system

Abstract

The system according to the embodiment aims to develop a character by utilizing input from the viewer. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a management unit, and a control unit. The reception unit receives input from viewers. The analysis unit analyzes the input received by the reception unit. The management unit manages characters generated based on the input analyzed by the analysis unit. The control unit controls the activities of the characters managed by the management unit.

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] Existing technology does not adequately provide a system for utilizing viewer input to develop characters, and there is room for improvement.

[0005] The system according to the embodiment aims to develop a character by utilizing input from the viewer. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a management unit, and a control unit. The reception unit receives input from viewers. The analysis unit analyzes the input received by the reception unit. The management unit manages characters generated based on the input analyzed by the analysis unit. The control unit controls the activities of the characters managed by the management unit. [Effects of the Invention]

[0007] The system according to the embodiment can utilize input from viewers to develop characters. [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) A system according to an embodiment of the present invention creates an AI Vtuber that develops solely through AI input, such as personality and hobbies, during the initial setup process. The system allows the owner to configure the AI ​​Vtuber's personality and hobbies, and the AI ​​then generates the Vtuber's character based on those settings and begins its activities. The AI ​​analyzes comments and input from viewers and reflects them in the Vtuber's growth. For example, it may create new clothes or compose songs in response to viewer requests. Monetization is achieved through advertising, subscriptions, and crowdfunding. Funds obtained through subscriptions and crowdfunding can be used to further enhance the Vtuber's activities. This allows the system to provide an AI Vtuber that grows continuously based on input from the owner and viewers. For example, viewers can develop a stronger attachment to the Vtuber by having their opinions and requests reflected. Owners can also earn revenue while watching their AI Vtuber grow.

[0029] The AI ​​Vtuber system according to the embodiment includes a reception unit, an analysis unit, a management unit, and a control unit. The reception unit receives input from viewers. The input from viewers includes, but is not limited to, comments, requests, and feedback. For example, the reception unit receives comments from viewers in text format. The reception unit can also receive requests from viewers in audio format. The reception unit can also receive feedback from viewers in image format. The analysis unit analyzes the input received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to, for example. For example, the analysis unit analyzes comments from viewers using natural language processing technology. The analysis unit can also analyze requests from viewers using sentiment analysis technology. The analysis unit can also analyze feedback from viewers using data mining technology. The management unit manages characters generated based on the input analyzed by the analysis unit. The management includes, for example, but is not limited to, managing the character's personality settings and behavior patterns. For example, the management unit sets the character's personality. The management unit can also manage the behavioral patterns of the characters. The management unit can also customize the appearance of the characters. The control unit controls the activities of the characters managed by the management unit. Examples of control include, but are not limited to, managing the character's schedule and adjusting the character's performance. For example, the control unit manages the character's schedule. The control unit can also adjust the character's performance. The control unit can also change the character's activities in real time based on the viewer's reactions. As a result, the AI ​​Vtuber system according to the embodiment can accept and analyze input from viewers and control the character's management and activities, thereby allowing the AI ​​Vtuber to grow.

[0030] Furthermore, the AI ​​Vtuber system includes a revenue management unit that manages revenue. The revenue management unit manages revenue. Revenue includes, but is not limited to, advertising revenue, donations, merchandise sales, and the like. The revenue management unit tracks, for example, advertising revenue. The revenue management unit can also manage donations. The revenue management unit can also analyze revenue from merchandise sales. Thus, by including the revenue management unit, revenue management becomes possible.

[0031] The reception unit can receive comments or requests from viewers. Examples of comments or requests include, but are not limited to, text comments, audio requests, and image requests. For example, the reception unit can receive text comments from viewers. The reception unit can also receive audio requests from viewers. The reception unit can also receive image requests from viewers. In this way, receiving comments and requests from viewers can be reflected in the growth of the AI ​​Vtuber.

[0032] The analysis unit can analyze comments or requests from viewers and reflect them in the growth of the Vtuber. The analysis can be performed using, for example, natural language processing technology, sentiment analysis technology, data mining technology, etc., but is not limited to these examples. For example, the analysis unit can analyze comments from viewers using natural language processing technology. The analysis unit can also analyze requests from viewers using sentiment analysis technology. The analysis unit can also analyze feedback from viewers using data mining technology. In this way, analyzing comments and requests from viewers can be reflected in the growth of the Vtuber.

[0033] The management unit can manage the personality or hobbies of the generated character. Management of the personality or hobbies includes, but is not limited to, setting personality traits, setting the type of hobby, and managing the frequency of setting, for example. The management unit, for example, sets the personality traits of the character. The management unit can also set the type of hobby of the character. The management unit can also manage the frequency of setting the personality or hobby of the character. In this way, by managing the personality and hobbies of the generated character, consistency of the character can be maintained.

[0034] The control unit can control the Vtuber's activities and create new clothes or songs. Examples of controlling activities include, but are not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit can manage the Vtuber's schedule. The control unit can also adjust the Vtuber's performance. The control unit can also change the Vtuber's activities in real-time based on viewer reactions. Creating new clothes or songs can include, but are not limited to, design processes, song selection criteria, and production tools. For example, the control unit can design new clothes. The control unit can also select new songs. The control unit can also create new clothes or songs using production tools. This allows the Vtuber's activities to be controlled and new clothes or songs to be created in response to viewer requests.

[0035] The reception unit can analyze the viewer's past comment history and select an appropriate reception method. The analysis of the past comment history includes, for example, a storage period for the history, an analysis algorithm, and a type of history, but is not limited to these examples. The reception unit, for example, stores the viewer's past comment history and analyzes it using an analysis algorithm. The reception unit can also perform analysis based on the type of the viewer's past comment history. The selection of an appropriate reception method includes, for example, the reception timing, the type of method, and selection criteria, but is not limited to these examples. The reception unit, for example, selects an optimal reception timing based on the viewer's past comment history. The reception unit can also select an optimal reception method based on the viewer's past comment history. The reception unit can also set optimal reception criteria based on the viewer's past comment history. In this way, the optimal reception method can be selected by analyzing the viewer's past comment history.

[0036] When receiving a comment or request, the reception unit may perform filtering based on the viewer's current areas of interest. Identifying the viewer's areas of interest may include, but is not limited to, the content of past comments, viewing history, survey results, etc. For example, the reception unit may analyze the content of past comments to identify the viewer's areas of interest. The reception unit may also analyze the viewer's viewing history to identify the viewer's areas of interest. The reception unit may also analyze the viewer's survey results to identify the viewer's areas of interest. Filtering may include, but is not limited to, a filtering algorithm, a method for setting criteria, a filtering frequency, etc. For example, the reception unit may apply a filtering algorithm based on the viewer's areas of interest. The reception unit may also set filtering criteria based on the viewer's areas of interest. The reception unit may also adjust the filtering frequency based on the viewer's areas of interest. By performing filtering based on the viewer's current areas of interest, more relevant comments and requests may be received.

[0037] When accepting a comment or request, the acceptance unit can select an appropriate acceptance means depending on the viewer's input method. Viewer input methods include, but are not limited to, text input, voice input, and image input. For example, when a viewer inputs a comment or request in text, the acceptance unit accepts the comment or request using text analysis technology. Furthermore, when a viewer inputs a comment or request in voice, the acceptance unit can also accept the comment or request using voice recognition technology. Furthermore, when a viewer inputs a request in image, the acceptance unit can also accept the comment or request using image recognition technology. Selection of an appropriate acceptance means includes, but is not limited to, chatbots, form input, voice recognition systems, and the like. For example, the acceptance unit selects a chatbot depending on the viewer's input method. Furthermore, the acceptance unit can also select form input depending on the viewer's input method. Furthermore, the acceptance unit can also select a voice recognition system depending on the viewer's input method. This allows for more efficient acceptance by selecting the optimal acceptance means depending on the viewer's input method.

[0038] When receiving comments or requests, the reception unit can prioritize relevant comments based on the viewer's geographical location information. Examples of the collection of the viewer's geographical location information include, but are not limited to, GPS data, IP addresses, and the accuracy of the location information. For example, the reception unit collects the viewer's GPS data to identify the location information. The reception unit can also analyze the viewer's IP address to identify the location information. The reception unit can also prioritize relevant comments by taking into account the accuracy of the viewer's location information. Examples of the selection of relevant comments include, but are not limited to, the degree of similarity of the comment content, the viewer's areas of interest, and past history. For example, the reception unit evaluates the degree of similarity of the comment content based on the viewer's location information. The reception unit can also evaluate the relevance of the comment based on the viewer's areas of interest. The reception unit can also evaluate the relevance of the comment based on the viewer's past history. This allows more relevant comments and requests to be received by taking into account the viewer's geographical location information.

[0039] When receiving a comment or request, the reception unit can analyze the viewer's social media activity and receive related comments. Collection of the viewer's social media activity includes, but is not limited to, for example, the content of posts, the number of followers, and the engagement rate. For example, the reception unit collects the content of posts by the viewer and identifies related comments. The reception unit can also analyze the number of followers of the viewer and identify related comments. The reception unit can also evaluate the viewer's engagement rate and identify related comments. Selection of related comments includes, but is not limited to, for example, the degree of similarity of the comment content, the viewer's areas of interest, and past history. For example, the reception unit evaluates the degree of similarity of the comment content based on the viewer's social media activity. The reception unit can also evaluate the relevance of the comment based on the viewer's areas of interest. The reception unit can also evaluate the relevance of the comment based on the viewer's past history. In this way, it is possible to receive related comments and requests by analyzing the viewer's social media activity.

[0040] When receiving a comment or request, the reception unit can customize the reception method based on the viewer's past feedback. Collection of the viewer's past feedback includes, but is not limited to, survey results, comments, requests, etc. For example, the reception unit collects the viewer's survey results and identifies the feedback. The reception unit can also analyze the viewer's comments and identify the feedback. The reception unit can also evaluate the viewer's request and identify the feedback. Customization of the reception method includes, but is not limited to, the frequency of customization, a method for setting criteria, an implementation method, etc. For example, the reception unit customizes the reception method based on the viewer's past feedback. The reception unit can also adjust the frequency of customization based on the viewer's past feedback. The reception unit can also set customization criteria based on the viewer's past feedback. This makes it possible to provide a more appropriate reception method by reflecting the viewer's past feedback.

[0041] When analyzing comments or requests, the analysis unit can improve the accuracy of the analysis based on the viewer's past behavioral history. Collection of the viewer's past behavioral history includes, but is not limited to, viewing history, comment history, and request history. For example, the analysis unit collects the viewer's viewing history to improve the accuracy of the analysis. The analysis unit can also analyze the viewer's comment history to improve the accuracy of the analysis. The analysis unit can also evaluate the viewer's request history to improve the accuracy of the analysis. Improvement of the analysis accuracy includes, but is not limited to, data preprocessing methods, algorithm selection, evaluation criteria, and the like. For example, the analysis unit preprocesses data based on the viewer's past behavioral history. The analysis unit can also select an algorithm based on the viewer's past behavioral history. The analysis unit can also set evaluation criteria based on the viewer's past behavioral history. This allows the analysis accuracy to be improved by referring to the viewer's past behavioral history.

[0042] When analyzing a comment or request, the analysis unit may perform analysis based on viewer attribute information. Collected viewer attribute information may include, but is not limited to, age, gender, occupation, and interests. For example, the analysis unit may collect and analyze the viewer's age. The analysis unit may also analyze and analyze the viewer's gender. The analysis unit may also evaluate and analyze the viewer's occupation. Examples of analysis may include, but are not limited to, natural language processing technology, sentiment analysis technology, and data mining technology. For example, the analysis unit may apply natural language processing technology based on the viewer attribute information. The analysis unit may also apply sentiment analysis technology based on the viewer attribute information. The analysis unit may also apply data mining technology based on the viewer attribute information. Taking viewer attribute information into consideration enables more relevant analysis.

[0043] When analyzing comments or requests, the analysis unit can weight the analysis based on the frequency of viewer submissions. Measurement of the frequency of viewer submissions includes, but is not limited to, the frequency of comments, requests, and feedback. For example, the analysis unit measures the frequency of viewer comments and weights the analysis. The analysis unit can also analyze the frequency of viewer requests and weight the analysis. The analysis unit can also evaluate the frequency of viewer feedback and weight the analysis. Weighting includes, but is not limited to, a weighting algorithm, weighting criteria, and implementation method based on frequency. For example, the analysis unit applies a weighting algorithm based on the frequency of viewer submissions. The analysis unit can also set weighting criteria based on the frequency of viewer submissions. The analysis unit can also adjust the weighting implementation method based on the frequency of viewer submissions. As a result, weighting the analysis based on the frequency of viewer submissions enables more appropriate analysis.

[0044] When analyzing comments or requests, the analysis unit may perform analysis based on the geographical distribution of viewers. Examples of collecting the geographical distribution of viewers include, but are not limited to, GPS data, IP addresses, and location information accuracy. For example, the analysis unit may collect GPS data of viewers to identify their geographical distribution. The analysis unit may also analyze IP addresses of viewers to identify their geographical distribution. The analysis unit may also perform analysis taking into account the accuracy of the viewer's location information. Examples of analysis include, but are not limited to, natural language processing technology, sentiment analysis technology, and data mining technology. For example, the analysis unit may apply natural language processing technology based on the geographical distribution of viewers. The analysis unit may also apply sentiment analysis technology based on the geographical distribution of viewers. The analysis unit may also apply data mining technology based on the geographical distribution of viewers. This enables more relevant analysis by taking into account the geographical distribution of viewers.

[0045] When analyzing a comment or request, the analysis unit can improve the accuracy of the analysis based on related literature. Examples of related literature include, but are not limited to, academic papers, technical reports, and patent documents. For example, the analysis unit may perform the analysis by referring to academic papers related to the content of the comment or request. The analysis unit may also perform the analysis by referring to news articles related to the content of the comment or request. The analysis unit may also perform the analysis by referring to specialized books related to the content of the comment or request. Examples of ways to improve the accuracy of the analysis include, but are not limited to, data preprocessing methods, algorithm selection, and evaluation criteria. For example, the analysis unit may perform data preprocessing based on related literature. The analysis unit may also select an algorithm based on related literature. The analysis unit may also set evaluation criteria based on related literature. By referring to related literature, the accuracy of the analysis can be improved.

[0046] When analyzing comments or requests, the analysis unit may perform an analysis based on the market value of the viewer. Evaluations of the viewer's market value include, but are not limited to, purchasing power, influence, and consumption behavior. For example, the analysis unit may evaluate and analyze the viewer's purchasing power. The analysis unit may also analyze and analyze the viewer's influence. The analysis unit may also evaluate and analyze the viewer's consumption behavior. For example, the analysis may include, but is not limited to, natural language processing technology, sentiment analysis technology, data mining technology, and the like. For example, the analysis unit may apply natural language processing technology based on the viewer's market value. The analysis unit may also apply sentiment analysis technology based on the viewer's market value. The analysis unit may also apply data mining technology based on the viewer's market value. This enables more effective analysis by taking the viewer's market value into consideration.

[0047] The management unit can improve the accuracy of management based on the viewer's past input when managing the character's personality or hobbies. Collection of the viewer's past input includes, but is not limited to, for example, comment history, request history, and feedback history. For example, the management unit collects the viewer's comment history to improve the accuracy of management. The management unit can also analyze the viewer's request history to improve the accuracy of management. The management unit can also evaluate the viewer's feedback history to improve the accuracy of management. Improvement of the accuracy of management can include, but is not limited to, for example, a data preprocessing method, selection of an algorithm, evaluation criteria, etc. For example, the management unit preprocesses data based on the viewer's past input. The management unit can also select an algorithm based on the viewer's past input. The management unit can also set evaluation criteria based on the viewer's past input. This allows the accuracy of management to be improved by referring to the viewer's past input.

[0048] The management unit can manage the character's personality or hobbies based on the viewer's attribute information. The collected viewer's attribute information includes, but is not limited to, age, gender, occupation, and interests. For example, the management unit collects and manages the viewer's age. The management unit can also analyze and manage the viewer's gender. The management unit can also evaluate and manage the viewer's occupation. The management includes, but is not limited to, personality setting, behavior patterns, and appearance customization. For example, the management unit sets the personality based on the viewer's attribute information. The management unit can also set behavior patterns based on the viewer's attribute information. The management unit can also customize the appearance based on the viewer's attribute information. This enables more appropriate character management by taking the viewer's attribute information into consideration.

[0049] When managing a character's personality or hobbies, the management unit may assign a management weight based on the frequency of viewer input. Measurement of the frequency of viewer input includes, but is not limited to, the frequency of comments, requests, and feedback. For example, the management unit may measure the frequency of viewer comments and assign a management weight. The management unit may also analyze the frequency of viewer requests and assign a management weight. The management unit may also evaluate the frequency of viewer feedback and assign a management weight. Weighting may include, but is not limited to, a weighting algorithm, weighting criteria, and implementation method based on frequency. For example, the management unit may apply a weighting algorithm based on the frequency of viewer input. The management unit may also set weighting criteria based on the frequency of viewer input. The management unit may also adjust the weighting implementation method based on the frequency of viewer input. This enables more appropriate character management by assigning management weights based on the frequency of viewer input.

[0050] The management unit may manage the character's personality or hobbies based on the geographical distribution of viewers. Examples of collecting the viewer's geographical distribution include, but are not limited to, GPS data, IP addresses, and the accuracy of location information. For example, the management unit may collect the viewer's GPS data to identify the geographical distribution. The management unit may also analyze the viewer's IP address to identify the geographical distribution. The management unit may also perform management taking into account the accuracy of the viewer's location information. Examples of management include, but are not limited to, setting the character's personality, behavioral patterns, and customizing the character's appearance. For example, the management unit may set the character's personality based on the viewer's geographical distribution. The management unit may also set the behavioral patterns based on the viewer's geographical distribution. The management unit may also customize the character's appearance based on the viewer's geographical distribution. This enables more appropriate character management by taking into account the viewer's geographical distribution.

[0051] The management unit can improve the accuracy of management based on related literature when managing a character's personality or hobbies. Examples of related literature include, but are not limited to, academic papers, technical reports, and patent documents. For example, the management unit can perform management by referring to academic papers related to the character's personality or hobbies. The management unit can also perform management by referring to news articles related to the character's personality or hobbies. The management unit can also perform management by referring to specialized books related to the character's personality or hobbies. Examples of improving the accuracy of management include, but are not limited to, data preprocessing methods, algorithm selection, and evaluation criteria. For example, the management unit can perform data preprocessing based on related literature. The management unit can also select an algorithm based on related literature. The management unit can also set evaluation criteria based on related literature. By doing so, the accuracy of management can be improved by referring to related literature.

[0052] The management unit may manage the character's personality or hobbies based on the viewer's market value. Evaluation of the viewer's market value may include, but is not limited to, purchasing power, influence, consumption behavior, etc. For example, the management unit may evaluate and manage the viewer's purchasing power. The management unit may also analyze and manage the viewer's influence. The management unit may also evaluate and manage the viewer's consumption behavior. Management may include, but is not limited to, personality setting, behavior patterns, and appearance customization, for example. For example, the management unit may set the personality based on the viewer's market value. The management unit may also set behavior patterns based on the viewer's market value. The management unit may also customize the appearance based on the viewer's market value. This enables more effective character management by taking the viewer's market value into consideration.

[0053] When controlling the activities of a Vtuber, the control unit can improve the accuracy of the control based on past viewer input. Collection of past viewer input includes, but is not limited to, comment history, request history, and feedback history. For example, the control unit collects viewer comment history to improve the accuracy of the control. The control unit can also analyze viewer request history to improve the accuracy of the control. The control unit can also evaluate viewer feedback history to improve the accuracy of the control. Improvement of the accuracy of the control includes, but is not limited to, data preprocessing methods, algorithm selection, evaluation criteria, and the like. For example, the control unit preprocesses data based on the viewer's past input. The control unit can also select an algorithm based on the viewer's past input. The control unit can also set evaluation criteria based on the viewer's past input. This allows the accuracy of the control to be improved by referring to the viewer's past input.

[0054] When controlling the activities of a Vtuber, the control unit can perform control based on viewer attribute information. Collected viewer attribute information includes, but is not limited to, age, gender, occupation, and interests. For example, the control unit collects and controls the viewer's age. The control unit can also analyze and control the viewer's gender. The control unit can also evaluate and control the viewer's occupation. Examples of control include, but are not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit manages schedules based on the viewer attribute information. The control unit can also adjust performances based on the viewer attribute information. The control unit can also make real-time changes based on the viewer attribute information. This enables more appropriate activity control by taking viewer attribute information into consideration.

[0055] When controlling the activities of a Vtuber, the control unit can weight the control based on the frequency of viewer input. Measurement of the frequency of viewer input includes, but is not limited to, the frequency of comments, requests, and feedback. For example, the control unit measures the frequency of viewer comments and weights the control. The control unit can also analyze the frequency of viewer requests and weight the control. The control unit can also evaluate the frequency of viewer feedback and weight the control. Weighting includes, but is not limited to, a weighting algorithm, weighting criteria, and implementation method based on frequency. For example, the control unit applies a weighting algorithm based on the frequency of viewer input. The control unit can also set weighting criteria based on the frequency of viewer input. The control unit can also adjust the weighting implementation method based on the frequency of viewer input. As a result, weighting the control based on the frequency of viewer input enables more appropriate activity control.

[0056] When controlling the activities of a Vtuber, the control unit can perform control based on the geographical distribution of viewers. Examples of collecting the geographical distribution of viewers include, but are not limited to, GPS data, IP addresses, and the accuracy of location information. For example, the control unit can collect GPS data of viewers to identify their geographical distribution. The control unit can also analyze the IP addresses of viewers to identify their geographical distribution. The control unit can also perform control taking into account the accuracy of the viewer's location information. Examples of control include, but are not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit can perform schedule management based on the geographical distribution of viewers. The control unit can also adjust performances based on the geographical distribution of viewers. The control unit can also make real-time changes based on the geographical distribution of viewers. This enables more appropriate activity control by taking into account the geographical distribution of viewers.

[0057] When controlling the activities of a Vtuber, the control unit can improve the accuracy of the control based on related literature. Examples of related literature include, but are not limited to, academic papers, technical reports, and patent documents. For example, the control unit performs control by referring to academic papers related to the Vtuber's activities. The control unit can also perform control by referring to news articles related to the Vtuber's activities. The control unit can also perform control by referring to specialized books related to the Vtuber's activities. Examples of improving the accuracy of the control include, but are not limited to, data preprocessing methods, algorithm selection, and evaluation criteria. For example, the control unit performs data preprocessing based on related literature. The control unit can also select an algorithm based on related literature. The control unit can also set evaluation criteria based on related literature. By referring to related literature, the accuracy of the control can be improved.

[0058] When controlling the activities of a Vtuber, the control unit can perform control based on the market value of viewers. Evaluations of viewer market value include, for example, purchasing power, influence, and consumption behavior, but are not limited to these examples. The control unit, for example, evaluates and controls the purchasing power of viewers. The control unit can also analyze and control the influence of viewers. The control unit can also evaluate and control the consumption behavior of viewers. Control includes, for example, schedule management, performance adjustment, and real-time changes based on viewer reactions, but are not limited to these examples. The control unit, for example, performs schedule management based on the market value of viewers. The control unit can also adjust performance based on the market value of viewers. The control unit can also make real-time changes based on the market value of viewers. This enables more effective activity control by taking viewer market value into consideration.

[0059] During revenue management, the revenue management unit can analyze the viewer's past consumption behavior and select an appropriate revenue management method. Collecting the viewer's past consumption behavior includes, but is not limited to, purchase history, consumption patterns, and expenditures. For example, the revenue management unit collects the viewer's purchase history and selects a revenue management method. The revenue management unit can also analyze the viewer's consumption patterns and select a revenue management method. The revenue management unit can also evaluate the viewer's expenditures and select a revenue management method. The selection of a revenue management method includes, but is not limited to, the type of revenue, management method selection criteria, and implementation method. For example, the revenue management unit selects a revenue management method based on the viewer's past consumption behavior. The revenue management unit can also set selection criteria based on the viewer's past consumption behavior. The revenue management unit can also adjust the implementation method based on the viewer's past consumption behavior. In this way, the optimal revenue management method can be selected by analyzing the viewer's past consumption behavior.

[0060] During revenue management, the revenue management unit can customize revenue management measures based on the viewer's current living situation. Collection of the viewer's living situation includes, but is not limited to, income, family structure, and lifestyle habits. For example, the revenue management unit collects the viewer's income and customizes the revenue management measures. The revenue management unit can also analyze the viewer's family structure and customize the revenue management measures. The revenue management unit can also evaluate the viewer's lifestyle habits and customize the revenue management measures. Customization of the revenue management measures includes, but is not limited to, the frequency of customization, a method for setting standards, and an implementation method. For example, the revenue management unit customizes the revenue management measures based on the viewer's living situation. The revenue management unit can also adjust the frequency of customization based on the viewer's living situation. The revenue management unit can also set customization standards based on the viewer's living situation. This enables more appropriate revenue management by customizing the revenue management measures based on the viewer's current living situation.

[0061] The revenue management unit can improve the revenue management method by reflecting viewer feedback during revenue management. Examples of collecting viewer feedback include, but are not limited to, survey results, comments, and requests. For example, the revenue management unit can collect viewer survey results and identify feedback. The revenue management unit can also analyze viewer comments and identify feedback. The revenue management unit can also evaluate viewer requests and identify feedback. Examples of improving the revenue management method include, but are not limited to, the frequency of improvement, a method for setting standards, and an implementation method. For example, the revenue management unit can improve the revenue management method based on viewer feedback. The revenue management unit can also adjust the frequency of improvement based on viewer feedback. The revenue management unit can also set standards for improvement based on viewer feedback. This allows the revenue management method to be continuously improved by reflecting viewer feedback.

[0062] During revenue management, the revenue management unit can select an appropriate revenue management method based on the viewer's geographical location information. Examples of the collection of viewer's geographical location information include, but are not limited to, GPS data, IP addresses, and location information accuracy. For example, the revenue management unit collects viewer's GPS data to identify the geographical location information. The revenue management unit can also analyze the viewer's IP address to identify the geographical location information. The revenue management unit can also select a revenue management method taking into account the accuracy of the viewer's location information. Examples of the selection of a revenue management method include, but are not limited to, the type of revenue, management method selection criteria, and implementation method. For example, the revenue management unit selects a revenue management method based on the viewer's geographical location information. The revenue management unit can also set selection criteria based on the viewer's geographical location information. The revenue management unit can also adjust the implementation method based on the viewer's geographical location information. This enables more appropriate revenue management by taking into account the viewer's geographical location information.

[0063] During revenue management, the revenue management unit may analyze viewers' social media activities and propose revenue management measures. Collecting viewers' social media activities may include, but is not limited to, for example, content of posts, number of followers, and engagement rate. For example, the revenue management unit may collect viewers' posts and propose revenue management measures. The revenue management unit may also analyze the number of viewers' followers and propose revenue management measures. The revenue management unit may also evaluate viewers' engagement rate and propose revenue management measures. Proposing revenue management measures may include, but is not limited to, for example, frequency of proposals, method of setting criteria, and implementation method. For example, the revenue management unit may propose revenue management measures based on viewers' social media activities. The revenue management unit may also adjust the frequency of proposals based on viewers' social media activities. The revenue management unit may also set criteria for proposals based on viewers' social media activities. This allows optimal revenue management measures to be proposed by analyzing viewers' social media activities.

[0064] During revenue management, the revenue management unit can customize the revenue management method based on past viewer feedback. Examples of collecting past viewer feedback include, but are not limited to, survey results, comments, and requests. For example, the revenue management unit can collect viewer survey results and identify feedback. The revenue management unit can also analyze viewer comments and identify feedback. The revenue management unit can also evaluate viewer requests and identify feedback. Examples of customizing the revenue management method include, but are not limited to, the frequency of customization, a method for setting standards, and an implementation method. For example, the revenue management unit customizes the revenue management method based on, for example, past viewer feedback. The revenue management unit can also adjust the frequency of customization based on the viewer's past feedback. The revenue management unit can also set customization standards based on the viewer's past feedback. This enables more appropriate revenue management by reflecting the viewer's past feedback.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] When analyzing a viewer's comments or requests, the analysis unit can refer to the viewer's past behavioral history. For example, it can analyze what kind of comments the viewer has left in the past and what kind of requests they have made, and use that information to more accurately understand the intention behind the current comment or request. It can also estimate the viewer's interests and concerns based on the viewer's past behavioral history, allowing for more personalized responses. Furthermore, it can predict the viewer's behavioral patterns based on the viewer's past behavioral history, and identify trends in future requests and comments. This makes it possible to perform more accurate analysis by referring to the viewer's past behavioral history.

[0067] The management unit can take into account the viewer's attribute information when managing the character's personality and hobbies. For example, the character's personality and hobbies can be set based on the viewer's attribute information, such as age, gender, and occupation. The character's behavior pattern can also be adjusted based on the viewer's attribute information. Furthermore, the character's appearance can also be customized based on the viewer's attribute information. In this way, by taking the viewer's attribute information into consideration, it is possible to provide a character that is more familiar to the viewer.

[0068] The control unit can take into account the geographical distribution of viewers when controlling the activities of Vtubers. For example, it can adjust the Vtuber's activity time based on the viewer's place of residence. It can also provide content targeted to specific regions based on the viewer's geographical distribution. It can also plan events and campaigns for each region based on the viewer's geographical distribution. This allows for activities that are more closely tied to the local area by taking the viewer's geographical distribution into account.

[0069] The revenue management department can analyze viewers' social media activity and propose revenue management measures. For example, it can propose optimal advertising strategies based on viewers' posts, number of followers, and engagement rates. It can also identify target demographics for crowdfunding based on viewers' social media activity. It can also propose merchandise sales promotion methods based on viewers' social media activity. This allows for more effective revenue management by analyzing viewers' social media activity.

[0070] The reception unit can analyze the viewer's past comment history and select an appropriate reception method. For example, it can analyze what kind of comments the viewer has left in the past and select the optimal reception timing based on that information. It can also select the optimal reception method based on the viewer's past comment history. Furthermore, it can set optimal reception criteria based on the viewer's past comment history. In this way, it is possible to select the optimal reception method by analyzing the viewer's past comment history.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The reception unit receives input from viewers. The input from viewers includes comments, requests, feedback, etc. For example, the reception unit can receive comments from viewers in text format, requests in audio format, and feedback in image format. Step 2: The analysis unit analyzes the input received by the reception unit. The analysis is performed using natural language processing technology, sentiment analysis technology, data mining technology, etc. For example, the analysis unit can analyze comments from viewers using natural language processing technology, analyze requests using sentiment analysis technology, and analyze feedback using data mining technology. Step 3: The management unit manages the characters generated based on the input analyzed by the analysis unit. Management includes setting the character's personality, managing behavior patterns, customizing appearance, etc. For example, the management unit can set the character's personality, manage behavior patterns, and customize appearance. Step 4: The control unit controls the activities of the characters managed by the management unit. The control includes managing the character's schedule, adjusting performance, and changing the character's activities in real time based on the viewer's reaction. For example, the control unit can manage the character's schedule, adjust performance, and change the character's activities in real time based on the viewer's reaction.

[0073] (Example 2) A system according to an embodiment of the present invention creates an AI Vtuber that develops solely through AI input, such as personality and hobbies, during the initial setup process. The system allows the owner to configure the AI ​​Vtuber's personality and hobbies, and the AI ​​then generates the Vtuber's character based on those settings and begins its activities. The AI ​​analyzes comments and input from viewers and reflects them in the Vtuber's growth. For example, it may create new clothes or compose songs in response to viewer requests. Monetization is achieved through advertising, subscriptions, and crowdfunding. Funds obtained through subscriptions and crowdfunding can be used to further enhance the Vtuber's activities. This allows the system to provide an AI Vtuber that grows continuously based on input from the owner and viewers. For example, viewers can develop a stronger attachment to the Vtuber by having their opinions and requests reflected. Owners can also earn revenue while watching their AI Vtuber grow.

[0074] The AI ​​Vtuber system according to the embodiment includes a reception unit, an analysis unit, a management unit, and a control unit. The reception unit receives input from viewers. The input from viewers includes, but is not limited to, comments, requests, and feedback. For example, the reception unit receives comments from viewers in text format. The reception unit can also receive requests from viewers in audio format. The reception unit can also receive feedback from viewers in image format. The analysis unit analyzes the input received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to, for example. For example, the analysis unit analyzes comments from viewers using natural language processing technology. The analysis unit can also analyze requests from viewers using sentiment analysis technology. The analysis unit can also analyze feedback from viewers using data mining technology. The management unit manages characters generated based on the input analyzed by the analysis unit. The management includes, for example, but is not limited to, managing the character's personality settings and behavior patterns. For example, the management unit sets the character's personality. The management unit can also manage the behavioral patterns of the characters. The management unit can also customize the appearance of the characters. The control unit controls the activities of the characters managed by the management unit. Examples of control include, but are not limited to, managing the character's schedule and adjusting the character's performance. For example, the control unit manages the character's schedule. The control unit can also adjust the character's performance. The control unit can also change the character's activities in real time based on the viewer's reactions. As a result, the AI ​​Vtuber system according to the embodiment can accept and analyze input from viewers and control the character's management and activities, thereby allowing the AI ​​Vtuber to grow.

[0075] Furthermore, the AI ​​Vtuber system includes a revenue management unit that manages revenue. The revenue management unit manages revenue. Revenue includes, but is not limited to, advertising revenue, donations, merchandise sales, and the like. The revenue management unit tracks, for example, advertising revenue. The revenue management unit can also manage donations. The revenue management unit can also analyze revenue from merchandise sales. Thus, by including the revenue management unit, revenue management becomes possible.

[0076] The reception unit can receive comments or requests from viewers. Examples of comments or requests include, but are not limited to, text comments, audio requests, and image requests. For example, the reception unit can receive text comments from viewers. The reception unit can also receive audio requests from viewers. The reception unit can also receive image requests from viewers. In this way, receiving comments and requests from viewers can be reflected in the growth of the AI ​​Vtuber.

[0077] The analysis unit can analyze comments or requests from viewers and reflect them in the growth of the Vtuber. The analysis can be performed using, for example, natural language processing technology, sentiment analysis technology, data mining technology, etc., but is not limited to these examples. For example, the analysis unit can analyze comments from viewers using natural language processing technology. The analysis unit can also analyze requests from viewers using sentiment analysis technology. The analysis unit can also analyze feedback from viewers using data mining technology. In this way, analyzing comments and requests from viewers can be reflected in the growth of the Vtuber.

[0078] The management unit can manage the personality or hobbies of the generated character. Management of the personality or hobbies includes, but is not limited to, setting personality traits, setting the type of hobby, and managing the frequency of setting, for example. The management unit, for example, sets the personality traits of the character. The management unit can also set the type of hobby of the character. The management unit can also manage the frequency of setting the personality or hobby of the character. In this way, by managing the personality and hobbies of the generated character, consistency of the character can be maintained.

[0079] The control unit can control the Vtuber's activities and create new clothes or songs. Examples of controlling activities include, but are not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit can manage the Vtuber's schedule. The control unit can also adjust the Vtuber's performance. The control unit can also change the Vtuber's activities in real-time based on viewer reactions. Creating new clothes or songs can include, but are not limited to, design processes, song selection criteria, and production tools. For example, the control unit can design new clothes. The control unit can also select new songs. The control unit can also create new clothes or songs using production tools. This allows the Vtuber's activities to be controlled and new clothes or songs to be created in response to viewer requests.

[0080] The reception unit can estimate the viewer's emotions and determine the priority of comments or requests based on the estimated viewer's emotions. Estimating the viewer's emotions can include, but is not limited to, an emotion analysis algorithm, a type of emotion, and estimation accuracy. For example, the reception unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The reception unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Determining the priority can include, but is not limited to, the intensity of the emotion, the viewer's influence, and the importance of the request. For example, the reception unit can determine the priority of comments or requests based on the intensity of the viewer's emotions. The reception unit can also determine the priority of comments or requests based on the viewer's influence. The reception unit can also determine the priority of comments or requests based on the importance of the request. This enables more appropriate responses by determining the priority of comments or requests based on the viewer's emotions.

[0081] The reception unit can analyze the viewer's past comment history and select an appropriate reception method. The analysis of the past comment history includes, for example, a storage period for the history, an analysis algorithm, and a type of history, but is not limited to these examples. The reception unit, for example, stores the viewer's past comment history and analyzes it using an analysis algorithm. The reception unit can also perform analysis based on the type of the viewer's past comment history. The selection of an appropriate reception method includes, for example, the reception timing, the type of method, and selection criteria, but is not limited to these examples. The reception unit, for example, selects an optimal reception timing based on the viewer's past comment history. The reception unit can also select an optimal reception method based on the viewer's past comment history. The reception unit can also set optimal reception criteria based on the viewer's past comment history. In this way, the optimal reception method can be selected by analyzing the viewer's past comment history.

[0082] When receiving a comment or request, the reception unit may perform filtering based on the viewer's current areas of interest. Identifying the viewer's areas of interest may include, but is not limited to, the content of past comments, viewing history, survey results, etc. For example, the reception unit may analyze the content of past comments to identify the viewer's areas of interest. The reception unit may also analyze the viewer's viewing history to identify the viewer's areas of interest. The reception unit may also analyze the viewer's survey results to identify the viewer's areas of interest. Filtering may include, but is not limited to, a filtering algorithm, a method for setting criteria, a filtering frequency, etc. For example, the reception unit may apply a filtering algorithm based on the viewer's areas of interest. The reception unit may also set filtering criteria based on the viewer's areas of interest. The reception unit may also adjust the filtering frequency based on the viewer's areas of interest. By performing filtering based on the viewer's current areas of interest, more relevant comments and requests may be received.

[0083] When accepting a comment or request, the acceptance unit can select an appropriate acceptance means depending on the viewer's input method. Viewer input methods include, but are not limited to, text input, voice input, and image input. For example, when a viewer inputs a comment or request in text, the acceptance unit accepts the comment or request using text analysis technology. Furthermore, when a viewer inputs a comment or request in voice, the acceptance unit can also accept the comment or request using voice recognition technology. Furthermore, when a viewer inputs a request in image, the acceptance unit can also accept the comment or request using image recognition technology. Selection of an appropriate acceptance means includes, but is not limited to, chatbots, form input, voice recognition systems, and the like. For example, the acceptance unit selects a chatbot depending on the viewer's input method. Furthermore, the acceptance unit can also select form input depending on the viewer's input method. Furthermore, the acceptance unit can also select a voice recognition system depending on the viewer's input method. This allows for more efficient acceptance by selecting the optimal acceptance means depending on the viewer's input method.

[0084] The reception unit can estimate the viewer's emotions and adjust the display method of the received comment or request based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, an emotion analysis algorithm, a type of emotion, and estimation accuracy. For example, the reception unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The reception unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Adjusting the display method includes, but is not limited to, display timing, display format, and adjustment criteria. For example, the reception unit can adjust the display method of the comment or request based on the intensity of the viewer's emotions. The reception unit can also adjust the display method of the comment or request based on the viewer's influence. The reception unit can also adjust the display method of the comment or request based on the importance of the request. Adjusting the display method based on the viewer's emotions makes it easier to attract the viewer's attention.

[0085] When receiving comments or requests, the reception unit can prioritize relevant comments based on the viewer's geographical location information. Examples of the collection of the viewer's geographical location information include, but are not limited to, GPS data, IP addresses, and the accuracy of the location information. For example, the reception unit collects the viewer's GPS data to identify the location information. The reception unit can also analyze the viewer's IP address to identify the location information. The reception unit can also prioritize relevant comments by taking into account the accuracy of the viewer's location information. Examples of the selection of relevant comments include, but are not limited to, the degree of similarity of the comment content, the viewer's areas of interest, and past history. For example, the reception unit evaluates the degree of similarity of the comment content based on the viewer's location information. The reception unit can also evaluate the relevance of the comment based on the viewer's areas of interest. The reception unit can also evaluate the relevance of the comment based on the viewer's past history. This allows more relevant comments and requests to be received by taking into account the viewer's geographical location information.

[0086] When receiving a comment or request, the reception unit can analyze the viewer's social media activity and receive related comments. Collection of the viewer's social media activity includes, but is not limited to, for example, the content of posts, the number of followers, and the engagement rate. For example, the reception unit collects the content of posts by the viewer and identifies related comments. The reception unit can also analyze the number of followers of the viewer and identify related comments. The reception unit can also evaluate the viewer's engagement rate and identify related comments. Selection of related comments includes, but is not limited to, for example, the degree of similarity of the comment content, the viewer's areas of interest, and past history. For example, the reception unit evaluates the degree of similarity of the comment content based on the viewer's social media activity. The reception unit can also evaluate the relevance of the comment based on the viewer's areas of interest. The reception unit can also evaluate the relevance of the comment based on the viewer's past history. In this way, it is possible to receive related comments and requests by analyzing the viewer's social media activity.

[0087] When receiving a comment or request, the reception unit can customize the reception method based on the viewer's past feedback. Collection of the viewer's past feedback includes, but is not limited to, survey results, comments, requests, etc. For example, the reception unit collects the viewer's survey results and identifies the feedback. The reception unit can also analyze the viewer's comments and identify the feedback. The reception unit can also evaluate the viewer's request and identify the feedback. Customization of the reception method includes, but is not limited to, the frequency of customization, a method for setting criteria, an implementation method, etc. For example, the reception unit customizes the reception method based on the viewer's past feedback. The reception unit can also adjust the frequency of customization based on the viewer's past feedback. The reception unit can also set customization criteria based on the viewer's past feedback. This makes it possible to provide a more appropriate reception method by reflecting the viewer's past feedback.

[0088] The analysis unit can estimate the viewer's emotions and determine the analysis priority based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, examples of an emotion analysis algorithm, a type of emotion, and estimation accuracy. For example, the analysis unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The analysis unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Determining the priority includes, but is not limited to, examples of the intensity of the emotion, the viewer's influence, and the importance of the request. For example, the analysis unit can determine the analysis priority of the comments and requests based on the intensity of the viewer's emotions. The analysis unit can also determine the analysis priority of the comments and requests based on the viewer's influence. The analysis unit can also determine the analysis priority of the comments and requests based on the importance of the request. This enables more appropriate analysis by determining the analysis priority based on the viewer's emotions.

[0089] When analyzing comments or requests, the analysis unit can improve the accuracy of the analysis based on the viewer's past behavioral history. Collection of the viewer's past behavioral history includes, but is not limited to, viewing history, comment history, and request history. For example, the analysis unit collects the viewer's viewing history to improve the accuracy of the analysis. The analysis unit can also analyze the viewer's comment history to improve the accuracy of the analysis. The analysis unit can also evaluate the viewer's request history to improve the accuracy of the analysis. Improvement of the analysis accuracy includes, but is not limited to, data preprocessing methods, algorithm selection, evaluation criteria, and the like. For example, the analysis unit preprocesses data based on the viewer's past behavioral history. The analysis unit can also select an algorithm based on the viewer's past behavioral history. The analysis unit can also set evaluation criteria based on the viewer's past behavioral history. This allows the analysis accuracy to be improved by referring to the viewer's past behavioral history.

[0090] When analyzing a comment or request, the analysis unit may perform analysis based on viewer attribute information. Collected viewer attribute information may include, but is not limited to, age, gender, occupation, and interests. For example, the analysis unit may collect and analyze the viewer's age. The analysis unit may also analyze and analyze the viewer's gender. The analysis unit may also evaluate and analyze the viewer's occupation. Examples of analysis may include, but are not limited to, natural language processing technology, sentiment analysis technology, and data mining technology. For example, the analysis unit may apply natural language processing technology based on the viewer attribute information. The analysis unit may also apply sentiment analysis technology based on the viewer attribute information. The analysis unit may also apply data mining technology based on the viewer attribute information. Taking viewer attribute information into consideration enables more relevant analysis.

[0091] When analyzing comments or requests, the analysis unit can weight the analysis based on the frequency of viewer submissions. Measurement of the frequency of viewer submissions includes, but is not limited to, the frequency of comments, requests, and feedback. For example, the analysis unit measures the frequency of viewer comments and weights the analysis. The analysis unit can also analyze the frequency of viewer requests and weight the analysis. The analysis unit can also evaluate the frequency of viewer feedback and weight the analysis. Weighting includes, but is not limited to, a weighting algorithm, weighting criteria, and implementation method based on frequency. For example, the analysis unit applies a weighting algorithm based on the frequency of viewer submissions. The analysis unit can also set weighting criteria based on the frequency of viewer submissions. The analysis unit can also adjust the weighting implementation method based on the frequency of viewer submissions. As a result, weighting the analysis based on the frequency of viewer submissions enables more appropriate analysis.

[0092] The analysis unit can estimate the viewer's emotions and adjust the display method of the analysis results based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, an emotion analysis algorithm, a type of emotion, and estimation accuracy. For example, the analysis unit can analyze viewer comments using an emotion analysis algorithm to estimate the viewer's emotions. The analysis unit can also analyze viewer requests using an emotion analysis algorithm to estimate the viewer's emotions. Adjusting the display method includes, but is not limited to, the timing of display, the display format, and adjustment criteria. For example, the analysis unit can adjust the display method of the analysis results based on the intensity of the viewer's emotions. The analysis unit can also adjust the display method of the analysis results based on the viewer's influence. The analysis unit can also adjust the display method of the analysis results based on the importance of the request. Adjusting the display method based on the viewer's emotions makes it easier to attract the viewer's attention.

[0093] When analyzing comments or requests, the analysis unit may perform analysis based on the geographical distribution of viewers. Examples of collecting the geographical distribution of viewers include, but are not limited to, GPS data, IP addresses, and location information accuracy. For example, the analysis unit may collect GPS data of viewers to identify their geographical distribution. The analysis unit may also analyze IP addresses of viewers to identify their geographical distribution. The analysis unit may also perform analysis taking into account the accuracy of the viewer's location information. Examples of analysis include, but are not limited to, natural language processing technology, sentiment analysis technology, and data mining technology. For example, the analysis unit may apply natural language processing technology based on the geographical distribution of viewers. The analysis unit may also apply sentiment analysis technology based on the geographical distribution of viewers. The analysis unit may also apply data mining technology based on the geographical distribution of viewers. This enables more relevant analysis by taking into account the geographical distribution of viewers.

[0094] When analyzing a comment or request, the analysis unit can improve the accuracy of the analysis based on related literature. Examples of related literature include, but are not limited to, academic papers, technical reports, and patent documents. For example, the analysis unit may perform the analysis by referring to academic papers related to the content of the comment or request. The analysis unit may also perform the analysis by referring to news articles related to the content of the comment or request. The analysis unit may also perform the analysis by referring to specialized books related to the content of the comment or request. Examples of ways to improve the accuracy of the analysis include, but are not limited to, data preprocessing methods, algorithm selection, and evaluation criteria. For example, the analysis unit may perform data preprocessing based on related literature. The analysis unit may also select an algorithm based on related literature. The analysis unit may also set evaluation criteria based on related literature. By referring to related literature, the accuracy of the analysis can be improved.

[0095] When analyzing comments or requests, the analysis unit may perform an analysis based on the market value of the viewer. Evaluations of the viewer's market value include, but are not limited to, purchasing power, influence, and consumption behavior. For example, the analysis unit may evaluate and analyze the viewer's purchasing power. The analysis unit may also analyze and analyze the viewer's influence. The analysis unit may also evaluate and analyze the viewer's consumption behavior. For example, the analysis may include, but is not limited to, natural language processing technology, sentiment analysis technology, data mining technology, and the like. For example, the analysis unit may apply natural language processing technology based on the viewer's market value. The analysis unit may also apply sentiment analysis technology based on the viewer's market value. The analysis unit may also apply data mining technology based on the viewer's market value. This enables more effective analysis by taking the viewer's market value into consideration.

[0096] The management unit can estimate the viewer's emotions and adjust the character's personality or hobby management method based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, an emotion analysis algorithm, a type of emotion, and estimation accuracy. For example, the management unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The management unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Adjusting the management method can include, but is not limited to, the frequency of adjustment, a method for setting standards, and a method for implementing the adjustment. For example, the management unit can adjust the character's personality or hobby management method based on the intensity of the viewer's emotions. The management unit can also adjust the character's personality or hobby management method based on the viewer's influence. The management unit can also adjust the character's personality or hobby management method based on the importance of the request. This enables more appropriate character management by adjusting the character's personality or hobby management method based on the viewer's emotions.

[0097] The management unit can improve the accuracy of management based on the viewer's past input when managing the character's personality or hobbies. Collection of the viewer's past input includes, but is not limited to, for example, comment history, request history, and feedback history. For example, the management unit collects the viewer's comment history to improve the accuracy of management. The management unit can also analyze the viewer's request history to improve the accuracy of management. The management unit can also evaluate the viewer's feedback history to improve the accuracy of management. Improvement of the accuracy of management can include, but is not limited to, for example, a data preprocessing method, selection of an algorithm, evaluation criteria, etc. For example, the management unit preprocesses data based on the viewer's past input. The management unit can also select an algorithm based on the viewer's past input. The management unit can also set evaluation criteria based on the viewer's past input. This allows the accuracy of management to be improved by referring to the viewer's past input.

[0098] The management unit can manage the character's personality or hobbies based on the viewer's attribute information. The collected viewer's attribute information includes, but is not limited to, age, gender, occupation, and interests. For example, the management unit collects and manages the viewer's age. The management unit can also analyze and manage the viewer's gender. The management unit can also evaluate and manage the viewer's occupation. The management includes, but is not limited to, personality setting, behavior patterns, and appearance customization. For example, the management unit sets the personality based on the viewer's attribute information. The management unit can also set behavior patterns based on the viewer's attribute information. The management unit can also customize the appearance based on the viewer's attribute information. This enables more appropriate character management by taking the viewer's attribute information into consideration.

[0099] When managing a character's personality or hobbies, the management unit may assign a management weight based on the frequency of viewer input. Measurement of the frequency of viewer input includes, but is not limited to, the frequency of comments, requests, and feedback. For example, the management unit may measure the frequency of viewer comments and assign a management weight. The management unit may also analyze the frequency of viewer requests and assign a management weight. The management unit may also evaluate the frequency of viewer feedback and assign a management weight. Weighting may include, but is not limited to, a weighting algorithm, weighting criteria, and implementation method based on frequency. For example, the management unit may apply a weighting algorithm based on the frequency of viewer input. The management unit may also set weighting criteria based on the frequency of viewer input. The management unit may also adjust the weighting implementation method based on the frequency of viewer input. This enables more appropriate character management by assigning management weights based on the frequency of viewer input.

[0100] The management unit can estimate the viewer's emotions and adjust the display method of the character's personality or hobbies based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, an emotion analysis algorithm, the type of emotion, and the accuracy of estimation. For example, the management unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The management unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Adjusting the display method includes, but is not limited to, the timing of display, the display format, and adjustment criteria. For example, the management unit can adjust the display method of the character's personality or hobbies based on the intensity of the viewer's emotions. The management unit can also adjust the display method of the character's personality or hobbies based on the viewer's influence. The management unit can also adjust the display method of the character's personality or hobbies based on the importance of the request. In this way, adjusting the display method based on the viewer's emotions makes it easier to attract the viewer's attention.

[0101] The management unit may manage the character's personality or hobbies based on the geographical distribution of viewers. Examples of collecting the viewer's geographical distribution include, but are not limited to, GPS data, IP addresses, and the accuracy of location information. For example, the management unit may collect the viewer's GPS data to identify the geographical distribution. The management unit may also analyze the viewer's IP address to identify the geographical distribution. The management unit may also perform management taking into account the accuracy of the viewer's location information. Examples of management include, but are not limited to, setting the character's personality, behavioral patterns, and customizing the character's appearance. For example, the management unit may set the character's personality based on the viewer's geographical distribution. The management unit may also set the behavioral patterns based on the viewer's geographical distribution. The management unit may also customize the character's appearance based on the viewer's geographical distribution. This enables more appropriate character management by taking into account the viewer's geographical distribution.

[0102] The management unit can improve the accuracy of management based on related literature when managing a character's personality or hobbies. Examples of related literature include, but are not limited to, academic papers, technical reports, and patent documents. For example, the management unit can perform management by referring to academic papers related to the character's personality or hobbies. The management unit can also perform management by referring to news articles related to the character's personality or hobbies. The management unit can also perform management by referring to specialized books related to the character's personality or hobbies. Examples of improving the accuracy of management include, but are not limited to, data preprocessing methods, algorithm selection, and evaluation criteria. For example, the management unit can perform data preprocessing based on related literature. The management unit can also select an algorithm based on related literature. The management unit can also set evaluation criteria based on related literature. By doing so, the accuracy of management can be improved by referring to related literature.

[0103] The management unit may manage the character's personality or hobbies based on the viewer's market value. Evaluation of the viewer's market value may include, but is not limited to, purchasing power, influence, consumption behavior, etc. For example, the management unit may evaluate and manage the viewer's purchasing power. The management unit may also analyze and manage the viewer's influence. The management unit may also evaluate and manage the viewer's consumption behavior. Management may include, but is not limited to, personality setting, behavior patterns, and appearance customization, for example. For example, the management unit may set the personality based on the viewer's market value. The management unit may also set behavior patterns based on the viewer's market value. The management unit may also customize the appearance based on the viewer's market value. This enables more effective character management by taking the viewer's market value into consideration.

[0104] The control unit can estimate the viewer's emotions and control the Vtuber's activities based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, an emotion analysis algorithm, the type of emotion, and the accuracy of the estimation. For example, the control unit can analyze viewer comments using an emotion analysis algorithm to estimate the viewer's emotions. The control unit can also analyze viewer requests using an emotion analysis algorithm to estimate the viewer's emotions. Controlling activities includes, but is not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit can control the Vtuber's activities based on the intensity of the viewer's emotions. The control unit can also control the Vtuber's activities based on the viewer's influence. The control unit can also control the Vtuber's activities based on the importance of the request. This allows the Vtuber's activities to be more appropriate by controlling the Vtuber's activities based on the viewer's emotions.

[0105] When controlling the activities of a Vtuber, the control unit can improve the accuracy of the control based on past viewer input. Collection of past viewer input includes, but is not limited to, comment history, request history, and feedback history. For example, the control unit collects viewer comment history to improve the accuracy of the control. The control unit can also analyze viewer request history to improve the accuracy of the control. The control unit can also evaluate viewer feedback history to improve the accuracy of the control. Improvement of the accuracy of the control includes, but is not limited to, data preprocessing methods, algorithm selection, evaluation criteria, and the like. For example, the control unit preprocesses data based on the viewer's past input. The control unit can also select an algorithm based on the viewer's past input. The control unit can also set evaluation criteria based on the viewer's past input. This allows the accuracy of the control to be improved by referring to the viewer's past input.

[0106] When controlling the activities of a Vtuber, the control unit can perform control based on viewer attribute information. Collected viewer attribute information includes, but is not limited to, age, gender, occupation, and interests. For example, the control unit collects and controls the viewer's age. The control unit can also analyze and control the viewer's gender. The control unit can also evaluate and control the viewer's occupation. Examples of control include, but are not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit manages schedules based on the viewer attribute information. The control unit can also adjust performances based on the viewer attribute information. The control unit can also make real-time changes based on the viewer attribute information. This enables more appropriate activity control by taking viewer attribute information into consideration.

[0107] When controlling the activities of a Vtuber, the control unit can weight the control based on the frequency of viewer input. Measurement of the frequency of viewer input includes, but is not limited to, the frequency of comments, requests, and feedback. For example, the control unit measures the frequency of viewer comments and weights the control. The control unit can also analyze the frequency of viewer requests and weight the control. The control unit can also evaluate the frequency of viewer feedback and weight the control. Weighting includes, but is not limited to, a weighting algorithm, weighting criteria, and implementation method based on frequency. For example, the control unit applies a weighting algorithm based on the frequency of viewer input. The control unit can also set weighting criteria based on the frequency of viewer input. The control unit can also adjust the weighting implementation method based on the frequency of viewer input. As a result, weighting the control based on the frequency of viewer input enables more appropriate activity control.

[0108] The control unit can estimate the viewer's emotions and adjust the display method of the Vtuber's activities based on the estimated viewer's emotions. Estimating the viewer's emotions includes, but is not limited to, an emotion analysis algorithm, the type of emotion, and the accuracy of the estimation. For example, the control unit can analyze viewer comments using an emotion analysis algorithm to estimate the viewer's emotions. The control unit can also analyze viewer requests using an emotion analysis algorithm to estimate the viewer's emotions. Adjusting the display method includes, but is not limited to, the timing of display, the display format, and adjustment criteria. For example, the control unit can adjust the display method of the Vtuber's activities based on the intensity of the viewer's emotions. The control unit can also adjust the display method of the Vtuber's activities based on the viewer's influence. The control unit can also adjust the display method of the Vtuber's activities based on the importance of the request. In this way, adjusting the display method based on the viewer's emotions makes it easier to attract the viewer's attention.

[0109] When controlling the activities of a Vtuber, the control unit can perform control based on the geographical distribution of viewers. Examples of collecting the geographical distribution of viewers include, but are not limited to, GPS data, IP addresses, and the accuracy of location information. For example, the control unit can collect GPS data of viewers to identify their geographical distribution. The control unit can also analyze the IP addresses of viewers to identify their geographical distribution. The control unit can also perform control taking into account the accuracy of the viewer's location information. Examples of control include, but are not limited to, schedule management, performance adjustment, and real-time changes based on viewer reactions. For example, the control unit can perform schedule management based on the geographical distribution of viewers. The control unit can also adjust performances based on the geographical distribution of viewers. The control unit can also make real-time changes based on the geographical distribution of viewers. This enables more appropriate activity control by taking into account the geographical distribution of viewers.

[0110] When controlling the activities of a Vtuber, the control unit can improve the accuracy of the control based on related literature. Examples of related literature include, but are not limited to, academic papers, technical reports, and patent documents. For example, the control unit performs control by referring to academic papers related to the Vtuber's activities. The control unit can also perform control by referring to news articles related to the Vtuber's activities. The control unit can also perform control by referring to specialized books related to the Vtuber's activities. Examples of improving the accuracy of the control include, but are not limited to, data preprocessing methods, algorithm selection, and evaluation criteria. For example, the control unit performs data preprocessing based on related literature. The control unit can also select an algorithm based on related literature. The control unit can also set evaluation criteria based on related literature. By referring to related literature, the accuracy of the control can be improved.

[0111] When controlling the activities of a Vtuber, the control unit can perform control based on the market value of viewers. Evaluations of viewer market value include, for example, purchasing power, influence, and consumption behavior, but are not limited to these examples. The control unit, for example, evaluates and controls the purchasing power of viewers. The control unit can also analyze and control the influence of viewers. The control unit can also evaluate and control the consumption behavior of viewers. Control includes, for example, schedule management, performance adjustment, and real-time changes based on viewer reactions, but are not limited to these examples. The control unit, for example, performs schedule management based on the market value of viewers. The control unit can also adjust performance based on the market value of viewers. The control unit can also make real-time changes based on the market value of viewers. This enables more effective activity control by taking viewer market value into consideration.

[0112] The revenue management unit can estimate viewer emotions and adjust the revenue management method based on the estimated viewer emotions. Estimating viewer emotions includes, but is not limited to, a sentiment analysis algorithm, a type of emotion, and estimation accuracy. For example, the revenue management unit can analyze viewer comments using a sentiment analysis algorithm to estimate viewer emotions. The revenue management unit can also analyze viewer requests using a sentiment analysis algorithm to estimate viewer emotions. Adjusting the revenue management method can include, but is not limited to, the frequency of adjustment, a method for setting standards, and a method for implementation. For example, the revenue management unit can adjust the revenue management method based on the intensity of viewer emotions. The revenue management unit can also adjust the revenue management method based on the influence of the viewer. The revenue management unit can also adjust the revenue management method based on the importance of the request. Adjusting the revenue management method based on viewer emotions enables more effective revenue management.

[0113] During revenue management, the revenue management unit can analyze the viewer's past consumption behavior and select an appropriate revenue management method. Collecting the viewer's past consumption behavior includes, but is not limited to, purchase history, consumption patterns, and expenditures. For example, the revenue management unit collects the viewer's purchase history and selects a revenue management method. The revenue management unit can also analyze the viewer's consumption patterns and select a revenue management method. The revenue management unit can also evaluate the viewer's expenditures and select a revenue management method. The selection of a revenue management method includes, but is not limited to, the type of revenue, management method selection criteria, and implementation method. For example, the revenue management unit selects a revenue management method based on the viewer's past consumption behavior. The revenue management unit can also set selection criteria based on the viewer's past consumption behavior. The revenue management unit can also adjust the implementation method based on the viewer's past consumption behavior. In this way, the optimal revenue management method can be selected by analyzing the viewer's past consumption behavior.

[0114] During revenue management, the revenue management unit can customize revenue management measures based on the viewer's current living situation. Collection of the viewer's living situation includes, but is not limited to, income, family structure, and lifestyle habits. For example, the revenue management unit collects the viewer's income and customizes the revenue management measures. The revenue management unit can also analyze the viewer's family structure and customize the revenue management measures. The revenue management unit can also evaluate the viewer's lifestyle habits and customize the revenue management measures. Customization of the revenue management measures includes, but is not limited to, the frequency of customization, a method for setting standards, and an implementation method. For example, the revenue management unit customizes the revenue management measures based on the viewer's living situation. The revenue management unit can also adjust the frequency of customization based on the viewer's living situation. The revenue management unit can also set customization standards based on the viewer's living situation. This enables more appropriate revenue management by customizing the revenue management measures based on the viewer's current living situation.

[0115] The revenue management unit can improve the revenue management method by reflecting viewer feedback during revenue management. Examples of collecting viewer feedback include, but are not limited to, survey results, comments, and requests. For example, the revenue management unit can collect viewer survey results and identify feedback. The revenue management unit can also analyze viewer comments and identify feedback. The revenue management unit can also evaluate viewer requests and identify feedback. Examples of improving the revenue management method include, but are not limited to, the frequency of improvement, a method for setting standards, and an implementation method. For example, the revenue management unit can improve the revenue management method based on viewer feedback. The revenue management unit can also adjust the frequency of improvement based on viewer feedback. The revenue management unit can also set standards for improvement based on viewer feedback. This allows the revenue management method to be continuously improved by reflecting viewer feedback.

[0116] The revenue management unit can estimate viewer emotions and determine revenue management priorities based on the estimated viewer emotions. Estimating viewer emotions can include, but is not limited to, a sentiment analysis algorithm, a type of emotion, and estimation accuracy. For example, the revenue management unit can analyze viewer comments using a sentiment analysis algorithm to estimate viewer emotions. The revenue management unit can also analyze viewer requests using a sentiment analysis algorithm to estimate viewer emotions. Determining priorities can include, but is not limited to, the intensity of emotions, the viewer's influence, and the importance of requests. For example, the revenue management unit can determine revenue management priorities based on the intensity of viewer emotions. The revenue management unit can also determine revenue management priorities based on the viewer's influence. The revenue management unit can also determine revenue management priorities based on the importance of requests. This enables more effective revenue management by determining revenue management priorities based on viewer emotions.

[0117] During revenue management, the revenue management unit can select an appropriate revenue management method based on the viewer's geographical location information. Examples of the collection of viewer's geographical location information include, but are not limited to, GPS data, IP addresses, and location information accuracy. For example, the revenue management unit collects viewer's GPS data to identify the geographical location information. The revenue management unit can also analyze the viewer's IP address to identify the geographical location information. The revenue management unit can also select a revenue management method taking into account the accuracy of the viewer's location information. Examples of the selection of a revenue management method include, but are not limited to, the type of revenue, management method selection criteria, and implementation method. For example, the revenue management unit selects a revenue management method based on the viewer's geographical location information. The revenue management unit can also set selection criteria based on the viewer's geographical location information. The revenue management unit can also adjust the implementation method based on the viewer's geographical location information. This enables more appropriate revenue management by taking into account the viewer's geographical location information.

[0118] During revenue management, the revenue management unit may analyze viewers' social media activities and propose revenue management measures. Collecting viewers' social media activities may include, but is not limited to, for example, content of posts, number of followers, and engagement rate. For example, the revenue management unit may collect viewers' posts and propose revenue management measures. The revenue management unit may also analyze the number of viewers' followers and propose revenue management measures. The revenue management unit may also evaluate viewers' engagement rate and propose revenue management measures. Proposing revenue management measures may include, but is not limited to, for example, frequency of proposals, method of setting criteria, and implementation method. For example, the revenue management unit may propose revenue management measures based on viewers' social media activities. The revenue management unit may also adjust the frequency of proposals based on viewers' social media activities. The revenue management unit may also set criteria for proposals based on viewers' social media activities. This allows optimal revenue management measures to be proposed by analyzing viewers' social media activities.

[0119] During revenue management, the revenue management unit can customize the revenue management method based on past viewer feedback. Examples of collecting past viewer feedback include, but are not limited to, survey results, comments, and requests. For example, the revenue management unit can collect viewer survey results and identify feedback. The revenue management unit can also analyze viewer comments and identify feedback. The revenue management unit can also evaluate viewer requests and identify feedback. Examples of customizing the revenue management method include, but are not limited to, the frequency of customization, a method for setting standards, and an implementation method. For example, the revenue management unit customizes the revenue management method based on, for example, past viewer feedback. The revenue management unit can also adjust the frequency of customization based on the viewer's past feedback. The revenue management unit can also set customization standards based on the viewer's past feedback. This enables more appropriate revenue management by reflecting the viewer's past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, analysis unit, management unit, control unit, and revenue management unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives comments and requests from viewers. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes viewer input using natural language processing technology. The management unit is realized by the specific processing unit 290 of the data processing device 12 and manages character personality settings and behavior patterns. The control unit is realized by the control unit 46A of the smart device 14 and controls the character's activities. The revenue management unit is realized by the specific processing unit 290 of the data processing device 12 and manages advertising revenue, donations, and revenue from merchandise sales. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, analysis unit, management unit, control unit, and revenue management unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives comments and requests from viewers. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes viewer input using natural language processing technology. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages character personality settings and behavior patterns. The control unit is realized, for example, by the control unit 46A of the smart glasses 214 and controls the character's activities. The revenue management unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages advertising revenue, donations, and revenue from merchandise sales. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, analysis unit, management unit, control unit, and revenue management unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset-type terminal 314 and receives comments and requests from viewers. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes viewer input using natural language processing technology. The management unit is realized by the specific processing unit 290 of the data processing device 12 and manages character personality settings and behavior patterns. The control unit is realized by the control unit 46A of the headset-type terminal 314 and controls the character's activities. The revenue management unit is realized by the specific processing unit 290 of the data processing device 12 and manages advertising revenue, donations, and revenue from merchandise sales. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, management unit, control unit, and revenue management unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives comments and requests from viewers. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes viewer input using natural language processing technology. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages the character's personality settings and behavior patterns. The control unit is realized, for example, by the control unit 46A of the robot 414 and controls the character's activities. The revenue management unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and manages advertising revenue, donations, and revenue from merchandise sales.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] When analyzing a viewer's comments or requests, the analysis unit can refer to the viewer's past behavioral history. For example, it can analyze what kind of comments the viewer has left in the past and what kind of requests they have made, and use that information to more accurately understand the intention behind the current comment or request. It can also estimate the viewer's interests and concerns based on the viewer's past behavioral history, allowing for more personalized responses. Furthermore, it can predict the viewer's behavioral patterns based on the viewer's past behavioral history, and identify trends in future requests and comments. This makes it possible to perform more accurate analysis by referring to the viewer's past behavioral history.

[0122] The management unit can take into account the viewer's attribute information when managing the character's personality and hobbies. For example, the character's personality and hobbies can be set based on the viewer's attribute information, such as age, gender, and occupation. The character's behavior pattern can also be adjusted based on the viewer's attribute information. Furthermore, the character's appearance can also be customized based on the viewer's attribute information. In this way, by taking the viewer's attribute information into consideration, it is possible to provide a character that is more familiar to the viewer.

[0123] The control unit can take into account the geographical distribution of viewers when controlling the activities of Vtubers. For example, it can adjust the Vtuber's activity time based on the viewer's place of residence. It can also provide content targeted to specific regions based on the viewer's geographical distribution. It can also plan events and campaigns for each region based on the viewer's geographical distribution. This allows for activities that are more closely tied to the local area by taking the viewer's geographical distribution into account.

[0124] The revenue management department can analyze viewers' social media activity and propose revenue management measures. For example, it can propose optimal advertising strategies based on viewers' posts, number of followers, and engagement rates. It can also identify target demographics for crowdfunding based on viewers' social media activity. It can also propose merchandise sales promotion methods based on viewers' social media activity. This allows for more effective revenue management by analyzing viewers' social media activity.

[0125] The reception unit can analyze the viewer's past comment history and select an appropriate reception method. For example, it can analyze what kind of comments the viewer has left in the past and select the optimal reception timing based on that information. It can also select the optimal reception method based on the viewer's past comment history. Furthermore, it can set optimal reception criteria based on the viewer's past comment history. In this way, it is possible to select the optimal reception method by analyzing the viewer's past comment history.

[0126] The reception unit can estimate the viewer's emotions and determine the priority of comments and requests based on the estimated viewer's emotions. For example, the reception unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The reception unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Furthermore, the reception unit can determine the priority of comments and requests based on the intensity of the viewer's emotions. This allows for more appropriate responses by determining the priority of comments and requests based on the viewer's emotions.

[0127] The analysis unit can estimate the viewer's emotions and determine the analysis priority based on the estimated viewer's emotions. For example, the analysis unit can analyze the viewer's comments using an emotion analysis algorithm to estimate the viewer's emotions. The analysis unit can also analyze the viewer's requests using an emotion analysis algorithm to estimate the viewer's emotions. Furthermore, the analysis priority of the comments and requests can be determined based on the intensity of the viewer's emotions. This allows for more appropriate analysis by determining the analysis priority based on the viewer's emotions.

[0128] The management unit can estimate the viewer's emotions and adjust the character's personality and hobby management method based on the estimated viewer's emotions. For example, the management unit can analyze viewer comments using an emotion analysis algorithm to estimate the viewer's emotions. It can also analyze viewer requests using an emotion analysis algorithm to estimate the viewer's emotions. It can also adjust the character's personality and hobby management method based on the intensity of the viewer's emotions. This allows for more appropriate character management by adjusting the character's personality and hobby management method based on the viewer's emotions.

[0129] The control unit can estimate the viewer's emotions and control the Vtuber's activities based on the estimated viewer's emotions. For example, the control unit can analyze viewer comments using an emotion analysis algorithm to estimate the viewer's emotions. It can also analyze viewer requests using an emotion analysis algorithm to estimate the viewer's emotions. It can also control the Vtuber's activities based on the intensity of the viewer's emotions. This allows for more appropriate activities by controlling the Vtuber's activities based on the viewer's emotions.

[0130] The revenue management unit can estimate viewer emotions and adjust the revenue management method based on the estimated viewer emotions. For example, the revenue management unit can analyze viewer comments using a sentiment analysis algorithm to estimate viewer emotions. The revenue management unit can also analyze viewer requests using a sentiment analysis algorithm to estimate viewer emotions. Furthermore, the revenue management method can be adjusted based on the intensity of the viewer emotions. This allows for more effective revenue management by adjusting the revenue management method based on viewer emotions.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The reception unit receives input from viewers. The input from viewers includes comments, requests, feedback, etc. For example, the reception unit can receive comments from viewers in text format, requests in audio format, and feedback in image format. Step 2: The analysis unit analyzes the input received by the reception unit. The analysis is performed using natural language processing technology, sentiment analysis technology, data mining technology, etc. For example, the analysis unit can analyze comments from viewers using natural language processing technology, analyze requests using sentiment analysis technology, and analyze feedback using data mining technology. Step 3: The management unit manages the characters generated based on the input analyzed by the analysis unit. Management includes setting the character's personality, managing behavior patterns, customizing appearance, etc. For example, the management unit can set the character's personality, manage behavior patterns, and customize appearance. Step 4: The control unit controls the activities of the characters managed by the management unit. The control includes managing the character's schedule, adjusting performance, and changing the character's activities in real time based on the viewer's reaction. For example, the control unit can manage the character's schedule, adjust performance, and change the character's activities in real time based on the viewer's reaction.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> 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.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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 identification processing unit 290 using these models.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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).

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] [Explanation of symbols]

[0205] 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. a reception unit that receives input from viewers; an analysis unit that analyzes the input received by the reception unit; a management unit that manages characters generated based on the input analyzed by the analysis unit; a control unit that controls the activities of the characters managed by the management unit; Equipped with A system characterized by:

2. Equipped with a revenue management department to manage revenue 2. The system of claim 1.

3. The reception unit Accept comments or requests from viewers 2. The system of claim 1.

4. The analysis unit Analyze comments or requests from viewers and reflect them in the Vtuber's growth 2. The system of claim 1.

5. The management unit Manage the generated character's personality or hobbies 2. The system of claim 1.

6. The control unit Control the Vtuber's activities and create new clothes or songs 2. The system of claim 1.

7. The reception unit Estimate viewer sentiment and prioritize comments or requests based on the estimated viewer sentiment 2. The system of claim 1.

8. The reception unit Analyze viewers' past comment history and select the appropriate reception method 2. The system of claim 1.

9. The reception unit When accepting comments or requests, filter them based on your audience's current interests 2. The system of claim 1.

10. The reception unit When accepting comments or requests, select the appropriate method based on the viewer's input method.

2. The system of claim 1.

Images