System

Abstract

To provide a system that offers prompt and appropriate advice for mental and technical concerns experienced by athletes.SOLUTION: A system according to an embodiment comprises: a reception unit; a generation unit; and a provision unit. The reception unit receives the input of concerns of athletes. The generation unit generates responses to the concerns input by the reception unit using generative AI on the basis of the statement records of commentators, managers, critics, coaches and other athletes. The provision unit provides the responses generated by the generation unit to the athletes.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to quickly obtain appropriate advice for athletes regarding their mental and technical concerns.

[0005] The system according to the embodiment aims to provide quick and appropriate advice to athletes regarding their mental and technical concerns. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, and a provision unit. The reception unit inputs the player's concerns. The generation unit generates an answer to the concern input by the reception unit using a generation AI based on the statements of commentators, managers, critics, coaches, and other players. The provision unit provides the answer generated by the generation unit to the player. Effect of the Invention

[0007] The system according to the embodiment can provide quick and appropriate advice to athletes regarding their mental and technical concerns. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The problem-solving system for baseball players according to the embodiment of the present invention is a system for solving mental and technical problems for players. In this system, when a player inputs a problem such as "how to deal with the yips" or "I can't get a strike when the bases are full," the generation AI generates and provides an answer based on what it has learned from the comments of commentators, managers, critics, coaches, and other players. Furthermore, it is possible to teach by showing actual movements on the screen of an avatar or electronic device. For example, a player inputs "I want to know how to throw a curveball." This information is input to the reception unit. Next, the generation AI generates an answer to the input problem. The generation AI has learned the comments of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, it provides specific advice on "how to throw a curveball." The generated answer is provided to the player through the provision unit. For example, the avatar actually shows the player how to throw a curveball, providing visual advice to the player. Furthermore, data for the generation AI to learn is collected from the Internet using automatic crawling technology. This allows the AI ​​to constantly learn the latest information. In addition, the generated answers are stored using cloud storage, and the system also has a feedback section that accepts feedback from players. This makes it possible to generate more appropriate answers that reflect the players' feedback. This system allows players to quickly and accurately solve their mental and technical problems. For example, players can receive specific advice, such as how to deal with the yips and how to handle short-bound balls well. Furthermore, visual advice using an avatar allows players to actually see the technical movements, which deepens their understanding. This allows the baseball player problem-solving system to quickly and accurately solve players' mental and technical problems.

[0029] A problem solving system for baseball players according to an embodiment includes a reception unit, a generation unit, and a provision unit. The reception unit inputs the player's problems. The player's problems include, for example, technical problems and mental problems, but are not limited to such examples. For example, the reception unit inputs that the player "I want to know how to throw a curveball." This information is input to the reception unit. The generation unit uses a generation AI to generate an answer to the problem input by the reception unit. The generation AI learns the remarks of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI generates an answer to the player's problem using a text generation AI (for example, LLM). In addition, the generation AI receives an instruction as a prompt, "Please tell me how to throw a curveball," and generates an answer based on the remarks. The generated answer is provided to the player through the provision unit. The provision unit provides visual advice to the player, for example, by having an avatar actually show how to throw a curveball. The providing unit can use the avatar to visually show technical movements. For example, the avatar can actually show the player how to throw a curveball, allowing the player to visually understand. This allows the baseball player's problem-solving system to efficiently solve the player's problems.

[0030] The reception unit inputs the player's worries. The player's worries include, for example, technical worries and mental worries, but are not limited to such examples. For example, the player inputs "I want to know how to throw a curveball" to the reception unit. This information is input to the reception unit. The reception unit provides an interface for the player to input the worries. Specifically, the player can easily input the worries through a smartphone app or a web application. The player can not only input the worries in the text input field, but also input voice, and upload images and videos. For example, the player can convey more specific worries to the reception unit by taking a video of his or her pitching form and uploading the video. The reception unit automatically classifies the input information and divides it into categories such as technical worries and mental worries. This makes it easier for the generation unit to generate an appropriate answer. In addition, the reception unit also manages the player's profile information and can refer to past worries and answer history. This makes it possible to provide a customized answer according to the individual situation of the player. Furthermore, the reception unit can analyze the content of the input worries and ask the player for additional information as necessary. For example, in response to a question such as "I want to know how to throw a curveball," the system prompts the user to enter detailed information such as the player's current pitching form and past training history. This allows the system to gather basic information that will enable the generator to generate a more specific and useful answer.

[0031] The generation unit uses the generation AI to generate an answer to the problem input by the reception unit. The generation AI learns the remarks of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI uses a text generation AI (e.g., LLM) to generate an answer to the player's problem. The generation AI also receives the instruction "Please tell me how to throw a curveball" as a prompt, and generates an answer based on the remarks. The generation AI makes full use of natural language processing technology to generate the optimal answer to the player's problem. Specifically, the generation AI analyzes the input problem and extracts appropriate information from the related knowledge base. For example, when a problem about "how to throw a curveball" is input, the generation AI refers to information such as advice from past great pitchers and coaches, technical books and papers, and suggests the most effective way to throw. The generation AI takes into account the player's profile information and past problem history in order to provide customized advice according to the player's level and situation. For example, it will explain basic throwing techniques to beginner players, and suggest more advanced techniques and tactics to advanced players. Generative AI also provides appropriate advice for players' mental concerns. For example, it will suggest relaxation techniques to ease tension before a match, or mental training methods to improve concentration. By constantly learning the latest information, generative AI can continue to provide the most effective advice to players.

[0032] The providing unit provides the answer generated by the generating unit to the player. The providing unit provides visual advice to the player, for example, by having an avatar actually show how to throw a curveball. The providing unit can visually show technical movements using an avatar. For example, by having an avatar actually show how to throw a curveball, the player can visually understand. The providing unit has various means for providing the generated answer to the player. Specifically, the answer can be provided in a format such as text, audio, video, animation, etc. For example, the answer in text format is notified to the player's smartphone or computer, and detailed explanations and procedures are described. The answer in audio format is provided as an audio guide so that the player can easily listen to it while traveling or practicing. The answer in video format is very useful for the player because it visually shows the actual pitching motion and practice method. The answer in animation format makes it easy for the player to understand visually by having the avatar reproduce the technical movements. The providing unit can select the optimal format according to the player's preferences and situation in order to provide the answer in a format that is most easily understandable to the player. Furthermore, the providing unit collects the results and feedback of the players who have actually tried the provided answers, and provides the feedback to the generating unit. This allows the generating unit to continuously improve the accuracy and usefulness of the answers based on the players' feedback. The providing unit provides the players with specific action plans to solve their problems, and supports the players in actually taking action. For example, the providing unit suggests practice menus and training plans, and provides a step-by-step guide for the players to achieve their goals. This allows the providing unit to provide strong support for the players to efficiently solve their problems and improve their performance.

[0033] The data collection unit includes an automatic crawling technology that collects data for the generation AI to learn from the Internet. The automatic crawling technology includes, but is not limited to, a web crawler and a scraping technology. For example, the data collection unit uses a web crawler to collect the latest information on the Internet. The web crawler crawls a specific website and collects necessary data. The data collection unit can also use scraping technology to extract data from a specific web page. For example, the data collection unit uses scraping technology to collect the remarks of commentators and directors. This allows the generation AI to constantly learn the latest information. A part or all of the above-mentioned processing in the data collection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the data collection unit inputs the crawling rules of the web crawler into the AI, and the AI ​​can calculate the optimal crawling route.

[0034] The present invention includes a storage unit that stores the answer generated by the generation unit using a cloud storage. The cloud storage includes, for example, a specific cloud service, but is not limited to such an example. For example, the storage unit uses a cloud storage service to store the generated answer. The cloud storage service supports a text format, a JSON format, and the like as a data storage format. The storage unit can store the generated answer in a text format. The storage unit can also store the generated answer in a JSON format. For example, the storage unit can upload the generated answer to the cloud storage and refer to it later. This allows the generated answer to be stored and referred to later. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input an upload rule to the cloud storage to the AI, and the AI ​​can calculate an optimal storage method.

[0035] The game system includes a feedback unit that accepts feedback from the player, and the generation unit further uses the feedback from the player to generate an answer. The feedback includes, for example, opinions and improvements on the answer provided by the player, but is not limited to such examples. For example, the feedback unit can input feedback such as "this advice was helpful" or "I would like a more specific explanation" for the answer provided by the player. The generation unit further uses the feedback accepted by the feedback unit to generate an answer. The generation unit generates an answer that reflects the feedback using a generation AI. For example, the generation AI receives the feedback from the player as a prompt and generates an improved answer based on the remarks. This makes it possible to generate a more appropriate answer that reflects the feedback from the player. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input the feedback from the player to an AI, which can calculate an optimal feedback collection method.

[0036] The generation unit can generate an answer to the problem input by the reception unit using the generation AI that has learned the remarks. The generation AI has learned the remarks of commentators, managers, critics, coaches, and other players, and generates an answer based on the remarks. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI generates an answer to the player's problem using a text generation AI (for example, LLM). The generation AI also receives the instruction "Please tell me how to throw a curveball" as a prompt, and generates an answer based on the remarks. In this way, an appropriate answer can be generated by using the generation AI that has learned the remarks. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input a prompt to the generation AI that has learned the remarks, and the AI ​​can generate an optimal answer.

[0037] The providing unit can visually provide technical advice to the player by showing the movement with an avatar. The providing unit can visually show technical movements using an avatar. For example, the avatar can actually show how to throw a curveball, so that the player can visually understand it. The avatar includes, for example, a 3D model and animation technology, but is not limited to such examples. For example, the providing unit can use a 3D model to show in detail how to throw a curveball. In addition, the providing unit can also reproduce the movement of how to throw a curveball in real time using animation technology. This allows the player to actually check the technical movements by providing visual advice. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the movement of the avatar to an AI, and the AI ​​can calculate the optimal movement.

[0038] The reception unit can analyze the player's past worry input history and provide an optimal input interface. For example, the reception unit can automatically display as candidates worries that the player has frequently input in the past. The reception unit can also preferentially suggest input methods (such as voice and text) that the player has used in the past. Furthermore, the reception unit can predict and suggest worries that will be input in a specific time period from the player's past input history. This makes it possible to provide an optimal input interface based on the past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the player's past input history data to a generation AI, which can then calculate an optimal input interface.

[0039] The reception unit can filter the input contents based on the player's current situation and condition when inputting the worries. For example, when the player is about to play a game, the reception unit can allow the player to input worries related to the game with priority. In addition, when the player is practicing, the reception unit can also allow the player to input technical worries with priority. Furthermore, when the player is resting, the reception unit can also allow the player to input mental worries with priority. This makes it possible to provide appropriate input contents according to the player's situation and condition. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the player's current situation data to the generation AI, and the generation AI can calculate the optimal input contents.

[0040] When inputting a worry, the reception unit can preferentially input a highly relevant worry in consideration of the geographical location information of the player. For example, when the player is at a specific stadium, the reception unit preferentially inputs a worry related to the stadium. In addition, when the player is on an away trip, the reception unit can also preferentially input a worry related to the away trip destination. Furthermore, when the player is at home, the reception unit can also preferentially input a worry in a relaxed environment. This makes it possible to input an appropriate worry based on the geographical location information of the player. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the player to the generation AI, which can calculate the optimal input content.

[0041] The reception unit can analyze the social media activity of the player when inputting the worries, and input the related worries. For example, when the player mentions a specific technique on social media, the reception unit preferentially inputs worries related to the technique. In addition, when the player expresses mental stress on social media, the reception unit can also preferentially input worries related to the stress. Furthermore, when the player mentions a specific game on social media, the reception unit can also preferentially input worries related to the game. This makes it possible to input appropriate worries based on the player's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the player's social media activity data to the generation AI, which can calculate optimal input contents.

[0042] The generating unit can adjust the level of detail of the answer based on the importance of the worry when generating the answer. For example, for a worry of high importance, the generating unit generates an answer including a detailed explanation and specific advice. Also, for a worry of medium importance, the generating unit can generate an answer with a moderate level of detail. Furthermore, for a worry of low importance, the generating unit can generate a concise answer. This makes it possible to provide an answer with an appropriate level of detail according to the importance of the worry. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input the importance data of the worry to the generating AI, which can calculate the optimal level of detail.

[0043] The generating unit can apply different generating algorithms depending on the category of the worry when generating an answer. For example, the generating unit applies a generating algorithm that provides technical advice to a technical worry. The generating unit can also apply a generating algorithm that provides psychological support to a mental worry. Furthermore, the generating unit can also apply a generating algorithm that provides strategic advice to a strategic worry. This makes it possible to provide an answer using an appropriate generating algorithm depending on the category of the worry. Some or all of the above-mentioned processing in the generating unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generating unit can input worry category data to the generating AI, which can then calculate an optimal generating algorithm.

[0044] The generation unit can determine the priority of the answers based on the time when the worries were submitted when generating the answers. For example, the generation unit can prioritize the most recently submitted worries and quickly generate answers. The generation unit can also postpone the processing of worries submitted earlier. Furthermore, the generation unit can also prioritize the processing of worries submitted before a specific event. This makes it possible to provide answers with an appropriate priority according to the time when the worries were submitted. A part or all of the above-mentioned processing in the generation unit can be performed, for example, using AI or can be performed without using AI. For example, the generation unit can input the data on the time when the worries were submitted to the generation AI, and the generation AI can calculate the optimal priority.

[0045] The generation unit can adjust the order of answers based on the relevance of the worries when generating answers. For example, the generation unit prioritizes processing of worries with high relevance and quickly generates answers. The generation unit can also process worries with a moderate relevance in an appropriate order. Furthermore, the generation unit can also process worries with low relevance later. This makes it possible to provide answers in an appropriate order according to the relevance of the worries. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input worry relevance data to the generation AI, which can then calculate the optimal order.

[0046] The providing unit can select the optimal providing method by referring to the player's past feedback at the time of providing. For example, the providing unit preferentially uses a providing method that the player has preferred in the past. The providing unit can also avoid a providing method that the player has been dissatisfied with in the past. Furthermore, the providing unit can analyze the player's past feedback and select the optimal providing method. In this way, an appropriate providing method can be selected based on the player's past feedback. A part or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or can be performed without using AI. For example, the providing unit can input the player's past feedback data to the generating AI, which can then calculate the optimal providing method.

[0047] The providing unit can customize the content to be provided based on the current situation of the player at the time of providing. For example, when the player is about to play a game, the providing unit provides advice related to the game. In addition, when the player is practicing, the providing unit can also provide technical advice. Furthermore, when the player is resting, the providing unit can also provide mental support. This makes it possible to provide appropriate content according to the player's current situation. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the player's current situation data to the generating AI, which can then calculate the optimal content to be provided.

[0048] The providing unit can provide optimal advice taking into consideration the geographical location information of the player at the time of providing. For example, when the player is in a specific stadium, the providing unit provides advice related to the stadium. In addition, when the player is on an away trip, the providing unit can also provide advice related to the away trip destination. Furthermore, when the player is at home, the providing unit can also provide advice in a relaxed environment. This makes it possible to provide appropriate advice based on the geographical location information of the player. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the player to the generating AI, which can calculate the optimal advice.

[0049] At the time of providing, the providing unit can analyze the social media activity of the player and suggest a means of advice. For example, if the player mentions a specific technique on social media, the providing unit can provide advice related to the technique. In addition, if the player expresses mental stress on social media, the providing unit can also provide advice related to the stress. Furthermore, if the player mentions a specific game on social media, the providing unit can also provide advice related to the game. This makes it possible to provide appropriate advice based on the player's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the player's social media activity data to the generating AI, which can calculate the optimal means of advice.

[0050] The data collection unit can optimize the collection algorithm by referring to the past collected data when collecting data. The data collection unit, for example, analyzes the patterns of the data collected in the past and determines the optimal collection method. The data collection unit can also adjust the collection frequency based on the past data collection history. Furthermore, the data collection unit can also determine the priority of the collection target by referring to the past data collection results. This makes it possible to apply the optimal collection algorithm based on the past collected data. A part or all of the above-mentioned processing in the data collection unit may be performed, for example, using AI or may be performed without using AI. For example, the data collection unit can input the past collected data to the generation AI, which can calculate the optimal collection algorithm.

[0051] The data collection unit can weight data based on the submission time of collected data when collecting data. For example, the data collection unit can weight recently collected data highly and use it preferentially. The data collection unit can also weight old data low and use it for reference. Furthermore, the data collection unit can weight data related to a specific event highly and use it preferentially. This allows appropriate weighting according to the submission time of collected data to be performed. Part or all of the above-mentioned processing in the data collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the data collection unit can input the submission time data of collected data to the generation AI, and the generation AI can calculate the optimal weighting.

[0052] The storage unit can optimize the storage algorithm by referring to the past stored data when storing. The storage unit, for example, analyzes the pattern of the data stored in the past and determines the optimal storage method. The storage unit can also adjust the storage frequency based on the past stored data. Furthermore, the storage unit can also determine the priority of the data to be stored by referring to the past stored data. This makes it possible to apply the optimal storage algorithm based on the past stored data. A part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can input the past stored data to a generation AI, which can calculate the optimal storage algorithm.

[0053] The storage unit can weight the stored data based on the time of data submission when storing the data. For example, the storage unit prioritizes storing recently submitted data by weighting it highly. The storage unit can also weight old data low and store it for reference. Furthermore, the storage unit can weight data related to a specific event highly and store it highly. This allows data to be stored with appropriate weighting according to the time of data submission. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input data on the time of data submission to the generation AI, which can calculate the optimal weighting.

[0054] The feedback unit can optimize the collection algorithm by referring to past feedback data when collecting feedback. The feedback unit, for example, analyzes past feedback data and determines an optimal collection method. The feedback unit can also adjust the collection frequency based on the past feedback data. Furthermore, the feedback unit can also determine the priority of the collection target by referring to the past feedback data. This makes it possible to apply an optimal collection algorithm based on the past feedback data. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input past feedback data to a generation AI, which can calculate an optimal collection algorithm.

[0055] The feedback unit can collect optimal feedback in consideration of the geographical location information of the player when collecting feedback. For example, when the player is in a specific stadium, the feedback unit collects feedback related to the stadium. In addition, when the player is on an away trip, the feedback unit can also collect feedback related to the away trip destination. Furthermore, when the player is at home, the feedback unit can also collect feedback in a relaxed environment. This makes it possible to collect appropriate feedback based on the geographical location information of the player. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit inputs the geographical location information of the player to the generation AI, which can calculate optimal feedback.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] When inputting a player's concerns, the reception unit can provide more specific advice by referring to the player's past performance data. For example, if a player has previously input a concern about how to throw a curveball, more detailed technical advice can be provided based on the performance data at that time. Also, if a player inputs a concern about performance in a specific game, specific improvements can be suggested by referring to the data from that game. Furthermore, improvements to training methods can be suggested based on data recorded by the player during practice. This makes it possible to provide more accurate advice by utilizing the player's past performance data.

[0058] When saving the generated answers, the saving unit can determine the priority of the saved data based on the player's feedback. For example, answers that the player has evaluated as particularly useful can be saved preferentially. In addition, for answers that the player has requested to be improved, a new answer that reflects the improvement can be saved. Furthermore, answers that the player frequently refers to can be saved preferentially to make them easier to access. This makes it possible to save appropriate data that reflects the player's feedback.

[0059] When generating an answer, the generator can adjust the content of the answer by referring to the player's past feedback. For example, if a player provides feedback that "I would like a more specific explanation" for a previously provided answer, the next answer will include a more detailed explanation. Also, if a player evaluates an answer as "helpful," an answer using a similar approach can be generated. Furthermore, if a player prefers answers in a specific format, an answer that matches that format can be generated. This makes it possible to provide more appropriate answers that reflect the player's feedback.

[0060] The reception unit can preferentially input highly relevant worries in consideration of the geographical location information of the player. For example, when the player is at a specific stadium, worries related to the stadium can be preferentially input. Also, when the player is away on an away trip, worries related to the away trip destination can be preferentially input. Furthermore, when the player is at home, worries in a relaxed environment can be preferentially input. In this way, appropriate worries can be input based on the geographical location information of the player.

[0061] The generator can adjust the level of detail of the answer based on the importance of the concern when generating the answer. For example, for a concern of high importance, an answer including a detailed explanation and specific advice can be generated. For a concern of medium importance, an answer with a moderate level of detail can be generated. Furthermore, for a concern of low importance, a concise answer can be generated. This makes it possible to provide an answer with an appropriate level of detail according to the importance of the concern.

[0062] At the time of providing, the providing unit can select the optimal providing method by referring to the player's past feedback. For example, the providing unit can preferentially use a providing method that the player has preferred in the past. Also, it can avoid a providing method that the player has been dissatisfied with in the past. Furthermore, it can analyze the player's past feedback and select the optimal providing method. In this way, it is possible to select an appropriate providing method based on the player's past feedback.

[0063] The process flow of the first embodiment will be briefly described below.

[0064] Step 1: The reception unit inputs the player's concerns. The player's concerns may include technical concerns and mental concerns. For example, a player may input, "I want to know how to throw a curveball." This information is entered into the reception unit. Step 2: The generation unit uses the generation AI to generate an answer to the problem entered by the reception unit. The generation AI learns from the statements of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI uses a text generation AI (e.g., LLM) to generate an answer to the player's problem. The generation AI also receives the instruction "Please teach me how to throw a curveball" as a prompt, and generates an answer based on the statements. Step 3: The providing unit provides the answer generated by the generating unit to the player. The providing unit provides visual advice to the player, for example, by having an avatar actually show how to throw a curveball. The providing unit can visually show technical movements using an avatar. For example, by having an avatar actually show how to throw a curveball, the player can visually understand.

[0065] (Example 2) The problem-solving system for baseball players according to the embodiment of the present invention is a system for solving mental and technical problems for players. In this system, when a player inputs a problem such as "how to deal with the yips" or "I can't get a strike when the bases are full," the generation AI generates and provides an answer based on what it has learned from the comments of commentators, managers, critics, coaches, and other players. Furthermore, it is possible to teach by showing actual movements on the screen of an avatar or electronic device. For example, a player inputs "I want to know how to throw a curveball." This information is input to the reception unit. Next, the generation AI generates an answer to the input problem. The generation AI has learned the comments of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, it provides specific advice on "how to throw a curveball." The generated answer is provided to the player through the provision unit. For example, the avatar actually shows the player how to throw a curveball, providing visual advice to the player. Furthermore, data for the generation AI to learn is collected from the Internet using automatic crawling technology. This allows the AI ​​to constantly learn the latest information. In addition, the generated answers are stored using cloud storage, and the system also has a feedback section that accepts feedback from players. This makes it possible to generate more appropriate answers that reflect the players' feedback. This system allows players to quickly and accurately solve their mental and technical problems. For example, players can receive specific advice, such as how to deal with the yips and how to handle short-bound balls well. Furthermore, visual advice using an avatar allows players to actually see the technical movements, which deepens their understanding. This allows the baseball player problem-solving system to quickly and accurately solve players' mental and technical problems.

[0066] A problem solving system for baseball players according to an embodiment includes a reception unit, a generation unit, and a provision unit. The reception unit inputs the player's problems. The player's problems include, for example, technical problems and mental problems, but are not limited to such examples. For example, the reception unit inputs that the player "I want to know how to throw a curveball." This information is input to the reception unit. The generation unit uses a generation AI to generate an answer to the problem input by the reception unit. The generation AI learns the remarks of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI generates an answer to the player's problem using a text generation AI (for example, LLM). In addition, the generation AI receives an instruction as a prompt, "Please tell me how to throw a curveball," and generates an answer based on the remarks. The generated answer is provided to the player through the provision unit. The provision unit provides visual advice to the player, for example, by having an avatar actually show how to throw a curveball. The providing unit can use the avatar to visually show technical movements. For example, the avatar can actually show the player how to throw a curveball, allowing the player to visually understand. This allows the baseball player's problem-solving system to efficiently solve the player's problems.

[0067] The reception unit inputs the player's worries. The player's worries include, for example, technical worries and mental worries, but are not limited to such examples. For example, the player inputs "I want to know how to throw a curveball" to the reception unit. This information is input to the reception unit. The reception unit provides an interface for the player to input the worries. Specifically, the player can easily input the worries through a smartphone app or a web application. The player can not only input the worries in the text input field, but also input voice, and upload images and videos. For example, the player can convey more specific worries to the reception unit by taking a video of his or her pitching form and uploading the video. The reception unit automatically classifies the input information and divides it into categories such as technical worries and mental worries. This makes it easier for the generation unit to generate an appropriate answer. In addition, the reception unit also manages the player's profile information and can refer to past worries and answer history. This makes it possible to provide a customized answer according to the individual situation of the player. Furthermore, the reception unit can analyze the content of the input worries and ask the player for additional information as necessary. For example, in response to a question such as "I want to know how to throw a curveball," the system prompts the user to enter detailed information such as the player's current pitching form and past training history. This allows the system to gather basic information that will enable the generator to generate a more specific and useful answer.

[0068] The generation unit uses the generation AI to generate an answer to the problem input by the reception unit. The generation AI learns the remarks of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI uses a text generation AI (e.g., LLM) to generate an answer to the player's problem. The generation AI also receives the instruction "Please tell me how to throw a curveball" as a prompt, and generates an answer based on the remarks. The generation AI makes full use of natural language processing technology to generate the optimal answer to the player's problem. Specifically, the generation AI analyzes the input problem and extracts appropriate information from the related knowledge base. For example, when a problem about "how to throw a curveball" is input, the generation AI refers to information such as advice from past great pitchers and coaches, technical books and papers, and suggests the most effective way to throw. The generation AI takes into account the player's profile information and past problem history in order to provide customized advice according to the player's level and situation. For example, it will explain basic throwing techniques to beginner players, and suggest more advanced techniques and tactics to advanced players. Generative AI also provides appropriate advice for players' mental concerns. For example, it will suggest relaxation techniques to ease tension before a match, or mental training methods to improve concentration. By constantly learning the latest information, generative AI can continue to provide the most effective advice to players.

[0069] The providing unit provides the answer generated by the generating unit to the player. The providing unit provides visual advice to the player, for example, by having an avatar actually show how to throw a curveball. The providing unit can visually show technical movements using an avatar. For example, by having an avatar actually show how to throw a curveball, the player can visually understand. The providing unit has various means for providing the generated answer to the player. Specifically, the answer can be provided in a format such as text, audio, video, animation, etc. For example, the answer in text format is notified to the player's smartphone or computer, and detailed explanations and procedures are described. The answer in audio format is provided as an audio guide so that the player can easily listen to it while traveling or practicing. The answer in video format is very useful for the player because it visually shows the actual pitching motion and practice method. The answer in animation format makes it easy for the player to understand visually by having the avatar reproduce the technical movements. The providing unit can select the optimal format according to the player's preferences and situation in order to provide the answer in a format that is most easily understandable to the player. Furthermore, the providing unit collects the results and feedback of the players who have actually tried the provided answers, and provides the feedback to the generating unit. This allows the generating unit to continuously improve the accuracy and usefulness of the answers based on the players' feedback. The providing unit provides the players with specific action plans to solve their problems, and supports the players in actually taking action. For example, the providing unit suggests practice menus and training plans, and provides a step-by-step guide for the players to achieve their goals. This allows the providing unit to provide strong support for the players to efficiently solve their problems and improve their performance.

[0070] The data collection unit includes an automatic crawling technology that collects data for the generation AI to learn from the Internet. The automatic crawling technology includes, but is not limited to, a web crawler and a scraping technology. For example, the data collection unit uses a web crawler to collect the latest information on the Internet. The web crawler crawls a specific website and collects necessary data. The data collection unit can also use scraping technology to extract data from a specific web page. For example, the data collection unit uses scraping technology to collect the remarks of commentators and directors. This allows the generation AI to constantly learn the latest information. A part or all of the above-mentioned processing in the data collection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the data collection unit inputs the crawling rules of the web crawler into the AI, and the AI ​​can calculate the optimal crawling route.

[0071] The present invention includes a storage unit that stores the answer generated by the generation unit using a cloud storage. The cloud storage includes, for example, a specific cloud service, but is not limited to such an example. For example, the storage unit uses a cloud storage service to store the generated answer. The cloud storage service supports a text format, a JSON format, and the like as a data storage format. The storage unit can store the generated answer in a text format. The storage unit can also store the generated answer in a JSON format. For example, the storage unit can upload the generated answer to the cloud storage and refer to it later. This allows the generated answer to be stored and referred to later. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input an upload rule to the cloud storage to the AI, and the AI ​​can calculate an optimal storage method.

[0072] The game system includes a feedback unit that accepts feedback from the player, and the generation unit further uses the feedback from the player to generate an answer. The feedback includes, for example, opinions and improvements on the answer provided by the player, but is not limited to such examples. For example, the feedback unit can input feedback such as "this advice was helpful" or "I would like a more specific explanation" for the answer provided by the player. The generation unit further uses the feedback accepted by the feedback unit to generate an answer. The generation unit generates an answer that reflects the feedback using a generation AI. For example, the generation AI receives the feedback from the player as a prompt and generates an improved answer based on the remarks. This makes it possible to generate a more appropriate answer that reflects the feedback from the player. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input the feedback from the player to an AI, which can calculate an optimal feedback collection method.

[0073] The generation unit can generate an answer to the problem input by the reception unit using the generation AI that has learned the remarks. The generation AI has learned the remarks of commentators, managers, critics, coaches, and other players, and generates an answer based on the remarks. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI generates an answer to the player's problem using a text generation AI (for example, LLM). The generation AI also receives the instruction "Please tell me how to throw a curveball" as a prompt, and generates an answer based on the remarks. In this way, an appropriate answer can be generated by using the generation AI that has learned the remarks. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the generation unit can input a prompt to the generation AI that has learned the remarks, and the AI ​​can generate an optimal answer.

[0074] The providing unit can visually provide technical advice to the player by showing the movement with an avatar. The providing unit can visually show technical movements using an avatar. For example, the avatar can actually show how to throw a curveball, so that the player can visually understand it. The avatar includes, for example, a 3D model and animation technology, but is not limited to such examples. For example, the providing unit can use a 3D model to show in detail how to throw a curveball. In addition, the providing unit can also reproduce the movement of how to throw a curveball in real time using animation technology. This allows the player to actually check the technical movements by providing visual advice. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the movement of the avatar to an AI, and the AI ​​can calculate the optimal movement.

[0075] The reception unit can estimate the player's emotion and adjust the input method of the worries based on the estimated emotion of the player. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the reception unit provides a simple interface and minimizes input procedures when the player is stressed. In addition, the reception unit can provide detailed input options and suggest a customizable input method when the player is relaxed. Furthermore, the reception unit can prioritize voice input when the player is in a hurry, so that the player can quickly input the worries. This makes it possible to provide an appropriate input method according to the player's emotion. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the player's emotion data to the generation AI, which can calculate the optimal input method.

[0076] The reception unit can analyze the player's past worry input history and provide an optimal input interface. For example, the reception unit can automatically display as candidates worries that the player has frequently input in the past. The reception unit can also preferentially suggest input methods (such as voice and text) that the player has used in the past. Furthermore, the reception unit can predict and suggest worries that will be input in a specific time period from the player's past input history. This makes it possible to provide an optimal input interface based on the past input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the player's past input history data to a generation AI, which can then calculate an optimal input interface.

[0077] The reception unit can filter the input contents based on the player's current situation and condition when inputting the worries. For example, when the player is about to play a game, the reception unit can allow the player to input worries related to the game with priority. In addition, when the player is practicing, the reception unit can also allow the player to input technical worries with priority. Furthermore, when the player is resting, the reception unit can also allow the player to input mental worries with priority. This makes it possible to provide appropriate input contents according to the player's situation and condition. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the player's current situation data to the generation AI, and the generation AI can calculate the optimal input contents.

[0078] The reception unit can estimate the player's emotion and determine the priority of the input worries based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, if the player feels strong anxiety, the reception unit processes the worry with the highest priority. Also, if the player feels light anxiety, the reception unit can also prioritize the worry with the next highest priority. Furthermore, if the player is relaxed, the reception unit can also process the worry with normal priority. This makes it possible to determine the priority of the worries according to the player's emotion. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit inputs the player's emotion data to the generation AI, and the generation AI can calculate the optimal priority.

[0079] When inputting a worry, the reception unit can preferentially input a highly relevant worry in consideration of the geographical location information of the player. For example, when the player is at a specific stadium, the reception unit preferentially inputs a worry related to the stadium. In addition, when the player is on an away trip, the reception unit can also preferentially input a worry related to the away trip destination. Furthermore, when the player is at home, the reception unit can also preferentially input a worry in a relaxed environment. This makes it possible to input an appropriate worry based on the geographical location information of the player. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the player to the generation AI, which can calculate the optimal input content.

[0080] The reception unit can analyze the social media activity of the player when inputting the worries, and input the related worries. For example, when the player mentions a specific technique on social media, the reception unit preferentially inputs worries related to the technique. In addition, when the player expresses mental stress on social media, the reception unit can also preferentially input worries related to the stress. Furthermore, when the player mentions a specific game on social media, the reception unit can also preferentially input worries related to the game. This makes it possible to input appropriate worries based on the player's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the player's social media activity data to the generation AI, which can calculate optimal input contents.

[0081] The generation unit can estimate the player's emotion and adjust the expression method of the answer based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the generation unit generates an answer in gentle language when the player feels anxious. In addition, the generation unit can also generate an answer including a detailed technical explanation when the player is relaxed. Furthermore, the generation unit can also generate an answer including encouraging words when the player is excited. This makes it possible to provide an answer in an appropriate expression method according to the player's emotion. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit inputs the player's emotion data into the generation AI, which can calculate the optimal expression method.

[0082] The generating unit can adjust the level of detail of the answer based on the importance of the worry when generating the answer. For example, for a worry of high importance, the generating unit generates an answer including a detailed explanation and specific advice. Also, for a worry of medium importance, the generating unit can generate an answer with a moderate level of detail. Furthermore, for a worry of low importance, the generating unit can generate a concise answer. This makes it possible to provide an answer with an appropriate level of detail according to the importance of the worry. A part or all of the above-mentioned processing in the generating unit may be performed, for example, using AI, or may be performed without using AI. For example, the generating unit can input the importance data of the worry to the generating AI, which can calculate the optimal level of detail.

[0083] The generating unit can apply different generating algorithms depending on the category of the worry when generating an answer. For example, the generating unit applies a generating algorithm that provides technical advice to a technical worry. The generating unit can also apply a generating algorithm that provides psychological support to a mental worry. Furthermore, the generating unit can also apply a generating algorithm that provides strategic advice to a strategic worry. This makes it possible to provide an answer using an appropriate generating algorithm depending on the category of the worry. Some or all of the above-mentioned processing in the generating unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generating unit can input worry category data to the generating AI, which can then calculate an optimal generating algorithm.

[0084] The generation unit can estimate the player's emotion and adjust the length of the answer based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the generation unit generates a short and to the point answer when the player is in a hurry. In addition, the generation unit can also generate a longer answer including a detailed explanation when the player is relaxed. Furthermore, the generation unit can also generate an answer with a visually stimulating effect when the player is excited. This makes it possible to provide an answer with an appropriate length according to the player's emotion. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the player's emotion data to the generation AI, and the generation AI can calculate the optimal length of the answer.

[0085] The generation unit can determine the priority of the answers based on the time when the worries were submitted when generating the answers. For example, the generation unit can prioritize the most recently submitted worries and quickly generate answers. The generation unit can also postpone the processing of worries submitted earlier. Furthermore, the generation unit can also prioritize the processing of worries submitted before a specific event. This makes it possible to provide answers with an appropriate priority according to the time when the worries were submitted. A part or all of the above-mentioned processing in the generation unit can be performed, for example, using AI or can be performed without using AI. For example, the generation unit can input the data on the time when the worries were submitted to the generation AI, and the generation AI can calculate the optimal priority.

[0086] The generation unit can adjust the order of answers based on the relevance of the worries when generating answers. For example, the generation unit prioritizes processing of worries with high relevance and quickly generates answers. The generation unit can also process worries with a moderate relevance in an appropriate order. Furthermore, the generation unit can also process worries with low relevance later. This makes it possible to provide answers in an appropriate order according to the relevance of the worries. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input worry relevance data to the generation AI, which can then calculate the optimal order.

[0087] The providing unit can estimate the emotion of the player and adjust the movement and expression of the avatar based on the estimated emotion of the player. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the player feels anxious, the providing unit provides advice with a gentle movement of the avatar. In addition, when the player is relaxed, the providing unit can also show the avatar a detailed technical movement. Furthermore, when the player is excited, the providing unit can also show the avatar an encouraging movement. This makes it possible to provide advice with an appropriate movement and expression according to the emotion of the player. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the emotion data of the player to the generation AI, and the generation AI can calculate the optimal movement and expression.

[0088] The providing unit can select the optimal providing method by referring to the player's past feedback at the time of providing. For example, the providing unit preferentially uses a providing method that the player has preferred in the past. The providing unit can also avoid a providing method that the player has been dissatisfied with in the past. Furthermore, the providing unit can analyze the player's past feedback and select the optimal providing method. In this way, an appropriate providing method can be selected based on the player's past feedback. A part or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or can be performed without using AI. For example, the providing unit can input the player's past feedback data to the generating AI, which can then calculate the optimal providing method.

[0089] The providing unit can customize the content to be provided based on the current situation of the player at the time of providing. For example, when the player is about to play a game, the providing unit provides advice related to the game. In addition, when the player is practicing, the providing unit can also provide technical advice. Furthermore, when the player is resting, the providing unit can also provide mental support. This makes it possible to provide appropriate content according to the player's current situation. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the player's current situation data to the generating AI, which can then calculate the optimal content to be provided.

[0090] The providing unit can estimate the emotion of the player and determine the priority of advice to be provided based on the estimated emotion of the player. The estimation of emotion is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the player feels strong anxiety, the providing unit provides the advice with the highest priority. In addition, when the player feels light anxiety, the providing unit can also provide the advice with the next highest priority. Furthermore, when the player is relaxed, the providing unit can also provide the advice with normal priority. This makes it possible to provide advice with an appropriate priority according to the emotion of the player. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit inputs the emotion data of the player to the generation AI, and the generation AI can calculate the optimal priority.

[0091] The providing unit can provide optimal advice taking into consideration the geographical location information of the player at the time of providing. For example, when the player is in a specific stadium, the providing unit provides advice related to the stadium. In addition, when the player is on an away trip, the providing unit can also provide advice related to the away trip destination. Furthermore, when the player is at home, the providing unit can also provide advice in a relaxed environment. This makes it possible to provide appropriate advice based on the geographical location information of the player. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the player to the generating AI, which can calculate the optimal advice.

[0092] At the time of providing, the providing unit can analyze the social media activity of the player and suggest a means of advice. For example, if the player mentions a specific technique on social media, the providing unit can provide advice related to the technique. In addition, if the player expresses mental stress on social media, the providing unit can also provide advice related to the stress. Furthermore, if the player mentions a specific game on social media, the providing unit can also provide advice related to the game. This makes it possible to provide appropriate advice based on the player's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the player's social media activity data to the generating AI, which can calculate the optimal means of advice.

[0093] The data collection unit can estimate the player's emotion and select data to be collected based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. For example, the data collection unit preferentially collects data related to psychological support when the player is feeling anxious. In addition, the data collection unit can also preferentially collect data related to technical advice when the player is relaxed. Furthermore, the data collection unit can also preferentially collect data related to motivation improvement when the player is excited. This makes it possible to collect appropriate data according to the player's emotion. A part or all of the above-mentioned processing in the data collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data collection unit inputs the player's emotion data into the generation AI, and the generation AI can calculate the optimal data selection.

[0094] The data collection unit can optimize the collection algorithm by referring to the past collected data when collecting data. The data collection unit, for example, analyzes the patterns of the data collected in the past and determines the optimal collection method. The data collection unit can also adjust the collection frequency based on the past data collection history. Furthermore, the data collection unit can also determine the priority of the collection target by referring to the past data collection results. This makes it possible to apply the optimal collection algorithm based on the past collected data. A part or all of the above-mentioned processing in the data collection unit may be performed, for example, using AI or may be performed without using AI. For example, the data collection unit can input the past collected data to the generation AI, which can calculate the optimal collection algorithm.

[0095] The data collection unit can estimate the player's emotion and adjust the frequency of data collection based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the data collection unit frequently collects data to provide the latest information when the player feels anxious. In addition, the data collection unit can also collect data at a normal frequency when the player is relaxed. Furthermore, the data collection unit can increase the frequency of data collection to provide detailed information when the player is excited. This makes it possible to collect data at an appropriate frequency according to the player's emotion. A part or all of the above-mentioned processing in the data collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data collection unit inputs the player's emotion data to the generation AI, and the generation AI can calculate the optimal collection frequency.

[0096] The data collection unit can weight data based on the submission time of collected data when collecting data. For example, the data collection unit can weight recently collected data highly and use it preferentially. The data collection unit can also weight old data low and use it for reference. Furthermore, the data collection unit can weight data related to a specific event highly and use it preferentially. This allows appropriate weighting according to the submission time of collected data to be performed. Part or all of the above-mentioned processing in the data collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the data collection unit can input the submission time data of collected data to the generation AI, and the generation AI can calculate the optimal weighting.

[0097] The storage unit can estimate the player's emotion and select data to be stored based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the player feels anxious, the storage unit preferentially stores data related to psychological support. In addition, when the player is relaxed, the storage unit can also preferentially store data related to technical advice. Furthermore, when the player is excited, the storage unit can also preferentially store data related to motivation improvement. This makes it possible to store appropriate data according to the player's emotion. A part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI, or may be performed without using AI. For example, the storage unit inputs the player's emotion data into the generation AI, and the generation AI can calculate the selection of optimal data.

[0098] The storage unit can optimize the storage algorithm by referring to the past stored data when storing. The storage unit, for example, analyzes the pattern of the data stored in the past and determines the optimal storage method. The storage unit can also adjust the storage frequency based on the past stored data. Furthermore, the storage unit can also determine the priority of the data to be stored by referring to the past stored data. This makes it possible to apply the optimal storage algorithm based on the past stored data. A part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can input the past stored data to a generation AI, which can calculate the optimal storage algorithm.

[0099] The storage unit can estimate the player's emotion and determine the priority of the stored data based on the estimated player's emotion. The estimation of emotion is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, if the player feels anxious, the storage unit stores the data with the highest priority. Also, if the player is relaxed, the storage unit can also store the data with the next highest priority. Furthermore, if the player is excited, the storage unit can also store the data with normal priority. This makes it possible to store data with an appropriate priority according to the player's emotion. A part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI, or may be performed without using AI. For example, the storage unit inputs the player's emotion data to the generation AI, which can calculate the optimal priority.

[0100] The storage unit can weight the stored data based on the time of data submission when storing the data. For example, the storage unit prioritizes storing recently submitted data by weighting it highly. The storage unit can also weight old data low and store it for reference. Furthermore, the storage unit can weight data related to a specific event highly and store it highly. This allows data to be stored with appropriate weighting according to the time of data submission. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input data on the time of data submission to the generation AI, which can calculate the optimal weighting.

[0101] The feedback unit can estimate the player's emotion and adjust the feedback collection method based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the feedback unit collects feedback in a simple question format when the player feels anxious. In addition, the feedback unit can also use a question format that requests detailed feedback when the player is relaxed. Furthermore, the feedback unit can also collect feedback in a free description format when the player is excited. This makes it possible to collect feedback in an appropriate manner according to the player's emotion. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit inputs the player's emotion data into the generation AI, which can calculate the optimal collection method.

[0102] The feedback unit can optimize the collection algorithm by referring to past feedback data when collecting feedback. The feedback unit, for example, analyzes past feedback data and determines an optimal collection method. The feedback unit can also adjust the collection frequency based on the past feedback data. Furthermore, the feedback unit can also determine the priority of the collection target by referring to the past feedback data. This makes it possible to apply an optimal collection algorithm based on the past feedback data. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback unit can input past feedback data to a generation AI, which can calculate an optimal collection algorithm.

[0103] The feedback unit can estimate the player's emotion and determine the priority of the feedback based on the estimated player's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, if the player feels strong anxiety, the feedback unit processes the feedback with the highest priority. Also, if the player feels light anxiety, the feedback unit can also give the feedback with the next highest priority. Furthermore, if the player is relaxed, the feedback unit can also process the feedback with normal priority. This makes it possible to process the feedback with an appropriate priority according to the player's emotion. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit inputs the player's emotion data into the generation AI, which can calculate the optimal priority.

[0104] The feedback unit can collect optimal feedback in consideration of the geographical location information of the player when collecting feedback. For example, when the player is in a specific stadium, the feedback unit collects feedback related to the stadium. In addition, when the player is on an away trip, the feedback unit can also collect feedback related to the away trip destination. Furthermore, when the player is at home, the feedback unit can also collect feedback in a relaxed environment. This makes it possible to collect appropriate feedback based on the geographical location information of the player. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit inputs the geographical location information of the player to the generation AI, which can calculate optimal feedback.

[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] When inputting a player's concerns, the reception unit can provide more specific advice by referring to the player's past performance data. For example, if a player has previously input a concern about how to throw a curveball, more detailed technical advice can be provided based on the performance data at that time. Also, if a player inputs a concern about performance in a specific game, specific improvements can be suggested by referring to the data from that game. Furthermore, improvements to training methods can be suggested based on data recorded by the player during practice. This makes it possible to provide more accurate advice by utilizing the player's past performance data.

[0107] The data collection unit can estimate the emotions of the player and select data to be collected based on the estimated emotions of the player. For example, if the player is feeling anxious, data related to psychological support can be collected with priority. Also, if the player is relaxed, data related to technical advice can be collected with priority. Furthermore, if the player is excited, data related to improving motivation can be collected with priority. In this way, appropriate data can be collected according to the emotions of the player.

[0108] When saving the generated answers, the saving unit can determine the priority of the saved data based on the player's feedback. For example, answers that the player has evaluated as particularly useful can be saved preferentially. In addition, for answers that the player has requested to be improved, a new answer that reflects the improvement can be saved. Furthermore, answers that the player frequently refers to can be saved preferentially to make them easier to access. This makes it possible to save appropriate data that reflects the player's feedback.

[0109] The feedback unit can estimate the emotions of the player and adjust the method of collecting feedback based on the estimated emotions of the player. For example, if the player feels anxious, feedback is collected in the form of a simple question. If the player is relaxed, a question format that requests detailed feedback can be used. Furthermore, if the player is excited, feedback can be collected in the form of free description. This makes it possible to collect feedback in an appropriate manner according to the emotions of the player.

[0110] When generating an answer, the generator can adjust the content of the answer by referring to the player's past feedback. For example, if a player provides feedback that "I would like a more specific explanation" for a previously provided answer, the next answer will include a more detailed explanation. Also, if a player evaluates an answer as "helpful," an answer using a similar approach can be generated. Furthermore, if a player prefers answers in a specific format, an answer that matches that format can be generated. This makes it possible to provide more appropriate answers that reflect the player's feedback.

[0111] The providing unit can estimate the player's emotions and adjust the avatar's movements and expressions based on the estimated player's emotions. For example, if the player feels anxious, the avatar can provide advice with gentle movements. If the player is relaxed, the avatar can show detailed technical movements. Furthermore, if the player is excited, the avatar can show encouraging movements. This makes it possible to provide advice with appropriate movements and expressions according to the player's emotions.

[0112] The reception unit can preferentially input highly relevant worries in consideration of the geographical location information of the player. For example, when the player is at a specific stadium, worries related to the stadium can be preferentially input. Also, when the player is away on an away trip, worries related to the away trip destination can be preferentially input. Furthermore, when the player is at home, worries in a relaxed environment can be preferentially input. In this way, appropriate worries can be input based on the geographical location information of the player.

[0113] The generator can adjust the level of detail of the answer based on the importance of the concern when generating the answer. For example, for a concern of high importance, an answer including a detailed explanation and specific advice can be generated. For a concern of medium importance, an answer with a moderate level of detail can be generated. Furthermore, for a concern of low importance, a concise answer can be generated. This makes it possible to provide an answer with an appropriate level of detail according to the importance of the concern.

[0114] At the time of providing, the providing unit can select the optimal providing method by referring to the player's past feedback. For example, the providing unit can preferentially use a providing method that the player has preferred in the past. Also, it can avoid a providing method that the player has been dissatisfied with in the past. Furthermore, it can analyze the player's past feedback and select the optimal providing method. In this way, it is possible to select an appropriate providing method based on the player's past feedback.

[0115] The generation unit can estimate the player's emotions and adjust the way in which the answer is expressed based on the estimated player's emotions. For example, if the player is feeling anxious, an answer can be generated using gentle language. If the player is relaxed, an answer including detailed technical explanations can be generated. Furthermore, if the player is excited, an answer including encouraging words can be generated. This makes it possible to provide answers in an appropriate way according to the player's emotions.

[0116] The process flow of the second embodiment will be briefly described below.

[0117] Step 1: The reception unit inputs the player's concerns. The player's concerns may include technical concerns and mental concerns. For example, a player may input, "I want to know how to throw a curveball." This information is entered into the reception unit. Step 2: The generation unit uses the generation AI to generate an answer to the problem entered by the reception unit. The generation AI learns from the statements of commentators, managers, critics, coaches, and other players, and generates an answer based on this. For example, the generation AI provides specific advice on "how to throw a curveball." The generation AI uses a text generation AI (e.g., LLM) to generate an answer to the player's problem. The generation AI also receives the instruction "Please teach me how to throw a curveball" as a prompt, and generates an answer based on the statements. Step 3: The providing unit provides the answer generated by the generating unit to the player. The providing unit provides visual advice to the player, for example, by having an avatar actually show how to throw a curveball. The providing unit can visually show technical movements using an avatar. For example, by having an avatar actually show how to throw a curveball, the player can visually understand.

[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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0120] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0121] For example, the reception unit can input the player's concerns using the reception device 38 of the smart device 14. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an answer to the player's concerns using a generation AI. The provision unit provides the generated answer to the player using the output device 40 of the smart device 14. The data collection unit collects data from the Internet via the communication I / F 26 of the data processing device 12. The storage unit stores the generated answer in cloud storage using the storage 32 of the data processing device 12. The feedback unit accepts the player's feedback using the reception device 38 of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes 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 the 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, the RAM 30, and the 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 the voice according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed in a secure state.

[0129] Fig. 4 shows an example of 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0132] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0137] For example, the reception unit can input the player's worries using the microphone 238 of the smart glasses 214. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an answer to the player's worries using a generation AI. The provision unit provides the generated answer to the player using the speaker 240 of the smart glasses 214. The data collection unit collects data from the Internet via the communication I / F 26 of the data processing device 12. The storage unit stores the generated answer in cloud storage using the storage 32 of the data processing device 12. The feedback unit accepts the player's feedback using the microphone 238 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes 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 type 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, the RAM 30, and the 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 the voice according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0148] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) 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 a voice indicating a user input for 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0153] For example, the reception unit can input the player's concerns using the microphone 238 of the headset type terminal 314. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an answer to the player's concerns using a generation AI. The provision unit provides the generated answer to the player using the speaker 240 of the headset type terminal 314. The data collection unit collects data from the Internet via the communication I / F 26 of the data processing device 12. The storage unit stores the generated answer in cloud storage using the storage 32 of the data processing device 12. The feedback unit accepts the player's feedback using the microphone 238 of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes 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, the RAM 30, and the 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 the voice according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of 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 performed in a secure state.

[0161] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0165] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) 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 a voice indicating a user input for 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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] For example, the reception unit can input the player's worries using the microphone 238 of the robot 414. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates an answer to the player's worries using a generation AI. The provision unit provides the generated answer to the player using the speaker 240 of the robot 414. The data collection unit collects data from the Internet via the communication I / F 26 of the data processing device 12. The storage unit stores the generated answer in cloud storage using the storage 32 of the data processing device 12. The feedback unit accepts the player's feedback using the microphone 238 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0171] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0172] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in 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 of emotion map 400 and usually 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 inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0175] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0176] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," 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 Universal Serial Bus (USB) 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] In addition, 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 upon 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] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0183] The hardware resource that executes the specific process may be one of these various processors, or may be 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 configuration using one 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 configuration using a processor that realizes the functions of the 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, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0186] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0187] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0188] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0189] (Appendix 1) A reception desk where players can input their concerns, A generating unit that generates an answer to the concern input by the receiving unit using a generating AI based on the statements of commentators, managers, critics, coaches, and other players; a providing unit that provides the answers generated by the generating unit to the player; A system characterized by: (Appendix 2) Equipped with a data collection unit that uses automatic crawling technology to collect data from the Internet for the generation AI to learn from 2. The system of claim 1, (Appendix 3) A storage unit is provided that stores the answer generated by the generation unit using cloud storage. 2. The system of claim 1, (Appendix 4) Equipped with a feedback section that accepts feedback from players, The generator further uses the player's feedback to generate the answer. 2. The system of claim 1, (Appendix 5) The generation part is Using a generation AI that has learned the statements, an answer to the concern input by the reception unit is generated. 2. The system of claim 1, (Appendix 6) The provision department Providing visual technical advice to the player by showing the avatar in action 2. The system of claim 1, (Appendix 7) The reception department is Estimate the player's emotions and adjust the way worries are input based on the estimated player's emotions 2. The system of claim 1, (Appendix 8) The reception department is Analyze the player's past worry input history and provide the optimal input interface 2. The system of claim 1, (Appendix 9) The reception department is When inputting concerns, filter input based on the player's current situation and condition 2. The system of claim 1, (Appendix 10) The reception department is Estimate the player's emotions and prioritize the input worries based on the estimated player's emotions 2. The system of claim 1, (Appendix 11) The reception department is When inputting concerns, the player's geographic location information is taken into consideration to prioritize input of more relevant concerns. 2. The system of claim 1, (Appendix 12) The reception department is When a player enters a concern, analyze their social media activity and enter related concerns. 2. The system of claim 1, (Appendix 13) The generation part is Infer the emotions of the players and adjust the way you express your answers based on the emotions of the players. 2. The system of claim 1, (Appendix 14) The generation part is When generating answers, adjust the level of detail of the answer based on the importance of the problem 2. The system of claim 1, (Appendix 15) The generation part is When generating answers, different generation algorithms are applied depending on the problem category. 2. The system of claim 1, (Appendix 16) The generation part is Infer the emotions of the players and adjust the length of the answers based on the emotions of the players. 2. The system of claim 1, (Appendix 17) The generation part is When generating answers, prioritize answers based on when the problem was submitted 2. The system of claim 1, (Appendix 18) The generation part is When generating answers, adjust the order of answers based on the relevance of the problem 2. The system of claim 1, (Appendix 19) The provision department Estimate the emotions of the player and adjust the avatar's movements and expressions based on the estimated emotions of the player 2. The system of claim 1, (Appendix 20) The provision department When providing the service, the optimal method of providing the service will be selected based on the player's past feedback. 2. The system of claim 1, (Appendix 21) The provision department At the time of delivery, tailor the delivery based on the player's current situation 2. The system of claim 1, (Appendix 22) The provision department Estimate the emotions of the players and prioritize advice based on the estimated emotions of the players. 2. The system of claim 1, (Appendix 23) The provision department When providing advice, the geographic location of the player is taken into account to provide optimal advice. 2. The system of claim 1, (Appendix 24) The provision department At the time of delivery, the social media activity of the player is analyzed to suggest measures of advice 2. The system of claim 1, (Appendix 25) The data collection section is Estimate the emotions of the players and select the data to be collected based on the estimated emotions of the players. 3. The system of claim 2, (Appendix 26) The data collection section is When collecting data, optimize the collection algorithm by referencing past collected data. 3. The system of claim 2, (Appendix 27) The data collection section is Estimate the emotions of the players and adjust the frequency of data collection based on the estimated emotions of the players. 3. The system of claim 2, (Appendix 28) The data collection section is When collecting data, weighting the data based on when it was submitted 3. The system of claim 2, (Appendix 29) The storage section is Estimate the emotions of the players and select the data to be saved based on the estimated emotions of the players. 4. The system of claim 3. (Appendix 30) The storage section is When saving, optimize the saving algorithm by referencing past saved data. 4. The system of claim 3. (Appendix 31) The storage section is Estimate the emotions of players and prioritize the data to be stored based on the estimated emotions of players. 4. The system of claim 3. (Appendix 32) The storage section is At the time of storage, the stored data is weighted based on when it was submitted 4. The system of claim 3. (Appendix 33) The feedback section is Infer player emotions and adjust how you collect feedback based on the inferred emotions. 5. The system of claim 4. (Appendix 34) The feedback section is When collecting feedback, optimize the collection algorithm by referencing past feedback data 5. The system of claim 4. (Appendix 35) The feedback section is Estimate the emotions of the players and prioritize feedback based on the estimated emotions of the players 5. The system of claim 4. (Appendix 36) The feedback section is When collecting feedback, consider the geographic location of the player to collect the most appropriate feedback. 5. The system of claim 4. [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 reception desk where players can input their concerns, A generating unit that generates an answer to the problem input by the receiving unit using a generating AI based on the statements of commentators, managers, critics, coaches, and other players; a providing unit that provides the answers generated by the generating unit to the player; A system characterized by:

2. Equipped with a data collection unit that uses automatic crawling technology from the Internet to collect data for the generation AI to learn.

2. The system of claim 1 .

3. A storage unit that stores the answer generated by the generation unit using cloud storage.

2. The system of claim 1 .

4. a feedback unit that receives feedback from the player; The generator further uses the player's feedback to generate the answer.

2. The system of claim 1 .

5. The generation unit is Using a generation AI that has learned the statement records, an answer to the concern input by the reception unit is generated.

2. The system of claim 1 .

6. The providing unit is Providing visual technical advice to the player by showing the avatar in action 2. The system of claim 1 .

7. The reception unit is The emotion of the player is estimated, and a method of inputting the worries is adjusted based on the estimated emotion of the player.

2. The system of claim 1 .

8. The reception unit is Analyze the player's past worry input history and provide an optimal input interface 2. The system of claim 1 .

Images