System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting game play videos of players all over the world; means for analyzing the collected game play videos to extract action patterns of the players; means for generating situation-solving information based on the extracted action patterns; means for automatically updating the generated situation-solving information on a website; and chatbot means for providing optimal situation-solving information based on a progress status and a play style of a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's increasingly complex games, even when players refer to existing strategy sites or related information, it often takes time to find the information they need, and the information provided is not always accurate or easy to understand. Furthermore, existing strategy information may not be tailored to each player's individual play style. This makes it difficult for players to have an efficient and satisfying gaming experience. To solve these problems, a system is needed that quickly provides strategy information optimized for the player's progress and play style. [Means for solving the problem]

[0005] The present invention provides a means for collecting gameplay videos of players around the world, analyzing them to extract player behavior patterns, and generating strategy information based on these. It also provides a system that includes a chatbot that automatically updates the generated strategy information on a website and responds to user inquiries by providing optimal strategy information based on the player's progress and playing style. This allows players to quickly and accurately obtain the latest strategy information and learn optimal strategies tailored to their own playing style.

[0006] "Gameplay video" is footage of a player playing a game.

[0007] "Means of collection" refers to the methods and techniques used to collect a particular object (in this case, gameplay videos).

[0008] "Analytical means" refers to the methods and techniques used to scrutinize collected data and extract meaningful information.

[0009] A "behavior pattern" refers to a series of actions or behaviors that a player takes to achieve a specific goal in the game.

[0010] "Strategy information" refers to information about procedures and methods for progressing through a game efficiently.

[0011] "Means of generation" refers to the methods and techniques used to produce the required output (in this case, strategy information).

[0012] "Means for updating the website" refers to the methods and technologies for automatically updating the generated information on the website.

[0013] "User progress" refers to the progress that a player has made in the game.

[0014] "Playstyle" refers to the strategy or method a player chooses to use to progress through the game.

[0015] A "chatbot" is an interactive program that automatically responds to questions from users.

[0016] A "natural language processing model" refers to a program or technology that interprets and responds to natural human language. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0029] 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.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] 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.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the strategy information they need through a chatbot. Specific embodiments for realizing this system will be described below.

[0039] Data collection

[0040] The server collects game player gameplay videos from the internet. Specifically, it automatically downloads videos related to the game name using, for example, a streaming platform's API. The collected videos are then stored in cloud storage or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[0041] Data analysis

[0042] The server breaks down the stored video into frames and extracts key frames, including high-action scenes, boss battles, and item acquisition scenes. The server then uses a deep learning model to analyze the player's behavioral patterns in the video. For example, it automatically extracts effective tactics for a particular boss battle or the optimal timing for using items.

[0043] Strategy information generation

[0044] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0045] Strategy wiki update

[0046] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to revert to previous versions at any time.

[0047] Preparing the chatbot

[0048] The server synchronizes the strategy information database with the chat bot's database, allowing the chat bot to obtain the latest strategy information. Furthermore, the server updates the chat bot's natural language processing model so that it can respond to user inquiries.

[0049] Responding to user inquiries

[0050] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates the stage the user is at. The server then generates optimal strategy information based on the user's progress and play style, and provides it through the chat bot. For example, it provides specific advice such as, "Your equipment has a fire attribute, so using water magic would be effective."

[0051] Specific examples

[0052] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[0053] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0054] The processing flow will be explained below.

[0055] Step 1: Collect gameplay footage

[0056] The server collects gameplay videos from the internet, for example, by using a streaming platform's API to automatically download videos related to a specific game. The downloaded videos are then stored along with metadata such as the game name, player name, and play time.

[0057] Step 2: Save the video

[0058] The server saves the collected videos to cloud storage or local storage. When saving, it organizes the folder structure to make analysis easier and registers appropriate metadata.

[0059] Step 3: Preprocessing the video

[0060] The server breaks down the stored video into frames. Important scenes (e.g., boss battles or item acquisition scenes) are extracted through frame analysis. The extracted frames are used in subsequent analysis steps.

[0061] Step 4: Analyze behavioral patterns

[0062] The server uses a deep learning model to analyze the player's behavior in the video. This analysis evaluates the reasons why the player chose a particular strategy and its effectiveness. For example, it can extract which attacks were used most frequently in a particular boss battle, and which items were used when.

[0063] Step 5: Update the database

[0064] The server registers the analysis results in a database and compares them with existing strategy information. If any new effective tactics or patterns of behavior are discovered, they are added and updated as new data.

[0065] Step 6: Generate strategy information

[0066] The server generates strategy information based on the newly extracted behavioral patterns. The generated information is saved in the form of text, images, and videos. For example, it generates information such as "The Dragon King's weak point is its head, so using water magic is effective," along with a video clip showing the specific tactics.

[0067] Step 7: Update the strategy wiki

[0068] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest walkthrough information. Update history is also saved, allowing users to return to previous versions if necessary.

[0069] Step 8: Chatbot Database Sync

[0070] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[0071] Step 9: Update the natural language processing model

[0072] The server updates the chatbot's natural language processing model to accommodate new user inquiry patterns, for example, training it to generate appropriate responses to questions like, "How do I beat boss XX?"

[0073] Step 10: Accepting user inquiries

[0074] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[0075] Step 11: Evaluate your progress

[0076] The server obtains the user's progress from the game's API and save data, and evaluates the progress. This determines which stage the user is currently in, which boss they are challenging, etc.

[0077] Step 12: Provide optimal information

[0078] The server generates optimal strategy information based on the user's progress and play style and provides it through a chatbot. For example, it can provide specific advice such as "Instant Strategy: Your equipment is fire-element, so using water magic would be effective."

[0079] Through the above steps, the system of the present invention can provide players with optimal strategy information and support an efficient gaming experience.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Conventional game strategy information systems have had difficulty quickly providing optimal strategy information based on the player's behavioral patterns and progress. In particular, providing the timely and detailed strategy information that players desire requires processing of massive amounts of data and advanced analysis, and conventional methods have had limitations in meeting this challenge.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for collecting gameplay videos of players from the Internet, means for breaking down the collected videos into frames and extracting scenes with a lot of action or important frames, and means for analyzing the extracted frames using a deep learning model to identify behavioral patterns, thereby making it possible to provide optimal strategy information based on the player's behavioral patterns and progress.

[0085] The "Internet" is a global communications network that connects computers and networks around the world.

[0086] "Player" refers to a user who actually operates and plays a computer game.

[0087] "Gameplay video" is recorded or streamed footage of a player interacting with a game.

[0088] A "frame" is each still image in a video, and a video is formed by playing these images consecutively.

[0089] A "deep learning model" is an algorithm that uses a multi-layer neural network to automatically learn the characteristics of data and perform analysis and prediction.

[0090] A "behavioral pattern" refers to a series of actions or choices that a player tends to make in a game.

[0091] "Way-to-win information" is information that includes advice, strategies, and hints for efficiently clearing a game.

[0092] A "website" is a collection of information that is publicly available on the Internet and accessible at a particular URL.

[0093] A "database" is a system for efficiently managing and searching large amounts of data.

[0094] A "chatbot" is a program that automatically converses with users through text.

[0095] A "game API" is a piece of programming that provides an interface for accessing game data and functionality.

[0096] "Save data" is data that saves the game progress, allowing players to resume from where they left off.

[0097] A "terminal" is a device that is directly operated by a user, and typically refers to a smartphone or personal computer.

[0098] A "natural language processing model" is a machine learning model for understanding and processing natural human language.

[0099] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the necessary strategy information through a chatbot. A specific embodiment of this system will be described.

[0100] Data collection

[0101] The server collects gameplay videos of players via the Internet. Specifically, it uses the streaming platform's API (e.g., YouTube Data API) to automatically download videos related to the specified game name. The collected videos are then stored in cloud storage (e.g., Amazon S3) or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[0102] Video frame analysis

[0103] The server breaks down the stored video into frames and extracts scenes with a lot of action and important frames. Specifically, it uses libraries such as OpenCV to divide the video into frames and detects scenes with a lot of action, boss battles, item acquisition scenes, etc. These important frames are then stored in a separate database and associated with corresponding metadata.

[0104] Behavioral pattern analysis

[0105] The server uses a deep learning model (e.g., a CNN model using TensorFlow) to analyze the extracted key frames and identify the player's behavioral patterns. The analysis includes effective tactics for specific boss battles and the optimal timing for using items. The results of this analysis are stored in a strategy information database.

[0106] Strategy information generation

[0107] Based on the results of the behavioral pattern analysis, the server generates strategy information in the form of text, images, and videos. For example, it generates specific information such as "A certain boss's weak spot is its head, so you should use a specific item to avoid attacks," along with a video clip explaining this.

[0108] Strategy wiki update

[0109] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to return to previous versions at any time.

[0110] Preparing the chatbot

[0111] The server synchronizes the strategy information database with the chatbot's database so that the latest strategy information can be obtained from the chatbot. Furthermore, the server updates the chatbot's natural language processing model (e.g., GPT-3) so that it can respond appropriately to user inquiries.

[0112] Responding to user inquiries

[0113] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API (such as the PlayFab API) or save data, and evaluates the user's current stage. The server then generates optimal strategy information that takes into account the user's progress and equipment, and provides it via the chat bot.

[0114] Specific examples

[0115] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[0116] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] The server uses the streaming platform's API to collect gameplay videos. In this case, the server searches for videos related to a specific game name and downloads videos that match the criteria. The input is the specific game name and related keywords, and the output is the downloaded video file. Specifically, the server uses the YouTube Data API to search for related videos for "Fantasy Quest" and downloads the corresponding videos.

[0120] Step 2:

[0121] The server saves the downloaded video file in cloud storage or local storage. When saving, metadata (game name, player name, playback time, etc.) is added to the video. The input is the video file and associated metadata, and the output is the saved video file and its metadata. Specifically, the server uploads the video file to Amazon S3 and adds the metadata.

[0122] Step 3:

[0123] The server divides the stored video into frames and extracts important frames. The input is the stored video file, and the output is the extracted important frames. Specifically, the server uses OpenCV to divide the video into frames and detect scenes with a lot of action, boss battles, and item acquisition scenes.

[0124] Step 4:

[0125] The server inputs the extracted important frames into a deep learning model to analyze the player's behavioral patterns. The inputs are the important frames and the deep learning model, and the output is the behavioral patterns resulting from the analysis. Specifically, the server inputs the important frames into a CNN model using TensorFlow to identify specific behavioral patterns.

[0126] Step 5:

[0127] The server generates strategy information based on the analysis results. The input is the analysis results of behavioral patterns, and the output is strategy information in the form of text, images, and videos. Specific operations include generating text and video clips on how to defeat a specific boss and when to use items.

[0128] Step 6:

[0129] The server reflects the generated walkthrough information on the walkthrough wiki site. The input is the generated walkthrough information, and the output is the updated walkthrough wiki page. Specifically, the server posts the new walkthrough information using the wiki site's API.

[0130] Step 7:

[0131] The server synchronizes the strategy information database with the chat bot database. The input is the strategy information database, and the output is the synchronized chat bot database. Specifically, the server uses the database replication function to perform the synchronization.

[0132] Step 8:

[0133] The server updates the chatbot's natural language processing model so that it can respond to user inquiries. The input is the natural language processing model and new data, and the output is the updated natural language processing model. Specifically, the server executes the process of updating the GPT-3 model.

[0134] Step 9:

[0135] A user accesses a chatbot using a device and asks for specific strategy information. The input is the user's text input, and the output is the chatbot's answer. Specifically, the user asks the chatbot, "Tell me how to beat the boss of the current stage."

[0136] Step 10:

[0137] The server obtains the user's progress from the game API and save data and provides optimal strategy information. The input is the user's progress data and play style data, and the output is optimized strategy information. Specifically, the server uses the PlayFab API to obtain and analyze the user's game progress. It then generates customized strategy information based on the user's equipment and current status and provides it via a chat bot.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] Today's game players need to quickly obtain complex and diverse game strategy information to progress effectively in games. However, the wide variety of strategy information available on the Internet makes it difficult to find information optimized for each player's progress and playing style. Furthermore, existing strategy websites and video content provide general information and lack the means to provide specific strategies and methods tailored to each user. To solve this problem, a system is needed that quickly provides optimal strategy information based on the user's progress and playing style.

[0141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0142] In this invention, the server includes means for collecting gameplay videos of players around the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on a user's progress and play style, means for notifying the user of the optimal strategy information through a smartphone application, and means for saving and sharing the user's play style and progress in a cloud-based database. This allows users to easily obtain individually optimized strategy information in real time and progress through the game effectively.

[0143] "Gameplay video" refers to video content that is recorded or streamed to show a player actually playing a game.

[0144] A "behavioral pattern" refers to a tendency for a game player to take a series of actions or behaviors in a particular situation.

[0145] "Strategy information" refers to information about strategies and methods for clearing or defeating difficult scenes or enemies in the game.

[0146] A "streaming platform API" is a mechanism for collecting and manipulating video data using a program interface provided by a streaming service.

[0147] A "natural language processing model" is an artificial intelligence technology that understands the natural language (sentences) entered by the user and generates an appropriate response.

[0148] A "chatbot" is an automated response system that provides information and answers questions through conversations with users.

[0149] A "smartphone application" is a software program that runs on a smartphone and provides specific functions or services.

[0150] A "cloud-based database" is a database system built on a remote server accessible via the Internet.

[0151] A system for realizing the present invention includes the following means.

[0152] A means of collecting gameplay videos from players around the world

[0153] The server uses the streaming platform's API to automatically collect gameplay videos from players around the world, allowing the server to collect a large number of gameplay videos related to a specific game.

[0154] Gameplay video analysis tool

[0155] The server breaks down the collected gameplay videos into frames and uses a deep learning model to analyze the player's behavioral patterns in the videos. This analysis allows it to extract effective tactics and optimal timing for specific scenes (e.g., boss battles, item acquisition, etc.). This analysis is performed using high-performance servers equipped with GPUs or cloud-based computing resources.

[0156] Strategy information generation means

[0157] The server generates game strategy information based on the analysis results. This strategy information is saved in the form of text, images, and video clips. For example, it may include specific tactical information such as "In boss battles, use water magic to avoid fire-element attacks."

[0158] Automatic website update methods

[0159] The generated strategy information is automatically updated by the server on a website that provides strategy information. This allows users to always access the latest strategy information. The website's backend uses a database management system (DBMS) to ensure smooth data updates.

[0160] Chatbot Means

[0161] Furthermore, the server is equipped with a chatbot that provides optimal strategy information in response to user inquiries. The chatbot incorporates a natural language processing model and generates appropriate answers to questions entered by the user. This allows users to obtain the strategy information they need in real time.

[0162] Smartphone application means

[0163] A dedicated smartphone application is provided so that users can quickly obtain strategy information via their smartphone. The application is designed to notify users of the most appropriate strategy information based on their progress and play style. For example, a notification such as "The fire-element weapon you are equipped with is effective in the next boss battle" can be provided in real time.

[0164] Cloud-based database solutions

[0165] Data about a user's play style and progress is stored in a cloud-based database, which provides consistent information across different devices. The database is highly scalable and can efficiently manage large amounts of data.

[0166] Examples of concrete examples and prompts

[0167] For example, in the case of the game "Fantasy Quest," the server collects gameplay videos from YouTube, analyzes them using a deep learning model, and generates a "strategy for defeating the Dragon King." When a user asks a smartphone application chatbot, "Tell me how to beat the Dragon King," the server instantly provides specific strategy information, such as "Use water magic to block fire attacks, then focus attacks on the head," based on the user's equipment and progress.

[0168] Prompt Sentence Examples

[0169] "Tell me some effective tactics for the boss battle in the next stage."

[0170] "How can I gain an advantage with my current equipment?"

[0171] "I want to know where to get a specific item."

[0172] By means of the above means, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] The server uses the streaming platform's API to collect gameplay videos from players around the world. The input is video metadata (game name, player name, URL, etc.), and the output is a video file stored in the server's local storage or cloud storage. Specifically, the server makes an API request, analyzes the response data, and downloads the video.

[0176] Step 2:

[0177] The server breaks down the collected gameplay videos into frames and extracts important frames. The input is the saved gameplay video file, and the output is a collection of frames containing important scenes. Specifically, it uses a video analysis algorithm to detect and extract scenes with a lot of action, boss battles, and item acquisition scenes.

[0178] Step 3:

[0179] The server uses a deep learning model to analyze the player's behavioral patterns in the video. The input is the extracted important frames, and the output is data about the player's behavioral patterns. Specifically, the deep learning model analyzes a sequence of frames and recognizes specific actions (e.g., the timing of using a specific technique).

[0180] Step 4:

[0181] The server generates strategy information based on the analysis results. The input is behavioral pattern data, and the output is strategy information in the form of text, images, and video clips. Specifically, the server uses a generative AI model to generate content describing optimal tactics and strategies based on specific behaviors.

[0182] Step 5:

[0183] The server automatically updates the generated strategy information to the website that provides the strategy information. The input is the generated strategy information, and the output is the updated web page. Specifically, the server inserts the new information into the website's database and regenerates the corresponding web page.

[0184] Step 6:

[0185] A user accesses a chatbot using a device (such as a smartphone or PC) and makes an inquiry to obtain specific strategy information. The input is a question (prompt) in natural language from the user, and the output is an answer from the chatbot. A specific example of how this works is when the user inputs, "Tell me how to beat the boss of the current stage."

[0186] Step 7:

[0187] The server generates optimal strategy information based on the user's progress and play style and provides it through the chatbot. The input is the user's progress, equipment data, and inquiry, and the output is a specific answer regarding the optimal strategy. Specifically, the server analyzes the progress data, generates appropriate strategy information, and provides it to the user via the chatbot.

[0188] Step 8:

[0189] It is designed to allow users to quickly obtain game strategy information through a smartphone application. The input is user account information and in-game progress data, and the output is notification messages within the application. Specifically, the application periodically sends requests to the server, receives the latest game strategy information, and notifies the user.

[0190] Step 9:

[0191] The server stores and shares data about users' play styles and progress in a cloud-based database. The input is the user's play data, and the output is a well-organized database stored in the cloud. Specifically, the server periodically collects play data and uploads and updates it to the cloud system.

[0192] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0193] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[0194] Data collection

[0195] The server collects game player gameplay videos from the internet. Using the streaming platform's API, it automatically downloads videos related to specific games and saves them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[0196] Data analysis

[0197] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. Next, a deep learning model is used to analyze the player's behavioral patterns. For example, it can extract attack patterns for specific boss battles and the optimal timing for using items.

[0198] Strategy information generation

[0199] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0200] Strategy wiki update

[0201] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[0202] Preparing the chatbot

[0203] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information. The server also updates the chatbot's natural language processing model, enabling it to respond to various user inquiries.

[0204] Emotion engine integration

[0205] The server integrates an emotion engine to acquire data for real-time user emotion recognition. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.).

[0206] Responding to user inquiries

[0207] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[0208] Emotionally responsive feedback

[0209] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0210] Specific examples

[0211] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[0212] When a user asks the chatbot, "Tell me how to beat Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking." In this way, the present invention can provide players with optimal strategy information, providing a system that ensures a comfortable gaming experience.

[0213] The processing flow will be explained below.

[0214] Step 1: Collect gameplay footage

[0215] The server uses the streaming platform's API to automatically download gameplay videos related to a specific game, and adds metadata such as the game name, player name, and playback time to the downloaded video.

[0216] Step 2: Save the video

[0217] The gameplay videos collected by the server are stored in cloud storage or local storage. By creating a folder structure and properly registering related metadata, subsequent analysis processing becomes easier.

[0218] Step 3: Preprocessing the video

[0219] The server breaks down the stored video into frames and extracts important scenes, such as boss battles and item acquisition scenes. The extracted frames are then used for analysis by a deep learning model.

[0220] Step 4: Analyze behavioral patterns

[0221] The server uses a deep learning model to analyze the player's behavior patterns within the extracted frames. For example, it can extract attack patterns in a specific boss battle or the timing of item use, and record this data as the player's behavior patterns.

[0222] Step 5: Update the database

[0223] The server registers the analysis results in a database, and if new effective tactics or patterns of behavior are found by comparing them with existing strategy information, they are added to the database.

[0224] Step 6: Generate strategy information

[0225] The server generates strategy information based on the information in the database. The strategy information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so water magic is effective against it," along with a video clip showing this information.

[0226] Step 7: Update the strategy wiki

[0227] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, ensuring that users always have access to the latest walkthrough information. Update history is also saved, making it possible to revert to previous versions if necessary.

[0228] Step 8: Chatbot Database Sync

[0229] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[0230] Step 9: Update the natural language processing model

[0231] The server updates the chatbot's natural language processing model to generate optimal responses to user queries. The trained model understands the user's question and provides the appropriate answer.

[0232] Step 10: Integrating the Emotion Engine

[0233] The server integrates an emotion engine to recognize the user's emotional state in real time, which analyzes the user's facial expressions, tone of voice, and text input to evaluate the user's emotional state.

[0234] Step 11: Accepting user inquiries

[0235] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[0236] Step 12: Evaluate your progress

[0237] The server obtains the user's progress from the game API and save data, determines the current stage of the game, and customizes the walkthrough information provided based on the user's progress.

[0238] Step 13: Emotionally responsive feedback

[0239] The server generates optimal strategy information and feedback based on the evaluation of the user's emotional state using an emotion engine. For example, if the user is feeling frustrated, the server will provide advice tailored to their emotions, such as "Water magic is effective. Stay calm and continue playing."

[0240] Through the above steps, the system of the present invention can provide the user with the strategy information they need quickly and accurately, and by providing feedback that takes into account the user's emotional state, it can provide a comfortable gaming experience.

[0241] Example 2

[0242] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0243] Conventional strategy information systems have the problem of only providing general strategy information without considering the player's play style or emotional state. This makes it difficult for players to obtain appropriate strategy information, which can reduce the enjoyment of gameplay. In addition, manually collecting and updating strategy information is cumbersome and lacks real-time performance.

[0244] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0245] In this invention, the server includes a means for collecting gameplay videos from the Internet, a means for extracting important scenes by breaking down the collected videos into frames, and a means for generating strategy information based on the extracted behavioral patterns, thereby enabling the prompt and appropriate provision of strategy information that takes into account the player's play style and emotional state.

[0246] A "gameplay video" is a video file that records the user playing a game.

[0247] The "Internet" is a communications network that connects computer networks around the world.

[0248] A "frame" is an individual still image that makes up a video.

[0249] "Important scenes" are particularly noteworthy moments during gameplay, such as boss battles and item acquisition.

[0250] A "behavior pattern" is a series of movements or actions that a player takes in the game.

[0251] "Strategy information" refers to specific advice and strategies to help you progress through the game to your advantage.

[0252] A "website" is a collection of informational pages available on the Internet.

[0253] "User emotional state" refers to emotions such as joy, anger, sadness, etc. that a player feels while playing a game.

[0254] A "chatbot" is a software application that automates interactions with users.

[0255] A "natural language processing model" refers to algorithms and techniques for understanding and analyzing human language.

[0256] A "streaming platform" is a service that distributes video and audio in real time over the Internet.

[0257] "API" stands for Application Program Interface, an interface for exchanging functions and data between different software applications.

[0258] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[0259] Data collection

[0260] The server uses the streaming platform's API to collect gameplay videos related to a specific game. For example, it uses the YouTube Data API to search for specific keywords and automatically download new videos. The downloaded videos are stored in cloud storage (e.g., Amazon S3 or Google Cloud Storage) and are assigned metadata (such as the game name, player name, and playback time).

[0261] Data analysis

[0262] The server breaks down the stored video into frames and extracts important scenes (such as boss battles and item acquisition scenes). Specifically, it uses video processing tools such as FFmpeg to convert the video to 30 frames per second, and then uses deep learning models (e.g., TensorFlow and PyTorch) to analyze the player's behavioral patterns. During this process, it extracts scenes with a lot of action, such as boss battles and item acquisition scenes.

[0263] Strategy information generation

[0264] The server generates strategy information based on the analysis results. A natural language generation model (e.g., GPT-3) is used to generate information in the form of text, images, and videos. The generated strategy information is stored in a database. For example, specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip illustrating this information are generated.

[0265] Strategy wiki update

[0266] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. Updates are performed periodically using Amazon Lambda or Cron, ensuring that users always have access to the latest information. Change history is also saved in a version control system (e.g., Git), allowing users to revert to previous versions as needed.

[0267] Preparing the chatbot

[0268] The server synchronizes the strategy information database with the chatbot's database. It uses natural language processing models such as Dialogflow to respond to user inquiries. This allows the chatbot to obtain the latest strategy information.

[0269] Emotion engine integration

[0270] The server integrates an emotion engine and collects data to recognize the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Specifically, it uses Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[0271] Responding to user inquiries

[0272] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[0273] Emotionally responsive feedback

[0274] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0275] Specific examples

[0276] For example, in the game "Fantasy Quest," a server collects gameplay footage from a streaming platform and extracts key scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on a strategy wiki and is instantly available to chatbots.

[0277] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking."

[0278] Example prompt: "Tell me how to defeat the Dragon King. If the emotional state is Frustrated, please also include some advice to calm the user down."

[0279] In this way, the present invention provides a system that provides players with optimal strategy information and realizes a comfortable gaming experience.

[0280] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0281] Step 1:

[0282] Gameplay video collection

[0283] The server uses the API of the streaming platform to collect gameplay videos related to a specific game. Search keywords and the API key of the streaming platform are given as input. The server downloads these videos from the Internet and stores them in cloud storage. The output is the collected video files and their metadata. Specifically, the server periodically calls the API to obtain a list of new videos and downloads each video sequentially.

[0284] Step 2:

[0285] Video frame decomposition

[0286] The server uses a video processing tool (e.g., FFmpeg) to break down the collected video into frames. A video file is given as input. The server breaks down the video into 30 frames per second and saves each frame in image format. As output, frame image files are obtained. Specifically, the server executes FFmpeg commands to convert the video into image files at the specified frame rate.

[0287] Step 3:

[0288] Extracting important scenes

[0289] The server analyzes each frame using a deep learning model (e.g., TensorFlow or PyTorch) and extracts important scenes. The decomposed frame images are given as input. The server uses an image recognition model to detect particularly important scenes, such as boss battles and item acquisition scenes. The output is a list of important frames. Specifically, the server inputs each frame image into the model and evaluates its importance based on the identification results of each frame.

[0290] Step 4:

[0291] Behavioral pattern analysis

[0292] The server analyzes the player's behavioral patterns based on frames of important scenes. As input, it receives important frame images and corresponding video sequences. The server uses a behavioral analysis model to analyze the player's behavioral patterns, such as attack patterns and item usage timing. As output, it obtains behavioral pattern data. Specifically, the server inputs the video sequences into the model and extracts behavioral patterns.

[0293] Step 5:

[0294] Generation of strategy information

[0295] The server generates walkthrough information based on the results of the behavioral pattern analysis. Behavioral pattern data is provided as input. The server uses a natural language generation model (e.g., GPT-3) to create walkthrough information in text format, and also generates images and videos as needed. The generated walkthrough information is obtained as output. Specifically, the server inputs the analysis results as prompts into the generation model to obtain the walkthrough information.

[0296] Step 6:

[0297] Automatic update of strategy information

[0298] The server runs a script to automatically update the walkthrough information on the website. The generated walkthrough information is given as input. The server uses a version control system (e.g., Git) to update the information on the walkthrough wiki site. The output is the updated website. Specifically, the server performs Git commit and push operations to update the website.

[0299] Step 7:

[0300] Chatbot database synchronization

[0301] The server synchronizes the strategy information database with the chatbot's database. The latest strategy information is provided as input. The server updates the natural language processing model (e.g., Dialogflow) to make the latest strategy information available to the chatbot. The output is an updated chatbot. Specifically, the server calls the Dialogflow API to update the dataset.

[0302] Step 8:

[0303] Emotion engine integration

[0304] The server integrates emotion engines to analyze the user's emotional state. The user's facial expressions, tone of voice, and text are given as input. The server evaluates the emotional state using an emotion analysis model (e.g., Microsoft Azure's Face API or IBM Watson's Tone Analyzer). The output is the user's emotional state data. Specifically, the server calls various emotion analysis APIs in sequence and obtains the integrated evaluation results.

[0305] Step 9:

[0306] Responding to user inquiries

[0307] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. The user's inquiry is given to the chatbot as input. The server takes into account the user's progress and emotional state and provides the most appropriate strategy information. The output is an answer from the chatbot. Specifically, the server has the chatbot generate an appropriate answer based on the user's progress data and emotional state data.

[0308] Step 10:

[0309] Emotionally responsive feedback

[0310] The server provides feedback based on the user's emotional state. The user's emotional state data is given as input. The server generates an interface and advice that is effective for the specific emotional state based on the emotional state. The output is feedback appropriate for the user. In concrete terms, the server generates specific advice and messages for the user based on the evaluation results of the emotion engine and provides them through the chatbot.

[0311] (Application example 2)

[0312] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0313] In recent years, online games have become popular with many players, resulting in increasingly complex game mechanisms and stages that are difficult to complete. Consequently, many players are seeking strategy guides and tend to search the Internet for them. However, these guides are not always suited to the player's progress or play style, requiring the player to spend a lot of time gathering and applying the information. Furthermore, the lack of feedback based on the player's emotional state can lead to frustration. Therefore, there is a need for a system that can quickly provide optimal strategy guides based on the player's progress, play style, and emotional state.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting gameplay videos of players from all over the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on the user's progress and play style, an emotion recognition engine for recognizing the user's emotional state, and means for providing appropriate feedback based on the user's emotional state. This makes it possible to quickly and effectively provide optimal strategy information that takes into account the player's progress, play style, and emotional state.

[0315] "Gameplay videos of players from around the world" refers to video recordings of games being played by multiple players from around the world, distributed via the Internet.

[0316] "Means of collection" refers to devices or systems, including hardware and software, for downloading specific videos from the Internet and storing them in cloud storage or local storage.

[0317] "Means of analyzing and extracting player behavior patterns" refers to a method of breaking down saved video into frames, identifying specific scenes and player behavior using deep learning models, and extracting those patterns.

[0318] "Means for generating strategy information" refers to a system that generates optimal strategies for specific tasks or boss battles in the game in the form of text, images, videos, etc., based on extracted player behavior patterns.

[0319] "Means for automatically updating to a website" refers to software and scripts that automatically upload the generated cheat information to an existing website, thereby providing users with the latest information at all times.

[0320] "Chatbot means" refers to a program and interface that uses natural language processing to automatically respond to inquiries from users and provide appropriate strategy information.

[0321] An "emotion recognition engine" refers to algorithms and software that analyze a user's facial expressions, tone of voice, text input, etc., and use the results to assess the user's emotional state.

[0322] "Means for providing feedback" refers to a program and interface for providing appropriate information or advice in response to the user's emotional state as assessed by the emotion recognition engine.

[0323] A specific embodiment of the present invention will be described below. This invention combines a system that automatically generates strategy information optimized for the play style of a game player and enables the player to quickly obtain the necessary strategy information through a chatbot with an emotion engine that recognizes the user's emotions.

[0324] Data collection

[0325] The server collects gameplay videos via the Internet. Specifically, it uses the streaming platform's API to automatically download videos related to specific games and save them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[0326] Data analysis

[0327] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. It then uses a deep learning model to analyze the player's behavioral patterns, extracting, for example, attack patterns for specific boss battles and optimal timing for using items.

[0328] Strategy information generation

[0329] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0330] Strategy wiki update

[0331] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, so users can always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[0332] Response to inquiries via chatbots

[0333] Using a device (such as a smartphone or PC), the user accesses the chatbot and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, assesses their current stage, and provides them with the most appropriate strategy information.

[0334] Emotion engine integration and feedback provision

[0335] The server integrates an emotion engine to acquire data for recognizing the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Based on the evaluation results of the emotion engine, the system provides an appropriate interface and feedback for a specific emotional state. For example, if a user is feeling frustrated with a game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0336] Example

[0337] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[0338] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy based on the user's progress, equipment, and emotional state.

[0339] Adding concrete examples and prompt sentence examples

[0340] Specifically, when a user wearing smart glasses is playing a game, the application uses the smart glasses' camera to capture the user's facial expressions in real time, analyzes their emotional state (e.g., "anger"), and then inputs prompt sentences like the following into the generative AI model:

[0341] Example prompt sentence:

[0342] I'm playing the game "Fantasy Quest" and I'm having trouble with the boss battle against the Dragon King. Can you tell me how to beat him? The user is currently in an "Anger" state.

[0343] This allows the generative AI model to provide specific strategy information that takes into account the user's emotional state, such as "Water magic is effective in defeating the Dragon King. Stay calm and keep attacking."

[0344] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0345] Step 1:

[0346] The server collects gameplay videos via the internet using the streaming platform's API. At this time, it obtains metadata (game name, player name, play time, etc.) along with the video data obtained from the API and stores them in cloud storage or local storage. The input is an API request, and the output is a video file and metadata.

[0347] Step 2:

[0348] The server breaks down the saved gameplay video into frames and extracts important frames. The input is the saved video file, and the output is a set of extracted important frames. Specifically, it uses a deep learning model to detect scenes with a lot of action, such as boss battles and item acquisition scenes, and saves these as frames.

[0349] Step 3:

[0350] The server analyzes the player's behavioral patterns based on the extracted important frames. This requires frame data as input and generates behavioral pattern data as output. A deep learning model is used for this analysis, and data such as attack patterns for specific boss battles and the optimal timing for using items can be extracted.

[0351] Step 4:

[0352] The server generates strategy information based on the analysis results. This strategy information is generated in the form of text, images, and videos. The input is behavioral pattern data, and the output is specific strategy information. For example, a text file containing information such as "The Dragon King's weak spot is its head, so use water magic to avoid its fire attacks" may be created.

[0353] Step 5:

[0354] The server automatically updates the generated walkthrough information on the walkthrough wiki site. Here, the walkthrough information data is input and the website is updated as output. This automatic update script runs, and the walkthrough information is always kept up to date.

[0355] Step 6:

[0356] The user accesses the chatbot using their device and asks for specific strategy information. At this time, the user's progress is obtained from the game API and save data, and the stage at which the user is is evaluated. The input is the user's query and progress data, and the output is the most appropriate strategy information. For example, if a user asks, "Tell me how to beat Dragon King," the server evaluates the user's progress and provides the appropriate strategy information through the chatbot.

[0357] Step 7:

[0358] The server integrates an emotion engine to capture data for real-time user emotion recognition. The input is real-time data from the camera and microphone, and the output is an evaluation of the user's emotional state. This emotion recognition is achieved by analyzing facial expressions, tone of voice, and text input.

[0359] Step 8:

[0360] The server provides appropriate feedback for a specific emotional state based on the evaluation results of the emotion engine. Emotional state data is input and feedback is generated as output. For example, if a user is feeling frustrated, the chatbot will provide advice such as, "Why don't you take a short break here?"

[0361] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0362] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0363] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0364] [Second embodiment]

[0365] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0366] 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.

[0367] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0368] 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.

[0369] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0370] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0371] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0372] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0373] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0374] 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.

[0375] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0376] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0377] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the strategy information they need through a chatbot. Specific embodiments for realizing this system will be described below.

[0378] Data collection

[0379] The server collects game player gameplay videos from the internet. Specifically, it automatically downloads videos related to the game name using, for example, a streaming platform's API. The collected videos are then stored in cloud storage or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[0380] Data analysis

[0381] The server breaks down the stored video into frames and extracts key frames, including high-action scenes, boss battles, and item acquisition scenes. The server then uses a deep learning model to analyze the player's behavioral patterns in the video. For example, it automatically extracts effective tactics for a particular boss battle or the optimal timing for using items.

[0382] Strategy information generation

[0383] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0384] Strategy wiki update

[0385] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to revert to previous versions at any time.

[0386] Preparing the chatbot

[0387] The server synchronizes the strategy information database with the chat bot's database, allowing the chat bot to obtain the latest strategy information. Furthermore, the server updates the chat bot's natural language processing model so that it can respond to user inquiries.

[0388] Responding to user inquiries

[0389] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates the stage the user is at. The server then generates optimal strategy information based on the user's progress and play style, and provides it through the chat bot. For example, it provides specific advice such as, "Your equipment has a fire attribute, so using water magic would be effective."

[0390] Specific examples

[0391] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[0392] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0393] The processing flow will be explained below.

[0394] Step 1: Collect gameplay footage

[0395] The server collects gameplay videos from the internet, for example, by using a streaming platform's API to automatically download videos related to a specific game. The downloaded videos are then stored along with metadata such as the game name, player name, and play time.

[0396] Step 2: Save the video

[0397] The server saves the collected videos to cloud storage or local storage. When saving, it organizes the folder structure and registers appropriate metadata to make analysis easier.

[0398] Step 3: Preprocessing the video

[0399] The server breaks down the stored video into frames. Important scenes (e.g., boss battles or item acquisition scenes) are extracted through frame analysis. The extracted frames are used in subsequent analysis steps.

[0400] Step 4: Analyze behavioral patterns

[0401] The server uses a deep learning model to analyze the player's behavior in the video. This analysis evaluates the reasons why the player chose a particular strategy and its effectiveness. For example, it can extract which attacks were used most frequently in a particular boss battle, and which items were used when.

[0402] Step 5: Update the database

[0403] The server registers the analysis results in a database and compares them with existing strategy information. If any new effective tactics or patterns of behavior are discovered, they are added and updated as new data.

[0404] Step 6: Generate strategy information

[0405] The server generates strategy information based on the newly extracted behavioral patterns. The generated information is saved in the form of text, images, and videos. For example, it could generate information such as "The Dragon King's weak point is its head, so using water magic is effective," along with a video clip showing the specific tactics.

[0406] Step 7: Update the strategy wiki

[0407] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest walkthrough information. Update history is also saved, allowing users to return to previous versions if necessary.

[0408] Step 8: Chatbot Database Sync

[0409] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[0410] Step 9: Update the natural language processing model

[0411] The server updates the chatbot's natural language processing model to accommodate new user inquiry patterns, for example, training it to generate appropriate responses to questions like, "How do I beat boss XX?"

[0412] Step 10: Accepting user inquiries

[0413] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[0414] Step 11: Evaluate your progress

[0415] The server obtains the user's progress from the game's API and save data, and evaluates the progress. This determines which stage the user is currently in, which boss they are challenging, etc.

[0416] Step 12: Provide optimal information

[0417] The server generates optimal strategy information based on the user's progress and play style and provides it through a chatbot. For example, it can provide specific advice such as, "Instant Strategy: Your equipment is fire-element, so using water magic would be effective."

[0418] Through the above steps, the system of the present invention can provide players with optimal strategy information and support an efficient gaming experience.

[0419] Example 1

[0420] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0421] Conventional game strategy information systems have had difficulty quickly providing optimal strategy information based on the player's behavioral patterns and progress. In particular, providing the timely and detailed strategy information that players desire requires processing of massive amounts of data and advanced analysis, and conventional methods have had limitations in meeting this challenge.

[0422] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0423] In this invention, the server includes means for collecting gameplay videos of players from the Internet, means for breaking down the collected videos into frames and extracting scenes with a lot of action or important frames, and means for analyzing the extracted frames using a deep learning model to identify behavioral patterns, thereby making it possible to provide optimal strategy information based on the player's behavioral patterns and progress.

[0424] The "Internet" is a global communications network that connects computers and networks around the world.

[0425] "Player" refers to a user who actually operates and plays a computer game.

[0426] "Gameplay video" is recorded or streamed footage of a player interacting with a game.

[0427] A "frame" is each still image in a video, and a video is formed by playing these images consecutively.

[0428] A "deep learning model" is an algorithm that uses a multi-layer neural network to automatically learn the characteristics of data and perform analysis and prediction.

[0429] A "behavioral pattern" refers to a series of actions or choices that a player tends to make in a game.

[0430] "Way-to-win information" is information that includes advice, strategies, and hints for efficiently clearing a game.

[0431] A "website" is a collection of information that is publicly available on the Internet and accessible at a particular URL.

[0432] A "database" is a system for efficiently managing and searching large amounts of data.

[0433] A "chatbot" is a program that automatically converses with users through text.

[0434] A "game API" is a piece of programming that provides an interface for accessing game data and functionality.

[0435] "Save data" is data that saves the game progress, allowing players to resume from where they left off.

[0436] A "terminal" is a device that is directly operated by a user, and typically refers to a smartphone or personal computer.

[0437] A "natural language processing model" is a machine learning model for understanding and processing natural human language.

[0438] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the necessary strategy information through a chatbot. A specific embodiment of this system will be described.

[0439] Data collection

[0440] The server collects gameplay videos of players via the Internet. Specifically, it uses the streaming platform's API (e.g., YouTube Data API) to automatically download videos related to the specified game name. The collected videos are then stored in cloud storage (e.g., Amazon S3) or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[0441] Video frame analysis

[0442] The server breaks down the stored video into frames and extracts scenes with a lot of action and important frames. Specifically, it uses libraries such as OpenCV to divide the video into frames and detects scenes with a lot of action, boss battles, item acquisition scenes, etc. These important frames are then stored in a separate database and assigned corresponding metadata.

[0443] Behavioral pattern analysis

[0444] The server uses a deep learning model (e.g., a CNN model using TensorFlow) to analyze the extracted key frames and identify the player's behavioral patterns. The analysis includes effective tactics for specific boss battles and the optimal timing for using items. The results of this analysis are stored in a strategy information database.

[0445] Strategy information generation

[0446] Based on the results of the behavioral pattern analysis, the server generates strategy information in the form of text, images, and videos. For example, it generates specific information such as "A certain boss's weak spot is its head, so you should use a specific item to avoid attacks," along with a video clip explaining this.

[0447] Strategy wiki update

[0448] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to return to previous versions at any time.

[0449] Preparing the chatbot

[0450] The server synchronizes the strategy information database with the chatbot's database so that the latest strategy information can be obtained from the chatbot. Furthermore, the server updates the chatbot's natural language processing model (e.g., GPT-3) so that it can respond appropriately to user inquiries.

[0451] Responding to user inquiries

[0452] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API (such as the PlayFab API) or save data, and evaluates the user's current stage. The server then generates optimal strategy information that takes into account the user's progress and equipment, and provides it via the chat bot.

[0453] Specific examples

[0454] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[0455] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0456] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0457] Step 1:

[0458] The server uses the streaming platform's API to collect gameplay videos. In this case, the server searches for videos related to a specific game name and downloads videos that match the criteria. The input is the specific game name and related keywords, and the output is the downloaded video file. Specifically, the server uses the YouTube Data API to search for related videos for "Fantasy Quest" and downloads the corresponding videos.

[0459] Step 2:

[0460] The server saves the downloaded video file in cloud storage or local storage. When saving, metadata (game name, player name, playback time, etc.) is added to the video. The input is the video file and associated metadata, and the output is the saved video file and its metadata. Specifically, the server uploads the video file to Amazon S3 and adds the metadata.

[0461] Step 3:

[0462] The server divides the stored video into frames and extracts important frames. The input is the stored video file, and the output is the extracted important frames. Specifically, the server uses OpenCV to divide the video into frames and detect scenes with a lot of action, boss battles, and item acquisition scenes.

[0463] Step 4:

[0464] The server inputs the extracted important frames into a deep learning model to analyze the player's behavioral patterns. The inputs are the important frames and the deep learning model, and the output is the behavioral patterns resulting from the analysis. Specifically, the server inputs the important frames into a CNN model using TensorFlow to identify specific behavioral patterns.

[0465] Step 5:

[0466] The server generates strategy information based on the analysis results. The input is the analysis results of behavioral patterns, and the output is strategy information in the form of text, images, and videos. Specific operations include generating text and video clips on how to defeat a specific boss and when to use items.

[0467] Step 6:

[0468] The server reflects the generated walkthrough information on the walkthrough wiki site. The input is the generated walkthrough information, and the output is the updated walkthrough wiki page. Specifically, the server posts the new walkthrough information using the wiki site's API.

[0469] Step 7:

[0470] The server synchronizes the strategy information database with the chat bot database. The input is the strategy information database, and the output is the synchronized chat bot database. Specifically, the server uses the database replication function to perform the synchronization.

[0471] Step 8:

[0472] The server updates the chatbot's natural language processing model so that it can respond to user inquiries. The input is the natural language processing model and new data, and the output is the updated natural language processing model. Specifically, the server executes the process of updating the GPT-3 model.

[0473] Step 9:

[0474] A user accesses a chatbot using a device and asks for specific strategy information. The input is the user's text input, and the output is the chatbot's answer. Specifically, the user asks the chatbot, "Tell me how to beat the boss of the current stage."

[0475] Step 10:

[0476] The server obtains the user's progress from the game API and save data and provides optimal strategy information. The input is the user's progress data and play style data, and the output is optimized strategy information. Specifically, the server uses the PlayFab API to obtain and analyze the user's game progress. It then generates customized strategy information based on the user's equipment and current status and provides it via a chat bot.

[0477] (Application example 1)

[0478] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0479] Today's game players need to quickly obtain complex and diverse game strategy information to progress effectively in games. However, the wide variety of strategy information available on the Internet makes it difficult to find information optimized for each player's progress and playing style. Furthermore, existing strategy websites and video content provide general information and lack the means to provide specific strategies and methods tailored to each user. To solve this problem, a system is needed that quickly provides optimal strategy information based on the user's progress and playing style.

[0480] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0481] In this invention, the server includes means for collecting gameplay videos of players around the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on a user's progress and play style, means for notifying the user of the optimal strategy information through a smartphone application, and means for saving and sharing the user's play style and progress in a cloud-based database. This allows users to easily obtain individually optimized strategy information in real time and progress through the game effectively.

[0482] "Gameplay video" refers to video content that is recorded or streamed to show a player actually playing a game.

[0483] A "behavioral pattern" refers to a tendency for a game player to take a series of actions or behaviors in a particular situation.

[0484] "Strategy information" refers to information about strategies and methods for clearing or defeating difficult scenes or enemies in the game.

[0485] A "streaming platform API" is a mechanism for collecting and manipulating video data using a program interface provided by a streaming service.

[0486] A "natural language processing model" is an artificial intelligence technology that understands the natural language (sentences) entered by the user and generates an appropriate response.

[0487] A "chatbot" is an automated response system that provides information and answers questions through conversations with users.

[0488] A "smartphone application" is a software program that runs on a smartphone and provides specific functions or services.

[0489] A "cloud-based database" is a database system built on a remote server accessible via the Internet.

[0490] A system for realizing the present invention includes the following means.

[0491] A means of collecting gameplay videos from players around the world

[0492] The server uses the streaming platform's API to automatically collect gameplay videos from players around the world, allowing the server to collect a large number of gameplay videos related to a specific game.

[0493] Gameplay video analysis tool

[0494] The server breaks down the collected gameplay videos into frames and uses a deep learning model to analyze the player's behavioral patterns in the videos. This analysis allows it to extract effective tactics and optimal timing for specific scenes (e.g., boss battles, item acquisition, etc.). This analysis is performed using high-performance servers equipped with GPUs or cloud-based computing resources.

[0495] Strategy information generation means

[0496] The server generates game strategy information based on the analysis results. This strategy information is saved in the form of text, images, and video clips. For example, it may include specific tactical information such as "In boss battles, use water magic to avoid fire-element attacks."

[0497] Automatic website update methods

[0498] The generated strategy information is automatically updated by the server on a website that provides strategy information. This allows users to always access the latest strategy information. The website's backend uses a database management system (DBMS) to ensure smooth data updates.

[0499] Chatbot Means

[0500] The server also includes a chatbot that provides optimal strategy information in response to user inquiries. The chatbot incorporates a natural language processing model and generates appropriate answers to questions entered by the user. This allows users to obtain the strategy information they need in real time.

[0501] Smartphone application means

[0502] A dedicated smartphone application is provided so that users can quickly obtain strategy information via their smartphone. The application is designed to notify users of the most appropriate strategy information based on their progress and play style. For example, a notification such as "The fire-element weapon you are equipped with is effective in the next boss battle" can be provided in real time.

[0503] Cloud-based database solutions

[0504] Data about a user's play style and progress is stored in a cloud-based database, which provides consistent information across different devices and is highly scalable, allowing for efficient management of large amounts of data.

[0505] Examples of concrete examples and prompts

[0506] For example, in the case of the game "Fantasy Quest," the server collects gameplay videos from YouTube, analyzes them using a deep learning model, and generates a "strategy for defeating the Dragon King." When a user asks a smartphone application chatbot, "Tell me how to beat the Dragon King," the server instantly provides specific strategy information, such as "Use water magic to block fire attacks, then focus attacks on the head," based on the user's equipment and progress.

[0507] Prompt Sentence Examples

[0508] "Tell me some effective tactics for the boss battle in the next stage."

[0509] "How can I gain an advantage with my current equipment?"

[0510] "I want to know where to get a specific item."

[0511] By means of the above means, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0512] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0513] Step 1:

[0514] The server uses the streaming platform's API to collect gameplay videos from players around the world. The input is video metadata (game name, player name, URL, etc.), and the output is a video file stored in the server's local storage or cloud storage. Specifically, the server makes an API request, analyzes the response data, and downloads the video.

[0515] Step 2:

[0516] The server breaks down the collected gameplay videos into frames and extracts important frames. The input is the saved gameplay video file, and the output is a collection of frames containing important scenes. Specifically, it uses a video analysis algorithm to detect and extract scenes with a lot of action, boss battles, and item acquisition scenes.

[0517] Step 3:

[0518] The server uses a deep learning model to analyze the player's behavioral patterns in the video. The input is the extracted important frames, and the output is data about the player's behavioral patterns. Specifically, the deep learning model analyzes a sequence of frames and recognizes specific actions (e.g., the timing of using a specific technique).

[0519] Step 4:

[0520] The server generates strategy information based on the analysis results. The input is behavioral pattern data, and the output is strategy information in the form of text, images, and video clips. Specifically, the server uses a generative AI model to generate content describing optimal tactics and strategies based on specific behaviors.

[0521] Step 5:

[0522] The server automatically updates the generated strategy information to the website that provides the strategy information. The input is the generated strategy information, and the output is the updated web page. Specifically, the server inserts the new information into the website's database and regenerates the corresponding web page.

[0523] Step 6:

[0524] A user accesses a chatbot using a device (such as a smartphone or PC) and makes an inquiry to obtain specific strategy information. The input is a question (prompt) in natural language from the user, and the output is an answer from the chatbot. A specific example of how this works is when the user inputs, "Tell me how to beat the boss of the current stage."

[0525] Step 7:

[0526] The server generates optimal strategy information based on the user's progress and play style and provides it through the chatbot. The input is the user's progress, equipment data, and inquiry, and the output is a specific answer regarding the optimal strategy. Specifically, the server analyzes the progress data, generates appropriate strategy information, and provides it to the user via the chatbot.

[0527] Step 8:

[0528] It is designed to allow users to quickly obtain game strategy information through a smartphone application. The input is user account information and in-game progress data, and the output is notification messages within the application. Specifically, the application periodically sends requests to the server, receives the latest game strategy information, and notifies the user.

[0529] Step 9:

[0530] The server stores and shares data about users' play styles and progress in a cloud-based database. The input is the user's play data, and the output is a well-organized database stored in the cloud. Specifically, the server periodically collects play data and uploads and updates it to the cloud system.

[0531] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0532] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[0533] Data collection

[0534] The server collects game player gameplay videos from the internet. Using the streaming platform's API, it automatically downloads videos related to specific games and saves them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[0535] Data analysis

[0536] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. Next, a deep learning model is used to analyze the player's behavioral patterns. For example, it can extract attack patterns for specific boss battles and the optimal timing for using items.

[0537] Strategy information generation

[0538] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0539] Strategy wiki update

[0540] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[0541] Preparing the chatbot

[0542] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information. The server also updates the chatbot's natural language processing model, enabling it to respond to various user inquiries.

[0543] Emotion engine integration

[0544] The server integrates an emotion engine to acquire data for real-time user emotion recognition. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.).

[0545] Responding to user inquiries

[0546] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[0547] Emotionally responsive feedback

[0548] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0549] Specific examples

[0550] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[0551] When a user asks the chatbot, "Tell me how to beat Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking." In this way, the present invention can provide players with optimal strategy information, providing a system that ensures a comfortable gaming experience.

[0552] The processing flow will be explained below.

[0553] Step 1: Collect gameplay footage

[0554] The server uses the streaming platform's API to automatically download gameplay videos related to a specific game, and adds metadata such as the game name, player name, and playback time to the downloaded video.

[0555] Step 2: Save the video

[0556] The gameplay videos collected by the server are stored in cloud storage or local storage. By creating a folder structure and properly registering related metadata, subsequent analysis processing becomes easier.

[0557] Step 3: Preprocessing the video

[0558] The server breaks down the stored video into frames and extracts important scenes, such as boss battles and item acquisition scenes. The extracted frames are then used for analysis by a deep learning model.

[0559] Step 4: Analyze behavioral patterns

[0560] The server uses a deep learning model to analyze the player's behavior patterns within the extracted frames. For example, it can extract attack patterns in a specific boss battle or the timing of item use, and record this data as the player's behavior patterns.

[0561] Step 5: Update the database

[0562] The server registers the analysis results in a database, and if new effective tactics or patterns of behavior are found by comparing them with existing strategy information, they are added to the database.

[0563] Step 6: Generate strategy information

[0564] The server generates strategy information based on the information in the database. The strategy information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so water magic is effective against it," along with a video clip showing this information.

[0565] Step 7: Update the strategy wiki

[0566] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, ensuring that users always have access to the latest walkthrough information. Update history is also saved, making it possible to revert to previous versions if necessary.

[0567] Step 8: Chatbot Database Sync

[0568] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[0569] Step 9: Update the natural language processing model

[0570] The server updates the chatbot's natural language processing model to generate optimal responses to user queries. The trained model understands the user's question and provides the appropriate answer.

[0571] Step 10: Integrating the Emotion Engine

[0572] The server integrates an emotion engine to recognize the user's emotional state in real time, which analyzes the user's facial expressions, tone of voice, and text input to evaluate the user's emotional state.

[0573] Step 11: Accepting user inquiries

[0574] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[0575] Step 12: Evaluate your progress

[0576] The server obtains the user's progress from the game API and save data, determines the current stage of the game, and customizes the walkthrough information provided based on the user's progress.

[0577] Step 13: Emotionally responsive feedback

[0578] The server generates optimal strategy information and feedback based on the evaluation of the user's emotional state using an emotion engine. For example, if the user is feeling frustrated, the server will provide advice tailored to their emotions, such as "Water magic is effective. Stay calm and continue playing."

[0579] Through the above steps, the system of the present invention can provide the user with the strategy information they need quickly and accurately, and by providing feedback that takes into account the user's emotional state, it can provide a comfortable gaming experience.

[0580] Example 2

[0581] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0582] Conventional strategy information systems have the problem of only providing general strategy information without considering the player's play style or emotional state. This makes it difficult for players to obtain appropriate strategy information, which can reduce the enjoyment of gameplay. In addition, manually collecting and updating strategy information is cumbersome and lacks real-time performance.

[0583] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0584] In this invention, the server includes a means for collecting gameplay videos from the Internet, a means for extracting important scenes by breaking down the collected videos into frames, and a means for generating strategy information based on the extracted behavioral patterns, thereby enabling the prompt and appropriate provision of strategy information that takes into account the player's play style and emotional state.

[0585] A "gameplay video" is a video file that records the user playing a game.

[0586] The "Internet" is a communications network that connects computer networks around the world.

[0587] A "frame" is an individual still image that makes up a video.

[0588] "Important scenes" are particularly noteworthy moments during gameplay, such as boss battles and item acquisition.

[0589] A "behavior pattern" is a series of movements or actions that a player takes in the game.

[0590] "Strategy information" refers to specific advice and strategies to help you progress through the game to your advantage.

[0591] A "website" is a collection of informational pages available on the Internet.

[0592] "User emotional state" refers to emotions such as joy, anger, sadness, etc. that a player feels while playing a game.

[0593] A "chatbot" is a software application that automates interactions with users.

[0594] A "natural language processing model" refers to algorithms and techniques for understanding and analyzing human language.

[0595] A "streaming platform" is a service that distributes video and audio in real time over the Internet.

[0596] "API" stands for Application Program Interface, an interface for exchanging functions and data between different software applications.

[0597] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[0598] Data collection

[0599] The server uses the streaming platform's API to collect gameplay videos related to a specific game. For example, it uses the YouTube Data API to search for specific keywords and automatically download new videos. The downloaded videos are stored in cloud storage (e.g., Amazon S3 or Google Cloud Storage) and are assigned metadata (such as the game name, player name, and playback time).

[0600] Data analysis

[0601] The server breaks down the stored video into frames and extracts important scenes (such as boss battles and item acquisition scenes). Specifically, it uses video processing tools such as FFmpeg to convert the video to 30 frames per second, and then uses deep learning models (e.g., TensorFlow and PyTorch) to analyze the player's behavioral patterns. During this process, it extracts scenes with a lot of action, such as boss battles and item acquisition scenes.

[0602] Strategy information generation

[0603] The server generates strategy information based on the analysis results. A natural language generation model (e.g., GPT-3) is used to generate information in the form of text, images, and videos. The generated strategy information is stored in a database. For example, specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip illustrating this information are generated.

[0604] Strategy wiki update

[0605] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. Updates are performed periodically using Amazon Lambda or Cron, ensuring that users always have access to the latest information. Change history is also saved in a version control system (e.g., Git), allowing users to revert to previous versions as needed.

[0606] Preparing the chatbot

[0607] The server synchronizes the strategy information database with the chatbot's database. It uses natural language processing models such as Dialogflow to respond to user inquiries. This allows the chatbot to obtain the latest strategy information.

[0608] Emotion engine integration

[0609] The server integrates an emotion engine and collects data to recognize the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Specifically, it uses Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[0610] Responding to user inquiries

[0611] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[0612] Emotionally responsive feedback

[0613] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0614] Specific examples

[0615] For example, in the game "Fantasy Quest," a server collects gameplay footage from a streaming platform and extracts key scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on a strategy wiki and is instantly available to chatbots.

[0616] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking."

[0617] Example prompt: "Tell me how to defeat the Dragon King. If the emotional state is Frustrated, please also include some advice to calm the user down."

[0618] In this way, the present invention provides a system that provides players with optimal strategy information and realizes a comfortable gaming experience.

[0619] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0620] Step 1:

[0621] Gameplay video collection

[0622] The server uses the API of the streaming platform to collect gameplay videos related to a specific game. Search keywords and the API key of the streaming platform are given as input. The server downloads these videos from the Internet and stores them in cloud storage. The output is the collected video files and their metadata. Specifically, the server periodically calls the API to obtain a list of new videos and downloads each video sequentially.

[0623] Step 2:

[0624] Video frame decomposition

[0625] The server uses a video processing tool (e.g., FFmpeg) to break down the collected video into frames. A video file is given as input. The server breaks down the video into 30 frames per second and saves each frame in image format. As output, frame image files are obtained. Specifically, the server executes FFmpeg commands to convert the video into image files at the specified frame rate.

[0626] Step 3:

[0627] Extracting important scenes

[0628] The server analyzes each frame using a deep learning model (e.g., TensorFlow or PyTorch) and extracts important scenes. The decomposed frame images are given as input. The server uses an image recognition model to detect particularly important scenes, such as boss battles and item acquisition scenes. The output is a list of important frames. Specifically, the server inputs each frame image into the model and evaluates its importance based on the identification results of each frame.

[0629] Step 4:

[0630] Behavioral pattern analysis

[0631] The server analyzes the player's behavioral patterns based on frames of important scenes. As input, it receives important frame images and corresponding video sequences. The server uses a behavioral analysis model to analyze the player's behavioral patterns, such as attack patterns and item usage timing. As output, it obtains behavioral pattern data. Specifically, the server inputs the video sequences into the model and extracts behavioral patterns.

[0632] Step 5:

[0633] Generation of strategy information

[0634] The server generates walkthrough information based on the results of the behavioral pattern analysis. Behavioral pattern data is provided as input. The server uses a natural language generation model (e.g., GPT-3) to create walkthrough information in text format, and also generates images and videos as needed. The generated walkthrough information is obtained as output. Specifically, the server inputs the analysis results as prompts into the generation model to obtain the walkthrough information.

[0635] Step 6:

[0636] Automatic update of strategy information

[0637] The server runs a script to automatically update the walkthrough information on the website. The generated walkthrough information is given as input. The server uses a version control system (e.g., Git) to update the information on the walkthrough wiki site. The output is the updated website. Specifically, the server performs Git commit and push operations to update the website.

[0638] Step 7:

[0639] Chatbot database synchronization

[0640] The server synchronizes the strategy information database with the chatbot's database. The latest strategy information is provided as input. The server updates the natural language processing model (e.g., Dialogflow) to make the latest strategy information available to the chatbot. The output is an updated chatbot. Specifically, the server calls the Dialogflow API to update the dataset.

[0641] Step 8:

[0642] Emotion engine integration

[0643] The server integrates emotion engines to analyze the user's emotional state. The user's facial expressions, tone of voice, and text are given as input. The server evaluates the emotional state using an emotion analysis model (e.g., Microsoft Azure's Face API or IBM Watson's Tone Analyzer). The output is the user's emotional state data. Specifically, the server calls various emotion analysis APIs in sequence and obtains the integrated evaluation results.

[0644] Step 9:

[0645] Responding to user inquiries

[0646] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. The user's inquiry is given to the chatbot as input. The server takes into account the user's progress and emotional state and provides the most appropriate strategy information. The output is an answer from the chatbot. Specifically, the server has the chatbot generate an appropriate answer based on the user's progress data and emotional state data.

[0647] Step 10:

[0648] Emotionally responsive feedback

[0649] The server provides feedback based on the user's emotional state. The user's emotional state data is given as input. The server generates an interface and advice that is effective for the specific emotional state based on the emotional state. The output is feedback appropriate for the user. In concrete terms, the server generates specific advice and messages for the user based on the evaluation results of the emotion engine and provides them through the chatbot.

[0650] (Application example 2)

[0651] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0652] In recent years, online games have become popular with many players, resulting in increasingly complex game mechanisms and stages that are difficult to complete. Consequently, many players are seeking strategy guides and tend to search the Internet for them. However, these guides are not always suited to the player's progress or play style, requiring the player to spend a lot of time gathering and applying the information. Furthermore, the lack of feedback based on the player's emotional state can lead to frustration. Therefore, there is a need for a system that can quickly provide optimal strategy guides based on the player's progress, play style, and emotional state.

[0653] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting gameplay videos of players from all over the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on the user's progress and play style, an emotion recognition engine for recognizing the user's emotional state, and means for providing appropriate feedback based on the user's emotional state. This makes it possible to quickly and effectively provide optimal strategy information that takes into account the player's progress, play style, and emotional state.

[0654] "Gameplay videos of players from around the world" refers to video recordings of games being played by multiple players from around the world, distributed via the Internet.

[0655] "Means of collection" refers to devices or systems, including hardware and software, for downloading specific videos from the Internet and storing them in cloud storage or local storage.

[0656] "Means of analyzing and extracting player behavior patterns" refers to a method of breaking down saved video into frames, identifying specific scenes and player behavior using deep learning models, and extracting those patterns.

[0657] "Means for generating strategy information" refers to a system that generates optimal strategies for specific tasks or boss battles in the game in the form of text, images, videos, etc., based on extracted player behavior patterns.

[0658] "Means for automatically updating to a website" refers to software and scripts that automatically upload the generated cheat information to an existing website, thereby providing users with the latest information at all times.

[0659] "Chatbot means" refers to a program and interface that uses natural language processing to automatically respond to inquiries from users and provide appropriate strategy information.

[0660] An "emotion recognition engine" refers to algorithms and software that analyze a user's facial expressions, tone of voice, text input, etc., and use the results to assess the user's emotional state.

[0661] "Means for providing feedback" refers to a program and interface for providing appropriate information or advice in response to the user's emotional state as assessed by the emotion recognition engine.

[0662] A specific embodiment of the present invention will be described below. This invention combines a system that automatically generates strategy information optimized for the play style of a game player and enables the player to quickly obtain the necessary strategy information through a chatbot with an emotion engine that recognizes the user's emotions.

[0663] Data collection

[0664] The server collects gameplay videos via the Internet. Specifically, it uses the streaming platform's API to automatically download videos related to specific games and save them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[0665] Data analysis

[0666] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. It then uses a deep learning model to analyze the player's behavioral patterns, extracting, for example, attack patterns for specific boss battles and optimal timing for using items.

[0667] Strategy information generation

[0668] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0669] Strategy wiki update

[0670] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, so users can always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[0671] Response to inquiries via chatbots

[0672] Using a device (such as a smartphone or PC), the user accesses the chatbot and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, assesses their current stage, and provides them with the most appropriate strategy information.

[0673] Emotion engine integration and feedback provision

[0674] The server integrates an emotion engine to acquire data for recognizing the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Based on the evaluation results of the emotion engine, the system provides an appropriate interface and feedback for a specific emotional state. For example, if a user is feeling frustrated with a game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0675] Example

[0676] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[0677] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy based on the user's progress, equipment, and emotional state.

[0678] Adding concrete examples and prompt sentence examples

[0679] Specifically, when a user wearing smart glasses is playing a game, the application uses the smart glasses' camera to capture the user's facial expressions in real time, analyzes their emotional state (e.g., "anger"), and then inputs prompt sentences like the following into the generative AI model:

[0680] Example prompt sentence:

[0681] I'm playing the game "Fantasy Quest" and I'm having trouble with the boss battle against the Dragon King. Can you tell me how to beat him? The user is currently in an "Anger" state.

[0682] This allows the generative AI model to provide specific strategy information that takes into account the user's emotional state, such as "Water magic is effective in defeating the Dragon King. Stay calm and keep attacking."

[0683] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0684] Step 1:

[0685] The server collects gameplay videos via the internet using the streaming platform's API. At this time, it obtains metadata (game name, player name, play time, etc.) along with the video data obtained from the API and stores them in cloud storage or local storage. The input is an API request, and the output is a video file and metadata.

[0686] Step 2:

[0687] The server breaks down the saved gameplay video into frames and extracts important frames. The input is the saved video file, and the output is a set of extracted important frames. Specifically, it uses a deep learning model to detect scenes with a lot of action, such as boss battles and item acquisition scenes, and saves these as frames.

[0688] Step 3:

[0689] The server analyzes the player's behavioral patterns based on the extracted important frames. This requires frame data as input and generates behavioral pattern data as output. A deep learning model is used for this analysis, and data such as attack patterns for specific boss battles and the optimal timing for using items can be extracted.

[0690] Step 4:

[0691] The server generates strategy information based on the analysis results. This strategy information is generated in the form of text, images, and videos. The input is behavioral pattern data, and the output is specific strategy information. For example, a text file containing information such as "The Dragon King's weak spot is its head, so use water magic to avoid its fire attacks" may be created.

[0692] Step 5:

[0693] The server automatically updates the generated walkthrough information on the walkthrough wiki site. Here, the walkthrough information data is input and the website is updated as output. This automatic update script runs, and the walkthrough information is always kept up to date.

[0694] Step 6:

[0695] The user accesses the chatbot using their device and asks for specific strategy information. At this time, the user's progress is obtained from the game API and save data, and the stage at which the user is is evaluated. The input is the user's query and progress data, and the output is the most appropriate strategy information. For example, if a user asks, "Tell me how to beat Dragon King," the server evaluates the user's progress and provides the appropriate strategy information through the chatbot.

[0696] Step 7:

[0697] The server integrates an emotion engine to capture data for real-time user emotion recognition. The input is real-time data from the camera and microphone, and the output is an evaluation of the user's emotional state. This emotion recognition is achieved by analyzing facial expressions, tone of voice, and text input.

[0698] Step 8:

[0699] The server provides appropriate feedback for a specific emotional state based on the evaluation results of the emotion engine. Emotional state data is input and feedback is generated as output. For example, if a user is feeling frustrated, the chatbot will provide advice such as, "Why don't you take a short break here?"

[0700] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0701] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0702] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0703] [Third embodiment]

[0704] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0705] 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.

[0706] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[0707] 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.

[0708] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0709] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0710] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0711] 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.

[0712] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0713] 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.

[0714] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0715] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0716] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the strategy information they need through a chatbot. Specific embodiments for realizing this system will be described below.

[0717] Data collection

[0718] The server collects game player gameplay videos from the internet. Specifically, it automatically downloads videos related to the game name using, for example, a streaming platform's API. The collected videos are then stored in cloud storage or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[0719] Data analysis

[0720] The server breaks down the stored video into frames and extracts key frames, including high-action scenes, boss battles, and item acquisition scenes. The server then uses a deep learning model to analyze the player's behavioral patterns in the video. For example, it automatically extracts effective tactics for a particular boss battle or the optimal timing for using items.

[0721] Strategy information generation

[0722] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0723] Strategy wiki update

[0724] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to revert to previous versions at any time.

[0725] Preparing the chatbot

[0726] The server synchronizes the strategy information database with the chat bot's database, allowing the chat bot to obtain the latest strategy information. Furthermore, the server updates the chat bot's natural language processing model so that it can respond to user inquiries.

[0727] Responding to user inquiries

[0728] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates the stage the user is at. The server then generates optimal strategy information based on the user's progress and play style, and provides it through the chat bot. For example, it provides specific advice such as, "Your equipment has a fire attribute, so using water magic would be effective."

[0729] Specific examples

[0730] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[0731] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0732] The processing flow will be explained below.

[0733] Step 1: Collect gameplay footage

[0734] The server collects gameplay videos from the internet, for example, by using a streaming platform's API to automatically download videos related to a specific game. The downloaded videos are then stored along with metadata such as the game name, player name, and play time.

[0735] Step 2: Save the video

[0736] The server saves the collected videos to cloud storage or local storage. When saving, it organizes the folder structure and registers appropriate metadata to make analysis easier.

[0737] Step 3: Preprocessing the video

[0738] The server breaks down the stored video into frames. Important scenes (e.g., boss battles or item acquisition scenes) are extracted through frame analysis. The extracted frames are used in subsequent analysis steps.

[0739] Step 4: Analyze behavioral patterns

[0740] The server uses a deep learning model to analyze the player's behavior in the video. This analysis evaluates the reasons why the player chose a particular strategy and its effectiveness. For example, it can extract which attacks were used most frequently in a particular boss battle, and which items were used when.

[0741] Step 5: Update the database

[0742] The server registers the analysis results in a database and compares them with existing strategy information. If any new effective tactics or patterns of behavior are discovered, they are added and updated as new data.

[0743] Step 6: Generate strategy information

[0744] The server generates strategy information based on the newly extracted behavioral patterns. The generated information is saved in the form of text, images, and videos. For example, it could generate information such as "The Dragon King's weak point is its head, so using water magic is effective," along with a video clip showing the specific tactics.

[0745] Step 7: Update the strategy wiki

[0746] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest walkthrough information. Update history is also saved, allowing users to return to previous versions if necessary.

[0747] Step 8: Chatbot Database Sync

[0748] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[0749] Step 9: Update the natural language processing model

[0750] The server updates the chatbot's natural language processing model to accommodate new user inquiry patterns, for example, training it to generate appropriate responses to questions like, "How do I beat boss XX?"

[0751] Step 10: Accepting user inquiries

[0752] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[0753] Step 11: Evaluate your progress

[0754] The server obtains the user's progress from the game's API and save data, and evaluates the progress. This determines which stage the user is currently in, which boss they are challenging, etc.

[0755] Step 12: Provide optimal information

[0756] The server generates optimal strategy information based on the user's progress and play style and provides it through a chatbot. For example, it can provide specific advice such as "Instant Strategy: Your equipment is fire-element, so using water magic would be effective."

[0757] Through the above steps, the system of the present invention can provide players with optimal strategy information and support an efficient gaming experience.

[0758] Example 1

[0759] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0760] Conventional game strategy information systems have had difficulty quickly providing optimal strategy information based on the player's behavioral patterns and progress. In particular, providing the timely and detailed strategy information that players desire requires processing of massive amounts of data and advanced analysis, and conventional methods have had limitations in meeting this challenge.

[0761] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0762] In this invention, the server includes means for collecting gameplay videos of players from the Internet, means for breaking down the collected videos into frames and extracting scenes with a lot of action or important frames, and means for analyzing the extracted frames using a deep learning model to identify behavioral patterns, thereby making it possible to provide optimal strategy information based on the player's behavioral patterns and progress.

[0763] The "Internet" is a global communications network that connects computers and networks around the world.

[0764] "Player" refers to a user who actually operates and plays a computer game.

[0765] "Gameplay video" is recorded or streamed footage of a player interacting with a game.

[0766] A "frame" is each still image in a video, and a video is formed by playing these images consecutively.

[0767] A "deep learning model" is an algorithm that uses a multi-layer neural network to automatically learn the characteristics of data and perform analysis and prediction.

[0768] A "behavioral pattern" refers to a series of actions or choices that a player tends to make in a game.

[0769] "Way-to-win information" is information that includes advice, strategies, and hints for efficiently clearing a game.

[0770] A "website" is a collection of information that is publicly available on the Internet and accessible at a particular URL.

[0771] A "database" is a system for efficiently managing and searching large amounts of data.

[0772] A "chatbot" is a program that automatically converses with users through text.

[0773] A "game API" is a piece of programming that provides an interface for accessing game data and functionality.

[0774] "Save data" is data that saves the game progress, allowing players to resume from where they left off.

[0775] A "terminal" is a device that is directly operated by a user, and typically refers to a smartphone or personal computer.

[0776] A "natural language processing model" is a machine learning model for understanding and processing natural human language.

[0777] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the necessary strategy information through a chatbot. A specific embodiment of this system will be described.

[0778] Data collection

[0779] The server collects gameplay videos of players via the Internet. Specifically, it uses the streaming platform's API (e.g., YouTube Data API) to automatically download videos related to the specified game name. The collected videos are then stored in cloud storage (e.g., Amazon S3) or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[0780] Video frame analysis

[0781] The server breaks down the stored video into frames and extracts scenes with a lot of action and important frames. Specifically, it uses libraries such as OpenCV to divide the video into frames and detects scenes with a lot of action, boss battles, item acquisition scenes, etc. These important frames are then stored in a separate database and assigned corresponding metadata.

[0782] Behavioral pattern analysis

[0783] The server uses a deep learning model (e.g., a CNN model using TensorFlow) to analyze the extracted key frames and identify the player's behavioral patterns. The analysis includes effective tactics for specific boss battles and the optimal timing for using items. The results of this analysis are stored in a strategy information database.

[0784] Strategy information generation

[0785] Based on the results of the behavioral pattern analysis, the server generates strategy information in the form of text, images, and videos. For example, it generates specific information such as "A certain boss's weak spot is its head, so you should use a specific item to avoid attacks," along with a video clip explaining this.

[0786] Strategy wiki update

[0787] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to return to previous versions at any time.

[0788] Preparing the chatbot

[0789] The server synchronizes the strategy information database with the chatbot's database so that the latest strategy information can be obtained from the chatbot. Furthermore, the server updates the chatbot's natural language processing model (e.g., GPT-3) so that it can respond appropriately to user inquiries.

[0790] Responding to user inquiries

[0791] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API (such as the PlayFab API) or save data, and evaluates the user's current stage. The server then generates optimal strategy information that takes into account the user's progress and equipment, and provides it via the chat bot.

[0792] Specific examples

[0793] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[0794] In this way, the present invention realizes a system that allows users to quickly and accurately acquire complex game strategy information and provides an efficient gaming experience.

[0795] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0796] Step 1:

[0797] The server uses the streaming platform's API to collect gameplay videos. In this case, the server searches for videos related to a specific game name and downloads videos that match the criteria. The input is the specific game name and related keywords, and the output is the downloaded video file. Specifically, the server uses the YouTube Data API to search for related videos for "Fantasy Quest" and downloads the corresponding videos.

[0798] Step 2:

[0799] The server saves the downloaded video file in cloud storage or local storage. When saving, metadata (game name, player name, playback time, etc.) is added to the video. The input is the video file and associated metadata, and the output is the saved video file and its metadata. Specifically, the server uploads the video file to Amazon S3 and adds the metadata.

[0800] Step 3:

[0801] The server divides the stored video into frames and extracts important frames. The input is the stored video file, and the output is the extracted important frames. Specifically, the server uses OpenCV to divide the video into frames and detect scenes with a lot of action, boss battles, and item acquisition scenes.

[0802] Step 4:

[0803] The server inputs the extracted important frames into a deep learning model to analyze the player's behavioral patterns. The inputs are the important frames and the deep learning model, and the output is the behavioral patterns resulting from the analysis. Specifically, the server inputs the important frames into a CNN model using TensorFlow to identify specific behavioral patterns.

[0804] Step 5:

[0805] The server generates strategy information based on the analysis results. The input is the analysis results of behavioral patterns, and the output is strategy information in the form of text, images, and videos. Specific operations include generating text and video clips on how to defeat a specific boss and when to use items.

[0806] Step 6:

[0807] The server reflects the generated walkthrough information on the walkthrough wiki site. The input is the generated walkthrough information, and the output is the updated walkthrough wiki page. Specifically, the server posts the new walkthrough information using the wiki site's API.

[0808] Step 7:

[0809] The server synchronizes the strategy information database with the chat bot database. The input is the strategy information database, and the output is the synchronized chat bot database. Specifically, the server uses the database replication function to perform the synchronization.

[0810] Step 8:

[0811] The server updates the chatbot's natural language processing model so that it can respond to user inquiries. The input is the natural language processing model and new data, and the output is the updated natural language processing model. Specifically, the server executes the process of updating the GPT-3 model.

[0812] Step 9:

[0813] A user accesses a chatbot using a device and asks for specific strategy information. The input is the user's text input, and the output is the chatbot's answer. Specifically, the user asks the chatbot, "Tell me how to beat the boss of the current stage."

[0814] Step 10:

[0815] The server obtains the user's progress from the game API and save data and provides optimal strategy information. The input is the user's progress data and play style data, and the output is optimized strategy information. Specifically, the server uses the PlayFab API to obtain and analyze the user's game progress. It then generates customized strategy information based on the user's equipment and current status and provides it via a chat bot.

[0816] (Application example 1)

[0817] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0818] Today's game players need to quickly obtain complex and diverse game strategy information to progress effectively in games. However, the wide variety of strategy information available on the Internet makes it difficult to find information optimized for each player's progress and playing style. Furthermore, existing strategy websites and video content provide general information and lack the means to provide specific strategies and methods tailored to each user. To solve this problem, a system is needed that quickly provides optimal strategy information based on the user's progress and playing style.

[0819] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0820] In this invention, the server includes means for collecting gameplay videos of players around the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on a user's progress and play style, means for notifying the user of the optimal strategy information through a smartphone application, and means for saving and sharing the user's play style and progress in a cloud-based database. This allows users to easily obtain individually optimized strategy information in real time and progress through the game effectively.

[0821] "Gameplay video" refers to video content that is recorded or streamed to show a player actually playing a game.

[0822] A "behavioral pattern" refers to a tendency for a game player to take a series of actions or behaviors in a particular situation.

[0823] "Strategy information" refers to information about strategies and methods for clearing or defeating difficult scenes or enemies in the game.

[0824] A "streaming platform API" is a mechanism for collecting and manipulating video data using a program interface provided by a streaming service.

[0825] A "natural language processing model" is an artificial intelligence technology that understands the natural language (sentences) entered by the user and generates an appropriate response.

[0826] A "chatbot" is an automated response system that provides information and answers questions through conversations with users.

[0827] A "smartphone application" is a software program that runs on a smartphone and provides specific functions or services.

[0828] A "cloud-based database" is a database system built on a remote server accessible via the Internet.

[0829] A system for realizing the present invention includes the following means.

[0830] A means of collecting gameplay videos from players around the world

[0831] The server uses the streaming platform's API to automatically collect gameplay videos from players around the world, allowing the server to collect a large number of gameplay videos related to a specific game.

[0832] Gameplay video analysis tool

[0833] The server breaks down the collected gameplay videos into frames and uses a deep learning model to analyze the player's behavioral patterns in the videos. This analysis allows it to extract effective tactics and optimal timing for specific scenes (e.g., boss battles, item acquisition, etc.). This analysis is performed using high-performance servers equipped with GPUs or cloud-based computing resources.

[0834] Strategy information generation means

[0835] The server generates game strategy information based on the analysis results. This strategy information is saved in the form of text, images, and video clips. For example, it may include specific tactical information such as "In boss battles, use water magic to avoid fire-element attacks."

[0836] Automatic website update methods

[0837] The generated strategy information is automatically updated by the server on a website that provides strategy information. This allows users to always access the latest strategy information. The website's backend uses a database management system (DBMS) to ensure smooth data updates.

[0838] Chatbot Means

[0839] Furthermore, the server is equipped with a chatbot that provides optimal strategy information in response to user inquiries. The chatbot incorporates a natural language processing model and generates appropriate answers to questions entered by the user. This allows users to obtain the strategy information they need in real time.

[0840] Smartphone application means

[0841] A dedicated smartphone application is provided so that users can quickly obtain strategy information via their smartphone. The application is designed to notify users of the most appropriate strategy information based on their progress and play style. For example, a notification such as "The fire-element weapon you are equipped with is effective in the next boss battle" can be provided in real time.

[0842] Cloud-based database solutions

[0843] Data about a user's play style and progress is stored in a cloud-based database, which provides consistent information across different devices. The database is highly scalable and can efficiently manage large amounts of data.

[0844] Examples of concrete examples and prompts

[0845] For example, in the case of the game "Fantasy Quest," the server collects gameplay videos from YouTube, analyzes them using a deep learning model, and generates a "strategy for defeating the Dragon King." When a user asks a smartphone application chatbot, "Tell me how to beat the Dragon King," the server instantly provides specific strategy information, such as "Use water magic to block fire attacks, then focus attacks on the head," based on the user's equipment and progress.

[0846] Prompt Sentence Examples

[0847] "Tell me some effective tactics for the boss battle in the next stage."

[0848] "How can I gain an advantage with my current equipment?"

[0849] "I want to know where to get a specific item."

[0850] By means of the above means, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[0851] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0852] Step 1:

[0853] The server uses the streaming platform's API to collect gameplay videos from players around the world. The input is video metadata (game name, player name, URL, etc.), and the output is a video file stored in the server's local storage or cloud storage. Specifically, the server makes an API request, analyzes the response data, and downloads the video.

[0854] Step 2:

[0855] The server breaks down the collected gameplay videos into frames and extracts important frames. The input is the saved gameplay video file, and the output is a collection of frames containing important scenes. Specifically, it uses a video analysis algorithm to detect and extract scenes with a lot of action, boss battles, and item acquisition scenes.

[0856] Step 3:

[0857] The server uses a deep learning model to analyze the player's behavioral patterns in the video. The input is the extracted important frames, and the output is data about the player's behavioral patterns. Specifically, the deep learning model analyzes a sequence of frames and recognizes specific actions (e.g., the timing of using a specific technique).

[0858] Step 4:

[0859] The server generates strategy information based on the analysis results. The input is behavioral pattern data, and the output is strategy information in the form of text, images, and video clips. Specifically, the server uses a generative AI model to generate content describing optimal tactics and strategies based on specific behaviors.

[0860] Step 5:

[0861] The server automatically updates the generated strategy information to the website that provides the strategy information. The input is the generated strategy information, and the output is the updated web page. Specifically, the server inserts the new information into the website's database and regenerates the corresponding web page.

[0862] Step 6:

[0863] A user accesses a chatbot using a device (such as a smartphone or PC) and makes an inquiry to obtain specific strategy information. The input is a question (prompt) in natural language from the user, and the output is an answer from the chatbot. A specific example of how this works is when the user inputs, "Tell me how to beat the boss of the current stage."

[0864] Step 7:

[0865] The server generates optimal strategy information based on the user's progress and play style and provides it through the chatbot. The input is the user's progress, equipment data, and inquiry, and the output is a specific answer regarding the optimal strategy. Specifically, the server analyzes the progress data, generates appropriate strategy information, and provides it to the user via the chatbot.

[0866] Step 8:

[0867] It is designed to allow users to quickly obtain game strategy information through a smartphone application. The input is user account information and in-game progress data, and the output is notification messages within the application. Specifically, the application periodically sends requests to the server, receives the latest game strategy information, and notifies the user.

[0868] Step 9:

[0869] The server stores and shares data about users' play styles and progress in a cloud-based database. The input is the user's play data, and the output is a well-organized database stored in the cloud. Specifically, the server periodically collects play data and uploads and updates it to the cloud system.

[0870] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0871] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[0872] Data collection

[0873] The server collects game player gameplay videos from the internet. Using the streaming platform's API, it automatically downloads videos related to specific games and saves them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[0874] Data analysis

[0875] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. Next, a deep learning model is used to analyze the player's behavioral patterns. For example, it can extract attack patterns for specific boss battles and the optimal timing for using items.

[0876] Strategy information generation

[0877] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[0878] Strategy wiki update

[0879] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[0880] Preparing the chatbot

[0881] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information. The server also updates the chatbot's natural language processing model, enabling it to respond to various user inquiries.

[0882] Emotion engine integration

[0883] The server integrates an emotion engine to acquire data for real-time user emotion recognition. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.).

[0884] Responding to user inquiries

[0885] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[0886] Emotionally responsive feedback

[0887] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0888] Specific examples

[0889] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[0890] When a user asks the chatbot, "Tell me how to beat Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking." In this way, the present invention can provide players with optimal strategy information, providing a system that ensures a comfortable gaming experience.

[0891] The processing flow will be explained below.

[0892] Step 1: Collect gameplay footage

[0893] The server uses the streaming platform's API to automatically download gameplay videos related to a specific game, and adds metadata such as the game name, player name, and playback time to the downloaded video.

[0894] Step 2: Save the video

[0895] The gameplay videos collected by the server are stored in cloud storage or local storage. By creating a folder structure and properly registering related metadata, subsequent analysis processing becomes easier.

[0896] Step 3: Preprocessing the video

[0897] The server breaks down the stored video into frames and extracts important scenes, such as boss battles and item acquisition scenes. The extracted frames are then used for analysis by a deep learning model.

[0898] Step 4: Analyze behavioral patterns

[0899] The server uses a deep learning model to analyze the player's behavior patterns within the extracted frames. For example, it can extract attack patterns in a specific boss battle or the timing of item use, and record this data as the player's behavior patterns.

[0900] Step 5: Update the database

[0901] The server registers the analysis results in a database, and if new effective tactics or patterns of behavior are found by comparing them with existing strategy information, they are added to the database.

[0902] Step 6: Generate strategy information

[0903] The server generates strategy information based on the information in the database. The strategy information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so water magic is effective against it," along with a video clip showing this information.

[0904] Step 7: Update the strategy wiki

[0905] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, ensuring that users always have access to the latest walkthrough information. Update history is also saved, making it possible to revert to previous versions if necessary.

[0906] Step 8: Chatbot Database Sync

[0907] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[0908] Step 9: Update the natural language processing model

[0909] The server updates the chatbot's natural language processing model to generate optimal responses to user queries. The trained model understands the user's question and provides the appropriate answer.

[0910] Step 10: Integrating the Emotion Engine

[0911] The server integrates an emotion engine to recognize the user's emotional state in real time, which analyzes the user's facial expressions, tone of voice, and text input to evaluate the user's emotional state.

[0912] Step 11: Accepting user inquiries

[0913] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[0914] Step 12: Evaluate your progress

[0915] The server obtains the user's progress from the game API and save data, determines the current stage of the game, and customizes the walkthrough information provided based on the user's progress.

[0916] Step 13: Emotionally responsive feedback

[0917] The server generates optimal strategy information and feedback based on the evaluation of the user's emotional state using an emotion engine. For example, if the user is feeling frustrated, the server will provide advice tailored to their emotions, such as "Water magic is effective. Stay calm and continue playing."

[0918] Through the above steps, the system of the present invention can provide the user with the strategy information they need quickly and accurately, and by providing feedback that takes into account the user's emotional state, it can provide a comfortable gaming experience.

[0919] Example 2

[0920] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0921] Conventional strategy information systems have the problem of only providing general strategy information without considering the player's play style or emotional state. This makes it difficult for players to obtain appropriate strategy information, which can reduce the enjoyment of gameplay. In addition, manually collecting and updating strategy information is cumbersome and lacks real-time performance.

[0922] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0923] In this invention, the server includes a means for collecting gameplay videos from the Internet, a means for extracting important scenes by breaking down the collected videos into frames, and a means for generating strategy information based on the extracted behavioral patterns, thereby enabling the prompt and appropriate provision of strategy information that takes into account the player's play style and emotional state.

[0924] A "gameplay video" is a video file that records the user playing a game.

[0925] The "Internet" is a communications network that connects computer networks around the world.

[0926] A "frame" is an individual still image that makes up a video.

[0927] "Important scenes" are particularly noteworthy moments during gameplay, such as boss battles and item acquisition.

[0928] A "behavior pattern" is a series of movements or actions that a player takes in the game.

[0929] "Strategy information" refers to specific advice and strategies to help you progress through the game to your advantage.

[0930] A "website" is a collection of informational pages available on the Internet.

[0931] "User emotional state" refers to emotions such as joy, anger, sadness, etc. that a player feels while playing a game.

[0932] A "chatbot" is a software application that automates interactions with users.

[0933] A "natural language processing model" refers to algorithms and techniques for understanding and analyzing human language.

[0934] A "streaming platform" is a service that distributes video and audio in real time over the Internet.

[0935] "API" stands for Application Program Interface, an interface for exchanging functions and data between different software applications.

[0936] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[0937] Data collection

[0938] The server uses the streaming platform's API to collect gameplay videos related to a specific game. For example, it uses the YouTube Data API to search for specific keywords and automatically download new videos. The downloaded videos are stored in cloud storage (e.g., Amazon S3 or Google Cloud Storage) and are assigned metadata (such as the game name, player name, and playback time).

[0939] Data analysis

[0940] The server breaks down the stored video into frames and extracts important scenes (such as boss battles and item acquisition scenes). Specifically, it uses video processing tools such as FFmpeg to convert the video to 30 frames per second, and then uses deep learning models (e.g., TensorFlow and PyTorch) to analyze the player's behavioral patterns. During this process, it extracts scenes with a lot of action, such as boss battles and item acquisition scenes.

[0941] Strategy information generation

[0942] The server generates strategy information based on the analysis results. A natural language generation model (e.g., GPT-3) is used to generate information in the form of text, images, and videos. The generated strategy information is stored in a database. For example, specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip illustrating this information are generated.

[0943] Strategy wiki update

[0944] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. Updates are performed periodically using Amazon Lambda or Cron, ensuring that users always have access to the latest information. Change history is also saved in a version control system (e.g., Git), allowing users to revert to previous versions as needed.

[0945] Preparing the chatbot

[0946] The server synchronizes the strategy information database with the chatbot's database. It uses natural language processing models such as Dialogflow to respond to user inquiries. This allows the chatbot to obtain the latest strategy information.

[0947] Emotion engine integration

[0948] The server integrates an emotion engine and collects data to recognize the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Specifically, it uses Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[0949] Responding to user inquiries

[0950] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[0951] Emotionally responsive feedback

[0952] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[0953] Specific examples

[0954] For example, in the game "Fantasy Quest," a server collects gameplay footage from a streaming platform and extracts key scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on a strategy wiki and is instantly available to chatbots.

[0955] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking."

[0956] Example prompt: "Tell me how to defeat the Dragon King. If the emotional state is Frustrated, please also include some advice to calm the user down."

[0957] In this way, the present invention provides a system that provides players with optimal strategy information and realizes a comfortable gaming experience.

[0958] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] Gameplay video collection

[0961] The server uses the API of the streaming platform to collect gameplay videos related to a specific game. Search keywords and the API key of the streaming platform are given as input. The server downloads these videos from the Internet and stores them in cloud storage. The output is the collected video files and their metadata. Specifically, the server periodically calls the API to obtain a list of new videos and downloads each video sequentially.

[0962] Step 2:

[0963] Video frame decomposition

[0964] The server uses a video processing tool (e.g., FFmpeg) to break down the collected video into frames. A video file is given as input. The server breaks down the video into 30 frames per second and saves each frame in image format. As output, frame image files are obtained. Specifically, the server executes FFmpeg commands to convert the video into image files at the specified frame rate.

[0965] Step 3:

[0966] Extracting important scenes

[0967] The server analyzes each frame using a deep learning model (e.g., TensorFlow or PyTorch) and extracts important scenes. The decomposed frame images are given as input. The server uses an image recognition model to detect particularly important scenes, such as boss battles and item acquisition scenes. The output is a list of important frames. Specifically, the server inputs each frame image into the model and evaluates its importance based on the identification results of each frame.

[0968] Step 4:

[0969] Behavioral pattern analysis

[0970] The server analyzes the player's behavioral patterns based on frames of important scenes. As input, it receives important frame images and corresponding video sequences. The server uses a behavioral analysis model to analyze the player's behavioral patterns, such as attack patterns and item usage timing. As output, it obtains behavioral pattern data. Specifically, the server inputs the video sequences into the model and extracts behavioral patterns.

[0971] Step 5:

[0972] Generation of strategy information

[0973] The server generates walkthrough information based on the results of the behavioral pattern analysis. Behavioral pattern data is provided as input. The server uses a natural language generation model (e.g., GPT-3) to create walkthrough information in text format, and also generates images and videos as needed. The generated walkthrough information is obtained as output. Specifically, the server inputs the analysis results as prompts into the generation model to obtain the walkthrough information.

[0974] Step 6:

[0975] Automatic update of strategy information

[0976] The server runs a script to automatically update the walkthrough information on the website. The generated walkthrough information is given as input. The server uses a version control system (e.g., Git) to update the information on the walkthrough wiki site. The output is the updated website. Specifically, the server performs Git commit and push operations to update the website.

[0977] Step 7:

[0978] Chatbot database synchronization

[0979] The server synchronizes the strategy information database with the chatbot's database. The latest strategy information is provided as input. The server updates the natural language processing model (e.g., Dialogflow) to make the latest strategy information available to the chatbot. The output is an updated chatbot. Specifically, the server calls the Dialogflow API to update the dataset.

[0980] Step 8:

[0981] Emotion engine integration

[0982] The server integrates emotion engines to analyze the user's emotional state. The user's facial expressions, tone of voice, and text are given as input. The server evaluates the emotional state using an emotion analysis model (e.g., Microsoft Azure's Face API or IBM Watson's Tone Analyzer). The output is the user's emotional state data. Specifically, the server calls various emotion analysis APIs in sequence and obtains the integrated evaluation results.

[0983] Step 9:

[0984] Responding to user inquiries

[0985] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. The user's inquiry is given to the chatbot as input. The server takes into account the user's progress and emotional state and provides the most appropriate strategy information. The output is an answer from the chatbot. Specifically, the server has the chatbot generate an appropriate answer based on the user's progress data and emotional state data.

[0986] Step 10:

[0987] Emotionally responsive feedback

[0988] The server provides feedback based on the user's emotional state. The user's emotional state data is given as input. The server generates an interface and advice that is effective for the specific emotional state based on the emotional state. The output is feedback appropriate for the user. In concrete terms, the server generates specific advice and messages for the user based on the evaluation results of the emotion engine and provides them through the chatbot.

[0989] (Application example 2)

[0990] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0991] In recent years, online games have become popular with many players, resulting in increasingly complex game mechanisms and stages that are difficult to complete. Consequently, many players are seeking strategy guides and tend to search the Internet for them. However, these guides are not always suited to the player's progress or play style, requiring the player to spend a lot of time gathering and applying the information. Furthermore, the lack of feedback based on the player's emotional state can lead to frustration. Therefore, there is a need for a system that can quickly provide optimal strategy guides based on the player's progress, play style, and emotional state.

[0992] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting gameplay videos of players from all over the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on the user's progress and play style, an emotion recognition engine for recognizing the user's emotional state, and means for providing appropriate feedback based on the user's emotional state. This makes it possible to quickly and effectively provide optimal strategy information that takes into account the player's progress, play style, and emotional state.

[0993] "Gameplay videos of players from around the world" refers to video recordings of games being played by multiple players from around the world, distributed via the Internet.

[0994] "Means of collection" refers to devices or systems, including hardware and software, for downloading specific videos from the Internet and storing them in cloud storage or local storage.

[0995] "Means of analyzing and extracting player behavior patterns" refers to a method of breaking down saved video into frames, identifying specific scenes and player behavior using deep learning models, and extracting those patterns.

[0996] "Means for generating strategy information" refers to a system that generates optimal strategies for specific tasks or boss battles in the game in the form of text, images, videos, etc., based on extracted player behavior patterns.

[0997] "Means for automatically updating to a website" refers to software and scripts that automatically upload the generated cheat information to an existing website, thereby providing users with the latest information at all times.

[0998] "Chatbot means" refers to a program and interface that uses natural language processing to automatically respond to inquiries from users and provide appropriate strategy information.

[0999] An "emotion recognition engine" refers to algorithms and software that analyze a user's facial expressions, tone of voice, text input, etc., and use the results to assess the user's emotional state.

[1000] "Means for providing feedback" refers to a program and interface for providing appropriate information or advice in response to the user's emotional state as assessed by the emotion recognition engine.

[1001] A specific embodiment of the present invention will be described below. This invention combines a system that automatically generates strategy information optimized for the play style of a game player and enables the player to quickly obtain the necessary strategy information through a chatbot with an emotion engine that recognizes the user's emotions.

[1002] Data collection

[1003] The server collects gameplay videos via the Internet. Specifically, it uses the streaming platform's API to automatically download videos related to specific games and save them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[1004] Data analysis

[1005] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. It then uses a deep learning model to analyze the player's behavioral patterns, extracting, for example, attack patterns for specific boss battles and optimal timing for using items.

[1006] Strategy information generation

[1007] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[1008] Strategy wiki update

[1009] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, so users can always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[1010] Response to inquiries via chatbots

[1011] Using a device (such as a smartphone or PC), the user accesses the chatbot and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, assesses their current stage, and provides them with the most appropriate strategy information.

[1012] Emotion engine integration and feedback provision

[1013] The server integrates an emotion engine to acquire data for recognizing the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Based on the evaluation results of the emotion engine, the system provides an appropriate interface and feedback for a specific emotional state. For example, if a user is feeling frustrated with a game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[1014] Example

[1015] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[1016] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy based on the user's progress, equipment, and emotional state.

[1017] Adding concrete examples and prompt sentence examples

[1018] Specifically, when a user wearing smart glasses is playing a game, the application uses the smart glasses' camera to capture the user's facial expressions in real time, analyzes their emotional state (e.g., "anger"), and then inputs prompt sentences like the following into the generative AI model:

[1019] Example prompt sentence:

[1020] I'm playing the game "Fantasy Quest" and I'm having trouble with the boss battle against the Dragon King. Can you tell me how to beat him? The user is currently in an "Anger" state.

[1021] This allows the generative AI model to provide specific strategy information that takes into account the user's emotional state, such as "Water magic is effective in defeating the Dragon King. Stay calm and keep attacking."

[1022] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1023] Step 1:

[1024] The server collects gameplay videos via the internet using the streaming platform's API. At this time, it obtains metadata (game name, player name, play time, etc.) along with the video data obtained from the API and stores them in cloud storage or local storage. The input is an API request, and the output is a video file and metadata.

[1025] Step 2:

[1026] The server breaks down the saved gameplay video into frames and extracts important frames. The input is the saved video file, and the output is a set of extracted important frames. Specifically, it uses a deep learning model to detect scenes with a lot of action, such as boss battles and item acquisition scenes, and saves these as frames.

[1027] Step 3:

[1028] The server analyzes the player's behavioral patterns based on the extracted important frames. This requires frame data as input and generates behavioral pattern data as output. A deep learning model is used for this analysis, and data such as attack patterns for specific boss battles and the optimal timing for using items can be extracted.

[1029] Step 4:

[1030] The server generates strategy information based on the analysis results. This strategy information is generated in the form of text, images, and videos. The input is behavioral pattern data, and the output is specific strategy information. For example, a text file containing information such as "The Dragon King's weak spot is its head, so use water magic to avoid its fire attacks" may be created.

[1031] Step 5:

[1032] The server automatically updates the generated walkthrough information on the walkthrough wiki site. Here, the walkthrough information data is input and the website is updated as output. This automatic update script runs, and the walkthrough information is always kept up to date.

[1033] Step 6:

[1034] The user accesses the chatbot using their device and asks for specific strategy information. At this time, the user's progress is obtained from the game API and save data, and the stage at which the user is is evaluated. The input is the user's query and progress data, and the output is the most appropriate strategy information. For example, if a user asks, "Tell me how to beat Dragon King," the server evaluates the user's progress and provides the appropriate strategy information through the chatbot.

[1035] Step 7:

[1036] The server integrates an emotion engine to capture data for real-time user emotion recognition. The input is real-time data from the camera and microphone, and the output is an evaluation of the user's emotional state. This emotion recognition is achieved by analyzing facial expressions, tone of voice, and text input.

[1037] Step 8:

[1038] The server provides appropriate feedback for a specific emotional state based on the evaluation results of the emotion engine. Emotional state data is input and feedback is generated as output. For example, if a user is feeling frustrated, the chatbot will provide advice such as, "Why don't you take a short break here?"

[1039] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1040] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1041] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1042] [Fourth embodiment]

[1043] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1044] 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.

[1045] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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).

[1046] 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.

[1047] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1048] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1049] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1050] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1051] 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.

[1052] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1053] 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.

[1054] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1055] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1056] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the strategy information they need through a chatbot. Specific embodiments for realizing this system will be described below.

[1057] Data collection

[1058] The server collects game player gameplay videos from the internet. Specifically, it automatically downloads videos related to the game name using, for example, a streaming platform's API. The collected videos are then stored in cloud storage or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[1059] Data analysis

[1060] The server breaks down the stored video into frames and extracts key frames, including high-action scenes, boss battles, and item acquisition scenes. The server then uses a deep learning model to analyze the player's behavioral patterns in the video. For example, it automatically extracts effective tactics for a particular boss battle or the optimal timing for using items.

[1061] Strategy information generation

[1062] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[1063] Strategy wiki update

[1064] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to revert to previous versions at any time.

[1065] Preparing the chatbot

[1066] The server synchronizes the strategy information database with the chat bot's database, allowing the chat bot to obtain the latest strategy information. Furthermore, the server updates the chat bot's natural language processing model so that it can respond to user inquiries.

[1067] Responding to user inquiries

[1068] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates the stage the user is at. The server then generates optimal strategy information based on the user's progress and play style, and provides it through the chat bot. For example, it provides specific advice such as, "Your equipment has a fire attribute, so using water magic would be effective."

[1069] Specific examples

[1070] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[1071] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[1072] The processing flow will be explained below.

[1073] Step 1: Collect gameplay footage

[1074] The server collects gameplay videos from the internet, for example, by using a streaming platform's API to automatically download videos related to a specific game. The downloaded videos are then stored along with metadata such as the game name, player name, and play time.

[1075] Step 2: Save the video

[1076] The server saves the collected videos to cloud storage or local storage. When saving, it organizes the folder structure and registers appropriate metadata to make analysis easier.

[1077] Step 3: Preprocessing the video

[1078] The server breaks down the stored video into frames. Important scenes (e.g., boss battles or item acquisition scenes) are extracted through frame analysis. The extracted frames are used in subsequent analysis steps.

[1079] Step 4: Analyze behavioral patterns

[1080] The server uses a deep learning model to analyze the player's behavior in the video. This analysis evaluates the reasons why the player chose a particular strategy and its effectiveness. For example, it can extract which attacks were used most frequently in a particular boss battle, and which items were used when.

[1081] Step 5: Update the database

[1082] The server registers the analysis results in a database and compares them with existing strategy information. If any new effective tactics or patterns of behavior are discovered, they are added and updated as new data.

[1083] Step 6: Generate strategy information

[1084] The server generates strategy information based on the newly extracted behavioral patterns. The generated information is saved in the form of text, images, and videos. For example, it could generate information such as "The Dragon King's weak point is its head, so using water magic is effective," along with a video clip showing the specific tactics.

[1085] Step 7: Update the strategy wiki

[1086] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest walkthrough information. Update history is also saved, allowing users to return to previous versions if necessary.

[1087] Step 8: Chatbot Database Sync

[1088] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[1089] Step 9: Update the natural language processing model

[1090] The server updates the chatbot's natural language processing model to accommodate new user inquiry patterns, for example, training it to generate appropriate responses to questions like, "How do I beat boss XX?"

[1091] Step 10: Accepting user inquiries

[1092] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[1093] Step 11: Evaluate your progress

[1094] The server obtains the user's progress from the game's API and save data, and evaluates the progress. This determines which stage the user is currently in, which boss they are challenging, etc.

[1095] Step 12: Provide optimal information

[1096] The server generates optimal strategy information based on the user's progress and play style and provides it through a chatbot. For example, it can provide specific advice such as "Instant Strategy: Your equipment is fire-element, so using water magic would be effective."

[1097] Through the above steps, the system of the present invention can provide players with optimal strategy information and support an efficient gaming experience.

[1098] Example 1

[1099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1100] Conventional game strategy information systems have had difficulty quickly providing optimal strategy information based on the player's behavioral patterns and progress. In particular, providing the timely and detailed strategy information that players desire requires processing of massive amounts of data and advanced analysis, and conventional methods have had limitations in meeting this challenge.

[1101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1102] In this invention, the server includes means for collecting gameplay videos of players from the Internet, means for breaking down the collected videos into frames and extracting scenes with a lot of action or important frames, and means for analyzing the extracted frames using a deep learning model to identify behavioral patterns, thereby making it possible to provide optimal strategy information based on the player's behavioral patterns and progress.

[1103] The "Internet" is a global communications network that connects computers and networks around the world.

[1104] "Player" refers to a user who actually operates and plays a computer game.

[1105] "Gameplay video" is recorded or streamed footage of a player interacting with a game.

[1106] A "frame" is each still image in a video, and a video is formed by playing these images consecutively.

[1107] A "deep learning model" is an algorithm that uses a multi-layer neural network to automatically learn the characteristics of data and perform analysis and prediction.

[1108] A "behavioral pattern" refers to a series of actions or choices that a player tends to make in a game.

[1109] "Way-to-win information" is information that includes advice, strategies, and hints for efficiently clearing a game.

[1110] A "website" is a collection of information that is publicly available on the Internet and accessible at a particular URL.

[1111] A "database" is a system for efficiently managing and searching large amounts of data.

[1112] A "chatbot" is a program that automatically converses with users through text.

[1113] A "game API" is a piece of programming that provides an interface for accessing game data and functionality.

[1114] "Save data" is data that saves the game progress, allowing players to resume from where they left off.

[1115] A "terminal" is a device that is directly operated by a user, and typically refers to a smartphone or personal computer.

[1116] A "natural language processing model" is a machine learning model for understanding and processing natural human language.

[1117] The present invention is a system that automatically generates strategy information optimized for a game player's play style and enables the player to quickly obtain the necessary strategy information through a chatbot. A specific embodiment of this system will be described.

[1118] Data collection

[1119] The server collects gameplay videos of players via the Internet. Specifically, it uses the streaming platform's API (e.g., YouTube Data API) to automatically download videos related to the specified game name. The collected videos are then stored in cloud storage (e.g., Amazon S3) or local storage. At this time, metadata (such as the game name, player name, and play time) is added to the stored videos.

[1120] Video frame analysis

[1121] The server breaks down the stored video into frames and extracts scenes with a lot of action and important frames. Specifically, it uses libraries such as OpenCV to divide the video into frames and detects scenes with a lot of action, boss battles, item acquisition scenes, etc. These important frames are then stored in a separate database and assigned corresponding metadata.

[1122] Behavioral pattern analysis

[1123] The server uses a deep learning model (e.g., a CNN model using TensorFlow) to analyze the extracted key frames and identify the player's behavioral patterns. The analysis includes effective tactics for specific boss battles and the optimal timing for using items. The results of this analysis are stored in a strategy information database.

[1124] Strategy information generation

[1125] Based on the results of the behavioral pattern analysis, the server generates strategy information in the form of text, images, and videos. For example, it generates specific information such as "A certain boss's weak spot is its head, so you should use a specific item to avoid attacks," along with a video clip explaining this.

[1126] Strategy wiki update

[1127] The server automatically updates the generated walkthrough information on the walkthrough wiki site, allowing users to always access the latest and most accurate information. The server also stores the wiki's change history, allowing users to return to previous versions at any time.

[1128] Preparing the chatbot

[1129] The server synchronizes the strategy information database with the chatbot's database so that the latest strategy information can be obtained from the chatbot. Furthermore, the server updates the chatbot's natural language processing model (e.g., GPT-3) so that it can respond appropriately to user inquiries.

[1130] Responding to user inquiries

[1131] The user accesses the chat bot using a device (such as a smartphone or PC) and makes a request to obtain specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API (such as the PlayFab API) or save data, and evaluates the user's current stage. The server then generates optimal strategy information that takes into account the user's progress and equipment, and provides it via the chat bot.

[1132] Specific examples

[1133] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is also instantly available to the chat bot. When a user asks the chat bot, "Tell me how to beat the Dragon King," the server provides the optimal strategy, taking into account the user's progress and equipment.

[1134] In this way, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[1135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1136] Step 1:

[1137] The server uses the streaming platform's API to collect gameplay videos. In this case, the server searches for videos related to a specific game name and downloads videos that match the criteria. The input is the specific game name and related keywords, and the output is the downloaded video file. Specifically, the server uses the YouTube Data API to search for related videos for "Fantasy Quest" and downloads the corresponding videos.

[1138] Step 2:

[1139] The server saves the downloaded video file in cloud storage or local storage. When saving, metadata (game name, player name, playback time, etc.) is added to the video. The input is the video file and associated metadata, and the output is the saved video file and its metadata. Specifically, the server uploads the video file to Amazon S3 and adds the metadata.

[1140] Step 3:

[1141] The server divides the stored video into frames and extracts important frames. The input is the stored video file, and the output is the extracted important frames. Specifically, the server uses OpenCV to divide the video into frames and detect scenes with a lot of action, boss battles, and item acquisition scenes.

[1142] Step 4:

[1143] The server inputs the extracted important frames into a deep learning model to analyze the player's behavioral patterns. The inputs are the important frames and the deep learning model, and the output is the behavioral patterns resulting from the analysis. Specifically, the server inputs the important frames into a CNN model using TensorFlow to identify specific behavioral patterns.

[1144] Step 5:

[1145] The server generates strategy information based on the analysis results. The input is the analysis results of behavioral patterns, and the output is strategy information in the form of text, images, and videos. Specific operations include generating text and video clips on how to defeat a specific boss and when to use items.

[1146] Step 6:

[1147] The server reflects the generated walkthrough information on the walkthrough wiki site. The input is the generated walkthrough information, and the output is the updated walkthrough wiki page. Specifically, the server posts the new walkthrough information using the wiki site's API.

[1148] Step 7:

[1149] The server synchronizes the strategy information database with the chat bot database. The input is the strategy information database, and the output is the synchronized chat bot database. Specifically, the server uses the database replication function to perform the synchronization.

[1150] Step 8:

[1151] The server updates the chatbot's natural language processing model so that it can respond to user inquiries. The input is the natural language processing model and new data, and the output is the updated natural language processing model. Specifically, the server executes the process of updating the GPT-3 model.

[1152] Step 9:

[1153] A user accesses a chatbot using a device and asks for specific strategy information. The input is the user's text input, and the output is the chatbot's answer. Specifically, the user asks the chatbot, "Tell me how to beat the boss of the current stage."

[1154] Step 10:

[1155] The server obtains the user's progress from the game API and save data and provides optimal strategy information. The input is the user's progress data and play style data, and the output is optimized strategy information. Specifically, the server uses the PlayFab API to obtain and analyze the user's game progress. It then generates customized strategy information based on the user's equipment and current status and provides it via a chat bot.

[1156] (Application example 1)

[1157] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1158] Today's game players need to quickly obtain complex and diverse game strategy information to progress effectively in games. However, the wide variety of strategy information available on the Internet makes it difficult to find information optimized for each player's progress and playing style. Furthermore, existing strategy websites and video content provide general information and lack the means to provide specific strategies and methods tailored to each user. To solve this problem, a system is needed that quickly provides optimal strategy information based on the user's progress and playing style.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1160] In this invention, the server includes means for collecting gameplay videos of players around the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on a user's progress and play style, means for notifying the user of the optimal strategy information through a smartphone application, and means for saving and sharing the user's play style and progress in a cloud-based database. This allows users to easily obtain individually optimized strategy information in real time and progress through the game effectively.

[1161] "Gameplay video" refers to video content that is recorded or streamed to show a player actually playing a game.

[1162] A "behavioral pattern" refers to a tendency for a game player to take a series of actions or behaviors in a particular situation.

[1163] "Strategy information" refers to information about strategies and methods for clearing or defeating difficult scenes or enemies in the game.

[1164] A "streaming platform API" is a mechanism for collecting and manipulating video data using a program interface provided by a streaming service.

[1165] A "natural language processing model" is an artificial intelligence technology that understands the natural language (sentences) entered by the user and generates an appropriate response.

[1166] A "chatbot" is an automated response system that provides information and answers questions through conversations with users.

[1167] A "smartphone application" is a software program that runs on a smartphone and provides specific functions or services.

[1168] A "cloud-based database" is a database system built on a remote server accessible via the Internet.

[1169] A system for realizing the present invention includes the following means.

[1170] A means of collecting gameplay videos from players around the world

[1171] The server uses the streaming platform's API to automatically collect gameplay videos from players around the world, allowing the server to collect a large number of gameplay videos related to a specific game.

[1172] Gameplay video analysis tool

[1173] The server breaks down the collected gameplay videos into frames and uses a deep learning model to analyze the player's behavioral patterns in the videos. This analysis allows it to extract effective tactics and optimal timing for specific scenes (e.g., boss battles, item acquisition, etc.). This analysis is performed using high-performance servers equipped with GPUs or cloud-based computing resources.

[1174] Strategy information generation means

[1175] The server generates game strategy information based on the analysis results. This strategy information is saved in the form of text, images, and video clips. For example, it may include specific tactical information such as "In boss battles, use water magic to avoid fire-element attacks."

[1176] Automatic website update methods

[1177] The generated strategy information is automatically updated by the server on a website that provides strategy information. This allows users to always access the latest strategy information. The website's backend uses a database management system (DBMS) to ensure smooth data updates.

[1178] Chatbot Means

[1179] Furthermore, the server is equipped with a chatbot that provides optimal strategy information in response to user inquiries. The chatbot incorporates a natural language processing model and generates appropriate answers to questions entered by the user. This allows users to obtain the strategy information they need in real time.

[1180] Smartphone application means

[1181] A dedicated smartphone application is provided so that users can quickly obtain strategy information via their smartphone. The application is designed to notify users of the most appropriate strategy information based on their progress and play style. For example, a notification such as "The fire-element weapon you are equipped with is effective in the next boss battle" can be provided in real time.

[1182] Cloud-based database solutions

[1183] Data about a user's play style and progress is stored in a cloud-based database, which provides consistent information across different devices. The database is highly scalable and can efficiently manage large amounts of data.

[1184] Examples of concrete examples and prompts

[1185] For example, in the case of the game "Fantasy Quest," the server collects gameplay videos from YouTube, analyzes them using a deep learning model, and generates a "strategy for defeating the Dragon King." When a user asks a smartphone application chatbot, "Tell me how to beat the Dragon King," the server instantly provides specific strategy information, such as "Use water magic to block fire attacks, then focus attacks on the head," based on the user's equipment and progress.

[1186] Prompt Sentence Examples

[1187] "Tell me some effective tactics for the boss battle in the next stage."

[1188] "How can I gain an advantage with my current equipment?"

[1189] "I want to know where to get a specific item."

[1190] By means of the above means, the present invention realizes a system that allows users to quickly and accurately obtain complex game strategy information and provides an efficient gaming experience.

[1191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1192] Step 1:

[1193] The server uses the streaming platform's API to collect gameplay videos from players around the world. The input is video metadata (game name, player name, URL, etc.), and the output is a video file stored in the server's local storage or cloud storage. Specifically, the server makes an API request, analyzes the response data, and downloads the video.

[1194] Step 2:

[1195] The server breaks down the collected gameplay videos into frames and extracts important frames. The input is the saved gameplay video file, and the output is a collection of frames containing important scenes. Specifically, it uses a video analysis algorithm to detect and extract scenes with a lot of action, boss battles, and item acquisition scenes.

[1196] Step 3:

[1197] The server uses a deep learning model to analyze the player's behavioral patterns in the video. The input is the extracted important frames, and the output is data about the player's behavioral patterns. Specifically, the deep learning model analyzes a sequence of frames and recognizes specific actions (e.g., the timing of using a specific technique).

[1198] Step 4:

[1199] The server generates strategy information based on the analysis results. The input is behavioral pattern data, and the output is strategy information in the form of text, images, and video clips. Specifically, the server uses a generative AI model to generate content describing optimal tactics and strategies based on specific behaviors.

[1200] Step 5:

[1201] The server automatically updates the generated strategy information to the website that provides the strategy information. The input is the generated strategy information, and the output is the updated web page. Specifically, the server inserts the new information into the website's database and regenerates the corresponding web page.

[1202] Step 6:

[1203] A user accesses a chatbot using a device (such as a smartphone or PC) and makes an inquiry to obtain specific strategy information. The input is a question (prompt) in natural language from the user, and the output is an answer from the chatbot. A specific example of how this works is when the user inputs, "Tell me how to beat the boss of the current stage."

[1204] Step 7:

[1205] The server generates optimal strategy information based on the user's progress and play style and provides it through the chatbot. The input is the user's progress, equipment data, and inquiry, and the output is a specific answer regarding the optimal strategy. Specifically, the server analyzes the progress data, generates appropriate strategy information, and provides it to the user via the chatbot.

[1206] Step 8:

[1207] It is designed to allow users to quickly obtain game strategy information through a smartphone application. The input is user account information and in-game progress data, and the output is notification messages within the application. Specifically, the application periodically sends requests to the server, receives the latest game strategy information, and notifies the user.

[1208] Step 9:

[1209] The server stores and shares data about users' play styles and progress in a cloud-based database. The input is the user's play data, and the output is a well-organized database stored in the cloud. Specifically, the server periodically collects play data and uploads and updates it to the cloud system.

[1210] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1211] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[1212] Data collection

[1213] The server collects game player gameplay videos from the internet. Using the streaming platform's API, it automatically downloads videos related to specific games and saves them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[1214] Data analysis

[1215] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. Next, a deep learning model is used to analyze the player's behavioral patterns. For example, it can extract attack patterns for specific boss battles and the optimal timing for using items.

[1216] Strategy information generation

[1217] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[1218] Strategy wiki update

[1219] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. This allows users to always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[1220] Preparing the chatbot

[1221] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information. The server also updates the chatbot's natural language processing model, enabling it to respond to various user inquiries.

[1222] Emotion engine integration

[1223] The server integrates an emotion engine to acquire data for real-time user emotion recognition. The emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.).

[1224] Responding to user inquiries

[1225] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[1226] Emotionally responsive feedback

[1227] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[1228] Specific examples

[1229] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[1230] When a user asks the chatbot, "Tell me how to beat Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking." In this way, the present invention can provide players with optimal strategy information, providing a system that ensures a comfortable gaming experience.

[1231] The processing flow will be explained below.

[1232] Step 1: Collect gameplay footage

[1233] The server uses the streaming platform's API to automatically download gameplay videos related to a specific game, and adds metadata such as the game name, player name, and playback time to the downloaded video.

[1234] Step 2: Save the video

[1235] The gameplay videos collected by the server are stored in cloud storage or local storage. By creating a folder structure and properly registering related metadata, subsequent analysis processing becomes easier.

[1236] Step 3: Preprocessing the video

[1237] The server breaks down the stored video into frames and extracts important scenes, such as boss battles and item acquisition scenes. The extracted frames are then used for analysis by a deep learning model.

[1238] Step 4: Analyze behavioral patterns

[1239] The server uses a deep learning model to analyze the player's behavior patterns within the extracted frames. For example, it can extract attack patterns in a specific boss battle or the timing of item use, and record this data as the player's behavior patterns.

[1240] Step 5: Update the database

[1241] The server registers the analysis results in a database, and if new effective tactics or patterns of behavior are found by comparing them with existing strategy information, they are added to the database.

[1242] Step 6: Generate strategy information

[1243] The server generates strategy information based on the information in the database. The strategy information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so water magic is effective against it," along with a video clip showing this information.

[1244] Step 7: Update the strategy wiki

[1245] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, ensuring that users always have access to the latest walkthrough information. Update history is also saved, making it possible to revert to previous versions if necessary.

[1246] Step 8: Chatbot Database Sync

[1247] The server synchronizes the strategy information database with the chatbot's database, allowing the chatbot to obtain the latest strategy information.

[1248] Step 9: Update the natural language processing model

[1249] The server updates the chatbot's natural language processing model to generate optimal responses to user queries. The trained model understands the user's question and provides the appropriate answer.

[1250] Step 10: Integrating the Emotion Engine

[1251] The server integrates an emotion engine to recognize the user's emotional state in real time, which analyzes the user's facial expressions, tone of voice, and text input to evaluate the user's emotional state.

[1252] Step 11: Accepting user inquiries

[1253] A user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss of the current stage."

[1254] Step 12: Evaluate your progress

[1255] The server obtains the user's progress from the game API and save data, determines the current stage of the game, and customizes the walkthrough information provided based on the user's progress.

[1256] Step 13: Emotionally responsive feedback

[1257] The server generates optimal strategy information and feedback based on the evaluation of the user's emotional state using an emotion engine. For example, if the user is feeling frustrated, the server will provide advice tailored to their emotions, such as "Water magic is effective. Stay calm and continue playing."

[1258] Through the above steps, the system of the present invention can provide the user with the strategy information they need quickly and accurately, and by providing feedback that takes into account the user's emotional state, it can provide a comfortable gaming experience.

[1259] Example 2

[1260] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1261] Conventional strategy information systems have the problem of only providing general strategy information without considering the player's play style or emotional state. This makes it difficult for players to obtain appropriate strategy information, which can reduce the enjoyment of gameplay. In addition, manually collecting and updating strategy information is cumbersome and lacks real-time performance.

[1262] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1263] In this invention, the server includes a means for collecting gameplay videos from the Internet, a means for extracting important scenes by breaking down the collected videos into frames, and a means for generating strategy information based on the extracted behavioral patterns, thereby enabling the prompt and appropriate provision of strategy information that takes into account the player's play style and emotional state.

[1264] A "gameplay video" is a video file that records the user playing a game.

[1265] The "Internet" is a communications network that connects computer networks around the world.

[1266] A "frame" is an individual still image that makes up a video.

[1267] "Important scenes" are particularly noteworthy moments during gameplay, such as boss battles and item acquisition.

[1268] A "behavior pattern" is a series of movements or actions that a player takes in the game.

[1269] "Strategy information" refers to specific advice and strategies to help you progress through the game to your advantage.

[1270] A "website" is a collection of informational pages available on the Internet.

[1271] "User emotional state" refers to emotions such as joy, anger, sadness, etc. that a player feels while playing a game.

[1272] A "chatbot" is a software application that automates interactions with users.

[1273] A "natural language processing model" refers to algorithms and techniques for understanding and analyzing human language.

[1274] A "streaming platform" is a service that distributes video and audio in real time over the Internet.

[1275] "API" stands for Application Program Interface, an interface for exchanging functions and data between different software applications.

[1276] The present invention combines a system that automatically generates strategy guides optimized for a game player's playing style and allows the player to quickly obtain the strategy guide information they need through a chatbot with an emotion engine that recognizes the user's emotions. Specific embodiments for realizing this system will be described below.

[1277] Data collection

[1278] The server uses the streaming platform's API to collect gameplay videos related to a specific game. For example, it uses the YouTube Data API to search for specific keywords and automatically download new videos. The downloaded videos are stored in cloud storage (e.g., Amazon S3 or Google Cloud Storage) and are assigned metadata (such as the game name, player name, and playback time).

[1279] Data analysis

[1280] The server breaks down the stored video into frames and extracts important scenes (such as boss battles and item acquisition scenes). Specifically, it uses video processing tools such as FFmpeg to convert the video to 30 frames per second, and then uses deep learning models (e.g., TensorFlow and PyTorch) to analyze the player's behavioral patterns. During this process, it extracts scenes with a lot of action, such as boss battles and item acquisition scenes.

[1281] Strategy information generation

[1282] The server generates strategy information based on the analysis results. A natural language generation model (e.g., GPT-3) is used to generate information in the form of text, images, and videos. The generated strategy information is stored in a database. For example, specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip illustrating this information are generated.

[1283] Strategy wiki update

[1284] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site. Updates are performed periodically using Amazon Lambda or Cron, ensuring that users always have access to the latest information. Change history is also saved in a version control system (e.g., Git), allowing users to revert to previous versions as needed.

[1285] Preparing the chatbot

[1286] The server synchronizes the strategy information database with the chatbot's database. It uses natural language processing models such as Dialogflow to respond to user inquiries. This allows the chatbot to obtain the latest strategy information.

[1287] Emotion engine integration

[1288] The server integrates an emotion engine and collects data to recognize the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Specifically, it uses Microsoft Azure's Face API and IBM Watson's Tone Analyzer.

[1289] Responding to user inquiries

[1290] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, and evaluates their current stage.

[1291] Emotionally responsive feedback

[1292] The server evaluates the user's emotional state and generates optimal strategy information based on the evaluation results. Based on the evaluation results of the emotion engine, the chatbot provides an appropriate interface and feedback for the specific emotional state. For example, if the user is feeling frustrated with the game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[1293] Specific examples

[1294] For example, in the game "Fantasy Quest," a server collects gameplay footage from a streaming platform and extracts key scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on a strategy wiki and is instantly available to chatbots.

[1295] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy, taking into account the user's progress, equipment, and emotional state. For example, if the user is feeling frustrated, the server will provide specific, emotionally sensitive advice such as, "Water magic is effective. Stay calm and keep attacking."

[1296] Example prompt: "Tell me how to defeat the Dragon King. If the emotional state is Frustrated, please also include some advice to calm the user down."

[1297] In this way, the present invention provides a system that provides players with optimal strategy information and realizes a comfortable gaming experience.

[1298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1299] Step 1:

[1300] Gameplay video collection

[1301] The server uses the API of the streaming platform to collect gameplay videos related to a specific game. Search keywords and the API key of the streaming platform are given as input. The server downloads these videos from the Internet and stores them in cloud storage. The output is the collected video files and their metadata. Specifically, the server periodically calls the API to obtain a list of new videos and downloads each video sequentially.

[1302] Step 2:

[1303] Video frame decomposition

[1304] The server uses a video processing tool (e.g., FFmpeg) to break down the collected video into frames. A video file is given as input. The server breaks down the video into 30 frames per second and saves each frame in image format. As output, frame image files are obtained. Specifically, the server executes FFmpeg commands to convert the video into image files at the specified frame rate.

[1305] Step 3:

[1306] Extracting important scenes

[1307] The server analyzes each frame using a deep learning model (e.g., TensorFlow or PyTorch) and extracts important scenes. The decomposed frame images are given as input. The server uses an image recognition model to detect particularly important scenes, such as boss battles and item acquisition scenes. The output is a list of important frames. Specifically, the server inputs each frame image into the model and evaluates its importance based on the identification results of each frame.

[1308] Step 4:

[1309] Behavioral pattern analysis

[1310] The server analyzes the player's behavioral patterns based on frames of important scenes. As input, it receives important frame images and corresponding video sequences. The server uses a behavioral analysis model to analyze the player's behavioral patterns, such as attack patterns and item usage timing. As output, it obtains behavioral pattern data. Specifically, the server inputs the video sequences into the model and extracts behavioral patterns.

[1311] Step 5:

[1312] Generation of strategy information

[1313] The server generates walkthrough information based on the results of the behavioral pattern analysis. Behavioral pattern data is provided as input. The server uses a natural language generation model (e.g., GPT-3) to create walkthrough information in text format, and also generates images and videos as needed. The generated walkthrough information is obtained as output. Specifically, the server inputs the analysis results as prompts into the generation model to obtain the walkthrough information.

[1314] Step 6:

[1315] Automatic update of strategy information

[1316] The server runs a script to automatically update the walkthrough information on the website. The generated walkthrough information is given as input. The server uses a version control system (e.g., Git) to update the information on the walkthrough wiki site. The output is the updated website. Specifically, the server performs Git commit and push operations to update the website.

[1317] Step 7:

[1318] Chatbot database synchronization

[1319] The server synchronizes the strategy information database with the chatbot's database. The latest strategy information is provided as input. The server updates the natural language processing model (e.g., Dialogflow) to make the latest strategy information available to the chatbot. The output is an updated chatbot. Specifically, the server calls the Dialogflow API to update the dataset.

[1320] Step 8:

[1321] Emotion engine integration

[1322] The server integrates emotion engines to analyze the user's emotional state. The user's facial expressions, tone of voice, and text are given as input. The server evaluates the emotional state using an emotion analysis model (e.g., Microsoft Azure's Face API or IBM Watson's Tone Analyzer). The output is the user's emotional state data. Specifically, the server calls various emotion analysis APIs in sequence and obtains the integrated evaluation results.

[1323] Step 9:

[1324] Responding to user inquiries

[1325] The user accesses the chatbot using a device (such as a smartphone or PC) and asks for specific strategy information. The user's inquiry is given to the chatbot as input. The server takes into account the user's progress and emotional state and provides the most appropriate strategy information. The output is an answer from the chatbot. Specifically, the server has the chatbot generate an appropriate answer based on the user's progress data and emotional state data.

[1326] Step 10:

[1327] Emotionally responsive feedback

[1328] The server provides feedback based on the user's emotional state. The user's emotional state data is given as input. The server generates an interface and advice that is effective for the specific emotional state based on the emotional state. The output is feedback appropriate for the user. In concrete terms, the server generates specific advice and messages for the user based on the evaluation results of the emotion engine and provides them through the chatbot.

[1329] (Application example 2)

[1330] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1331] In recent years, online games have become popular with many players, resulting in increasingly complex game mechanisms and stages that are difficult to complete. Consequently, many players are seeking strategy guides and tend to search the Internet for them. However, these guides are not always suited to the player's progress or play style, requiring the player to spend a lot of time gathering and applying the information. Furthermore, the lack of feedback based on the player's emotional state can lead to frustration. Therefore, there is a need for a system that can quickly provide optimal strategy guides based on the player's progress, play style, and emotional state.

[1332] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting gameplay videos of players from all over the world, means for analyzing the collected gameplay videos to extract player behavior patterns, means for generating strategy information based on the extracted behavior patterns, means for automatically updating the generated strategy information on a website, chatbot means for providing optimal strategy information based on the user's progress and play style, an emotion recognition engine for recognizing the user's emotional state, and means for providing appropriate feedback based on the user's emotional state. This makes it possible to quickly and effectively provide optimal strategy information that takes into account the player's progress, play style, and emotional state.

[1333] "Gameplay videos of players from around the world" refers to video recordings of games being played by multiple players from around the world, distributed via the Internet.

[1334] "Means of collection" refers to devices or systems, including hardware and software, for downloading specific videos from the Internet and storing them in cloud storage or local storage.

[1335] "Means of analyzing and extracting player behavior patterns" refers to a method of breaking down saved video into frames, identifying specific scenes and player behavior using deep learning models, and extracting those patterns.

[1336] "Means for generating strategy information" refers to a system that generates optimal strategies for specific tasks or boss battles in the game in the form of text, images, videos, etc., based on extracted player behavior patterns.

[1337] "Means for automatically updating to a website" refers to software and scripts that automatically upload the generated cheat information to an existing website, thereby providing users with the latest information at all times.

[1338] "Chatbot means" refers to a program and interface that uses natural language processing to automatically respond to inquiries from users and provide appropriate strategy information.

[1339] An "emotion recognition engine" refers to algorithms and software that analyze a user's facial expressions, tone of voice, text input, etc., and use the results to assess the user's emotional state.

[1340] "Means for providing feedback" refers to a program and interface for providing appropriate information or advice in response to the user's emotional state as assessed by the emotion recognition engine.

[1341] A specific embodiment of the present invention will be described below. This invention combines a system that automatically generates strategy information optimized for the play style of a game player and enables the player to quickly obtain the necessary strategy information through a chatbot with an emotion engine that recognizes the user's emotions.

[1342] Data collection

[1343] The server collects gameplay videos via the Internet. Specifically, it uses the streaming platform's API to automatically download videos related to specific games and save them in cloud storage or local storage. When the videos are saved, metadata (such as the game name, player name, and playback time) is added.

[1344] Data analysis

[1345] The server breaks down the stored video into frames and extracts key frames, including action-packed scenes such as boss battles and item acquisition scenes. It then uses a deep learning model to analyze the player's behavioral patterns, extracting, for example, attack patterns for specific boss battles and optimal timing for using items.

[1346] Strategy information generation

[1347] The server generates strategy information based on the analysis results. The generated information is saved in the form of text, images, and videos. For example, it generates specific information such as "The Dragon King's weak spot is its head, so to avoid its fire attacks, it is best to use water magic" and a video clip showing this information.

[1348] Strategy wiki update

[1349] The server runs an automatic update script and updates the generated walkthrough information on the walkthrough wiki site, so users can always access the latest information. The server also stores a change history, allowing users to return to previous versions if necessary.

[1350] Response to inquiries via chatbots

[1351] Using a device (such as a smartphone or PC), the user accesses the chatbot and asks for specific strategy information. For example, they might type, "Tell me how to beat the boss in the current stage." The server retrieves the user's progress from the game API and save data, assesses their current stage, and provides them with the most appropriate strategy information.

[1352] Emotion engine integration and feedback provision

[1353] The server integrates an emotion engine to acquire data for recognizing the user's emotions in real time. This emotion engine analyzes the user's facial expressions, tone of voice, and text input to evaluate their emotional state (e.g., joy, sadness, surprise, anger, etc.). Based on the evaluation results of the emotion engine, the system provides an appropriate interface and feedback for a specific emotional state. For example, if a user is feeling frustrated with a game, the chatbot will recognize this and provide advice such as, "Why don't you take a short break here?"

[1354] Example

[1355] For example, in the game "Fantasy Quest," the server collects gameplay videos of "Fantasy Quest" from YouTube and extracts important scenes (such as boss battles and moments when items are obtained). It then uses a deep learning model to analyze the player's behavioral patterns and generates strategy information, such as "To defeat the Dragon King, first block his fire attacks with water magic, then focus your attacks on his head." This information is automatically updated on the strategy wiki and is instantly available to chatbots.

[1356] When a user asks the chatbot, "Tell me how to beat the Dragon King," the server will provide the optimal strategy based on the user's progress, equipment, and emotional state.

[1357] Adding concrete examples and prompt sentence examples

[1358] Specifically, when a user wearing smart glasses is playing a game, the application uses the smart glasses' camera to capture the user's facial expressions in real time, analyzes their emotional state (e.g., "anger"), and then inputs prompt sentences like the following into the generative AI model:

[1359] Example prompt sentence:

[1360] I'm playing the game "Fantasy Quest" and I'm having trouble with the boss battle against the Dragon King. Can you tell me how to beat him? The user is currently in an "Anger" state.

[1361] This allows the generative AI model to provide specific strategy information that takes into account the user's emotional state, such as "Water magic is effective in defeating the Dragon King. Stay calm and keep attacking."

[1362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1363] Step 1:

[1364] The server collects gameplay videos via the internet using the streaming platform's API. At this time, it obtains metadata (game name, player name, play time, etc.) along with the video data obtained from the API and stores them in cloud storage or local storage. The input is an API request, and the output is a video file and metadata.

[1365] Step 2:

[1366] The server breaks down the saved gameplay video into frames and extracts important frames. The input is the saved video file, and the output is a set of extracted important frames. Specifically, it uses a deep learning model to detect scenes with a lot of action, such as boss battles and item acquisition scenes, and saves these as frames.

[1367] Step 3:

[1368] The server analyzes the player's behavioral patterns based on the extracted important frames. This requires frame data as input and generates behavioral pattern data as output. A deep learning model is used for this analysis, and data such as attack patterns for specific boss battles and the optimal timing for using items can be extracted.

[1369] Step 4:

[1370] The server generates strategy information based on the analysis results. This strategy information is generated in the form of text, images, and videos. The input is behavioral pattern data, and the output is specific strategy information. For example, a text file containing information such as "The Dragon King's weak spot is its head, so use water magic to avoid its fire attacks" may be created.

[1371] Step 5:

[1372] The server automatically updates the generated walkthrough information on the walkthrough wiki site. Here, the walkthrough information data is input and the website is updated as output. This automatic update script runs, and the walkthrough information is always kept up to date.

[1373] Step 6:

[1374] The user accesses the chatbot using their device and asks for specific strategy information. At this time, the user's progress is obtained from the game API and save data, and the stage at which the user is is evaluated. The input is the user's query and progress data, and the output is the most appropriate strategy information. For example, if a user asks, "Tell me how to beat Dragon King," the server evaluates the user's progress and provides the appropriate strategy information through the chatbot.

[1375] Step 7:

[1376] The server integrates an emotion engine to capture data for real-time user emotion recognition. The input is real-time data from the camera and microphone, and the output is an evaluation of the user's emotional state. This emotion recognition is achieved by analyzing facial expressions, tone of voice, and text input.

[1377] Step 8:

[1378] The server provides appropriate feedback for a specific emotional state based on the evaluation results of the emotion engine. Emotional state data is input and feedback is generated as output. For example, if a user is feeling frustrated, the chatbot will provide advice such as, "Why don't you take a short break here?"

[1379] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1380] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) 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 voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1381] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1382] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1383] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1384] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1385] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1386] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1387] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1388] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1389] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1390] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1391] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1392] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1393] 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.

[1394] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1395] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1396] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1397] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1398] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1399] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1400] The following is further disclosed regarding the above embodiment.

[1401] (Claim 1)

[1402] A means of collecting gameplay videos from players around the world,

[1403] A means of analyzing collected gameplay videos to extract player behavior patterns;

[1404] A means for generating strategy information based on the extracted behavioral patterns;

[1405] means for automatically updating the generated strategy information on a website;

[1406] A system including a chatbot means for providing optimal strategy information based on a user's progress and playing style.

[1407] (Claim 2)

[1408] 10. The system of claim 1, further comprising means for utilizing an API of a streaming platform to collect gameplay videos.

[1409] (Claim 3)

[1410] 2. The system according to claim 1, further comprising a chatbot means for responding to user inquiries using a natural language processing model.

[1411] "Example 1"

[1412] (Claim 1)

[1413] a means for collecting gameplay videos of players from the Internet;

[1414] A method for breaking down collected videos into frames and extracting scenes with a lot of movement and important frames.

[1415] A means for analyzing the extracted frames using a deep learning model to identify behavioral patterns;

[1416] A means for generating strategy information in text, image, and video formats based on the analysis results;

[1417] A means for automatically reflecting the generated strategy information on a website;

[1418] A means to synchronize the strategy information database with the chatbot database and provide the latest information,

[1419] A chatbot that obtains the user's progress from the game API and save data and provides optimal strategy information.

[1420] A method to provide strategy information taking into account the user's equipment when accessing the chatbot from a terminal, and

[1421] A system including:

[1422] (Claim 2)

[1423] The system of claim 1, which utilizes a streaming platform's API to collect gameplay videos.

[1424] (Claim 3)

[1425] 2. The system of claim 1, further comprising a chatbot means for responding to user inquiries using a natural language processing model.

[1426] "Application Example 1"

[1427] (Claim 1)

[1428] A means of collecting gameplay videos from players around the world,

[1429] A means of analyzing collected gameplay videos to extract player behavior patterns;

[1430] A means for generating strategy information based on the extracted behavioral patterns;

[1431] means for automatically updating the generated strategy information on a website;

[1432] A chatbot means for providing optimal strategy information based on the user's progress and play style;

[1433] A means of notifying users of optimal strategy information through a smartphone application;

[1434] A means to store and share users' playstyles and progress in a cloud-based database;

[1435] A system including:

[1436] (Claim 2)

[1437] 10. The system of claim 1, further comprising means for collecting gameplay videos using an API of a streaming platform.

[1438] (Claim 3)

[1439] 2. The system of claim 1, further comprising a chatbot means for responding to user inquiries using a natural language processing model.

[1440] "Example 2: Combining Emotion Engines"

[1441] (Claim 1)

[1442] A means of collecting gameplay videos from the Internet,

[1443] A method for breaking down collected videos into frames and extracting important scenes;

[1444] A means for generating strategy information based on the extracted behavioral patterns;

[1445] means for automatically updating the generated strategy information on a website;

[1446] A means for analyzing the emotional state of a user and providing optimal strategy information;

[1447] A system including a chatbot means for providing optimal strategy information based on a user's progress and playing style.

[1448] (Claim 2)

[1449] The system of claim 1, which utilizes a streaming platform's API to collect gameplay videos.

[1450] (Claim 3)

[1451] 2. The system of claim 1, further comprising a chatbot means for responding to user inquiries using a natural language processing model.

[1452] "Application example 2 when combining emotion engines"

[1453] (Claim 1)

[1454] A means of collecting gameplay videos from players around the world,

[1455] A means of analyzing collected gameplay videos to extract player behavior patterns;

[1456] A means for generating strategy information based on the extracted behavioral patterns;

[1457] means for automatically updating the generated strategy information on a website;

[1458] A chatbot means for providing optimal strategy information based on the user's progress and play style;

[1459] an emotion recognition engine for recognizing the emotional state of a user;

[1460] means for providing appropriate feedback based on the user's emotional state;

[1461] A system including:

[1462] (Claim 2)

[1463] 10. The system of claim 1, further comprising means for utilizing an API of a streaming platform to collect gameplay videos.

[1464] (Claim 3)

[1465] 2. The system of claim 1, further comprising a chatbot means for responding to user inquiries using a natural language processing model. [Explanation of symbols]

[1466] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting gameplay videos from players around the world, A means of analyzing collected gameplay videos to extract player behavior patterns; A means for generating strategy information based on the extracted behavioral patterns; means for automatically updating the generated strategy information on a website; A system including a chatbot means for providing optimal strategy information based on a user's progress and playing style.

2. 10. The system of claim 1, further comprising means for utilizing an API of a streaming platform to collect gameplay videos.

3. 10. The system of claim 1, further comprising a chatbot means for responding to user inquiries using a natural language processing model.

Images