System

Abstract

An object of a system according to an embodiment is to provide a real-time and accurate commentary in a game in which a large number of players participate.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, a pickup unit, and a live commentary unit. The collection unit monitors a player's motion in the game in real time and collects data. The analysis unit accurately grasps what is happening based on the data collected by the collection unit. The pickup part selects the most interesting part based on the result analyzed by the analysis part. The live commentary part performs live commentary and explanation on the part selected by the pickup part.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] With conventional technology, it was difficult to provide accurate commentary and commentary in real time in games involving a large number of players.

[0005] The system according to the embodiment aims to provide accurate real-time commentary and commentary in games in which many players participate. [Means for solving the problem]

[0006] The system according to the embodiment comprises a collection unit, an analysis unit, a pick-up unit, and a commentary unit. The collection unit monitors the movements of players in the game in real time and collects data. The analysis unit accurately grasps what is happening based on the data collected by the collection unit. The pick-up unit selects the most interesting parts based on the results of the analysis by the analysis unit. The commentary unit provides commentary and explanation of the parts selected by the pick-up unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide accurate real-time commentary and commentary in games in which many players participate. [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) An AI system according to an embodiment of the present invention provides accurate commentary and commentary on the actions of multiple players in real time. The AI ​​system monitors the actions of players in a game in real time, collects data, analyzes the collected data, and accurately understands what is happening. Furthermore, when battles are occurring simultaneously in multiple locations, the AI ​​selects the most interesting parts and provides commentary and commentary. For example, the AI ​​system collects detailed information about each player's location, behavioral data, and battle status. Next, based on the collected data, the AI ​​system analyzes the player's behavior patterns and the progress of the battle to determine which parts are the most interesting. Furthermore, when multiple battles are occurring simultaneously, the AI ​​system analyzes the status of each battle and selects the most interesting battle. This allows the AI ​​system to accurately commentate and commentary on the most interesting parts for viewers. This allows the AI ​​system to grasp the situation in the game in real time, select the most interesting parts, and provide commentary and commentary, thereby providing compelling content to viewers. For example, accurate commentary and commentary on fast-paced battles or battles occurring simultaneously in multiple locations can provide a more immersive experience for viewers.

[0029] The AI ​​system according to the embodiment includes a collection unit, an analysis unit, a pick-up unit, and a commentary unit. The collection unit monitors the movements of players in a game in real time and collects data. The collection unit collects detailed information, such as each player's location information and behavioral data, and the status of the battle. For example, the collection unit acquires player location information using GPS data or in-game coordinates. The collection unit can also collect player behavioral data such as movement patterns and action types. The collection unit can also collect battle status information such as the progress of the battle and information on participating players. The analysis unit accurately grasps what is happening based on the data collected by the collection unit. The analysis unit analyzes, for example, player behavior patterns and the progress of the battle. The analysis unit analyzes player behavior patterns using, for example, frequency analysis or time series analysis. The analysis unit can also analyze the progress of the battle as a determining factor for the battle phase and victory or defeat. The pick-up unit selects the most interesting parts based on the results of the analysis by the analysis unit. For example, when battles are occurring simultaneously in multiple locations, the pickup unit selects the most interesting battle. For example, the pickup unit selects the most important battle based on the scale and impact of the battle. The pickup unit can also select the most interesting part based on viewer reactions and the importance of in-game events. The commentary unit provides live commentary and commentary on the part selected by the pickup unit. For example, the commentary unit provides audio commentary and text commentary. For example, the commentary unit provides live commentary in real time using audio commentary. The commentary unit can also provide commentary along with the video using text commentary. This allows the AI ​​system according to the embodiment to monitor the movements of players in the game in real time and provide accurate live commentary and commentary.

[0030] The collection unit can collect each player's location information, behavioral data, and battle status. For example, the collection unit acquires each player's location information using GPS data or in-game coordinates. For example, the collection unit collects player behavioral data as movement patterns and action types. The collection unit can also collect battle status as battle progress and participating player information. For example, the collection unit acquires player location information in real time and analyzes player movement patterns. The collection unit can also identify the player's action type based on the player's behavioral data. The collection unit can also monitor the battle progress in real time and collect information on battle phases and participating players. This allows for more accurate analysis by collecting detailed data on each player.

[0031] The analysis unit can analyze the player's behavioral patterns and the progress of the battle based on the collected data. The analysis unit, for example, analyzes the player's behavioral patterns using frequency analysis or time series analysis. The analysis unit can, for example, identify the player's behavioral trends based on the player's behavioral patterns. The analysis unit can also analyze the progress of the battle as the phase of the battle and the determining factors of victory or defeat. For example, the analysis unit monitors the progress of the battle in real time and identifies the phase of the battle. The analysis unit can also analyze the determining factors of victory or defeat of the battle and predict the outcome of the battle. In this way, by analyzing the player's behavioral patterns and the progress of the battle, it is possible to accurately grasp what is happening.

[0032] The pickup unit can select the most important battle when battles are occurring simultaneously in multiple locations. The pickup unit can select the most important battle based on, for example, the scale and impact of the battle. The pickup unit can select the battle that is most interesting to viewers based on, for example, the scale of the battle. The pickup unit can also evaluate the importance of in-game events based on the impact of the battle and select the most important battle. For example, when multiple battles are occurring simultaneously, the pickup unit analyzes the situation of each battle and selects the most interesting battle. The pickup unit can also select the part that is most interesting to viewers based on viewer reactions. This makes it possible to select the most interesting battle even when battles are occurring simultaneously in multiple locations.

[0033] The commentary section can provide live commentary and explanation of the selected portion. The commentary section, for example, provides audio commentary and text commentary. The commentary section can, for example, provide live commentary in real time using audio commentary. The commentary section can also provide commentary along with the video using text commentary. For example, the commentary section can provide audio commentary of the status of the selected battle in real time, providing viewers with a sense of realism. The commentary section can also display details of the selected battle as text commentary, providing viewers with an easy-to-understand explanation. This allows for accurate live commentary and explanation of the selected portion.

[0034] The collection unit can analyze each player's past behavior history and select an appropriate data collection method. The collection unit can, for example, determine data collection priorities based on actions that the player frequently performed in the past. The collection unit can, for example, analyze the player's past behavior patterns and select the most efficient data collection method. The collection unit can also predict the timing of a specific behavior from the player's past behavior history and collect data. For example, the collection unit can adjust data collection priorities based on the player's past behavior history. The collection unit can analyze the player's past behavior patterns and select the optimal data collection method. In this way, the optimal data collection method can be selected by analyzing the player's past behavior history.

[0035] When collecting data, the collection unit can filter the data based on the player's current in-game role and situation. For example, if the player is a leader, the collection unit prioritizes collecting the player's actions. For example, if the player is in a support role, the collection unit can collect data with an emphasis on cooperation with other players. Furthermore, if the player is currently performing a specific mission, the collection unit can prioritize collecting data related to that mission. For example, the collection unit adjusts the priority of data collection based on the player's role and situation. The collection unit can analyze the player's current in-game role and situation and select the optimal data collection method. This allows more relevant data to be collected by filtering data according to the player's role and situation.

[0036] When collecting data, the collection unit can select the optimal collection means depending on the input method of the player. For example, if the player is using voice input, the collection unit can prioritize collecting voice data. For example, if the player is using text input, the collection unit can prioritize collecting text data. Furthermore, if the player is using gesture input, the collection unit can also prioritize collecting gesture data. For example, the collection unit selects the optimal data collection means based on the input method of the player. The collection unit can analyze the input method of the player and select the optimal data collection means. This enables efficient data collection by selecting the optimal collection means depending on the input method of the player.

[0037] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the player. For example, when the player is in a specific area, the collection unit prioritizes collecting data related to that area. For example, when the player is moving, the collection unit can collect data related to the area to which the player has moved. Furthermore, when the player is participating in a specific event, the collection unit can prioritize collecting data related to the event. For example, the collection unit prioritizes collecting highly relevant data based on the geographical location information of the player. The collection unit can analyze the geographical location information of the player and select the optimal data collection means. In this way, highly relevant data can be prioritized by taking into account the geographical location information of the player.

[0038] When collecting data, the collection unit can analyze the player's social media activities and collect related data. For example, the collection unit can collect related data based on information shared by the player on social media. For example, the collection unit can analyze the player's social media activities and collect data that may be of interest to the player. The collection unit can also collect related data by referring to the activities of the player's friends on social media. For example, the collection unit can prioritize collecting related data based on the player's social media activities. The collection unit can analyze the player's social media activities and select the optimal data collection means. This allows for efficient collection of related data by analyzing the player's social media activities.

[0039] When collecting data, the collection unit can customize the collection method by reflecting the player's past feedback. For example, the collection unit can adjust the priority of data collection based on feedback provided by the player in the past. For example, the collection unit can analyze the player's past feedback and select the optimal data collection method. The collection unit can also customize a specific data collection method based on the player's past feedback. For example, the collection unit can adjust the priority of data collection based on the player's past feedback. The collection unit can analyze the player's past feedback and select the optimal data collection method. In this way, the collection method can be optimized by reflecting the player's past feedback.

[0040] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the player's actions. For example, the analysis unit performs a detailed analysis of data on players who have taken important actions. For example, the analysis unit can perform a simplified analysis of data on players who have taken general actions. The analysis unit can also focus on analyzing data on players who have taken actions related to a specific event. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the player's actions. The analysis unit can analyze the importance of the player's actions and select the optimal analysis method. This allows for efficient analysis by adjusting the level of detail of the analysis according to the importance of the player's actions.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the player's behavior category. For example, the analysis unit can apply a combat analysis algorithm to a player who has taken combat actions. For example, the analysis unit can apply a search analysis algorithm to a player who has taken search actions. The analysis unit can also apply a negotiation analysis algorithm to a player who has taken negotiation actions. For example, the analysis unit selects an optimal analysis algorithm based on the player's behavior category. The analysis unit can analyze the player's behavior category and select an optimal analysis method. This allows for more accurate analysis by applying different analysis algorithms depending on the player's behavior category.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the player's past behavioral patterns. The analysis unit, for example, predicts and analyzes current behavior based on the player's past behavioral patterns. The analysis unit, for example, can analyze the player's past behavioral patterns and optimize the analysis algorithm. The analysis unit can also improve the accuracy of the analysis results by referring to the player's past behavioral patterns. For example, the analysis unit predicts current behavior based on the player's past behavioral patterns and improves the accuracy of the analysis. The analysis unit can analyze the player's past behavioral patterns and select the optimal analysis method. In this way, the accuracy of the analysis can be improved by referring to the player's past behavioral patterns.

[0043] During analysis, the analysis unit can determine the priority of analysis based on the time when the player's actions occurred. For example, the analysis unit prioritizes analysis of the most recent actions. For example, the analysis unit can prioritize analysis of actions taken around the time when a specific event occurred. The analysis unit can also prioritize analysis of data taken around the time when the player performed an important action. For example, the analysis unit determines the priority of analysis based on the time when the player's actions occurred. The analysis unit can analyze the time when the player's actions occurred and select the optimal analysis method. This enables efficient analysis by determining the priority of analysis based on the time when the player's actions occurred.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the player's actions. For example, the analysis unit prioritizes analysis of highly relevant actions. For example, the analysis unit can postpone analysis of less relevant actions. The analysis unit can also prioritize analysis of actions related to a specific event. For example, the analysis unit adjusts the order of analysis based on the relevance of the player's actions. The analysis unit can analyze the relevance of the player's actions and select the optimal analysis method. In this way, adjusting the order of analysis based on the relevance of the player's actions enables efficient analysis.

[0045] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the player's level of expertise. For example, the analysis unit can provide analysis results that use a lot of technical terms to a player with high levels of expertise. For example, the analysis unit can provide analysis results in easy-to-understand language to a player with low levels of expertise. The analysis unit can also adjust the way in which the analysis results are expressed according to the player's level of expertise. For example, the analysis unit can adjust the use of technical terms in the analysis based on the player's level of expertise. The analysis unit can analyze the player's level of expertise and select the optimal analysis method. In this way, by adjusting the use of technical terms in the analysis according to the player's level of expertise, more appropriate analysis results can be provided.

[0046] The picking unit can improve the accuracy of picking by taking into account the interrelationships between battles when picking. For example, when multiple battles are linked, the picking unit picks them by taking into account the interrelationships between them. For example, the picking unit can pick the most important battle by taking into account chain reactions between battles. The picking unit can also analyze the interrelationships between battles and pick out the scenes that are most interesting to viewers. For example, the picking unit improves the accuracy of picking based on the interrelationships between battles. The picking unit can analyze the interrelationships between battles and select the optimal picking method. In this way, the accuracy of picking is improved by taking into account the interrelationships between battles.

[0047] The pickup unit can pick up scenes taking into consideration the player's attribute information when picking up scenes. The pickup unit can pick up important scenes taking into consideration the player's skill level, for example. The pickup unit can pick up relevant scenes taking into consideration the player's role, for example. The pickup unit can also pick up interesting scenes based on the player's past behavior history. For example, the pickup unit can adjust the pickup priority based on the player's attribute information. The pickup unit can analyze the player's attribute information and select the optimal pickup method. In this way, more relevant scenes can be picked up by taking the player's attribute information into consideration.

[0048] The pickup unit can weight the pickups based on the frequency of battle occurrence when picking up scenes. For example, the pickup unit prioritizes picking up battles that occur frequently. For example, the pickup unit can emphasize picking up battles that occur rarely. The pickup unit can also analyze the frequency of battle occurrence and pick up the most important scenes. For example, the pickup unit weights the pickups based on the frequency of battle occurrence. The pickup unit can analyze the frequency of battle occurrence and select the optimal pickup method. In this way, by weighting the pickups based on the frequency of battle occurrence, more important scenes can be selected.

[0049] The pickup unit can take into consideration the geographical distribution of battles when picking up scenes. For example, the pickup unit prioritizes picking up battles that occurred in a specific area. For example, the pickup unit can simultaneously pick up battles that occurred in multiple areas. The pickup unit can also analyze the geographical distribution of battles and pick out scenes that are most interesting to viewers. For example, the pickup unit can adjust the priority of picking up scenes based on the geographical distribution of battles. The pickup unit can analyze the geographical distribution of battles and select the optimal pickup method. This allows more relevant scenes to be picked up by taking the geographical distribution of battles into consideration.

[0050] The picking unit can improve the accuracy of the picking by referring to literature related to the battle when picking up scenes. For example, the picking unit refers to literature related to the battle and picks out important scenes. For example, the picking unit can pick out scenes that are interesting to viewers based on background information about the battle. The picking unit can also analyze literature related to the battle and improve the accuracy of the picking. For example, the picking unit improves the accuracy of the picking based on literature related to the battle. The picking unit can analyze literature related to the battle and select the optimal picking method. In this way, the accuracy of the picking is improved by referring to literature related to the battle.

[0051] The picking unit can take into consideration the market value of the battle when picking it. For example, the picking unit prioritizes picking battles with high market value. For example, the picking unit can postpone picking battles with low market value. The picking unit can also analyze the market value of the battle and pick the scenes that are most interesting to viewers. For example, the picking unit can adjust the picking priority based on the market value of the battle. The picking unit can analyze the market value of the battle and select the optimal picking method. In this way, the most interesting scenes to viewers can be picked by taking the market value of the battle into consideration.

[0052] The commentary unit can adjust the level of detail of the commentary based on the importance of the battle during commentary. For example, the commentary unit provides detailed commentary of important battles. For example, the commentary unit can provide simplified commentary of general battles. The commentary unit can also focus on battles related to specific events. For example, the commentary unit adjusts the level of detail of the commentary based on the importance of the battle. The commentary unit can analyze the importance of the battle and select the optimal commentary method. This allows for efficient commentary by adjusting the level of detail of the commentary according to the importance of the battle.

[0053] The commentary unit can apply different commentary algorithms depending on the battle category during commentary. For example, the commentary unit can apply a battle commentary algorithm to a combat battle. For example, the commentary unit can apply a search commentary algorithm to a search battle. The commentary unit can also apply a negotiation commentary algorithm to a negotiation battle. For example, the commentary unit selects the optimal commentary algorithm based on the battle category. The commentary unit can analyze the battle category and select the optimal commentary method. This allows for more accurate commentary by applying different commentary algorithms depending on the battle category.

[0054] During commentary, the commentary unit can improve the accuracy of the commentary by referring to the user's past commentary results. The commentary unit, for example, optimizes the current commentary based on the user's past commentary results. The commentary unit, for example, can analyze the user's past commentary results and optimize the commentary algorithm. The commentary unit can also improve the accuracy of the commentary by referring to the user's past commentary results. For example, the commentary unit optimizes the current commentary based on the user's past commentary results. The commentary unit can analyze the user's past commentary results and select the optimal commentary means. In this way, the accuracy of the commentary can be improved by referring to the user's past commentary results.

[0055] During commentary, the commentary unit can determine the priority of commentary based on the time of battle occurrence. For example, the commentary unit gives priority to the most recent battle. For example, the commentary unit can give priority to commentary on battles when a specific event occurs. The commentary unit can also give priority to commentary on battles when a player takes an important action. For example, the commentary unit determines the priority of commentary based on the time of battle occurrence. The commentary unit can analyze the time of battle occurrence and select the optimal commentary method. This enables efficient commentary by determining the priority of commentary based on the time of battle occurrence.

[0056] The commentary unit can adjust the order of commentary based on the relevance of the battles during commentary. For example, the commentary unit gives priority to commentary on highly relevant battles. For example, the commentary unit can postpone commentary on less relevant battles. The commentary unit can also give priority to commentary on battles related to a specific event. For example, the commentary unit adjusts the order of commentary based on the relevance of the battles. The commentary unit can analyze the relevance of the battles and select the optimal commentary method. This allows for efficient commentary by adjusting the order of commentary based on the relevance of the battles.

[0057] The commentary unit can adjust the use of technical terms in the commentary during commentary according to the user's level of expertise. For example, the commentary unit can provide a commentary that uses a lot of technical terms to a user with high level of expertise. For example, the commentary unit can provide a commentary in easy-to-understand language to a user with low level of expertise. The commentary unit can also adjust the way the commentary is expressed according to the user's level of expertise. For example, the commentary unit adjusts the use of technical terms in the commentary based on the user's level of expertise. The commentary unit can analyze the user's level of expertise and select the optimal commentary method. In this way, by adjusting the use of technical terms in the commentary according to the user's level of expertise, a more appropriate commentary can be provided.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The collection unit collects the player's biometric information, and the analysis unit can estimate the player's physical condition based on that information. For example, the collection unit collects biometric information such as the player's heart rate, body temperature, and sweat rate. The analysis unit can estimate the player's physical condition based on this data and issue a warning if the player's physical condition deteriorates. The collection unit can also monitor the player's biometric information in real time and immediately notify the player if an abnormality is detected. This makes it possible to monitor the player's health condition and take appropriate measures.

[0060] The analysis unit can estimate a player's skill level based on the player's behavioral data. For example, the analysis unit can analyze the player's behavioral patterns and success rate to evaluate the player's skill level. The analysis unit can also adjust the in-game difficulty level according to the player's skill level. The analysis unit can also suggest an appropriate training program based on the player's skill level. This can support the player in improving their skills.

[0061] The picking unit can select the most interesting scenes based on the player's past play history. For example, the picking unit selects interesting scenes based on scenes that the player liked to watch in the past or the behavior of a particular player. The picking unit can analyze the player's past play history and provide the most attractive scenes for viewers. The picking unit can also predict scenes that will attract the viewer's interest based on the player's past play history. This makes it possible to provide more attractive content for viewers.

[0062] The collection unit can analyze the social media activities of the player and collect related data. For example, the collection unit collects related data based on information shared by the player on social media. The collection unit can analyze the player's social media activities and collect data that may be of interest to the player. The collection unit can also collect related data by referring to the activities of the player's friends on social media. In this way, the analysis of the player's social media activities can efficiently collect related data.

[0063] The collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the player. For example, if the player is in a specific area, the collection unit can prioritize collecting data related to that area. If the player is moving, the collection unit can collect data related to the area to which the player has moved. Furthermore, if the player is participating in a specific event, the collection unit can also prioritize collecting data related to the event. In this way, highly relevant data can be prioritized by taking into account the geographical location information of the player.

[0064] The analysis unit can determine the priority of analysis based on the time when the player's actions occurred. For example, the analysis unit can prioritize analyzing the most recent actions. The analysis unit can prioritize analyzing actions when a specific event occurred. The analysis unit can also prioritize analyzing data when the player took an important action. In this way, by determining the priority of analysis based on the time when the player's actions occurred, efficient analysis can be performed.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The collection unit monitors the movements of players in the game in real time and collects data. The collection unit collects detailed information, such as each player's location information, behavioral data, and battle status. The collection unit obtains player location information using GPS data and in-game coordinates, and collects player behavioral data as movement patterns and action types. It also collects battle status as the battle progress and information on participating players. Step 2: The analysis unit accurately understands what is happening based on the data collected by the collection unit. The analysis unit analyzes the player's behavioral patterns and the progress of the battle, and uses frequency analysis and time series analysis to analyze the player's behavioral patterns. It also analyzes the progress of the battle as a determining factor for the battle phase and victory or defeat. Step 3: The selection section selects the most interesting parts based on the results of the analysis by the analysis section. If multiple battles are occurring simultaneously, the selection section selects the most interesting battle, and the most important battle based on the scale and impact of the battle. The selection section also selects the most interesting parts based on the viewer reaction and the importance of in-game events. Step 4: The commentary section provides commentary and explanation of the part selected by the picking section. The commentary section provides audio commentary and text commentary, and provides commentary in real time using audio commentary. It can also provide commentary along with the video using text commentary.

[0067] (Example 2) An AI system according to an embodiment of the present invention provides accurate commentary and commentary on the actions of multiple players in real time. The AI ​​system monitors the actions of players in a game in real time, collects data, analyzes the collected data, and accurately understands what is happening. Furthermore, when battles are occurring simultaneously in multiple locations, the AI ​​selects the most interesting parts and provides commentary and commentary. For example, the AI ​​system collects detailed information about each player's location, behavioral data, and battle status. Next, based on the collected data, the AI ​​system analyzes the player's behavior patterns and the progress of the battle to determine which parts are the most interesting. Furthermore, when multiple battles are occurring simultaneously, the AI ​​system analyzes the status of each battle and selects the most interesting battle. This allows the AI ​​system to accurately commentate and commentary on the most interesting parts for viewers. This allows the AI ​​system to grasp the situation in the game in real time, select the most interesting parts, and provide commentary and commentary, thereby providing compelling content to viewers. For example, accurate commentary and commentary on fast-paced battles or battles occurring simultaneously in multiple locations can provide a more immersive experience for viewers.

[0068] The AI ​​system according to the embodiment includes a collection unit, an analysis unit, a pick-up unit, and a commentary unit. The collection unit monitors the movements of players in a game in real time and collects data. The collection unit collects detailed information, such as each player's location information and behavioral data, and the status of the battle. For example, the collection unit acquires player location information using GPS data or in-game coordinates. The collection unit can also collect player behavioral data such as movement patterns and action types. The collection unit can also collect battle status information such as the progress of the battle and information on participating players. The analysis unit accurately grasps what is happening based on the data collected by the collection unit. The analysis unit analyzes, for example, player behavior patterns and the progress of the battle. The analysis unit analyzes player behavior patterns using, for example, frequency analysis or time series analysis. The analysis unit can also analyze the progress of the battle as a determining factor for the battle phase and victory or defeat. The pick-up unit selects the most interesting parts based on the results of the analysis by the analysis unit. For example, when battles are occurring simultaneously in multiple locations, the pickup unit selects the most interesting battle. For example, the pickup unit selects the most important battle based on the scale and impact of the battle. The pickup unit can also select the most interesting part based on viewer reactions and the importance of in-game events. The commentary unit provides live commentary and commentary on the part selected by the pickup unit. For example, the commentary unit provides audio commentary and text commentary. For example, the commentary unit provides live commentary in real time using audio commentary. The commentary unit can also provide commentary along with the video using text commentary. This allows the AI ​​system according to the embodiment to monitor the movements of players in the game in real time and provide accurate live commentary and commentary.

[0069] The collection unit can collect each player's location information, behavioral data, and battle status. For example, the collection unit acquires each player's location information using GPS data or in-game coordinates. For example, the collection unit collects player behavioral data as movement patterns and action types. The collection unit can also collect battle status as battle progress and participating player information. For example, the collection unit acquires player location information in real time and analyzes player movement patterns. The collection unit can also identify the player's action type based on the player's behavioral data. The collection unit can also monitor the battle progress in real time and collect information on battle phases and participating players. This allows for more accurate analysis by collecting detailed data on each player.

[0070] The analysis unit can analyze the player's behavioral patterns and the progress of the battle based on the collected data. The analysis unit, for example, analyzes the player's behavioral patterns using frequency analysis or time series analysis. The analysis unit can, for example, identify the player's behavioral trends based on the player's behavioral patterns. The analysis unit can also analyze the progress of the battle as the phase of the battle and the determining factors of victory or defeat. For example, the analysis unit monitors the progress of the battle in real time and identifies the phase of the battle. The analysis unit can also analyze the determining factors of victory or defeat of the battle and predict the outcome of the battle. In this way, by analyzing the player's behavioral patterns and the progress of the battle, it is possible to accurately grasp what is happening.

[0071] The pickup unit can select the most important battle when battles are occurring simultaneously in multiple locations. The pickup unit can select the most important battle based on, for example, the scale and impact of the battle. The pickup unit can select the battle that is most interesting to viewers based on, for example, the scale of the battle. The pickup unit can also evaluate the importance of in-game events based on the impact of the battle and select the most important battle. For example, when multiple battles are occurring simultaneously, the pickup unit analyzes the situation of each battle and selects the most interesting battle. The pickup unit can also select the part that is most interesting to viewers based on viewer reactions. This makes it possible to select the most interesting battle even when battles are occurring simultaneously in multiple locations.

[0072] The commentary section can provide live commentary and explanation of the selected portion. The commentary section, for example, provides audio commentary and text commentary. The commentary section can, for example, provide live commentary in real time using audio commentary. The commentary section can also provide commentary along with the video using text commentary. For example, the commentary section can provide audio commentary of the status of the selected battle in real time, providing viewers with a sense of realism. The commentary section can also display details of the selected battle as text commentary, providing viewers with an easy-to-understand explanation. This allows for accurate live commentary and explanation of the selected portion.

[0073] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, when the user is excited, the collection unit can collect data frequently in real time and immediately reflect the data. For example, when the user is relaxed, the collection unit can reduce the frequency of data collection and collect only important events. Furthermore, when the user is feeling stressed, the collection unit can adjust the timing of data collection to reduce the user's burden. For example, the collection unit can capture the user's facial expressions with a camera and estimate the user's emotions using an emotion estimation algorithm. The collection unit can adjust the timing of data collection based on the user's emotion score. This allows for more appropriate data collection by adjusting the timing of data collection according to the user's emotions. Emotion estimation is achieved 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.

[0074] The collection unit can analyze each player's past behavior history and select an appropriate data collection method. The collection unit can, for example, determine data collection priorities based on actions that the player frequently performed in the past. The collection unit can, for example, analyze the player's past behavior patterns and select the most efficient data collection method. The collection unit can also predict the timing of a specific behavior from the player's past behavior history and collect data. For example, the collection unit can adjust data collection priorities based on the player's past behavior history. The collection unit can analyze the player's past behavior patterns and select the optimal data collection method. In this way, the optimal data collection method can be selected by analyzing the player's past behavior history.

[0075] When collecting data, the collection unit can filter the data based on the player's current in-game role and situation. For example, if the player is a leader, the collection unit prioritizes collecting the player's actions. For example, if the player is in a support role, the collection unit can collect data with an emphasis on cooperation with other players. Furthermore, if the player is currently performing a specific mission, the collection unit can prioritize collecting data related to that mission. For example, the collection unit adjusts the priority of data collection based on the player's role and situation. The collection unit can analyze the player's current in-game role and situation and select the optimal data collection method. This allows more relevant data to be collected by filtering data according to the player's role and situation.

[0076] When collecting data, the collection unit can select the optimal collection means depending on the input method of the player. For example, if the player is using voice input, the collection unit can prioritize collecting voice data. For example, if the player is using text input, the collection unit can prioritize collecting text data. Furthermore, if the player is using gesture input, the collection unit can also prioritize collecting gesture data. For example, the collection unit selects the optimal data collection means based on the input method of the player. The collection unit can analyze the input method of the player and select the optimal data collection means. This enables efficient data collection by selecting the optimal collection means depending on the input method of the player.

[0077] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user emotions. For example, if the user is excited, the collection unit can prioritize collecting data on action scenes. For example, if the user is relaxed, the collection unit can prioritize collecting data related to story progression. Furthermore, if the user is stressed, the collection unit can prioritize collecting data on important events. For example, the collection unit can capture the user's facial expressions with a camera and estimate the emotions using an emotion estimation algorithm. The collection unit can determine the priority of data to be collected based on the user's emotion score. This allows for the priority of data to be collected according to the user's emotions, thereby prioritizing more important data. 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.

[0078] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the player. For example, when the player is in a specific area, the collection unit prioritizes collecting data related to that area. For example, when the player is moving, the collection unit can collect data related to the area to which the player has moved. Furthermore, when the player is participating in a specific event, the collection unit can prioritize collecting data related to the event. For example, the collection unit prioritizes collecting highly relevant data based on the geographical location information of the player. The collection unit can analyze the geographical location information of the player and select the optimal data collection means. In this way, highly relevant data can be prioritized by taking into account the geographical location information of the player.

[0079] When collecting data, the collection unit can analyze the player's social media activities and collect related data. For example, the collection unit can collect related data based on information shared by the player on social media. For example, the collection unit can analyze the player's social media activities and collect data that may be of interest to the player. The collection unit can also collect related data by referring to the activities of the player's friends on social media. For example, the collection unit can prioritize collecting related data based on the player's social media activities. The collection unit can analyze the player's social media activities and select the optimal data collection means. This allows for efficient collection of related data by analyzing the player's social media activities.

[0080] When collecting data, the collection unit can customize the collection method by reflecting the player's past feedback. For example, the collection unit can adjust the priority of data collection based on feedback provided by the player in the past. For example, the collection unit can analyze the player's past feedback and select the optimal data collection method. The collection unit can also customize a specific data collection method based on the player's past feedback. For example, the collection unit can adjust the priority of data collection based on the player's past feedback. The collection unit can analyze the player's past feedback and select the optimal data collection method. In this way, the collection method can be optimized by reflecting the player's past feedback.

[0081] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user emotions. For example, if the user is excited, the analysis unit can provide a visually stimulating analysis result. For example, if the user is relaxed, the analysis unit can provide a calming analysis result. Furthermore, if the user is stressed, the analysis unit can provide a simple and easy-to-understand analysis result. For example, the analysis unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The analysis unit can adjust the presentation method of the analysis based on the user's emotion score. This allows for more appropriate analysis results to be provided by adjusting the presentation method of the analysis according to the user's emotions. Emotion estimation is achieved 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.

[0082] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the player's actions. For example, the analysis unit performs a detailed analysis of data on players who have taken important actions. For example, the analysis unit can perform a simplified analysis of data on players who have taken general actions. The analysis unit can also focus on analyzing data on players who have taken actions related to a specific event. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the player's actions. The analysis unit can analyze the importance of the player's actions and select the optimal analysis method. This allows for efficient analysis by adjusting the level of detail of the analysis according to the importance of the player's actions.

[0083] During analysis, the analysis unit can apply different analysis algorithms depending on the player's behavior category. For example, the analysis unit can apply a combat analysis algorithm to a player who has taken combat actions. For example, the analysis unit can apply a search analysis algorithm to a player who has taken search actions. The analysis unit can also apply a negotiation analysis algorithm to a player who has taken negotiation actions. For example, the analysis unit selects an optimal analysis algorithm based on the player's behavior category. The analysis unit can analyze the player's behavior category and select an optimal analysis method. This allows for more accurate analysis by applying different analysis algorithms depending on the player's behavior category.

[0084] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the player's past behavioral patterns. The analysis unit, for example, predicts and analyzes current behavior based on the player's past behavioral patterns. The analysis unit, for example, can analyze the player's past behavioral patterns and optimize the analysis algorithm. The analysis unit can also improve the accuracy of the analysis results by referring to the player's past behavioral patterns. For example, the analysis unit predicts current behavior based on the player's past behavioral patterns and improves the accuracy of the analysis. The analysis unit can analyze the player's past behavioral patterns and select the optimal analysis method. In this way, the accuracy of the analysis can be improved by referring to the player's past behavioral patterns.

[0085] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is excited, the analysis unit can provide a short and concise analysis result. For example, if the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is stressed, the analysis unit can provide a simple and short analysis result. For example, the analysis unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The analysis unit can adjust the length of the analysis based on the user's emotion score. This allows for more appropriate analysis results to be provided by adjusting the length of the analysis according to the user's emotions. Emotion estimation is achieved 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.

[0086] During analysis, the analysis unit can determine the priority of analysis based on the time when the player's actions occurred. For example, the analysis unit prioritizes analysis of the most recent actions. For example, the analysis unit can prioritize analysis of actions taken around the time when a specific event occurred. The analysis unit can also prioritize analysis of data taken around the time when the player performed an important action. For example, the analysis unit determines the priority of analysis based on the time when the player's actions occurred. The analysis unit can analyze the time when the player's actions occurred and select the optimal analysis method. This enables efficient analysis by determining the priority of analysis based on the time when the player's actions occurred.

[0087] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the player's actions. For example, the analysis unit prioritizes analysis of highly relevant actions. For example, the analysis unit can postpone analysis of less relevant actions. The analysis unit can also prioritize analysis of actions related to a specific event. For example, the analysis unit adjusts the order of analysis based on the relevance of the player's actions. The analysis unit can analyze the relevance of the player's actions and select the optimal analysis method. In this way, adjusting the order of analysis based on the relevance of the player's actions enables efficient analysis.

[0088] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the player's level of expertise. For example, the analysis unit can provide analysis results that use a lot of technical terms to a player with high levels of expertise. For example, the analysis unit can provide analysis results in easy-to-understand language to a player with low levels of expertise. The analysis unit can also adjust the way in which the analysis results are expressed according to the player's level of expertise. For example, the analysis unit can adjust the use of technical terms in the analysis based on the player's level of expertise. The analysis unit can analyze the player's level of expertise and select the optimal analysis method. In this way, by adjusting the use of technical terms in the analysis according to the player's level of expertise, more appropriate analysis results can be provided.

[0089] The pickup unit can estimate the user's emotions and adjust the pickup criteria based on the estimated user emotions. For example, if the user is excited, the pickup unit can prioritize picking up action scenes. For example, if the user is relaxed, the pickup unit can prioritize picking up scenes related to story progression. Furthermore, if the user is stressed, the pickup unit can prioritize picking up scenes of important events. For example, the pickup unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The pickup unit can adjust the pickup criteria based on the user's emotion score. This allows more interesting scenes to be selected by adjusting the pickup criteria according to the user's emotions. Emotion estimation is realized 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.

[0090] The picking unit can improve the accuracy of picking by taking into account the interrelationships between battles when picking. For example, when multiple battles are linked, the picking unit picks them by taking into account the interrelationships between them. For example, the picking unit can pick the most important battle by taking into account chain reactions between battles. The picking unit can also analyze the interrelationships between battles and pick out the scenes that are most interesting to viewers. For example, the picking unit improves the accuracy of picking based on the interrelationships between battles. The picking unit can analyze the interrelationships between battles and select the optimal picking method. In this way, the accuracy of picking is improved by taking into account the interrelationships between battles.

[0091] The pickup unit can pick up scenes taking into consideration the player's attribute information when picking up scenes. The pickup unit can pick up important scenes taking into consideration the player's skill level, for example. The pickup unit can pick up relevant scenes taking into consideration the player's role, for example. The pickup unit can also pick up interesting scenes based on the player's past behavior history. For example, the pickup unit can adjust the pickup priority based on the player's attribute information. The pickup unit can analyze the player's attribute information and select the optimal pickup method. In this way, more relevant scenes can be picked up by taking the player's attribute information into consideration.

[0092] The pickup unit can weight the pickups based on the frequency of battle occurrence when picking up scenes. For example, the pickup unit prioritizes picking up battles that occur frequently. For example, the pickup unit can emphasize picking up battles that occur rarely. The pickup unit can also analyze the frequency of battle occurrence and pick up the most important scenes. For example, the pickup unit weights the pickups based on the frequency of battle occurrence. The pickup unit can analyze the frequency of battle occurrence and select the optimal pickup method. In this way, by weighting the pickups based on the frequency of battle occurrence, more important scenes can be selected.

[0093] The picking unit can estimate the user's emotions and adjust the order in which the picking results are displayed based on the estimated user emotions. For example, if the user is excited, the picking unit can first display an action scene. For example, if the user is relaxed, the picking unit can first display a scene related to the progression of the story. Furthermore, if the user is stressed, the picking unit can first display a scene of an important event. For example, the picking unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The picking unit can adjust the order in which the picking results are displayed based on the user's emotion score. This allows for more interesting scenes to be provided by adjusting the order in which the picking results are displayed according to the user's emotions. 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.

[0094] The pickup unit can take into consideration the geographical distribution of battles when picking up scenes. For example, the pickup unit prioritizes picking up battles that occurred in a specific area. For example, the pickup unit can simultaneously pick up battles that occurred in multiple areas. The pickup unit can also analyze the geographical distribution of battles and pick out scenes that are most interesting to viewers. For example, the pickup unit can adjust the priority of picking up scenes based on the geographical distribution of battles. The pickup unit can analyze the geographical distribution of battles and select the optimal pickup method. This allows more relevant scenes to be picked up by taking the geographical distribution of battles into consideration.

[0095] The picking unit can improve the accuracy of the picking by referring to literature related to the battle when picking up scenes. For example, the picking unit refers to literature related to the battle and picks out important scenes. For example, the picking unit can pick out scenes that are interesting to viewers based on background information about the battle. The picking unit can also analyze literature related to the battle and improve the accuracy of the picking. For example, the picking unit improves the accuracy of the picking based on literature related to the battle. The picking unit can analyze literature related to the battle and select the optimal picking method. In this way, the accuracy of the picking is improved by referring to literature related to the battle.

[0096] The picking unit can take into consideration the market value of the battle when picking it. For example, the picking unit prioritizes picking battles with high market value. For example, the picking unit can postpone picking battles with low market value. The picking unit can also analyze the market value of the battle and pick the scenes that are most interesting to viewers. For example, the picking unit can adjust the picking priority based on the market value of the battle. The picking unit can analyze the market value of the battle and select the optimal picking method. In this way, the most interesting scenes to viewers can be picked by taking the market value of the battle into consideration.

[0097] The commentary unit can estimate the user's emotions and adjust the way the commentary is expressed based on the estimated user emotions. For example, if the user is excited, the commentary unit can provide commentary using energetic expressions. For example, if the user is relaxed, the commentary unit can provide commentary in a calm tone. Furthermore, if the user is stressed, the commentary unit can provide commentary using simple and easy-to-understand expressions. For example, the commentary unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The commentary unit can adjust the way the commentary is expressed based on the user's emotion score. This allows for providing a more appropriate commentary by adjusting the way the commentary is expressed according to the user's emotions. 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.

[0098] The commentary unit can adjust the level of detail of the commentary based on the importance of the battle during commentary. For example, the commentary unit provides detailed commentary of important battles. For example, the commentary unit can provide simplified commentary of general battles. The commentary unit can also focus on battles related to specific events. For example, the commentary unit adjusts the level of detail of the commentary based on the importance of the battle. The commentary unit can analyze the importance of the battle and select the optimal commentary method. This allows for efficient commentary by adjusting the level of detail of the commentary according to the importance of the battle.

[0099] The commentary unit can apply different commentary algorithms depending on the battle category during commentary. For example, the commentary unit can apply a battle commentary algorithm to a combat battle. For example, the commentary unit can apply a search commentary algorithm to a search battle. The commentary unit can also apply a negotiation commentary algorithm to a negotiation battle. For example, the commentary unit selects the optimal commentary algorithm based on the battle category. The commentary unit can analyze the battle category and select the optimal commentary method. This allows for more accurate commentary by applying different commentary algorithms depending on the battle category.

[0100] During commentary, the commentary unit can improve the accuracy of the commentary by referring to the user's past commentary results. The commentary unit, for example, optimizes the current commentary based on the user's past commentary results. The commentary unit, for example, can analyze the user's past commentary results and optimize the commentary algorithm. The commentary unit can also improve the accuracy of the commentary by referring to the user's past commentary results. For example, the commentary unit optimizes the current commentary based on the user's past commentary results. The commentary unit can analyze the user's past commentary results and select the optimal commentary means. In this way, the accuracy of the commentary can be improved by referring to the user's past commentary results.

[0101] The commentary unit can estimate the user's emotions and adjust the length of the commentary based on the estimated user emotions. For example, if the user is excited, the commentary unit can provide a short and to-the-point commentary. For example, if the user is relaxed, the commentary unit can provide a detailed commentary. Furthermore, if the user is stressed, the commentary unit can provide a simple and short commentary. For example, the commentary unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The commentary unit can adjust the length of the commentary based on the user's emotion score. This allows for a more appropriate commentary to be provided by adjusting the length of the commentary according to the user's emotions. 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.

[0102] During commentary, the commentary unit can determine the priority of commentary based on the time of battle occurrence. For example, the commentary unit gives priority to the most recent battle. For example, the commentary unit can give priority to commentary on battles when a specific event occurs. The commentary unit can also give priority to commentary on battles when a player takes an important action. For example, the commentary unit determines the priority of commentary based on the time of battle occurrence. The commentary unit can analyze the time of battle occurrence and select the optimal commentary method. This enables efficient commentary by determining the priority of commentary based on the time of battle occurrence.

[0103] The commentary unit can adjust the order of commentary based on the relevance of the battles during commentary. For example, the commentary unit gives priority to commentary on highly relevant battles. For example, the commentary unit can postpone commentary on less relevant battles. The commentary unit can also give priority to commentary on battles related to a specific event. For example, the commentary unit adjusts the order of commentary based on the relevance of the battles. The commentary unit can analyze the relevance of the battles and select the optimal commentary method. This allows for efficient commentary by adjusting the order of commentary based on the relevance of the battles.

[0104] The commentary unit can adjust the use of technical terms in the commentary during commentary according to the user's level of expertise. For example, the commentary unit can provide a commentary that uses a lot of technical terms to a user with high level of expertise. For example, the commentary unit can provide a commentary in easy-to-understand language to a user with low level of expertise. The commentary unit can also adjust the way the commentary is expressed according to the user's level of expertise. For example, the commentary unit adjusts the use of technical terms in the commentary based on the user's level of expertise. The commentary unit can analyze the user's level of expertise and select the optimal commentary method. In this way, by adjusting the use of technical terms in the commentary according to the user's level of expertise, a more appropriate commentary can be provided. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, pick-up unit, and commentary 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 collects player position information and behavior data using the camera 42 and communication I / F 44 of the smart device 14, and monitors the battle situation using the specific processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12 to understand the player's behavior patterns and the progress of the battle. For example, the pick-up unit selects the most interesting parts based on the analysis results by the specific processing unit 290 of the data processing device 12. For example, the commentary unit provides audio commentary or text commentary using the output device 40 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, pickup unit, and commentary 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 collects player position information and behavior data using the camera 42 and communication I / F 44 of the smart glasses 214, and monitors the battle situation using the specific processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12 to grasp the player's behavior patterns and the progress of the battle. For example, the pickup unit selects the most interesting parts based on the analysis results by the specific processing unit 290 of the data processing device 12. The commentary unit provides audio commentary and text commentary using the speaker 240 of the smart glasses 214, for example. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, pickup unit, and commentary 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 collects player position information and behavior data using the camera 42 and communication I / F 44 of the headset-type terminal 314, and monitors the battle situation using the specific processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12 to grasp the player's behavior patterns and the progress of the battle. For example, the pickup unit selects the most interesting parts based on the analysis results by the specific processing unit 290 of the data processing device 12. The commentary unit provides audio commentary and text commentary using the speaker 240 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, pickup unit, and commentary 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 collects player position information and behavioral data using the camera 42 and communication I / F 44 of the robot 414, and monitors the battle situation using the specific processing unit 290 of the data processing device 12. For example, the analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12 to grasp the player's behavioral patterns and the progress of the battle. For example, the pickup unit selects the most interesting parts based on the analysis results by the specific processing unit 290 of the data processing device 12. The commentary unit provides audio commentary and text commentary using the speaker 240 of the robot 414, for example.

[0105] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0106] The collection unit collects the player's biometric information, and the analysis unit can estimate the player's physical condition based on that information. For example, the collection unit collects biometric information such as the player's heart rate, body temperature, and sweat rate. The analysis unit can estimate the player's physical condition based on this data and issue a warning if the player's physical condition deteriorates. The collection unit can also monitor the player's biometric information in real time and immediately notify the player if an abnormality is detected. This makes it possible to monitor the player's health condition and take appropriate measures.

[0107] The analysis unit can estimate a player's skill level based on the player's behavioral data. For example, the analysis unit can analyze the player's behavioral patterns and success rate to evaluate the player's skill level. The analysis unit can also adjust the in-game difficulty level according to the player's skill level. The analysis unit can also suggest an appropriate training program based on the player's skill level. This can support the player in improving their skills.

[0108] The picking unit can select the most interesting scenes based on the player's past play history. For example, the picking unit selects interesting scenes based on scenes that the player liked to watch in the past or the behavior of a particular player. The picking unit can analyze the player's past play history and provide the most attractive scenes for viewers. The picking unit can also predict scenes that will attract the viewer's interest based on the player's past play history. This makes it possible to provide more attractive content for viewers.

[0109] The commentary team can estimate the player's emotions and adjust the tone of the commentary based on the estimated emotions. For example, if the player is excited, the commentary team can use an energetic tone to commentate. If the player is relaxed, the commentary team can use a calm tone to commentate. Also, if the player is stressed, the commentary team can use a simple, easy-to-understand tone to commentate. In this way, by adjusting the tone of the commentary according to the player's emotions, more appropriate commentary can be provided.

[0110] The collection unit can analyze the social media activities of the player and collect related data. For example, the collection unit collects related data based on information shared by the player on social media. The collection unit can analyze the player's social media activities and collect data that may be of interest to the player. The collection unit can also collect related data by referring to the activities of the player's friends on social media. In this way, the analysis of the player's social media activities can efficiently collect related data.

[0111] The analysis unit can estimate the player's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the player is excited, the analysis unit can provide visually stimulating analysis results. If the player is relaxed, the analysis unit can provide analysis results in a calm tone. Furthermore, if the player is stressed, the analysis unit can provide simple and easy-to-understand analysis results. In this way, by adjusting the display method of the analysis results according to the player's emotions, more appropriate analysis results can be provided.

[0112] The pickup unit can estimate the player's emotions and adjust the pickup criteria based on the estimated emotions. For example, if the player is excited, the pickup unit can prioritize picking up action scenes. If the player is relaxed, the pickup unit can prioritize picking up scenes related to story progression. Also, if the player is stressed, the pickup unit can prioritize picking up scenes of important events. In this way, by adjusting the pickup criteria according to the player's emotions, more interesting scenes can be selected.

[0113] The collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the player. For example, if the player is in a specific area, the collection unit can prioritize collecting data related to that area. If the player is moving, the collection unit can collect data related to the area to which the player has moved. Furthermore, if the player is participating in a specific event, the collection unit can also prioritize collecting data related to the event. In this way, highly relevant data can be prioritized by taking into account the geographical location information of the player.

[0114] The analysis unit can determine the priority of analysis based on the time when the player's actions occurred. For example, the analysis unit can prioritize analyzing the most recent actions. The analysis unit can prioritize analyzing actions when a specific event occurred. The analysis unit can also prioritize analyzing data when the player took an important action. In this way, by determining the priority of analysis based on the time when the player's actions occurred, efficient analysis can be performed.

[0115] The commentary unit can estimate the user's emotions and adjust the length of the commentary based on the estimated emotions. For example, if the user is excited, the commentary unit can provide a short, to-the-point commentary. If the user is relaxed, the commentary unit can provide a detailed commentary. Also, if the user is stressed, the commentary unit can provide a simple, short commentary. In this way, by adjusting the length of the commentary according to the user's emotions, a more appropriate commentary can be provided.

[0116] The processing flow of the second embodiment will be briefly explained below.

[0117] Step 1: The collection unit monitors the movements of players in the game in real time and collects data. The collection unit collects detailed information, such as each player's location information, behavioral data, and battle status. The collection unit obtains player location information using GPS data and in-game coordinates, and collects player behavioral data as movement patterns and action types. It also collects battle status as the battle progress and information on participating players. Step 2: The analysis unit accurately understands what is happening based on the data collected by the collection unit. The analysis unit analyzes the player's behavioral patterns and the progress of the battle, and uses frequency analysis and time series analysis to analyze the player's behavioral patterns. It also analyzes the progress of the battle as a determining factor for the battle phase and victory or defeat. Step 3: The selection section selects the most interesting parts based on the results of the analysis by the analysis section. If multiple battles are occurring simultaneously, the selection section selects the most interesting battle, and the most important battle based on the scale and impact of the battle. The selection section also selects the most interesting parts based on the viewer reaction and the importance of in-game events. Step 4: The commentary section provides commentary and explanation of the part selected by the picking section. The commentary section provides audio commentary and text commentary, and provides commentary in real time using audio commentary. It can also provide commentary along with the video using text commentary.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0123] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0169] 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.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0176] 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."

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] [Explanation of symbols]

[0190] 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 monitors the player's movements in the game in real time and collects data; an analysis unit that accurately grasps what is happening based on the data collected by the collection unit; a picking unit that selects the most interesting part based on the analysis result by the analysis unit; a commentary unit that provides commentary and explanation on the part selected by the pickup unit. A system characterized by:

2. The collecting unit Collect each player's location information, behavioral data, and battle status 2. The system of claim 1.

3. The analysis unit Based on the collected data, the player's behavior patterns and the progress of the battle are analyzed.

2. The system of claim 1.

4. The pickup unit includes: If multiple battles are happening at the same time, choose the most important one.

2. The system of claim 1.

5. The commentary section Commentary and commentary on the selected section 2. The system of claim 1.

6. The collecting unit Inferring user emotions and adjusting the timing of data collection based on the estimated user emotions 2. The system of claim 1.

7. The collecting unit Analyze each player's past behavior history and select the appropriate data collection method 2. The system of claim 1.

8. The collecting unit Filtering data collection based on the player's current in-game role and situation 2. The system of claim 1.

Images