimate emotions from influencers' past posts and prioritize influencers who elicit positive emotions. For example, the influencer selection unit uses a generation AI to analyze influencers' past posts and estimate emotions. It prioritizes the selection of influencers whose posts contain many positive emotions. For example, it lists influencers who frequently express joy and gratitude. It also analyzes followers' emotional responses to influencer posts to identify influencers who elicit positive emotions. For example, it calculates an emotion score based on followers' comments and reactions and selects influencers with high scores. It also uses emotion estimation technology to identify elements that elicit positive emotions from influencer posts and prioritizes the selection of influencers who contain many of those elements. For example, it selects influencers whose posts contain many positive storytelling and encouraging messages. This prioritizes the selection of influencers who elicit positive emotions, thereby improving the success rate of campaigns.

[0064] The influencer selection unit can analyze the purchasing history and behavioral patterns of influencer followers to identify influencers with a high affinity for a product. For example, the influencer selection unit uses a generation AI to analyze the purchasing history of influencer followers and select influencers with followers who have a high purchasing intent for a specific product category. For example, it identifies influencers with followers who have a high purchasing history for fashion products. It also analyzes the behavioral patterns of followers to select influencers with followers who are highly interested in specific products or services. For example, it identifies influencers with followers who respond frequently to posts about health foods. It also comprehensively analyzes the purchasing history and behavioral patterns of followers to identify influencers with a high affinity for a product. For example, it selects influencers who frequently purchase products from a specific brand and have followers who show high engagement with posts about that brand. This identifies influencers with a high affinity for a product, thereby improving marketing effectiveness.

[0065] The influencer selection unit can analyze the time and frequency of influencer postings and propose collaborations at the most effective times. For example, the generation AI in the influencer selection unit analyzes the influencer's past posting times and engagement rates to identify the most effective posting times. For example, if content posted at a specific time period receives high engagement, that time period will be suggested. The influencer selection unit can also analyze the influencer's posting frequency and propose the optimal collaboration timing. For example, if posting several times a week is most effective, collaboration at that frequency will be suggested. The influencer selection unit can also analyze the online activity times of the influencer's followers and propose collaborations at times when the most followers are online. For example, it can suggest posting at times when follower activity is at its peak. This improves engagement rates by proposing collaborations at the most effective times.

[0066] The influencer selection unit can also include the performance of video content and live streaming in its evaluation. For example, the generation AI analyzes the number of views and engagement rates of influencers' video content to select high-performing influencers. For example, it identifies influencers with videos that have many views and many comments and shares. It also analyzes the number of viewers and real-time engagement of influencers' live streaming to select high-performing influencers. For example, it identifies influencers with a large number of viewers during live streaming and active comments and reactions. It also comprehensively evaluates the performance of video content and live streaming to select the most effective influencer. For example, it selects influencers who show high engagement in both videos and live streaming. This enables a more comprehensive evaluation of influencers by including the performance of video content and live streaming in its evaluation.

[0067] The influencer selection unit can select influencers from a global perspective, including influencers from different cultural spheres and regions. For example, the generation AI analyzes data on influencers from different cultural spheres and regions to select the most suitable influencers from a global perspective. For example, it lists the most suitable influencers for each region, such as Asia, Europe, and America. It also analyzes the attributes and behavioral patterns of followers in different cultural spheres to select influencers according to their cultural background. For example, it identifies influencers that are popular in specific cultural spheres. In addition, to select influencers from a global perspective, it compares the performance of influencers from different regions and selects the most effective influencers. For example, it selects influencers based on engagement rates and reach in each region. This enables international marketing strategies by selecting influencers from a global perspective.

[0068] The influencer selection unit can use the emotion estimation function to analyze the emotional reactions of influencers' followers and select the influencer who will garner the most empathy. For example, the influencer selection unit uses a generation AI to analyze the emotional reactions of followers to influencer posts and select influencers with many positive emotional reactions. For example, it identifies influencers with many comments of joy and gratitude. It also selects influencers who will garner empathy based on follower emotional reaction data. For example, it lists influencers with high emotional scores. It also uses emotion estimation technology to analyze followers' emotional reactions in real time and selects the influencer who will garner the most empathy. For example, it selects based on the emotional reactions immediately after a post. This improves the effectiveness of the campaign by selecting the influencer who will garner the most empathy.

[0069] The outreach unit can analyze an influencer's past collaboration history and automatically generate the most effective outreach message. In the outreach unit, for example, the generation AI analyzes an influencer's past collaboration history and extracts characteristics of successful collaborations. Based on this, the most effective outreach message is automatically generated. For example, elements of messages that have received high engagement in the past are incorporated. In addition, customized outreach messages are generated based on the influencer's past collaboration history. For example, messages tailored to the influencer's preferences and interests are created. In addition, the generation AI analyzes the influencer's past collaboration history and identifies the timing and content of the most effective message. Based on this, the optimal outreach message is automatically generated. In this way, the automatic generation of the most effective outreach message improves the success rate of collaboration with influencers.

[0070] The outreach department can analyze influencers' active hours and conduct outreach at the times when they are most likely to receive a response. For example, the generation AI in the outreach department analyzes the influencer's past posting times and engagement rates to identify the times when they are most likely to receive a response. For example, if content posted at a specific time period receives high engagement, outreach will be conducted at that time period. The outreach department can also analyze influencers' active hours and suggest the optimal outreach timing. For example, messages can be sent at the time when the influencer is most active. The outreach department can also analyze followers' online activity times and conduct outreach at the time when the most followers are online. For example, messages can be sent at the time when followers are most active. This improves the influencer's response rate by conducting outreach at the time when they are most likely to receive a response.

[0071] The outreach unit can use the emotion estimation function to send customized messages according to the influencer's emotional state. For example, the generation AI in the outreach unit analyzes the influencer's emotional state in real time and sends customized messages according to that emotion. For example, sending an encouraging message when the influencer is in a positive emotional state. The emotion estimation function also generates personalized messages based on the influencer's emotional state. For example, if the influencer is feeling stressed, sending a message encouraging them to relax. The emotional state of the influencer can also be analyzed and customized messages sent at the optimal timing for that state. For example, proposing collaboration when emotions are high. In this way, by sending customized messages according to the influencer's emotional state, relationships with influencers can be improved.

[0072] The outreach department can include personalized content based on the influencer's interests in the outreach message. For example, the outreach department uses a generation AI to analyze the influencer's past postings and interests, and include personalized content based on that in the outreach message. For example, the outreach department provides information related to topics that interest the influencer. The outreach message also includes customized content based on the influencer's profile and follower attributes. For example, the outreach message may introduce products or services that the influencer's followers are interested in. The outreach message may also analyze the influencer's past collaboration history, and include personalized content that incorporates elements of successful collaborations in the outreach message. This makes it easier to attract the influencer's attention by including personalized content based on the influencer's interests.

[0073] The outreach department can integrate different platforms (e.g., social media, email, messaging apps) to achieve multi-channel outreach. For example, the outreach department will build a system in which generation AI integrates different platforms and performs outreach across multiple channels, such as social media, email, and messaging apps. For example, the same message can be sent simultaneously across multiple platforms. It also generates optimal outreach messages by taking into account the characteristics of each platform. For example, it can provide short messages on social media and detailed information via email. In addition, to achieve multi-channel outreach, a system will be developed that integrates data from each platform and sends unified messages. This will enable multi-channel outreach, increasing opportunities to reach influencers.

[0074] The outreach unit can use the emotion estimation function to monitor influencers' emotional responses in real time and send follow-up messages at the optimal timing. For example, the outreach unit's generation AI monitors influencers' emotional responses in real time and sends follow-up messages when emotions are high. For example, it makes additional suggestions when positive emotions are strong. The emotion estimation function is also used to generate follow-up messages according to the influencer's emotional state. For example, it provides detailed information when emotions are calm. A system is also built that analyzes influencers' emotional responses and sends follow-up messages at the optimal timing. For example, it sends a reminder message when emotions reach their peak. This allows influencers' emotional responses to be monitored in real time and follow-up messages to be sent at the optimal timing, improving relationships with influencers.

[0075] The collaboration management unit can analyze the content of influencer posts and suggest content that is most suitable for a company's brand image. For example, the generation AI in the collaboration management unit analyzes influencer past posts and suggests content that matches the company's brand image. For example, it selects influencers whose posts match the brand's values ​​and message. It also generates content that is best suited to the company's brand image based on the influencer's posts. For example, it suggests visual content that incorporates the brand's colors and logo. The generation AI also analyzes the influencer's posts and suggests storytelling that matches the company's brand image. For example, it suggests stories related to the brand's history and mission. This maintains brand consistency by suggesting content that is most suitable for the company's brand image.

[0076] The collaboration management unit can track the progress of collaboration in real time and automatically issue alerts when problems occur. For example, the collaboration management unit uses the generation AI to track the progress of collaboration in real time and automatically issue alerts when schedule delays or uncompleted tasks occur. For example, it can send reminders for tasks with approaching deadlines. It also builds a system that analyzes the progress of collaboration and automatically issues alerts when problems occur. For example, it can send notifications if feedback from influencers is delayed. The generation AI can also monitor the progress of collaboration in real time and automatically issue alerts when problems occur. For example, it can send a request for corrections if there are any errors in the content of a post. This allows the progress of collaboration to be tracked in real time and alerts can be issued automatically when problems occur, enabling rapid response.

[0077] The collaboration management unit can use the emotion estimation function to analyze influencer feedback and suggest areas for improving collaboration. For example, the collaboration management unit uses the generative AI to analyze influencer feedback using the emotion estimation function and make suggestions to strengthen areas with a lot of positive feedback and improve areas with a lot of negative feedback. For example, it strengthens elements that the influencer perceived favorably. It also analyzes influencer feedback and uses the emotion estimation function to identify areas for improving collaboration. For example, it makes suggestions to correct areas that the influencer found dissatisfied. It also uses the emotion estimation function to build a system that analyzes influencer feedback in real time and suggests areas for improving collaboration. For example, it identifies areas for improvement based on the emotion score of the feedback. In this way, by analyzing influencer feedback and suggesting areas for improving collaboration, the quality of collaboration is improved.

[0078] The collaboration management unit can monitor the reactions of influencers' followers in real time and adjust strategies as necessary. For example, in the collaboration management unit, the generation AI monitors the reactions of influencers' followers in real time and analyzes engagement rates and comment content. Based on this, the collaboration strategy is adjusted as necessary. For example, the content of posts is changed if follower reactions are low. A system is also built to adjust the progress of collaboration based on followers' real-time reactions. For example, additional posts are made if follower reactions are positive. The generation AI also monitors followers' reactions in real time and adjusts the collaboration strategy as necessary. For example, the posting schedule is changed based on follower feedback. In this way, the effectiveness of collaboration is maximized by monitoring the reactions of influencers' followers in real time and adjusting the strategy as necessary.

[0079] The collaboration management unit can integrate collaboration history with different companies and brands and suggest the most suitable collaboration partner. For example, in the collaboration management unit, the generation AI analyzes an influencer's past collaboration history and integrates collaboration data with different companies and brands. Based on this, the unit suggests the most suitable collaboration partner. For example, elements of past successful collaborations can be incorporated. A system can also be built to suggest the most suitable partner based on the collaboration history with different companies and brands. For example, collaborations with companies that have the same target demographic can be suggested. The generation AI can also integrate collaboration history with different companies and brands and suggest the most suitable collaboration partner. For example, it can analyze the factors that made past collaborations successful and suggest similar companies. In this way, effective collaborations can be achieved by integrating collaboration history with different companies and brands and suggesting the most suitable collaboration partner.

[0080] The collaboration management unit can use the emotion estimation function to monitor the emotional state of influencers and provide support to draw out positive emotions. For example, the collaboration management unit uses a generative AI to monitor the emotional state of influencers in real time and provide support to draw out positive emotions. For example, if an influencer is feeling stressed, it can send a message encouraging them to relax. In addition, the emotion estimation function can be used to build a system that provides support according to the influencer's emotional state. For example, it can suggest content that will increase positive emotions. It can also analyze the influencer's emotional state and provide support to draw out positive emotions. For example, it can send messages of gratitude or words of encouragement. In this way, the influencer's emotional state can be monitored and support to draw out positive emotions can be provided, thereby improving the influencer's motivation.

[0081] The user interface unit can incorporate an emotion estimation function to provide operation guides and support according to the user's emotional state. The user interface unit, for example, incorporates the emotion estimation function into the interface and analyzes the user's emotional state in real time. For example, if the user is feeling stressed, an operation guide encouraging relaxation is displayed. The emotion estimation function is also used to provide customized support according to the user's emotional state. For example, a detailed explanation is displayed if the user is confused. A system is also constructed that analyzes the user's emotional state and provides operation guides and support optimal for that state. For example, an encouraging message is displayed if the user is feeling positive. This improves the user's operation experience by providing operation guides and support according to the user's emotional state.

[0082] The user interface unit can provide a customization function that analyzes a user's operation history and prioritizes displaying the most frequently used functions. The user interface unit, for example, provides a customization function in which a generation AI analyzes a user's operation history and prioritizes displaying the most frequently used functions. For example, menu items frequently used by the user are displayed at the top. In addition, a system is constructed that provides a customized interface based on the user's operation history. For example, the interface is automatically adjusted according to the user's operation patterns. In addition, a customization function in which a generation AI analyzes a user's operation history and prioritizes displaying the most frequently used functions is provided. For example, pages frequently accessed by the user are placed on the home screen. This improves user operation efficiency by analyzing a user's operation history and displaying the most frequently used functions preferentially.

[0083] The user interface unit can continuously improve the interface design based on user feedback. In the user interface unit, for example, the generation AI analyzes user feedback and continuously improves the interface design. For example, it makes suggestions to correct parts that the user is dissatisfied with. In addition, a system is built to improve the interface design based on user feedback. For example, it makes design changes that reflect user opinions. In addition, the generation AI analyzes user feedback in real time and continuously improves the interface design. For example, it identifies areas for improvement in the design based on user feedback. In this way, user satisfaction is increased by continuously improving the interface design based on user feedback.

[0084] The user interface unit can add a voice operation function to the interface, enabling hands-free operation. The user interface unit, for example, adds a voice operation function to the interface, allowing the user to operate it hands-free. For example, opening a menu or performing a search using a voice command. Furthermore, using the voice operation function, a system can be built that allows the user to operate the interface without using their hands. For example, selecting and outreaching influencers by voice. Furthermore, the generation AI analyzes the voice operation function and performs operations according to the user's voice command. For example, checking the progress of a collaboration by voice. In this way, adding a voice operation function to the interface and enabling hands-free operation improves user convenience.

[0085] The user interface unit can employ a responsive design that is compatible with different devices (e.g., smartphones, tablets, and PCs). The user interface unit, for example, employs a responsive design for the interface to optimize display on different devices. For example, the display is automatically adjusted for smartphones, tablets, and PCs. A system can also be built that provides an interface compatible with different devices. For example, a design can be adopted in which the layout changes depending on the screen size of the device. A generative AI can also be employed to analyze the characteristics of the device and provide a responsive design that provides the optimal display. For example, a portrait layout can be provided for smartphones, and a landscape layout can be provided for PCs. This improves the user's operating experience by employing a responsive design that is compatible with different devices.

[0086] The user interface unit can use the emotion estimation function to provide customized themes and color schemes according to the user's emotional state. For example, the user interface unit uses the emotion estimation function to analyze the user's emotional state in real time and provide customized themes and color schemes according to that state. For example, when the user is relaxed, a theme with calm colors is displayed. Furthermore, a system is constructed that dynamically changes the interface theme and color scheme based on the user's emotional state. For example, when the user is feeling stressed, a color scheme with a relaxing effect is provided. Furthermore, based on the emotion estimation data, a theme and color scheme optimal for the user's emotional state is suggested. For example, a theme with bright colors that enhance positive emotions is provided. In this way, by providing customized themes and color schemes according to the user's emotional state, the user's operation experience is improved.

[0087] The analysis unit can analyze the content of influencer posts and identify the most effective posting patterns and trends. In this analysis unit, for example, the generation AI analyzes the content of influencer posts in the past and identifies the most effective posting patterns. For example, if content posted at a particular time of day or day of the week has received high engagement, the system will suggest that pattern. The system also builds a system that identifies the latest trends based on the content of influencer posts. For example, it analyzes posts that frequently use particular hashtags or keywords to identify trends. The generation AI also analyzes the content of influencer posts and identifies the most effective posting patterns and trends. For example, if a particular visual style or content format has received high engagement, the system will suggest that pattern. This allows the system to analyze the content of influencer posts and identify the most effective posting patterns and trends, thereby improving marketing strategies.

[0088] The analysis department can monitor the effectiveness of the campaign in real time and adjust the strategy as necessary. For example, the generation AI in the analysis department monitors the effectiveness of the campaign in real time and analyzes the engagement rate and reach. Based on this, the strategy can be adjusted as necessary. For example, changing the content of posts if engagement is low. A system can also be built that monitors the progress of the campaign in real time and adjusts the strategy as necessary. For example, making an additional post if a particular post is receiving more response than expected. The generation AI can also monitor the effectiveness of the campaign in real time and adjust the strategy as necessary. For example, changing the posting schedule based on the response of followers. In this way, by monitoring the effectiveness of the campaign in real time and adjusting the strategy as necessary, marketing effectiveness can be improved.

[0089] The analysis unit can use the emotion estimation function to analyze the emotional responses of followers and suggest areas for improving the campaign. For example, the analysis unit uses a generation AI to analyze the emotional responses of followers in real time and make suggestions to strengthen areas with a lot of positive emotional responses and improve areas with a lot of negative emotional responses. For example, it may strengthen elements that followers perceived favorably. It also analyzes the emotional responses of followers and uses the emotion estimation function to identify areas for improving the campaign. For example, it may make suggestions to correct areas that followers found dissatisfied. It also uses the emotion estimation function to build a system that analyzes the emotional responses of followers in real time and suggests areas for improving the campaign. For example, it may identify areas for improvement based on emotion scores. In this way, by analyzing the emotional responses of followers and suggesting areas for improving the campaign, marketing effectiveness is improved.

[0090] The analysis unit can visualize the analysis results so that users can understand them intuitively. For example, the generation AI analyzes the effectiveness of a campaign and visualizes the results. For example, it displays engagement rates and reach numbers in graphs and charts. The analysis unit also builds a system that visualizes the analysis results so that users can understand them intuitively. For example, it allows important indicators to be checked at a glance in dashboard format. The generation AI also visualizes the analysis results so that users can understand them intuitively. For example, it provides interactive graphs and charts so that detailed data can be checked. In this way, visualizing the analysis results so that users can understand them intuitively makes it easier to interpret the data.

[0091] The analysis unit can compare the effectiveness of different campaigns and identify the most successful strategy. For example, the generation AI in the analysis unit analyzes the effectiveness of different campaigns and compares engagement rates and reach. Based on this, the most successful strategy is identified. For example, if a particular post format has high engagement, that format is recommended. In addition, a system is built to compare the effectiveness of different campaigns and identify the most successful strategy. For example, success factors are analyzed based on past campaign data. In addition, the generation AI compares the effectiveness of different campaigns and identifies the most successful strategy. For example, if an approach to a particular target demographic has been successful, that approach is recommended. In this way, by comparing the effectiveness of different campaigns and identifying the most successful strategy, the success rate of the next campaign is improved.

[0092] The analysis unit can use the emotion estimation function to monitor followers' emotional responses in real time and suggest the optimal posting timing and content. For example, the analysis unit uses a generation AI to monitor followers' emotional responses in real time and suggest the optimal posting timing when emotions are high. For example, an additional post is made when positive emotions are strong. The emotion estimation function can also be used to build a system that suggests the optimal posting timing and content based on followers' emotional responses. For example, detailed information is provided when emotions are calm. The emotional responses of followers can also be analyzed and suggested as the optimal posting timing and content. For example, a reminder message is sent when emotions are at their peak. In this way, engagement rates can be improved by monitoring followers' emotional responses in real time and suggesting the optimal posting timing and content.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The influencer selection unit can estimate emotions from influencers' past posts and prioritize influencers who evoke positive emotions. For example, the generation AI analyzes influencers' past posts and estimates emotions. It prioritizes the selection of influencers whose posts contain many positive emotions. For example, it lists influencers who frequently express joy and gratitude. It also analyzes followers' emotional responses to influencer posts to identify influencers who evoke positive emotions. For example, it calculates an emotion score based on followers' comments and reactions and selects influencers with high scores. It also uses emotion estimation technology to identify elements that evoke positive emotions from influencer posts and prioritizes the selection of influencers who contain many of those elements. For example, it selects influencers whose posts contain many positive storytelling and encouraging messages. This prioritizes the selection of influencers who evoke positive emotions, thereby improving the success rate of campaigns.

[0095] The influencer selection unit can analyze the purchasing history and behavioral patterns of influencers' followers to identify influencers with a high affinity for a product. For example, the generation AI analyzes the purchasing history of influencers' followers to select influencers with followers who have a high purchasing intent for a specific product category. For example, it identifies influencers with followers who have a high purchasing history of fashion products. It also analyzes followers' behavioral patterns to select influencers with followers who are highly interested in specific products or services. For example, it identifies influencers with followers who respond frequently to posts about health foods. It also comprehensively analyzes followers' purchasing history and behavioral patterns to identify influencers with a high affinity for a product. For example, it selects influencers who frequently purchase products from a specific brand and have followers who show high engagement with posts about that brand. This identifies influencers with a high affinity for a product, thereby improving marketing effectiveness.

[0096] The influencer selection unit can analyze an influencer's posting times and frequency to suggest collaborations at the most effective times. For example, the generation AI can analyze an influencer's past posting times and engagement rates to identify the most effective posting times. For example, if content posted at a specific time period receives high engagement, that time period will be suggested. It can also analyze an influencer's posting frequency to suggest the optimal timing for collaboration. For example, if posting several times a week is most effective, it can suggest collaboration at that frequency. It can also analyze the online activity times of an influencer's followers to suggest collaborations at times when the most followers are online. For example, it can suggest posting at times when follower activity is at its peak. This improves engagement rates by suggesting collaborations at the most effective times.

[0097] The influencer selection unit can also evaluate the performance of video content and live streaming. For example, the generation AI analyzes the number of views and engagement rates of influencers' video content to select high-performing influencers. For example, it identifies influencers with videos that have many views and many comments and shares. It also analyzes the number of viewers and real-time engagement of influencers' live streaming to select high-performing influencers. For example, it identifies influencers with a large number of viewers during live streaming and active comments and reactions. It also comprehensively evaluates the performance of video content and live streaming to select the most effective influencer. For example, it selects influencers who show high engagement in both videos and live streaming. This enables a more comprehensive evaluation of influencers by including the performance of video content and live streaming in the evaluation.

[0098] The influencer selection unit can select influencers from a global perspective, including influencers from different cultural spheres and regions. For example, the generation AI analyzes data on influencers from different cultural spheres and regions to select the most suitable influencers from a global perspective. For example, it can list the most suitable influencers for each region, such as Asia, Europe, and America. It can also analyze the attributes and behavioral patterns of followers in different cultural spheres to select influencers according to their cultural background. For example, it can identify influencers who are popular in specific cultural spheres. In addition, to select influencers from a global perspective, it compares the performance of influencers from different regions and selects the most effective influencers. For example, it can select influencers based on engagement rates and reach in each region. This allows for selection from a global perspective, enabling international marketing strategies.

[0099] The outreach department can analyze an influencer's past collaboration history and automatically generate the most effective outreach message. For example, the generation AI analyzes an influencer's past collaboration history and extracts the characteristics of successful collaborations. Based on this, the most effective outreach message is automatically generated. For example, elements of messages that have previously received high engagement are incorporated. Customized outreach messages are also generated based on the influencer's past collaboration history. For example, messages tailored to the influencer's preferences and interests are created. The generation AI also analyzes the influencer's past collaboration history and identifies the timing and content of the most effective message. Based on this, the optimal outreach message is automatically generated. This automatically generates the most effective outreach message, improving the success rate of collaboration with influencers.

[0100] The outreach department analyzes influencers' active hours and can reach out to them at the times when they are most likely to receive a response. For example, the generation AI analyzes the influencer's past posting times and engagement rates to identify the times when they are most likely to receive a response. For example, if content posted at a specific time period receives high engagement, outreach will be carried out at that time period. The outreach department also analyzes the influencer's active hours and suggests the optimal outreach timing. For example, messages will be sent at the time when the influencer is most active. The outreach department also analyzes the online activity times of followers and carries out outreach at the time when the most followers are online. For example, messages will be sent at the time when follower activity is at its peak. This improves the influencer's response rate by outreach at the time when they are most likely to receive a response.

[0101] The outreach department can use the emotion estimation function to send customized messages according to the influencer's emotional state. For example, the generation AI analyzes the influencer's emotional state in real time and sends customized messages according to that emotion. For example, sending an encouraging message when the influencer is in a positive emotional state. The emotion estimation function can also be used to generate personalized messages based on the influencer's emotional state. For example, if the influencer is feeling stressed, a message encouraging them to relax can be sent. The outreach department can also analyze the influencer's emotional state and send customized messages at the optimal time for that state. For example, proposing collaboration when emotions are high. This improves relationships with influencers by sending customized messages according to their emotional state.

[0102] The outreach department can include personalized content based on the influencer's interests in outreach messages. For example, the generative AI can analyze the influencer's past postings and interests, and include personalized content based on that in the outreach message. For example, providing information related to topics that interest the influencer. In addition, customized content can be included in the outreach message based on the influencer's profile and follower attributes. For example, introducing products and services that the influencer's followers are interested in. In addition, the outreach message can analyze the influencer's past collaboration history, and include personalized content that incorporates elements of successful collaborations. This makes it easier to attract the influencer's attention by including personalized content based on the influencer's interests.

[0103] The outreach department can integrate different platforms (e.g., social media, email, messaging apps) to achieve multi-channel outreach. For example, a generation AI can integrate different platforms and build a system for outreach across multiple channels, such as social media, email, and messaging apps. For example, the same message can be sent simultaneously across multiple platforms. It also generates optimal outreach messages by taking into account the characteristics of each platform. For example, it can provide short messages on social media and detailed information via email. In addition, to achieve multi-channel outreach, a system can be developed that integrates data from each platform and sends unified messages. This will enable multi-channel outreach, increasing opportunities to reach influencers.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The influencer selection department selects the most suitable influencers by analyzing influencer profiles, past posts, and follower attributes. For example, the generation AI searches a database of influencers and lists the influencers who are best suited to a company's products. Step 2: The outreach department sends customized messages to the influencers selected by the influencer selection department. For example, the generation AI sends collaboration proposals to the selected influencers. Step 3: The collaboration management unit manages the collaboration schedule with influencers and analyzes progress and feedback. For example, the generative AI manages the collaboration schedule with influencers and tracks progress. Step 4: The user interface section provides a user-friendly interface, including drag-and-drop functionality and intuitive navigation. Step 5: The analytics department analyzes influencer performance and campaign effectiveness. For example, the generative AI analyzes the engagement rate, reach, and conversion rate of influencer posts and provides a detailed report to the company.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0112] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0113] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0115] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0116] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0117] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0118] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0119] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0120] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0126] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0131] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0134] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0137] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0147] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0148] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0153] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] 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.

[0165] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0166] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0167] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0171] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The influencer selection department analyzes influencer profiles, past posts, and follower attributes to select the most suitable influencers, an outreach unit that transmits customized messages to the influencers selected by the influencer selection unit; The collaboration management department manages collaboration schedules with influencers and analyzes progress and feedback. a user interface unit that provides a user-friendly interface; An analysis unit that analyzes influencer performance and campaign effectiveness. A system characterized by:

2. The influencer selection unit Emotions are estimated from the influencers' past posts, and influencers who evoke positive emotions are preferentially selected.

2. The system of claim 1.

3. The influencer selection unit Analyze the purchasing history and behavioral patterns of the influencers' followers to identify influencers who have a high affinity with the product.

2. The system of claim 1.

4. The influencer selection unit Analyze the influencer's posting times and frequency to propose collaborations at the most effective times 2. The system of claim 1.

5. The influencer selection unit The performance of video content and live streaming will also be included in the evaluation.

2. The system of claim 1.

6. The influencer selection unit Selection will be made from a global perspective, including influencers from different cultures and regions.

2. The system of claim 1.

Images