System

Abstract

An object of the system according to the embodiment is to analyze a reaction of a viewer and a voting result in real time and recommend an optimal situation.SOLUTION: A system includes a collection unit, an analysis unit, and a recommendation unit. The collection part collects the reaction or voting result of the viewer. The analysis unit analyzes the data collected by the collection unit. The recommendation unit recommends a tactical situation based on the analysis result obtained by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology does not adequately reflect viewer reactions and voting results in the game situation in real time, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze viewer reactions and voting results in real time and recommend the optimal battle situation. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a recommendation unit. The collection unit collects viewer reactions or voting results. The analysis unit analyzes the data collected by the collection unit. The recommendation unit recommends a battle situation based on the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze viewer reactions and voting results in real time and recommend the optimal battle situation. [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 game progress support system according to an embodiment of the present invention collects viewer reactions and voting results, analyzes them using a generation AI, and recommends optimal game situations to players. The game progress support system collects viewer reactions and voting results, analyzes them using a generation AI, and recommends optimal game situations to players. The system also counts the number of viewers and provides power-ups based on the number of viewers. Furthermore, the system also has a function that allows players playing the same game to directly participate in the game. For example, the game progress support system collects viewer reactions and voting results. For example, detailed data such as which weapons and locations viewers selected and which players they are rooting for is collected. Next, the game progress support system uses a generation AI to analyze the collected data. The generation AI analyzes the viewer reactions and voting results and recommends optimal game situations to players. For example, if a large number of viewers selected a specific location, the system recommends a game situation at that location. Next, the game progress support system counts the number of viewers and provides power-ups based on the number of viewers. For example, if the number of viewers exceeds a certain number, the player's abilities are powered up. Next, the game progress support system has a function that allows people playing the same game to directly participate. For example, if a viewer requests to participate, that information is accepted and added to the game. This allows viewers to actively participate in the progress of the game, providing a more enjoyable gaming experience through dialogue and cooperation with players. For example, viewers can give advice to players or cooperate with players to advance the game in their favor. This deepens the bond between viewers and players, providing a more enjoyable gaming experience. This allows the game progress support system to recommend optimal game situations to players based on viewer reactions and voting results. For example, viewers can give advice to players or cooperate with players to advance the game in their favor. This deepens the bond between viewers and players, providing a more enjoyable gaming experience.

[0029] A game progress support system according to an embodiment includes a collection unit, an analysis unit, and a recommendation unit. The collection unit collects viewer responses or voting results. Viewer responses include, but are not limited to, comments, reactions, emotes, and the like. For example, if a viewer selects a specific weapon, the collection unit collects that information. The collection unit can also collect which player the viewer is rooting for. For example, if a viewer sends a cheering message to a specific player, the collection unit collects that information. The analysis unit uses a generation AI to analyze the data collected by the collection unit. The analysis is performed, for example, based on a data analysis method or an algorithm used, but is not limited to, the example. For example, the generation AI analyzes viewer responses and voting results and recommends the optimal battle situation to the player. The analysis unit can also analyze trends in viewer responses and voting results. For example, if a large number of viewers select a specific location, the generation AI recommends a battle situation at that location. The recommendation unit recommends a battle situation based on the analysis results obtained by the analysis unit. Recommendations are made based on, for example, the progress of the game and the status of the players, but are not limited to such examples. For example, the recommendation unit recommends the optimal game situation to the players based on the viewers' reactions and voting results. The recommendation unit can also recommend tactics to the players based on the viewers' reactions and voting results. For example, if a large number of viewers support a particular tactic, the recommendation unit recommends that tactic to the players. In this way, the game progress support system according to the embodiment can recommend the optimal game situation to the players based on the viewers' reactions and voting results.

[0030] The game progress support system includes a counting unit that counts the number of viewers. The counting unit counts the number of viewers. The number of viewers includes, for example, the real-time number of viewers and the cumulative number of viewers, but is not limited to these examples. The counting unit, for example, counts the number of viewers in real time. The counting unit can also count the cumulative number of viewers. For example, the counting unit counts the number of viewers at regular time intervals. The counting unit can also count fluctuations in the number of viewers. For example, if the number of viewers suddenly increases, the counting unit counts the fluctuations. In this way, by counting the number of viewers, it is possible to power up based on the number of viewers. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit can input the count of the number of viewers into an AI model and output the fluctuations in the number of viewers.

[0031] The game progress support system includes a power-up unit that performs power-up based on the number of viewers counted by the counting unit. The power-up unit performs power-up based on the number of viewers counted by the counting unit. Examples of power-up include, but are not limited to, improving a player's abilities and strengthening a weapon. For example, the power-up unit improves a player's abilities when the number of viewers exceeds a certain number. The power-up unit can also strengthen weapons based on the number of viewers. For example, when the number of viewers increases, the attacking power of the weapon is strengthened. The power-up unit can also strengthen defensive power based on the number of viewers. For example, when the number of viewers decreases, the defensive power is strengthened. In this way, the player's abilities can be powered up based on the number of viewers. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the power-up unit can input viewer count data into an AI model and output a power-up method.

[0032] The game progress support system includes a reception unit that receives information when a user playing the same game requests to participate. The reception unit receives the information when a user playing the same game requests to participate. The request to participate may include, but is not limited to, a method for submitting the request and conditions for acceptance. For example, the reception unit receives information when a user requests to participate. The reception unit can also receive a method for submitting the request. For example, when a user submits a request to participate through an online form, the reception unit receives the information. The reception unit can also set conditions for accepting the request to participate. For example, the reception unit only accepts requests from users who meet certain conditions. This allows viewers to directly participate in the game. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the request to participate into an AI model and output a method for accepting the request.

[0033] The game progress support system includes an adding unit that adds a participant to the game based on the participation request received by the receiving unit. The adding unit adds the participant to the game based on the participation request received by the receiving unit. The adding of the participant includes, for example, an adding procedure and an adding condition, but is not limited to these examples. The adding unit adds the participant based on the participation request received by the receiving unit. The adding unit can also set a procedure for adding the participant. For example, the participant is added according to a specific procedure. The adding unit can also set conditions for adding the participant. For example, only participants who meet specific conditions are added. In this way, the participant can be added to the game based on the participation request received. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input data of the participation request into an AI model and output a method for adding the participant.

[0034] The collection unit can analyze the viewer's past reaction history and select an appropriate collection method. The collection unit analyzes the viewer's past reaction history and selects an appropriate collection method. Past reaction history includes, for example, timings at which the viewer frequently reacted in the past, voting patterns, reactions to specific events, etc., but is not limited to these examples. The collection unit selects the optimal collection timing based on, for example, timings at which the viewer frequently reacted in the past. The collection unit can also analyze the viewer's past voting patterns and select the optimal collection method. For example, the collection unit selects the optimal collection method based on the viewer's past voting patterns. The collection unit can also predict reactions to specific events from the viewer's past reaction history and adjust the collection method. For example, the collection unit predicts reactions to specific events from the viewer's past reaction history and adjusts the collection method. By selecting the optimal collection method based on the past reaction history, the accuracy of data collection is improved. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI. For example, the collection unit can input viewers' past reaction history data into the generation AI and have the generation AI select the optimal collection method.

[0035] The collection unit may filter responses and voting results based on the viewer's current areas of interest when collecting the responses and voting results. The collection unit may filter responses and voting results based on the viewer's current areas of interest when collecting the responses and voting results. Viewer areas of interest include, but are not limited to, weapons, locations, and specific players. For example, the collection unit may preferentially collect responses and voting results related to weapons and locations in which the viewer is currently interested. Furthermore, if a viewer is interested in a specific player, the collection unit may preferentially collect responses and voting results related to that player. For example, if a viewer is interested in a specific player, the collection unit may preferentially collect responses and voting results related to that player. Furthermore, the collection unit may filter and collect highly relevant data based on the viewer's current areas of interest. For example, the collection unit may filter and collect highly relevant data based on the viewer's current areas of interest. In this way, highly relevant data can be collected by filtering data based on the viewer's areas of interest. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input viewer interest area data into the generation AI and have the generation AI perform filtering.

[0036] The collection unit can select the optimal collection means depending on the viewer's input method when collecting reactions or voting results. The collection unit selects the optimal collection means depending on the viewer's input method when collecting reactions or voting results. Viewer input methods include, but are not limited to, voice, text, and images. For example, when viewers react or vote using voice, the collection unit collects data using voice recognition technology. Furthermore, when viewers react or vote using text, the collection unit can also collect data using text analysis technology. For example, when viewers react or vote using text, the collection unit collects data using text analysis technology. Furthermore, when viewers react or vote using images, the collection unit can also collect data using image recognition technology. For example, when viewers react or vote using images, the collection unit collects data using image recognition technology. This improves the efficiency of data collection by selecting the optimal collection means depending on the viewer's input method. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input viewer input method data into the generation AI and have the generation AI select the optimal collection method.

[0037] When collecting responses and voting results, the collection unit can prioritize collecting highly relevant data by taking into account the viewer's geographical location information. When collecting responses and voting results, the collection unit prioritizes collecting highly relevant data by taking into account the viewer's geographical location information. Examples of viewer's geographical location information include, but are not limited to, GPS data and IP addresses. For example, if viewers are concentrated in a specific area, the collection unit prioritizes collecting data related to that area. The collection unit can also collect responses and voting results by area based on the viewer's geographical location information. For example, the collection unit collects responses and voting results by area based on the viewer's geographical location information. The collection unit can also collect data reflecting regional trends by taking into account the viewer's geographical location information. For example, the collection unit collects data reflecting regional trends by taking into account the viewer's geographical location information. In this way, highly relevant data for each area can be collected by taking into account the viewer's geographical location information. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the viewer's geographic location data into the generation AI and cause the generation AI to collect highly relevant data.

[0038] The collection unit can analyze viewers' social media activities and collect related data when collecting reactions and voting results. The collection unit analyzes viewers' social media activities and collects related data when collecting reactions and voting results. Viewers' social media activities include, but are not limited to, post content and the number of followers. The collection unit collects, for example, reactions shared by viewers on social media and voting results. The collection unit can also analyze viewers' social media activities and collect related data. For example, the collection unit analyzes viewers' social media activities and collects related data. The collection unit can also collect related data by referring to the activities of the viewers' friends on social media. For example, the collection unit collects related data by referring to the activities of the viewers' friends on social media. In this way, highly relevant data can be collected by analyzing the viewers' social media activities. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input viewers' social media activity data into the generation AI and cause the generation AI to collect related data.

[0039] The collection unit can customize the collection method by reflecting past viewer feedback when collecting reactions and voting results. The collection unit customizes the collection method by reflecting past viewer feedback when collecting reactions and voting results. Past feedback includes, but is not limited to, survey results and comment history. The collection unit customizes the optimal collection method, for example, based on feedback provided by viewers in the past. The collection unit can also adjust the collection timing by reflecting past viewer feedback. For example, the collection unit adjusts the collection timing by reflecting past viewer feedback. The collection unit can also customize the collection means by referring to past viewer feedback. For example, the collection unit customizes the collection means by referring to past viewer feedback. In this way, the optimal collection method can be customized by reflecting past viewer feedback. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past viewer feedback data into a generation AI and cause the generation AI to customize the collection method.

[0040] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the data during analysis. The importance of the data includes, for example, the impact of the data and the frequency of use, but is not limited to these examples. For example, the analysis unit performs a detailed analysis on important data. The analysis unit can also perform a simplified analysis on general data. For example, the analysis unit performs a simplified analysis on general data. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. For example, the analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the data. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0041] The analysis unit can apply different analysis algorithms depending on the data category during analysis. The analysis unit applies different analysis algorithms depending on the data category during analysis. Data categories include, but are not limited to, text data, numerical data, etc. The analysis unit can apply a specific analysis algorithm to data related to weapons, for example. The analysis unit can also apply a different analysis algorithm to data related to locations. For example, the analysis unit can apply a different analysis algorithm to data related to locations. The analysis unit can also select an optimal analysis algorithm depending on the data category. For example, the analysis unit selects an optimal analysis algorithm depending on the data category. This improves the accuracy of the analysis by applying the optimal analysis algorithm depending on the data category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the data category to the generation AI and cause the generation AI to select an analysis algorithm.

[0042] The analysis unit can improve the accuracy of the analysis by referring to the viewer's past analysis results during analysis. The analysis unit improves the accuracy of the analysis by referring to the viewer's past analysis results during analysis. Past analysis results include, but are not limited to, methods for saving and referencing analysis results. The analysis unit can improve the accuracy of the current analysis, for example, based on the viewer's past analysis results. The analysis unit can also adjust the analysis algorithm by referring to the viewer's past analysis results. For example, the analysis unit can adjust the analysis algorithm by referring to the viewer's past analysis results. The analysis unit can also reduce analysis errors by using the viewer's past analysis results. For example, the analysis unit can reduce analysis errors by using the viewer's past analysis results. As a result, the accuracy of the current analysis is improved by referring to the past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0043] The analysis unit can determine the analysis priority based on the time of data submission during analysis. The analysis unit determines the analysis priority based on the time of data submission during analysis. The time of data submission includes, but is not limited to, the submission date and time, the submission frequency, etc. The analysis unit, for example, prioritizes analysis of the most recent data. The analysis unit can also postpone analysis of data submitted earlier. For example, the analysis unit postpones analysis of data submitted earlier. The analysis unit can also dynamically adjust the analysis priority based on the time of data submission. For example, the analysis unit dynamically adjusts the analysis priority based on the time of data submission. In this way, by determining the analysis priority based on the time of data submission, the most recent data can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time of data submission to the generation AI and have the generation AI determine the analysis priority.

[0044] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. The analysis unit adjusts the order of analysis based on the relevance of the data during analysis. Data relevance includes, but is not limited to, co-occurrence frequency, correlation, etc. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. For example, the analysis unit postpones analysis of less relevant data. The analysis unit can also dynamically adjust the order of analysis based on the relevance of the data. For example, the analysis unit dynamically adjusts the order of analysis based on the relevance of the data. In this way, by adjusting the order of analysis based on the relevance of the data, highly relevant data can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the relevance of the data to the generation AI and cause the generation AI to adjust the order of analysis.

[0045] The analysis unit can adjust the use of technical terms in the analysis according to the viewer's level of expertise during analysis. The analysis unit can adjust the use of technical terms in the analysis according to the viewer's level of expertise during analysis. The viewer's level of expertise includes, but is not limited to, survey results, past viewing history, etc. For example, if the viewer has specialized knowledge, the analysis unit can provide an analysis that uses a lot of technical terms. Furthermore, if the viewer has only general knowledge, the analysis unit can provide an analysis in simple language. For example, if the viewer has only general knowledge, the analysis unit can provide an analysis in simple language. Furthermore, the analysis unit can dynamically adjust the use of technical terms in the analysis according to the viewer's level of expertise. For example, the analysis unit dynamically adjusts the use of technical terms in the analysis according to the viewer's level of expertise. By adjusting the use of technical terms in the analysis according to the viewer's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the viewer's expertise level data into the generation AI and have the generation AI adjust the use of technical terms.

[0046] The recommendation unit can adjust the level of detail of the recommendation based on the importance of the battle situation when making a recommendation. The recommendation unit adjusts the level of detail of the recommendation based on the importance of the battle situation when making a recommendation. The importance of the battle situation includes, for example, the progress of the game, the status of the players, etc., but is not limited to these examples. The recommendation unit, for example, provides a detailed recommendation for an important battle situation. The recommendation unit can also provide a simplified recommendation for a general battle situation. For example, the recommendation unit provides a simplified recommendation for a general battle situation. The recommendation unit can also dynamically adjust the level of detail of the recommendation according to the importance of the battle situation. For example, the recommendation unit dynamically adjusts the level of detail of the recommendation according to the importance of the battle situation. This enables efficient recommendations by adjusting the level of detail of the recommendation according to the importance of the battle situation. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input battle situation importance data to the generation AI and cause the generation AI to adjust the level of detail of the recommendation.

[0047] The recommendation unit can apply different recommendation algorithms depending on the category of the battle situation when making a recommendation. The recommendation unit applies different recommendation algorithms depending on the category of the battle situation when making a recommendation. The battle situation categories include, for example, attack phase, defense phase, etc., but are not limited to these examples. The recommendation unit applies a specific recommendation algorithm to, for example, a battle situation related to weapons. The recommendation unit can also apply a different recommendation algorithm to a battle situation related to a location. For example, the recommendation unit applies a different recommendation algorithm to a battle situation related to a location. The recommendation unit can also select an optimal recommendation algorithm depending on the category of the battle situation. For example, the recommendation unit selects an optimal recommendation algorithm depending on the category of the battle situation. As a result, by applying the optimal recommendation algorithm depending on the category of the battle situation, the accuracy of the recommendation is improved. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input battle situation category data to the generation AI and have the generation AI select a recommendation algorithm.

[0048] The recommendation unit can improve the accuracy of recommendations by referring to the viewer's past recommendation results when making recommendations. The recommendation unit improves the accuracy of recommendations by referring to the viewer's past recommendation results when making recommendations. Past recommendation results include, for example, a method for saving recommendation results and a procedure for referencing them, but are not limited to these examples. The recommendation unit improves the accuracy of current recommendations, for example, based on the viewer's past recommendation results. The recommendation unit can also adjust the recommendation algorithm by referring to the viewer's past recommendation results. For example, the recommendation unit adjusts the recommendation algorithm by referring to the viewer's past recommendation results. The recommendation unit can also reduce recommendation errors by using the viewer's past recommendation results. For example, the recommendation unit reduces recommendation errors by using the viewer's past recommendation results. This improves the accuracy of current recommendations by referring to past recommendation results. Some or all of the above-described processing in the recommendation unit may be performed using AI, for example, or may be performed without using AI. For example, the recommendation unit may input past recommendation result data into the generation AI and cause the generation AI to improve the accuracy of recommendations.

[0049] The recommendation unit can determine the priority of recommendations based on the submission time of the battle status when making a recommendation. The recommendation unit determines the priority of recommendations based on the submission time of the battle status when making a recommendation. The submission time of the battle status includes, for example, the submission date and time, the submission frequency, etc., but is not limited to these examples. The recommendation unit, for example, preferentially recommends the latest battle status. The recommendation unit can also recommend battle statuses that have been submitted earlier but later. For example, the recommendation unit recommends battle statuses that have been submitted earlier but later. The recommendation unit can also dynamically adjust the priority of recommendations based on the submission time of the battle status. For example, the recommendation unit dynamically adjusts the priority of recommendations based on the submission time of the battle status. As a result, by determining the priority of recommendations based on the submission time of the battle status, the latest battle status can be preferentially recommended. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input data on the submission time of the battle situation to the generation AI and have the generation AI determine the priority of the recommendations.

[0050] The recommendation unit can adjust the order of recommendations based on the relevance of the battle situation when making a recommendation. The recommendation unit adjusts the order of recommendations based on the relevance of the battle situation when making a recommendation. The relevance of the battle situation includes, for example, co-occurrence frequency, correlation, etc., but is not limited to these examples. The recommendation unit, for example, preferentially recommends highly relevant battle situations. The recommendation unit can also postpone recommending less relevant battle situations. For example, the recommendation unit postpones recommending less relevant battle situations. The recommendation unit can also dynamically adjust the order of recommendations based on the relevance of the battle situation. For example, the recommendation unit dynamically adjusts the order of recommendations based on the relevance of the battle situation. In this way, by adjusting the order of recommendations based on the relevance of the battle situation, highly relevant battle situations can be preferentially recommended. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input battle situation association data to the generation AI and cause the generation AI to adjust the order of recommendations.

[0051] The recommendation unit can adjust the use of technical terms in the recommendation according to the viewer's level of expertise when making a recommendation. The recommendation unit adjusts the use of technical terms in the recommendation according to the viewer's level of expertise when making a recommendation. The viewer's level of expertise includes, but is not limited to, survey results, past viewing history, etc. For example, if the viewer has technical expertise, the recommendation unit provides a recommendation that uses a lot of technical terms. Furthermore, if the viewer has only general knowledge, the recommendation unit can also provide a recommendation in simple language. For example, if the viewer has only general knowledge, the recommendation unit can provide a recommendation in simple language. Furthermore, the recommendation unit can dynamically adjust the use of technical terms in the recommendation according to the viewer's level of expertise. For example, the recommendation unit dynamically adjusts the use of technical terms in the recommendation according to the viewer's level of expertise. In this way, by adjusting the use of technical terms in the recommendation according to the viewer's level of expertise, it is possible to provide a recommendation that is easier to understand. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input viewer expertise level data to the generation AI and cause the generation AI to adjust the use of technical terms.

[0052] The counting unit can improve the accuracy of counting by referring to the viewer's past viewing history when counting. The counting unit improves the accuracy of counting by referring to the viewer's past viewing history when counting. Past viewing history includes, but is not limited to, a viewing history storage method and a reference procedure. For example, the counting unit improves the accuracy of counting the current number of viewers based on the viewer's past viewing history. The counting unit can also adjust the counting algorithm by referring to the viewer's past viewing history. For example, the counting unit adjusts the counting algorithm by referring to the viewer's past viewing history. The counting unit can also reduce counting errors by using the viewer's past viewing history. For example, the counting unit reduces counting errors by using the viewer's past viewing history. As a result, the accuracy of counting the current number of viewers is improved by referring to the past viewing history. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit can input past viewing history data to a generation AI and cause the generation AI to improve counting accuracy.

[0053] The counting unit may take viewer attribute information into consideration when counting. The counting unit may take viewer attribute information into consideration when counting. Viewer attribute information includes, for example, age, gender, and interests, but is not limited to these examples. The counting unit may count the number of viewers based on attribute information such as the viewer's age and gender. The counting unit may also count the number of viewers with a specific attribute by taking viewer attribute information into consideration. For example, the counting unit may count the number of viewers with a specific attribute by taking viewer attribute information into consideration. The counting unit may also improve the accuracy of the counting based on the viewer attribute information. For example, the counting unit improves the accuracy of the counting based on the viewer attribute information. This allows the number of viewers with a specific attribute to be accurately counted by taking viewer attribute information into consideration. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer attribute information data to a generation AI and cause the generation AI to adjust the counting method.

[0054] The counting unit may take into account the geographical distribution of viewers when counting. The counting unit may take into account the geographical distribution of viewers when counting. Examples of the geographical distribution of viewers include, but are not limited to, GPS data and IP addresses. For example, the counting unit may count the number of viewers for each region based on the geographical distribution of viewers. The counting unit may also count the number of viewers for a specific region by taking into account the geographical distribution of viewers. For example, the counting unit may count the number of viewers for a specific region by taking into account the geographical distribution of viewers. The counting unit may also improve the accuracy of the counting based on the geographical distribution of viewers. For example, the counting unit improves the accuracy of the counting based on the geographical distribution of viewers. This allows the number of viewers for each region to be accurately counted by taking into account the geographical distribution of viewers. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer geographical distribution data to the generation AI and cause the generation AI to adjust the counting method.

[0055] The counting unit may improve the accuracy of counting by referring to viewer-related data when counting. The counting unit improves the accuracy of counting by referring to viewer-related data when counting. Examples of related data include, but are not limited to, viewing history and social media activity. For example, the counting unit improves the accuracy of counting the current number of viewers based on the viewer-related data. The counting unit may also adjust the counting algorithm by referring to the viewer-related data. For example, the counting unit may adjust the counting algorithm by referring to the viewer-related data. The counting unit may also reduce counting errors by using the viewer-related data. For example, the counting unit may reduce counting errors by using the viewer-related data. As a result, the accuracy of counting the current number of viewers is improved by referring to the viewer-related data. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer-related data into a generation AI and cause the generation AI to improve counting accuracy.

[0056] The power-up unit can analyze fluctuations in the number of viewers and select an optimal power-up method during power-up. The power-up unit analyzes fluctuations in the number of viewers and selects an optimal power-up method during power-up. Fluctuations in the number of viewers include, but are not limited to, real-time fluctuations and cumulative fluctuations. For example, the power-up unit can provide a visually stimulating power-up when the number of viewers suddenly increases. The power-up unit can also provide a more subdued power-up method when the number of viewers is stable. The power-up unit can also select an optimal power-up method based on fluctuations in the number of viewers. For example, the power-up unit selects an optimal power-up method based on fluctuations in the number of viewers. This allows the optimal power-up method to be selected by analyzing fluctuations in the number of viewers. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without AI. For example, the power-up unit can input data on fluctuations in the number of viewers into a generation AI and have the generation AI select a power-up method.

[0057] The power-up unit may perform a power-up by taking into consideration the viewer's attribute information. The power-up unit may perform a power-up by taking into consideration the viewer's attribute information. The viewer's attribute information may include, but is not limited to, age, gender, and interests. The power-up unit may adjust the power-up method based on the viewer's attribute information, such as age and gender. The power-up unit may also provide a power-up for a specific attribute by taking into consideration the viewer's attribute information. For example, the power-up unit may provide a power-up for a specific attribute by taking into consideration the viewer's attribute information. The power-up unit may also improve the accuracy of the power-up based on the viewer's attribute information. In this way, the power-up for a specific attribute can be provided by taking into consideration the viewer's attribute information. Some or all of the above-described processing in the power-up unit may be performed using, or without using, AI. For example, the power-up unit may input viewer's attribute information data into a generation AI and cause the generation AI to adjust the power-up method.

[0058] The power-up unit can select an optimal power-up method by taking into account the viewer's geographical location information when powering up. The power-up unit selects an optimal power-up method by taking into account the viewer's geographical location information when powering up. The viewer's geographical location information includes, but is not limited to, GPS data, IP address, etc. For example, the power-up unit provides a power-up method for each region based on the viewer's geographical location information. The power-up unit can also provide a power-up for a specific region by taking into account the viewer's geographical location information. For example, the power-up unit provides a power-up for a specific region by taking into account the viewer's geographical location information. The power-up unit can also improve the accuracy of the power-up based on the viewer's geographical location information. For example, the power-up unit improves the accuracy of the power-up based on the viewer's geographical location information. In this way, the optimal power-up method for each region can be provided by taking into account the viewer's geographical location information. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the power-up unit can input the viewer's geographical location information data into the generation AI and have the generation AI select a power-up method.

[0059] The power-up unit can analyze the viewer's social media activity and suggest a power-up method at the time of power-up. The power-up unit can analyze the viewer's social media activity and suggest a power-up method at the time of power-up. The viewer's social media activity includes, but is not limited to, the content of posts and the number of followers. The power-up unit can, for example, suggest an optimal power-up method based on the viewer's social media activity. The power-up unit can also suggest a power-up method by taking into account the activities of the viewer's friends on social media. For example, the power-up unit can suggest a power-up method by taking into account the activities of the viewer's friends on social media. The power-up unit can also analyze the content of the viewer's social media posts and suggest a related power-up method. For example, the power-up unit can analyze the content of the viewer's social media posts and suggest a related power-up method. In this way, the optimal power-up method can be suggested by analyzing the viewer's social media activity. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the power-up unit can input the viewer's social media activity data into the generation AI and have the generation AI execute suggestions for power-up measures.

[0060] The reception unit can select the optimal reception method by referring to the viewer's past participation history when receiving the request. The reception unit can select the optimal reception method by referring to the viewer's past participation history when receiving the request. The past participation history includes, for example, a history storage method and a reference procedure, but is not limited to these examples. The reception unit can adjust the reception method for the current participation request based on the viewer's past participation history, for example. The reception unit can also adjust the reception algorithm by referring to the viewer's past participation history. For example, the reception unit adjusts the reception algorithm by referring to the viewer's past participation history. The reception unit can also reduce reception errors by using the viewer's past participation history. For example, the reception unit reduces reception errors by using the viewer's past participation history. In this way, the reception method for the current participation request can be adjusted by referring to the viewer's past participation history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the viewer's past participation history data into the generation AI and have the generation AI select the reception method.

[0061] The reception unit may take into consideration viewer attribute information when accepting applications. The reception unit may take into consideration viewer attribute information when accepting applications. Viewer attribute information includes, but is not limited to, age, gender, and interests. The reception unit may adjust the method for accepting participation requests based on attribute information such as the viewer's age and gender. The reception unit may also prioritize accepting participation requests for specific attributes by taking into consideration the viewer attribute information. For example, the reception unit may prioritize accepting participation requests for specific attributes by taking into consideration the viewer attribute information. The reception unit may also improve the accuracy of the reception based on the viewer attribute information. For example, the reception unit may improve the accuracy of the reception based on the viewer attribute information. This allows participation requests for specific attributes to be prioritized by taking into consideration the viewer attribute information. Some or all of the above-described processing by the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input viewer attribute information data to the generation AI and cause the generation AI to adjust the reception method.

[0062] The reception unit may receive requests taking into account the geographical distribution of viewers when receiving the requests. The reception unit may receive requests taking into account the geographical distribution of viewers when receiving the requests. Examples of the geographical distribution of viewers include, but are not limited to, GPS data and IP addresses. For example, the reception unit may receive requests to participate by region based on the geographical distribution of viewers. The reception unit may also preferentially receive requests to participate for specific regions by taking into account the geographical distribution of viewers. For example, the reception unit may preferentially receive requests to participate for specific regions by taking into account the geographical distribution of viewers. The reception unit may also improve the accuracy of the reception based on the geographical distribution of viewers. In this way, by taking into account the geographical distribution of viewers, it is possible to accurately receive requests to participate by region. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input viewer geographical distribution data to the generation AI and cause the generation AI to adjust the reception method.

[0063] The reception unit can improve the accuracy of reception by referring to the viewer's related data when receiving the request. The reception unit improves the accuracy of reception by referring to the viewer's related data when receiving the request. Examples of related data include, but are not limited to, viewing history and social media activity. The reception unit can improve the accuracy of reception of current participation requests, for example, based on the viewer's related data. The reception unit can also adjust the reception algorithm by referring to the viewer's related data. For example, the reception unit adjusts the reception algorithm by referring to the viewer's related data. The reception unit can also reduce reception errors by using the viewer's related data. For example, the reception unit reduces reception errors by using the viewer's related data. As a result, the accuracy of reception of current participation requests is improved by referring to the viewer's related data. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the viewer's related data into the generation AI and cause the generation AI to adjust the reception method.

[0064] When adding a participant, the adding unit can select the optimal addition method by referring to the viewer's past participation history. When adding a participant, the adding unit selects the optimal addition method by referring to the viewer's past participation history. The past participation history includes, for example, a history storage method and a reference procedure, but is not limited to these examples. For example, the adding unit adjusts the addition method for the current participant based on the viewer's past participation history. The adding unit can also adjust the addition algorithm by referring to the viewer's past participation history. For example, the adding unit adjusts the addition algorithm by referring to the viewer's past participation history. The adding unit can also reduce addition errors by using the viewer's past participation history. For example, the adding unit reduces addition errors by using the viewer's past participation history. In this way, the adding unit can adjust the addition method for the current participant by referring to the viewer's past participation history. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input the viewer's past participation history data into the generation AI and cause the generation AI to select an addition method.

[0065] The adding unit may add participants taking into consideration viewer attribute information when adding participants. The adding unit may add participants taking into consideration viewer attribute information when adding participants. Viewer attribute information includes, but is not limited to, age, gender, and interests. The adding unit may adjust a method for adding participants based on attribute information such as the viewer's age and gender. The adding unit may also preferentially add participants with specific attributes by taking into consideration the viewer attribute information. For example, the adding unit may preferentially add participants with specific attributes by taking into consideration the viewer attribute information. The adding unit may also improve the accuracy of the addition based on the viewer attribute information. For example, the adding unit may improve the accuracy of the addition based on the viewer attribute information. In this way, participants with specific attributes can be preferentially added by taking into consideration the viewer attribute information. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input viewer attribute information data to the generation AI and cause the generation AI to adjust the addition method.

[0066] The adding unit may add participants taking into consideration the geographical distribution of viewers when adding participants. The adding unit may add participants taking into consideration the geographical distribution of viewers when adding participants. Examples of the geographical distribution of viewers include, but are not limited to, GPS data and IP addresses. For example, the adding unit may add participants for each region based on the geographical distribution of viewers. The adding unit may also prioritize adding participants for a specific region by taking into consideration the geographical distribution of viewers. For example, the adding unit may prioritize adding participants for a specific region by taking into consideration the geographical distribution of viewers. The adding unit may also improve the accuracy of the addition based on the geographical distribution of viewers. For example, the adding unit improves the accuracy of the addition based on the geographical distribution of viewers. This allows participants for each region to be accurately added by taking into consideration the geographical distribution of viewers. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input viewer geographical distribution data to the generating AI and cause the generating AI to adjust the addition method.

[0067] The adding unit may improve the accuracy of the addition by referring to the viewer's related data when adding the current participant. The adding unit may improve the accuracy of the addition by referring to the viewer's related data when adding the current participant. Examples of related data include, but are not limited to, viewing history and social media activity. The adding unit may improve the accuracy of the addition of the current participant, for example, based on the viewer's related data. The adding unit may also adjust the adding algorithm by referring to the viewer's related data. For example, the adding unit may adjust the adding algorithm by referring to the viewer's related data. The adding unit may also reduce the error of the addition by using the viewer's related data. For example, the adding unit may reduce the error of the addition by using the viewer's related data. As a result, the accuracy of the addition of the current participant is improved by referring to the viewer's related data. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input the viewer's related data to the generation AI and cause the generation AI to adjust the addition method.

[0068] When adding a participant, the adding unit may analyze the viewer's social media activity and refer to related data. When adding a participant, the adding unit may analyze the viewer's social media activity and refer to related data. The viewer's social media activity may include, but is not limited to, the content of posts and the number of followers. The adding unit may add an optimal participant based on, for example, the viewer's social media activity. The adding unit may also add a participant based on the activity of the viewer's friends on social media. For example, the adding unit may add a participant based on the activity of the viewer's friends on social media. The adding unit may also analyze the content of the viewer's social media posts and add a related participant. For example, the adding unit may analyze the content of the viewer's social media posts and add a related participant. In this way, the optimal participant can be added by analyzing the viewer's social media activity. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input the viewer's social media activity data to the generation AI and cause the generation AI to adjust the addition method.

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

[0070] The counting unit can improve the accuracy of counting by referring to the viewer's past viewing history when counting. The past viewing history includes, but is not limited to, a viewing history storage method and a reference procedure. For example, the counting unit improves the accuracy of counting the current number of viewers based on the viewer's past viewing history. The counting unit can also adjust the counting algorithm by referring to the viewer's past viewing history. For example, the counting unit adjusts the counting algorithm by referring to the viewer's past viewing history. The counting unit can also reduce counting errors by using the viewer's past viewing history. For example, the counting unit reduces counting errors by using the viewer's past viewing history. By referring to the past viewing history, the accuracy of counting the current number of viewers is improved. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without AI. For example, the counting unit can input past viewing history data into a generation AI and cause the generation AI to improve counting accuracy.

[0071] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. The importance of the data includes, but is not limited to, the impact of the data and the frequency of use. For example, the analysis unit performs a detailed analysis on important data. The analysis unit can also perform a simplified analysis on general data. For example, the analysis unit performs a simplified analysis on general data. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. For example, the analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the data. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the data. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0072] When making a recommendation, the recommendation unit can adjust the level of detail of the recommendation based on the importance of the game situation. The importance of the game situation includes, for example, the progress of the game and the condition of the players, but is not limited to these examples. For example, the recommendation unit provides a detailed recommendation for an important game situation. The recommendation unit can also provide a simplified recommendation for a general game situation. For example, the recommendation unit provides a simplified recommendation for a general game situation. The recommendation unit can also dynamically adjust the level of detail of the recommendation according to the importance of the game situation. For example, the recommendation unit dynamically adjusts the level of detail of the recommendation according to the importance of the game situation. This enables efficient recommendations by adjusting the level of detail of the recommendation according to the importance of the game situation. Some or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI or without using AI. For example, the recommendation unit can input battle situation importance data into the generation AI and have the generation AI adjust the level of detail of the recommendations.

[0073] The reception unit can select the optimal reception method by referring to the viewer's past participation history when receiving the request. The past participation history includes, for example, a history storage method and a reference procedure, but is not limited to these examples. The reception unit can adjust the reception method for the current participation request based on the viewer's past participation history. The reception unit can also adjust the reception algorithm by referring to the viewer's past participation history. For example, the reception unit adjusts the reception algorithm by referring to the viewer's past participation history. The reception unit can also reduce reception errors by using the viewer's past participation history. For example, the reception unit reduces reception errors by using the viewer's past participation history. In this way, the reception method for the current participation request can be adjusted by referring to the viewer's past participation history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the viewer's past participation history data into the generation AI and have the generation AI select the reception method.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The collection unit collects viewer responses or voting results. Viewer responses include comments, reactions, emotes, etc. The collection unit also collects information on whether viewers selected a specific weapon or supported a specific player. Step 2: The analysis unit analyzes the data collected by the collection unit. Using the generation AI, it analyzes viewer reactions and voting results and recommends optimal game situations to the players. It also analyzes trends in viewer reactions and voting results. Step 3: The recommendation unit recommends the best game situation based on the analysis results obtained by the analysis unit. Based on the game progress and the players' condition, the unit recommends the best game situation and tactics to the players based on the viewers' reactions and voting results.

[0076] (Example 2) A game progress support system according to an embodiment of the present invention collects viewer reactions and voting results, analyzes them using a generation AI, and recommends optimal game situations to players. The game progress support system collects viewer reactions and voting results, analyzes them using a generation AI, and recommends optimal game situations to players. The system also counts the number of viewers and provides power-ups based on the number of viewers. Furthermore, the system also has a function that allows players playing the same game to directly participate in the game. For example, the game progress support system collects viewer reactions and voting results. For example, detailed data such as which weapons and locations viewers selected and which players they are rooting for is collected. Next, the game progress support system uses a generation AI to analyze the collected data. The generation AI analyzes the viewer reactions and voting results and recommends optimal game situations to players. For example, if a large number of viewers selected a specific location, the system recommends a game situation at that location. Next, the game progress support system counts the number of viewers and provides power-ups based on the number of viewers. For example, if the number of viewers exceeds a certain number, the player's abilities are powered up. Next, the game progress support system has a function that allows people playing the same game to directly participate. For example, if a viewer requests to participate, that information is accepted and added to the game. This allows viewers to actively participate in the progress of the game, providing a more enjoyable gaming experience through dialogue and cooperation with players. For example, viewers can give advice to players or cooperate with players to advance the game in their favor. This deepens the bond between viewers and players, providing a more enjoyable gaming experience. This allows the game progress support system to recommend optimal game situations to players based on viewer reactions and voting results. For example, viewers can give advice to players or cooperate with players to advance the game in their favor. This deepens the bond between viewers and players, providing a more enjoyable gaming experience.

[0077] A game progress support system according to an embodiment includes a collection unit, an analysis unit, and a recommendation unit. The collection unit collects viewer responses or voting results. Viewer responses include, but are not limited to, comments, reactions, emotes, and the like. For example, if a viewer selects a specific weapon, the collection unit collects that information. The collection unit can also collect which player the viewer is rooting for. For example, if a viewer sends a cheering message to a specific player, the collection unit collects that information. The analysis unit uses a generation AI to analyze the data collected by the collection unit. The analysis is performed, for example, based on a data analysis method or an algorithm used, but is not limited to, the example. For example, the generation AI analyzes viewer responses and voting results and recommends the optimal battle situation to the player. The analysis unit can also analyze trends in viewer responses and voting results. For example, if a large number of viewers select a specific location, the generation AI recommends a battle situation at that location. The recommendation unit recommends a battle situation based on the analysis results obtained by the analysis unit. Recommendations are made based on, for example, the progress of the game and the status of the players, but are not limited to such examples. For example, the recommendation unit recommends the optimal game situation to the players based on the viewers' reactions and voting results. The recommendation unit can also recommend tactics to the players based on the viewers' reactions and voting results. For example, if a large number of viewers support a particular tactic, the recommendation unit recommends that tactic to the players. In this way, the game progress support system according to the embodiment can recommend the optimal game situation to the players based on the viewers' reactions and voting results.

[0078] The game progress support system includes a counting unit that counts the number of viewers. The counting unit counts the number of viewers. The number of viewers includes, for example, the real-time number of viewers and the cumulative number of viewers, but is not limited to these examples. The counting unit, for example, counts the number of viewers in real time. The counting unit can also count the cumulative number of viewers. For example, the counting unit counts the number of viewers at regular time intervals. The counting unit can also count fluctuations in the number of viewers. For example, if the number of viewers suddenly increases, the counting unit counts the fluctuations. In this way, by counting the number of viewers, it is possible to power up based on the number of viewers. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit can input the count of the number of viewers into an AI model and output the fluctuations in the number of viewers.

[0079] The game progress support system includes a power-up unit that performs power-up based on the number of viewers counted by the counting unit. The power-up unit performs power-up based on the number of viewers counted by the counting unit. Examples of power-up include, but are not limited to, improving a player's abilities and strengthening a weapon. For example, the power-up unit improves a player's abilities when the number of viewers exceeds a certain number. The power-up unit can also strengthen weapons based on the number of viewers. For example, when the number of viewers increases, the attacking power of the weapon is strengthened. The power-up unit can also strengthen defensive power based on the number of viewers. For example, when the number of viewers decreases, the defensive power is strengthened. In this way, the player's abilities can be powered up based on the number of viewers. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the power-up unit can input viewer count data into an AI model and output a power-up method.

[0080] The game progress support system includes a reception unit that receives information when a user playing the same game requests to participate. The reception unit receives the information when a user playing the same game requests to participate. The request to participate may include, but is not limited to, a method for submitting the request and conditions for acceptance. For example, the reception unit receives information when a user requests to participate. The reception unit can also receive a method for submitting the request. For example, when a user submits a request to participate through an online form, the reception unit receives the information. The reception unit can also set conditions for accepting the request to participate. For example, the reception unit only accepts requests from users who meet certain conditions. This allows viewers to directly participate in the game. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the request to participate into an AI model and output a method for accepting the request.

[0081] The game progress support system includes an adding unit that adds a participant to the game based on the participation request received by the receiving unit. The adding unit adds the participant to the game based on the participation request received by the receiving unit. The adding of the participant includes, for example, an adding procedure and an adding condition, but is not limited to these examples. The adding unit adds the participant based on the participation request received by the receiving unit. The adding unit can also set a procedure for adding the participant. For example, the participant is added according to a specific procedure. The adding unit can also set conditions for adding the participant. For example, only participants who meet specific conditions are added. In this way, the participant can be added to the game based on the participation request received. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input data of the participation request into an AI model and output a method for adding the participant.

[0082] The collection unit can estimate viewer emotions and adjust the timing of collecting responses and voting results based on the estimated viewer emotions. The collection unit can estimate viewer emotions and adjust the timing of collecting responses and voting results based on the estimated viewer emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, when a viewer is excited, the collection unit collects responses and voting results in real time. Also, when a viewer is relaxed, the collection unit can collect responses and voting results at regular intervals. For example, when a viewer is relaxed, the collection unit collects responses and voting results at regular intervals. Also, when a viewer is concentrated, the collection unit can collect responses and voting results immediately after an important event. For example, when a viewer is concentrated, the collection unit collects responses and voting results immediately after an important event. This allows for more appropriate data collection by adjusting the collection timing according to the viewer emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit may input viewer emotion data into the generation AI and cause the generation AI to adjust the collection timing.

[0083] The collection unit can analyze the viewer's past reaction history and select an appropriate collection method. The collection unit analyzes the viewer's past reaction history and selects an appropriate collection method. Past reaction history includes, for example, timings at which the viewer frequently reacted in the past, voting patterns, reactions to specific events, etc., but is not limited to these examples. The collection unit selects the optimal collection timing based on, for example, timings at which the viewer frequently reacted in the past. The collection unit can also analyze the viewer's past voting patterns and select the optimal collection method. For example, the collection unit selects the optimal collection method based on the viewer's past voting patterns. The collection unit can also predict reactions to specific events from the viewer's past reaction history and adjust the collection method. For example, the collection unit predicts reactions to specific events from the viewer's past reaction history and adjusts the collection method. By selecting the optimal collection method based on the past reaction history, the accuracy of data collection is improved. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or without AI. For example, the collection unit can input viewers' past reaction history data into the generation AI and have the generation AI select the optimal collection method.

[0084] The collection unit may filter responses and voting results based on the viewer's current areas of interest when collecting the responses and voting results. The collection unit may filter responses and voting results based on the viewer's current areas of interest when collecting the responses and voting results. Viewer areas of interest include, but are not limited to, weapons, locations, and specific players. For example, the collection unit may preferentially collect responses and voting results related to weapons and locations in which the viewer is currently interested. Furthermore, if a viewer is interested in a specific player, the collection unit may preferentially collect responses and voting results related to that player. For example, if a viewer is interested in a specific player, the collection unit may preferentially collect responses and voting results related to that player. Furthermore, the collection unit may filter and collect highly relevant data based on the viewer's current areas of interest. For example, the collection unit may filter and collect highly relevant data based on the viewer's current areas of interest. In this way, highly relevant data can be collected by filtering data based on the viewer's areas of interest. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input viewer interest area data into the generation AI and have the generation AI perform filtering.

[0085] The collection unit can select the optimal collection means depending on the viewer's input method when collecting reactions or voting results. The collection unit selects the optimal collection means depending on the viewer's input method when collecting reactions or voting results. Viewer input methods include, but are not limited to, voice, text, and images. For example, when viewers react or vote using voice, the collection unit collects data using voice recognition technology. Furthermore, when viewers react or vote using text, the collection unit can also collect data using text analysis technology. For example, when viewers react or vote using text, the collection unit collects data using text analysis technology. Furthermore, when viewers react or vote using images, the collection unit can also collect data using image recognition technology. For example, when viewers react or vote using images, the collection unit collects data using image recognition technology. This improves the efficiency of data collection by selecting the optimal collection means depending on the viewer's input method. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input viewer input method data into the generation AI and have the generation AI select the optimal collection method.

[0086] The collection unit can estimate viewer emotions and prioritize data to be collected based on the estimated viewer emotions. The collection unit can estimate viewer emotions and prioritize data to be collected based on the estimated viewer emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, when a viewer is excited, the collection unit prioritizes collecting important reactions and voting results. Furthermore, when a viewer is relaxed, the collection unit can collect overall reactions and voting results evenly. For example, when a viewer is relaxed, the collection unit collects overall reactions and voting results evenly. Furthermore, when a viewer is concentrated, the collection unit can prioritize collecting reactions and voting results related to a specific event. For example, when a viewer is concentrated, the collection unit prioritizes collecting reactions and voting results related to a specific event. In this way, by prioritizing data according to viewer emotions, important data can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit may input viewer emotion data into the generation AI and have the generation AI determine the priority of the data.

[0087] When collecting responses and voting results, the collection unit can prioritize collecting highly relevant data by taking into account the viewer's geographical location information. When collecting responses and voting results, the collection unit prioritizes collecting highly relevant data by taking into account the viewer's geographical location information. Examples of viewer's geographical location information include, but are not limited to, GPS data and IP addresses. For example, if viewers are concentrated in a specific area, the collection unit prioritizes collecting data related to that area. The collection unit can also collect responses and voting results by area based on the viewer's geographical location information. For example, the collection unit collects responses and voting results by area based on the viewer's geographical location information. The collection unit can also collect data reflecting regional trends by taking into account the viewer's geographical location information. For example, the collection unit collects data reflecting regional trends by taking into account the viewer's geographical location information. In this way, highly relevant data for each area can be collected by taking into account the viewer's geographical location information. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the viewer's geographic location data into the generation AI and cause the generation AI to collect highly relevant data.

[0088] The collection unit can analyze viewers' social media activities and collect related data when collecting reactions and voting results. The collection unit analyzes viewers' social media activities and collects related data when collecting reactions and voting results. Viewers' social media activities include, but are not limited to, post content and the number of followers. The collection unit collects, for example, reactions shared by viewers on social media and voting results. The collection unit can also analyze viewers' social media activities and collect related data. For example, the collection unit analyzes viewers' social media activities and collects related data. The collection unit can also collect related data by referring to the activities of the viewers' friends on social media. For example, the collection unit collects related data by referring to the activities of the viewers' friends on social media. In this way, highly relevant data can be collected by analyzing the viewers' social media activities. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input viewers' social media activity data into the generation AI and cause the generation AI to collect related data.

[0089] The collection unit can customize the collection method by reflecting past viewer feedback when collecting reactions and voting results. The collection unit customizes the collection method by reflecting past viewer feedback when collecting reactions and voting results. Past feedback includes, but is not limited to, survey results and comment history. The collection unit customizes the optimal collection method, for example, based on feedback provided by viewers in the past. The collection unit can also adjust the collection timing by reflecting past viewer feedback. For example, the collection unit adjusts the collection timing by reflecting past viewer feedback. The collection unit can also customize the collection means by referring to past viewer feedback. For example, the collection unit customizes the collection means by referring to past viewer feedback. In this way, the optimal collection method can be customized by reflecting past viewer feedback. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past viewer feedback data into a generation AI and cause the generation AI to customize the collection method.

[0090] The analysis unit can estimate the viewer's emotion and adjust the way the analysis is presented based on the estimated viewer's emotion. The analysis unit can estimate the viewer's emotion and adjust the way the analysis is presented based on the estimated viewer's emotion. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the analysis unit can provide a visually stimulating analysis result. Furthermore, if the viewer is relaxed, the analysis unit can provide the analysis result in a calm way. For example, if the viewer is relaxed, the analysis unit can provide the analysis result in a calm way. Furthermore, if the viewer is concentrated, the analysis unit can provide a detailed analysis result. For example, if the viewer is concentrated, the analysis unit can provide a detailed analysis result. In this way, by adjusting the way the analysis is presented based on the viewer's emotion, more appropriate analysis results can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input viewer emotion data into the generation AI and have the generation AI adjust the method of expressing the analysis.

[0091] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the data during analysis. The importance of the data includes, for example, the impact of the data and the frequency of use, but is not limited to these examples. For example, the analysis unit performs a detailed analysis on important data. The analysis unit can also perform a simplified analysis on general data. For example, the analysis unit performs a simplified analysis on general data. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. For example, the analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the data. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0092] The analysis unit can apply different analysis algorithms depending on the data category during analysis. The analysis unit applies different analysis algorithms depending on the data category during analysis. Data categories include, but are not limited to, text data, numerical data, etc. The analysis unit can apply a specific analysis algorithm to data related to weapons, for example. The analysis unit can also apply a different analysis algorithm to data related to locations. For example, the analysis unit can apply a different analysis algorithm to data related to locations. The analysis unit can also select an optimal analysis algorithm depending on the data category. For example, the analysis unit selects an optimal analysis algorithm depending on the data category. This improves the accuracy of the analysis by applying the optimal analysis algorithm depending on the data category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the data category to the generation AI and cause the generation AI to select an analysis algorithm.

[0093] The analysis unit can improve the accuracy of the analysis by referring to the viewer's past analysis results during analysis. The analysis unit improves the accuracy of the analysis by referring to the viewer's past analysis results during analysis. Past analysis results include, but are not limited to, methods for saving and referencing analysis results. The analysis unit can improve the accuracy of the current analysis, for example, based on the viewer's past analysis results. The analysis unit can also adjust the analysis algorithm by referring to the viewer's past analysis results. For example, the analysis unit can adjust the analysis algorithm by referring to the viewer's past analysis results. The analysis unit can also reduce analysis errors by using the viewer's past analysis results. For example, the analysis unit can reduce analysis errors by using the viewer's past analysis results. As a result, the accuracy of the current analysis is improved by referring to the past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0094] The analysis unit can estimate the viewer's emotion and adjust the length of the analysis based on the estimated viewer's emotion. The analysis unit can estimate the viewer's emotion and adjust the length of the analysis based on the estimated viewer's emotion. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the analysis unit can provide a short and concise analysis. Also, if the viewer is relaxed, the analysis unit can provide a detailed analysis. For example, if the viewer is relaxed, the analysis unit can provide a detailed analysis. Also, if the viewer is concentrated, the analysis unit can provide a longer analysis. For example, if the viewer is concentrated, the analysis unit can provide a longer analysis. In this way, by adjusting the length of the analysis according to the viewer's emotion, more appropriate analysis results can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input viewer emotion data into the generation AI and have the generation AI adjust the length of the analysis.

[0095] The analysis unit can determine the analysis priority based on the time of data submission during analysis. The analysis unit determines the analysis priority based on the time of data submission during analysis. The time of data submission includes, but is not limited to, the submission date and time, the submission frequency, etc. The analysis unit, for example, prioritizes analysis of the most recent data. The analysis unit can also postpone analysis of data submitted earlier. For example, the analysis unit postpones analysis of data submitted earlier. The analysis unit can also dynamically adjust the analysis priority based on the time of data submission. For example, the analysis unit dynamically adjusts the analysis priority based on the time of data submission. In this way, by determining the analysis priority based on the time of data submission, the most recent data can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the time of data submission to the generation AI and have the generation AI determine the analysis priority.

[0096] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. The analysis unit adjusts the order of analysis based on the relevance of the data during analysis. Data relevance includes, but is not limited to, co-occurrence frequency, correlation, etc. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. For example, the analysis unit postpones analysis of less relevant data. The analysis unit can also dynamically adjust the order of analysis based on the relevance of the data. For example, the analysis unit dynamically adjusts the order of analysis based on the relevance of the data. In this way, by adjusting the order of analysis based on the relevance of the data, highly relevant data can be prioritized for analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the relevance of the data to the generation AI and cause the generation AI to adjust the order of analysis.

[0097] The analysis unit can adjust the use of technical terms in the analysis according to the viewer's level of expertise during analysis. The analysis unit can adjust the use of technical terms in the analysis according to the viewer's level of expertise during analysis. The viewer's level of expertise includes, but is not limited to, survey results, past viewing history, etc. For example, if the viewer has specialized knowledge, the analysis unit can provide an analysis that uses a lot of technical terms. Furthermore, if the viewer has only general knowledge, the analysis unit can provide an analysis in simple language. For example, if the viewer has only general knowledge, the analysis unit can provide an analysis in simple language. Furthermore, the analysis unit can dynamically adjust the use of technical terms in the analysis according to the viewer's level of expertise. For example, the analysis unit dynamically adjusts the use of technical terms in the analysis according to the viewer's level of expertise. By adjusting the use of technical terms in the analysis according to the viewer's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the viewer's expertise level data into the generation AI and have the generation AI adjust the use of technical terms.

[0098] The recommendation unit can estimate the viewer's emotions and adjust the way recommendations are expressed based on the estimated viewer's emotions. The recommendation unit can estimate the viewer's emotions and adjust the way recommendations are expressed based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the recommendation unit can provide a visually stimulating recommendation. Also, if the viewer is relaxed, the recommendation unit can provide a recommendation using a calm expression. For example, if the viewer is relaxed, the recommendation unit can provide a recommendation using a calm expression. Also, if the viewer is concentrating, the recommendation unit can provide a detailed recommendation. For example, if the viewer is concentrating, the recommendation unit can provide a detailed recommendation. This allows for more appropriate recommendations to be provided by adjusting the way recommendations are expressed according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recommendation unit may be performed using AI, or may be performed without using AI. For example, the recommendation unit may input viewer emotional data into the generation AI and cause the generation AI to adjust the way the recommendation is expressed.

[0099] The recommendation unit can adjust the level of detail of the recommendation based on the importance of the battle situation when making a recommendation. The recommendation unit adjusts the level of detail of the recommendation based on the importance of the battle situation when making a recommendation. The importance of the battle situation includes, for example, the progress of the game, the status of the players, etc., but is not limited to these examples. The recommendation unit, for example, provides a detailed recommendation for an important battle situation. The recommendation unit can also provide a simplified recommendation for a general battle situation. For example, the recommendation unit provides a simplified recommendation for a general battle situation. The recommendation unit can also dynamically adjust the level of detail of the recommendation according to the importance of the battle situation. For example, the recommendation unit dynamically adjusts the level of detail of the recommendation according to the importance of the battle situation. This enables efficient recommendations by adjusting the level of detail of the recommendation according to the importance of the battle situation. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input battle situation importance data to the generation AI and cause the generation AI to adjust the level of detail of the recommendation.

[0100] The recommendation unit can apply different recommendation algorithms depending on the category of the battle situation when making a recommendation. The recommendation unit applies different recommendation algorithms depending on the category of the battle situation when making a recommendation. The battle situation categories include, for example, attack phase, defense phase, etc., but are not limited to these examples. The recommendation unit applies a specific recommendation algorithm to, for example, a battle situation related to weapons. The recommendation unit can also apply a different recommendation algorithm to a battle situation related to a location. For example, the recommendation unit applies a different recommendation algorithm to a battle situation related to a location. The recommendation unit can also select an optimal recommendation algorithm depending on the category of the battle situation. For example, the recommendation unit selects an optimal recommendation algorithm depending on the category of the battle situation. As a result, by applying the optimal recommendation algorithm depending on the category of the battle situation, the accuracy of the recommendation is improved. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input battle situation category data to the generation AI and have the generation AI select a recommendation algorithm.

[0101] The recommendation unit can improve the accuracy of recommendations by referring to the viewer's past recommendation results when making recommendations. The recommendation unit improves the accuracy of recommendations by referring to the viewer's past recommendation results when making recommendations. Past recommendation results include, for example, a method for saving recommendation results and a procedure for referencing them, but are not limited to these examples. The recommendation unit improves the accuracy of current recommendations, for example, based on the viewer's past recommendation results. The recommendation unit can also adjust the recommendation algorithm by referring to the viewer's past recommendation results. For example, the recommendation unit adjusts the recommendation algorithm by referring to the viewer's past recommendation results. The recommendation unit can also reduce recommendation errors by using the viewer's past recommendation results. For example, the recommendation unit reduces recommendation errors by using the viewer's past recommendation results. This improves the accuracy of current recommendations by referring to past recommendation results. Some or all of the above-described processing in the recommendation unit may be performed using AI, for example, or may be performed without using AI. For example, the recommendation unit may input past recommendation result data into the generation AI and cause the generation AI to improve the accuracy of recommendations.

[0102] The recommendation unit can estimate the viewer's emotions and adjust the length of the recommendation based on the estimated viewer's emotions. The recommendation unit can estimate the viewer's emotions and adjust the length of the recommendation based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the recommendation unit can provide a short and to-the-point recommendation. Also, if the viewer is relaxed, the recommendation unit can provide a detailed recommendation. For example, if the viewer is relaxed, the recommendation unit can provide a detailed recommendation. Also, if the viewer is focused, the recommendation unit can provide a longer recommendation. For example, if the viewer is focused, the recommendation unit can provide a longer recommendation. In this way, by adjusting the length of the recommendation according to the viewer's emotions, more appropriate recommendations can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recommendation unit may be performed using AI, or may be performed without using AI. For example, the recommendation unit may input viewer emotion data into the generation AI and cause the generation AI to adjust the length of the recommendation.

[0103] The recommendation unit can determine the priority of recommendations based on the submission time of the battle status when making a recommendation. The recommendation unit determines the priority of recommendations based on the submission time of the battle status when making a recommendation. The submission time of the battle status includes, for example, the submission date and time, the submission frequency, etc., but is not limited to these examples. The recommendation unit, for example, preferentially recommends the latest battle status. The recommendation unit can also recommend battle statuses that have been submitted earlier but later. For example, the recommendation unit recommends battle statuses that have been submitted earlier but later. The recommendation unit can also dynamically adjust the priority of recommendations based on the submission time of the battle status. For example, the recommendation unit dynamically adjusts the priority of recommendations based on the submission time of the battle status. As a result, by determining the priority of recommendations based on the submission time of the battle status, the latest battle status can be preferentially recommended. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input data on the submission time of the battle situation to the generation AI and have the generation AI determine the priority of the recommendations.

[0104] The recommendation unit can adjust the order of recommendations based on the relevance of the battle situation when making a recommendation. The recommendation unit adjusts the order of recommendations based on the relevance of the battle situation when making a recommendation. The relevance of the battle situation includes, for example, co-occurrence frequency, correlation, etc., but is not limited to these examples. The recommendation unit, for example, preferentially recommends highly relevant battle situations. The recommendation unit can also postpone recommending less relevant battle situations. For example, the recommendation unit postpones recommending less relevant battle situations. The recommendation unit can also dynamically adjust the order of recommendations based on the relevance of the battle situation. For example, the recommendation unit dynamically adjusts the order of recommendations based on the relevance of the battle situation. In this way, by adjusting the order of recommendations based on the relevance of the battle situation, highly relevant battle situations can be preferentially recommended. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input battle situation association data to the generation AI and cause the generation AI to adjust the order of recommendations.

[0105] The recommendation unit can adjust the use of technical terms in the recommendation according to the viewer's level of expertise when making a recommendation. The recommendation unit adjusts the use of technical terms in the recommendation according to the viewer's level of expertise when making a recommendation. The viewer's level of expertise includes, but is not limited to, survey results, past viewing history, etc. For example, if the viewer has technical expertise, the recommendation unit provides a recommendation that uses a lot of technical terms. Furthermore, if the viewer has only general knowledge, the recommendation unit can also provide a recommendation in simple language. For example, if the viewer has only general knowledge, the recommendation unit can provide a recommendation in simple language. Furthermore, the recommendation unit can dynamically adjust the use of technical terms in the recommendation according to the viewer's level of expertise. For example, the recommendation unit dynamically adjusts the use of technical terms in the recommendation according to the viewer's level of expertise. In this way, by adjusting the use of technical terms in the recommendation according to the viewer's level of expertise, it is possible to provide a recommendation that is easier to understand. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input viewer expertise level data to the generation AI and cause the generation AI to adjust the use of technical terms.

[0106] The counting unit can estimate the viewer's emotions and adjust the viewer counting method based on the estimated viewer's emotions. The counting unit can estimate the viewer's emotions and adjust the viewer counting method based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, when a viewer is excited, the counting unit counts the viewer number in real time. Also, when a viewer is relaxed, the counting unit can count the viewer number at regular time intervals. For example, when a viewer is relaxed, the counting unit counts the viewer number at regular time intervals. Also, when a viewer is concentrated, the counting unit can count the viewer number immediately after an important event. For example, when a viewer is concentrated, the counting unit counts the viewer number immediately after an important event. This allows for more accurate viewer counting by adjusting the counting method according to the viewer's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer emotion data into the generation AI and have the generation AI adjust the counting method.

[0107] The counting unit can improve the accuracy of counting by referring to the viewer's past viewing history when counting. The counting unit improves the accuracy of counting by referring to the viewer's past viewing history when counting. Past viewing history includes, but is not limited to, a viewing history storage method and a reference procedure. For example, the counting unit improves the accuracy of counting the current number of viewers based on the viewer's past viewing history. The counting unit can also adjust the counting algorithm by referring to the viewer's past viewing history. For example, the counting unit adjusts the counting algorithm by referring to the viewer's past viewing history. The counting unit can also reduce counting errors by using the viewer's past viewing history. For example, the counting unit reduces counting errors by using the viewer's past viewing history. As a result, the accuracy of counting the current number of viewers is improved by referring to the past viewing history. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit can input past viewing history data to a generation AI and cause the generation AI to improve counting accuracy.

[0108] The counting unit may take viewer attribute information into consideration when counting. The counting unit may take viewer attribute information into consideration when counting. Viewer attribute information includes, for example, age, gender, and interests, but is not limited to these examples. The counting unit may count the number of viewers based on attribute information such as the viewer's age and gender. The counting unit may also count the number of viewers with a specific attribute by taking viewer attribute information into consideration. For example, the counting unit may count the number of viewers with a specific attribute by taking viewer attribute information into consideration. The counting unit may also improve the accuracy of the counting based on the viewer attribute information. For example, the counting unit improves the accuracy of the counting based on the viewer attribute information. This allows the number of viewers with a specific attribute to be accurately counted by taking viewer attribute information into consideration. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer attribute information data to a generation AI and cause the generation AI to adjust the counting method.

[0109] The counting unit can estimate the viewer's emotions and adjust the display method of the counting results based on the estimated viewer's emotions. The counting unit can estimate the viewer's emotions and adjust the display method of the counting results based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the counting unit can provide a visually stimulating display method. Furthermore, if the viewer is relaxed, the counting unit can provide the counting results in a calm display method. For example, if the viewer is relaxed, the counting unit can provide the counting results in a calm display method. Furthermore, if the viewer is concentrated, the counting unit can provide detailed counting results. For example, if the viewer is concentrated, the counting unit can provide detailed counting results. This allows for more appropriate display by adjusting the display method of the counting results according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer emotion data into the generating AI and have the generating AI adjust the display method of the counting results.

[0110] The counting unit may take into account the geographical distribution of viewers when counting. The counting unit may take into account the geographical distribution of viewers when counting. Examples of the geographical distribution of viewers include, but are not limited to, GPS data and IP addresses. For example, the counting unit may count the number of viewers for each region based on the geographical distribution of viewers. The counting unit may also count the number of viewers for a specific region by taking into account the geographical distribution of viewers. For example, the counting unit may count the number of viewers for a specific region by taking into account the geographical distribution of viewers. The counting unit may also improve the accuracy of the counting based on the geographical distribution of viewers. For example, the counting unit improves the accuracy of the counting based on the geographical distribution of viewers. This allows the number of viewers for each region to be accurately counted by taking into account the geographical distribution of viewers. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer geographical distribution data to the generation AI and cause the generation AI to adjust the counting method.

[0111] The counting unit may improve the accuracy of counting by referring to viewer-related data when counting. The counting unit improves the accuracy of counting by referring to viewer-related data when counting. Examples of related data include, but are not limited to, viewing history and social media activity. For example, the counting unit improves the accuracy of counting the current number of viewers based on the viewer-related data. The counting unit may also adjust the counting algorithm by referring to the viewer-related data. For example, the counting unit may adjust the counting algorithm by referring to the viewer-related data. The counting unit may also reduce counting errors by using the viewer-related data. For example, the counting unit may reduce counting errors by using the viewer-related data. As a result, the accuracy of counting the current number of viewers is improved by referring to the viewer-related data. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without using AI. For example, the counting unit may input viewer-related data into a generation AI and cause the generation AI to improve counting accuracy.

[0112] The power-up unit can estimate the viewer's emotions and adjust the power-up method based on the estimated viewer's emotions. The power-up unit can estimate the viewer's emotions and adjust the power-up method based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the power-up unit can provide a visually stimulating power-up. Also, if the viewer is relaxed, the power-up unit can provide a calm power-up method. For example, if the viewer is relaxed, the power-up unit can provide a calm power-up method. Also, if the viewer is concentrated, the power-up unit can provide a detailed power-up method. For example, if the viewer is concentrated, the power-up unit can provide a detailed power-up method. This allows for more effective power-up by adjusting the power-up method according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the power-up unit may be performed using AI, for example, or may be performed without using AI. For example, the power-up unit may input viewer emotion data into the generation AI and have the generation AI adjust the power-up method.

[0113] The power-up unit can analyze fluctuations in the number of viewers and select an optimal power-up method during power-up. The power-up unit analyzes fluctuations in the number of viewers and selects an optimal power-up method during power-up. Fluctuations in the number of viewers include, but are not limited to, real-time fluctuations and cumulative fluctuations. For example, the power-up unit can provide a visually stimulating power-up when the number of viewers suddenly increases. The power-up unit can also provide a more subdued power-up method when the number of viewers is stable. The power-up unit can also select an optimal power-up method based on fluctuations in the number of viewers. For example, the power-up unit selects an optimal power-up method based on fluctuations in the number of viewers. This allows the optimal power-up method to be selected by analyzing fluctuations in the number of viewers. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without AI. For example, the power-up unit can input data on fluctuations in the number of viewers into a generation AI and have the generation AI select a power-up method.

[0114] The power-up unit may perform a power-up by taking into consideration the viewer's attribute information. The power-up unit may perform a power-up by taking into consideration the viewer's attribute information. The viewer's attribute information may include, but is not limited to, age, gender, and interests. The power-up unit may adjust the power-up method based on the viewer's attribute information, such as age and gender. The power-up unit may also provide a power-up for a specific attribute by taking into consideration the viewer's attribute information. For example, the power-up unit may provide a power-up for a specific attribute by taking into consideration the viewer's attribute information. The power-up unit may also improve the accuracy of the power-up based on the viewer's attribute information. In this way, the power-up for a specific attribute can be provided by taking into consideration the viewer's attribute information. Some or all of the above-described processing in the power-up unit may be performed using, or without using, AI. For example, the power-up unit may input viewer's attribute information data into a generation AI and cause the generation AI to adjust the power-up method.

[0115] The power-up unit can estimate the viewer's emotions and prioritize power-ups based on the estimated viewer's emotions. The power-up unit can estimate the viewer's emotions and prioritize power-ups based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the power-up unit can prioritize providing visually stimulating power-ups. Also, if the viewer is relaxed, the power-up unit can prioritize providing calming power-up methods. For example, if the viewer is relaxed, the power-up unit can prioritize providing calming power-up methods. Also, if the viewer is focused, the power-up unit can prioritize providing detailed power-up methods. For example, if the viewer is focused, the power-up unit can prioritize providing detailed power-up methods. This enables more effective power-ups by prioritizing power-ups according to the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the power-up unit may be performed using AI, or may be performed without using AI. For example, the power-up unit may input viewer emotional data into the generation AI and have the generation AI determine the priority of power-ups.

[0116] The power-up unit can select an optimal power-up method by taking into account the viewer's geographical location information when powering up. The power-up unit selects an optimal power-up method by taking into account the viewer's geographical location information when powering up. The viewer's geographical location information includes, but is not limited to, GPS data, IP address, etc. For example, the power-up unit provides a power-up method for each region based on the viewer's geographical location information. The power-up unit can also provide a power-up for a specific region by taking into account the viewer's geographical location information. For example, the power-up unit provides a power-up for a specific region by taking into account the viewer's geographical location information. The power-up unit can also improve the accuracy of the power-up based on the viewer's geographical location information. For example, the power-up unit improves the accuracy of the power-up based on the viewer's geographical location information. In this way, the optimal power-up method for each region can be provided by taking into account the viewer's geographical location information. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the power-up unit can input the viewer's geographical location information data into the generation AI and have the generation AI select a power-up method.

[0117] The power-up unit can analyze the viewer's social media activity and suggest a power-up method at the time of power-up. The power-up unit can analyze the viewer's social media activity and suggest a power-up method at the time of power-up. The viewer's social media activity includes, but is not limited to, the content of posts and the number of followers. The power-up unit can, for example, suggest an optimal power-up method based on the viewer's social media activity. The power-up unit can also suggest a power-up method by taking into account the activities of the viewer's friends on social media. For example, the power-up unit can suggest a power-up method by taking into account the activities of the viewer's friends on social media. The power-up unit can also analyze the content of the viewer's social media posts and suggest a related power-up method. For example, the power-up unit can analyze the content of the viewer's social media posts and suggest a related power-up method. In this way, the optimal power-up method can be suggested by analyzing the viewer's social media activity. Some or all of the above-described processing in the power-up unit may be performed using, for example, AI, or may be performed without using AI. For example, the power-up unit can input the viewer's social media activity data into the generation AI and have the generation AI execute suggestions for power-up measures.

[0118] The reception unit can estimate the viewer's emotions and adjust the method for accepting participation requests based on the estimated viewer's emotions. The reception unit can estimate the viewer's emotions and adjust the method for accepting participation requests based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the reception unit can accept participation requests using a simple procedure. Also, if the viewer is relaxed, the reception unit can accept participation requests using a detailed procedure. For example, if the viewer is relaxed, the reception unit can accept participation requests using a detailed procedure. Also, if there is a concentration of viewers, the reception unit can prioritize accepting participation requests that meet certain conditions. For example, if there is a concentration of viewers, the reception unit prioritizes accepting participation requests that meet certain conditions. This allows for more appropriate acceptance by adjusting the method for accepting participation requests based on the viewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input viewer emotion data into the generation AI and cause the generation AI to adjust the reception method.

[0119] The reception unit can select the optimal reception method by referring to the viewer's past participation history when receiving the request. The reception unit can select the optimal reception method by referring to the viewer's past participation history when receiving the request. The past participation history includes, for example, a history storage method and a reference procedure, but is not limited to these examples. The reception unit can adjust the reception method for the current participation request based on the viewer's past participation history, for example. The reception unit can also adjust the reception algorithm by referring to the viewer's past participation history. For example, the reception unit adjusts the reception algorithm by referring to the viewer's past participation history. The reception unit can also reduce reception errors by using the viewer's past participation history. For example, the reception unit reduces reception errors by using the viewer's past participation history. In this way, the reception method for the current participation request can be adjusted by referring to the viewer's past participation history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the viewer's past participation history data into the generation AI and have the generation AI select the reception method.

[0120] The reception unit may take into consideration viewer attribute information when accepting applications. The reception unit may take into consideration viewer attribute information when accepting applications. Viewer attribute information includes, but is not limited to, age, gender, and interests. The reception unit may adjust the method for accepting participation requests based on attribute information such as the viewer's age and gender. The reception unit may also prioritize accepting participation requests for specific attributes by taking into consideration the viewer attribute information. For example, the reception unit may prioritize accepting participation requests for specific attributes by taking into consideration the viewer attribute information. The reception unit may also improve the accuracy of the reception based on the viewer attribute information. For example, the reception unit may improve the accuracy of the reception based on the viewer attribute information. This allows participation requests for specific attributes to be prioritized by taking into consideration the viewer attribute information. Some or all of the above-described processing by the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit may input viewer attribute information data to the generation AI and cause the generation AI to adjust the reception method.

[0121] The reception unit can estimate the viewer's emotion and adjust the display method of the reception result based on the estimated viewer's emotion. The reception unit can estimate the viewer's emotion and adjust the display method of the reception result based on the estimated viewer's emotion. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the reception unit can provide a visually stimulating display method. Furthermore, if the viewer is relaxed, the reception unit can provide the reception result in a calm display method. For example, if the viewer is relaxed, the reception unit can provide the reception result in a calm display method. Furthermore, if the viewer is concentrated, the reception unit can provide detailed reception results. For example, if the viewer is concentrated, the reception unit provides detailed reception results. This enables more appropriate display by adjusting the display method of the reception result according to the viewer's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input viewer emotion data into the generation AI and cause the generation AI to adjust the display method of the reception result.

[0122] The reception unit may receive requests taking into account the geographical distribution of viewers when receiving the requests. The reception unit may receive requests taking into account the geographical distribution of viewers when receiving the requests. Examples of the geographical distribution of viewers include, but are not limited to, GPS data and IP addresses. For example, the reception unit may receive requests to participate by region based on the geographical distribution of viewers. The reception unit may also preferentially receive requests to participate for specific regions by taking into account the geographical distribution of viewers. For example, the reception unit may preferentially receive requests to participate for specific regions by taking into account the geographical distribution of viewers. The reception unit may also improve the accuracy of the reception based on the geographical distribution of viewers. In this way, by taking into account the geographical distribution of viewers, it is possible to accurately receive requests to participate by region. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input viewer geographical distribution data to the generation AI and cause the generation AI to adjust the reception method.

[0123] The reception unit can improve the accuracy of reception by referring to the viewer's related data when receiving the request. The reception unit improves the accuracy of reception by referring to the viewer's related data when receiving the request. Examples of related data include, but are not limited to, viewing history and social media activity. The reception unit can improve the accuracy of reception of current participation requests, for example, based on the viewer's related data. The reception unit can also adjust the reception algorithm by referring to the viewer's related data. For example, the reception unit adjusts the reception algorithm by referring to the viewer's related data. The reception unit can also reduce reception errors by using the viewer's related data. For example, the reception unit reduces reception errors by using the viewer's related data. As a result, the accuracy of reception of current participation requests is improved by referring to the viewer's related data. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the viewer's related data into the generation AI and cause the generation AI to adjust the reception method.

[0124] The adding unit can estimate the viewer's emotions and adjust the method for adding participants based on the estimated viewer's emotions. The adding unit can estimate the viewer's emotions and adjust the method for adding participants based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, when the viewer is excited, the adding unit can quickly add participants. Furthermore, when the viewer is relaxed, the adding unit can add participants using a detailed procedure. For example, when the viewer is relaxed, the adding unit can add participants using a detailed procedure. Furthermore, when the viewer is concentrated, the adding unit can prioritize adding participants that meet certain conditions. For example, when the viewer is concentrated, the adding unit prioritizes adding participants that meet certain conditions. This allows for more appropriate addition by adjusting the method for adding participants according to the viewer's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input viewer emotion data to the generating AI and have the generating AI adjust the adding method.

[0125] When adding a participant, the adding unit can select the optimal addition method by referring to the viewer's past participation history. When adding a participant, the adding unit selects the optimal addition method by referring to the viewer's past participation history. The past participation history includes, for example, a history storage method and a reference procedure, but is not limited to these examples. For example, the adding unit adjusts the addition method for the current participant based on the viewer's past participation history. The adding unit can also adjust the addition algorithm by referring to the viewer's past participation history. For example, the adding unit adjusts the addition algorithm by referring to the viewer's past participation history. The adding unit can also reduce addition errors by using the viewer's past participation history. For example, the adding unit reduces addition errors by using the viewer's past participation history. In this way, the adding unit can adjust the addition method for the current participant by referring to the viewer's past participation history. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit can input the viewer's past participation history data into the generation AI and cause the generation AI to select an addition method.

[0126] The adding unit may add participants taking into consideration viewer attribute information when adding participants. The adding unit may add participants taking into consideration viewer attribute information when adding participants. Viewer attribute information includes, but is not limited to, age, gender, and interests. The adding unit may adjust a method for adding participants based on attribute information such as the viewer's age and gender. The adding unit may also preferentially add participants with specific attributes by taking into consideration the viewer attribute information. For example, the adding unit may preferentially add participants with specific attributes by taking into consideration the viewer attribute information. The adding unit may also improve the accuracy of the addition based on the viewer attribute information. For example, the adding unit may improve the accuracy of the addition based on the viewer attribute information. In this way, participants with specific attributes can be preferentially added by taking into consideration the viewer attribute information. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input viewer attribute information data to the generation AI and cause the generation AI to adjust the addition method.

[0127] The addition unit can estimate the viewer's emotion and adjust the display method of the additional results based on the estimated viewer's emotion. The addition unit can estimate the viewer's emotion and adjust the display method of the additional results based on the estimated viewer's emotion. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the addition unit can provide a visually stimulating display method. Also, if the viewer is relaxed, the addition unit can provide the additional results in a calm display method. For example, if the viewer is relaxed, the addition unit can provide the additional results in a calm display method. Also, if the viewer is concentrated, the addition unit can provide detailed additional results. For example, if the viewer is concentrated, the addition unit can provide detailed additional results. This allows for more appropriate display by adjusting the display method of the additional results according to the viewer's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input viewer emotion data to the generating AI and cause the generating AI to adjust the display method of the added result.

[0128] The adding unit may add participants taking into consideration the geographical distribution of viewers when adding participants. The adding unit may add participants taking into consideration the geographical distribution of viewers when adding participants. Examples of the geographical distribution of viewers include, but are not limited to, GPS data and IP addresses. For example, the adding unit may add participants for each region based on the geographical distribution of viewers. The adding unit may also prioritize adding participants for a specific region by taking into consideration the geographical distribution of viewers. For example, the adding unit may prioritize adding participants for a specific region by taking into consideration the geographical distribution of viewers. The adding unit may also improve the accuracy of the addition based on the geographical distribution of viewers. For example, the adding unit improves the accuracy of the addition based on the geographical distribution of viewers. This allows participants for each region to be accurately added by taking into consideration the geographical distribution of viewers. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input viewer geographical distribution data to the generating AI and cause the generating AI to adjust the addition method.

[0129] The adding unit may improve the accuracy of the addition by referring to the viewer's related data when adding the current participant. The adding unit may improve the accuracy of the addition by referring to the viewer's related data when adding the current participant. Examples of related data include, but are not limited to, viewing history and social media activity. The adding unit may improve the accuracy of the addition of the current participant, for example, based on the viewer's related data. The adding unit may also adjust the adding algorithm by referring to the viewer's related data. For example, the adding unit may adjust the adding algorithm by referring to the viewer's related data. The adding unit may also reduce the error of the addition by using the viewer's related data. For example, the adding unit may reduce the error of the addition by using the viewer's related data. As a result, the accuracy of the addition of the current participant is improved by referring to the viewer's related data. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input the viewer's related data to the generation AI and cause the generation AI to adjust the addition method.

[0130] When adding a participant, the adding unit may analyze the viewer's social media activity and refer to related data. When adding a participant, the adding unit may analyze the viewer's social media activity and refer to related data. The viewer's social media activity may include, but is not limited to, the content of posts and the number of followers. The adding unit may add an optimal participant based on, for example, the viewer's social media activity. The adding unit may also add a participant based on the activity of the viewer's friends on social media. For example, the adding unit may add a participant based on the activity of the viewer's friends on social media. The adding unit may also analyze the content of the viewer's social media posts and add a related participant. For example, the adding unit may analyze the content of the viewer's social media posts and add a related participant. In this way, the optimal participant can be added by analyzing the viewer's social media activity. Some or all of the above-described processing in the adding unit may be performed using, for example, AI, or may be performed without using AI. For example, the adding unit may input the viewer's social media activity data to the generation AI and cause the generation AI to adjust the addition method. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, and recommendation 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 collection unit can collect viewer reactions and voting results using the camera 42 and microphone 38B of the smart device 14. For example, the analysis unit analyzes data collected by the specific processing unit 290 of the data processing device 12 and recommends optimal game situations to players using a generation AI. For example, the recommendation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and recommends game situations to players based on the analysis results. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, and recommendation 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 collection unit can collect viewer reactions and voting results using the camera 42 and microphone 238 of the smart glasses 214. For example, the analysis unit analyzes data collected by the specific processing unit 290 of the data processing device 12 and recommends optimal game situations to players using a generation AI. For example, the recommendation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and recommends game situations to players based on the analysis results. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, and recommendation unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit can collect viewer reactions and voting results using the camera 42 and microphone 238 of the headset-type terminal 314. For example, the analysis unit analyzes data collected by the specific processing unit 290 of the data processing device 12 and recommends optimal game situations to players using a generation AI. For example, the recommendation unit is realized by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12, and recommends game situations to players based on the analysis results. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, and recommendation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect viewer reactions and voting results using the camera 42 and microphone 238 of the robot 414. For example, the analysis unit analyzes data collected by the specific processing unit 290 of the data processing device 12 and recommends optimal battle situations to players using a generation AI. For example, the recommendation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and recommends battle situations to players based on the analysis results.

[0131] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0132] The analysis unit can estimate the viewer's emotions and adjust the way the analysis is presented based on the estimated viewer's emotions. Examples of viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the analysis unit can provide a visually stimulating analysis result. Furthermore, if the viewer is relaxed, the analysis unit can provide the analysis result in a calm way. For example, if the viewer is relaxed, the analysis unit can provide the analysis result in a calm way. Furthermore, if the viewer is focused, the analysis unit can provide a detailed analysis result. For example, if the viewer is focused, the analysis unit provides a detailed analysis result. This allows for adjusting the way the analysis is presented according to the viewer's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input viewer emotional data into the generation AI and have the generation AI adjust the way the analysis is expressed.

[0133] The counting unit can estimate the viewer's emotion and adjust the viewer counting method based on the estimated viewer's emotion. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, when the viewer is excited, the counting unit counts the viewer number in real time. Furthermore, when the viewer is relaxed, the counting unit can also count the viewer number at regular time intervals. For example, when the viewer is relaxed, the counting unit counts the viewer number at regular time intervals. Furthermore, when the viewer is concentrated, the counting unit can also count the viewer number immediately after an important event. For example, when the viewer is concentrated, the counting unit counts the viewer number immediately after an important event. This allows for more accurate viewer counting by adjusting the counting method according to the viewer's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or without AI. For example, the counting unit can input viewer emotion data into the generation AI and have the generation AI adjust the counting method.

[0134] The recommendation unit can estimate the viewer's emotions and adjust the way recommendations are expressed based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the recommendation unit can provide a visually stimulating recommendation. Also, if the viewer is relaxed, the recommendation unit can provide a recommendation using a calm expression. For example, if the viewer is relaxed, the recommendation unit can provide a recommendation using a calm expression. Also, if the viewer is focused, the recommendation unit can provide a detailed recommendation. For example, if the viewer is focused, the recommendation unit can provide a detailed recommendation. In this way, by adjusting the way recommendations are expressed according to the viewer's emotions, more appropriate recommendations can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recommendation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recommendation unit may input viewer emotion data into the generation AI and have the generation AI adjust the way recommendations are presented.

[0135] The power-up unit can estimate the viewer's emotions and adjust the power-up method based on the estimated viewer's emotions. Examples of viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the power-up unit can provide a visually stimulating power-up. Also, if the viewer is relaxed, the power-up unit can provide a calming power-up method. For example, if the viewer is relaxed, the power-up unit can provide a calming power-up method. Also, if the viewer is concentrated, the power-up unit can provide a detailed power-up method. This allows for more effective power-up by adjusting the power-up method according to the viewer's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the power-up unit can be performed using, for example, AI, or without AI. For example, the power-up unit can input the viewer's emotional data into the generation AI and have the generation AI adjust the power-up method.

[0136] The reception unit can estimate the viewer's emotions and adjust the method for accepting participation requests based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, if the viewer is excited, the reception unit can accept participation requests using a simple procedure. Furthermore, if the viewer is relaxed, the reception unit can also accept participation requests using a detailed procedure. For example, if the viewer is relaxed, the reception unit can also accept participation requests using a detailed procedure. Furthermore, if the viewer is concentrated, the reception unit can prioritize accepting participation requests that meet specific conditions. For example, if the viewer is concentrated, the reception unit prioritizes accepting participation requests that meet specific conditions. This allows for more appropriate acceptance by adjusting the method for accepting participation requests according to the viewer's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input viewer emotion data into the generation AI and have the generation AI adjust the reception method.

[0137] The counting unit can improve the accuracy of counting by referring to the viewer's past viewing history when counting. The past viewing history includes, but is not limited to, a viewing history storage method and a reference procedure. For example, the counting unit improves the accuracy of counting the current number of viewers based on the viewer's past viewing history. The counting unit can also adjust the counting algorithm by referring to the viewer's past viewing history. For example, the counting unit adjusts the counting algorithm by referring to the viewer's past viewing history. The counting unit can also reduce counting errors by using the viewer's past viewing history. For example, the counting unit reduces counting errors by using the viewer's past viewing history. By referring to the past viewing history, the accuracy of counting the current number of viewers is improved. Some or all of the above-described processing in the counting unit may be performed using, for example, AI, or may be performed without AI. For example, the counting unit can input past viewing history data into a generation AI and cause the generation AI to improve counting accuracy.

[0138] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. The importance of the data includes, but is not limited to, the impact of the data and the frequency of use. For example, the analysis unit performs a detailed analysis on important data. The analysis unit can also perform a simplified analysis on general data. For example, the analysis unit performs a simplified analysis on general data. The analysis unit can also dynamically adjust the level of detail of the analysis according to the importance of the data. For example, the analysis unit dynamically adjusts the level of detail of the analysis according to the importance of the data. This enables efficient analysis by adjusting the level of detail of the analysis according to the importance of the data. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input data on the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0139] When making a recommendation, the recommendation unit can adjust the level of detail of the recommendation based on the importance of the game situation. The importance of the game situation includes, for example, the progress of the game and the condition of the players, but is not limited to these examples. For example, the recommendation unit provides a detailed recommendation for an important game situation. The recommendation unit can also provide a simplified recommendation for a general game situation. For example, the recommendation unit provides a simplified recommendation for a general game situation. The recommendation unit can also dynamically adjust the level of detail of the recommendation according to the importance of the game situation. For example, the recommendation unit dynamically adjusts the level of detail of the recommendation according to the importance of the game situation. This enables efficient recommendations by adjusting the level of detail of the recommendation according to the importance of the game situation. Some or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI or without using AI. For example, the recommendation unit can input battle situation importance data into the generation AI and have the generation AI adjust the level of detail of the recommendations.

[0140] The adding unit can estimate the viewer's emotions and adjust the method for adding participants based on the estimated viewer's emotions. Viewer emotions include, but are not limited to, excitement, relaxation, and concentration. For example, when the viewer is excited, the adding unit can quickly add participants. Furthermore, when the viewer is relaxed, the adding unit can also add participants using a detailed procedure. For example, when the viewer is relaxed, the adding unit can add participants using a detailed procedure. Furthermore, when the viewer is concentrated, the adding unit can also prioritize adding participants who meet specific conditions. For example, when the viewer is concentrated, the adding unit prioritizes adding participants who meet specific conditions. This allows for more appropriate addition by adjusting the method for adding participants according to the viewer's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the adding unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the adding unit can input the viewer's emotional data into the generating AI and cause the generating AI to adjust the adding method.

[0141] The reception unit can select the optimal reception method by referring to the viewer's past participation history when receiving the request. The past participation history includes, for example, a history storage method and a reference procedure, but is not limited to these examples. The reception unit can adjust the reception method for the current participation request based on the viewer's past participation history. The reception unit can also adjust the reception algorithm by referring to the viewer's past participation history. For example, the reception unit adjusts the reception algorithm by referring to the viewer's past participation history. The reception unit can also reduce reception errors by using the viewer's past participation history. For example, the reception unit reduces reception errors by using the viewer's past participation history. In this way, the reception method for the current participation request can be adjusted by referring to the viewer's past participation history. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the viewer's past participation history data into the generation AI and have the generation AI select the reception method.

[0142] The processing flow of the second embodiment will be briefly explained below.

[0143] Step 1: The collection unit collects viewer responses or voting results. Viewer responses include comments, reactions, emotes, etc. The collection unit also collects information on whether viewers selected a specific weapon or supported a specific player. Step 2: The analysis unit analyzes the data collected by the collection unit. Using the generation AI, it analyzes viewer reactions and voting results and recommends optimal game situations to the players. It also analyzes trends in viewer reactions and voting results. Step 3: The recommendation unit recommends the best game situation based on the analysis results obtained by the analysis unit. Based on the game progress and the players' condition, the unit recommends the best game situation and tactics to the players based on the viewers' reactions and voting results.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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 AI 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.

[0162] 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.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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 AI 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.

[0178] 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.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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 AI 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.

[0195] 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.

[0196] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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).

[0201] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0202] 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."

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Explanation of symbols]

[0216] 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 collection unit that collects viewer responses or voting results; an analysis unit that analyzes the data collected by the collection unit; a recommendation unit that recommends a battle situation based on the analysis result obtained by the analysis unit. A system characterized by:

2. Equipped with a counting unit that counts the number of viewers The system of claim 1 .

3. a power-up unit that performs power-up based on the number of viewers counted by the counting unit; 3. The system of claim 2.

4. A reception unit is provided to receive information when a user playing the same game requests to participate in the game. The system of claim 1 .

5. an addition unit that adds a participant to the game based on the participation request received by the reception unit; 5. The system of claim 4.

6. The collecting unit Estimate viewer emotions and adjust the timing of collecting responses and voting results according to the estimated viewer emotions. The system of claim 1 .

7. The collecting unit Analyze past viewer responses and select the appropriate collection method The system of claim 1 .

8. The collecting unit When collecting responses and polls, filter them based on your audience's current interests The system of claim 1 .

9. The collecting unit When collecting responses or poll results, choose the best collection method depending on the viewer's input method The system of claim 1 .

Images