System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a voice input from a user; means for converting the received voice input into a character string; means for extracting a keyword from the character string; means for generating a sentence based on the extracted keyword; and means for displaying the generated sentence in an in-game chat.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 online action games, it is difficult for users to exchange information quickly without using VoiceChat. This is because typing takes time, requires players to take their hands off the controller, and VoiceChat with other players can be uncomfortable or embarrassing. This can cause problems such as slow game progress and hinder team play. Therefore, a new method to solve this problem is needed. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: A system including means for receiving voice input from a user and means for converting the voice input into text is provided. Furthermore, means for extracting keywords from the text and means for generating text based on the extracted keywords are provided. The system also includes means for displaying the generated text in an in-game chat. This system allows users to share information quickly and smoothly through voice input, eliminating the need to take their hands off the controller. Furthermore, text generation using a generative AI model enables clear information provision without relying on VoiceChat.

[0006] A "user" is a player who uses voice input and shares information within the game.

[0007] "Audio input" refers to the audio data emitted by the player through a microphone.

[0008] A "character string" is text data converted from voice input using a voice recognition system.

[0009] "Keywords" are words or phrases extracted from a string of characters that indicate important information within the game.

[0010] "Generative AI" refers to an artificial intelligence model that generates natural-sounding sentences based on keywords.

[0011] "In-game chat" refers to a feature in an online game interface that allows players to exchange text messages with each other.

[0012] "System" refers to the set of technical components that handle everything from receiving voice input to generating text and displaying it in the in-game chat. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0035] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device.

[0036] The device then converts the received voice input into text. This conversion is performed using the device's built-in voice recognition system. The voice recognition system analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0037] The converted string is sent from the device to the server. The server analyzes the received text data and extracts keywords from the string. Specifically, it uses natural language processing (NLP) algorithms to detect important words and phrases. In this case, the keywords "enemy" and "left" are extracted.

[0038] Once the keywords are extracted, the server uses a generative AI model to generate sentences based on these keywords. The generative AI model generates natural and appropriate sentences based on the given keywords and background information. For example, sentence generation based on the extracted keywords "enemy" and "left" would generate a sentence such as "The enemy is on your left."

[0039] The generated text is sent from the server to the device, which then displays it in the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0040] As a concrete example, consider a user playing an online FPS game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into a string and sends it to the server. The server extracts keywords from the string, and a generative AI model generates the sentence "enemy on the left." Finally, the generated sentence is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0041] As a result, this system provides an environment in which users can share information efficiently and clearly without letting go of their controllers.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] The user speaks into the microphone of the device.

[0045] Action: The user verbally utters the specific command "enemy, left."

[0046] Step 2:

[0047] The device receives voice input and converts the voice into text using a voice recognition system.

[0048] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0049] Step 3:

[0050] The terminal transmits the generated text data to the server.

[0051] Operation: The device sends a request to send text data to the server over the network.

[0052] Step 4:

[0053] The server analyzes the received text data and extracts keywords from the string.

[0054] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0055] Step 5:

[0056] The server sends input data to the generative AI model based on the extracted keywords.

[0057] How it works: The server formats the keywords and necessary contextual information and sends a request to the generation AI's API.

[0058] Step 6:

[0059] Generative AI generates appropriate sentences.

[0060] How it works: The generative AI model generates the sentence "The enemy is on your left" based on the keywords and context information provided.

[0061] Step 7:

[0062] The server sends the generated text to the terminal.

[0063] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0064] Step 8:

[0065] The text received by the device will be displayed in the in-game chat.

[0066] What it does: The game client on the device displays the received text in a chat window, allowing the user's teammates to view this information.

[0067] This series of processing steps allows users to share information efficiently and smoothly progress through game play.

[0068] Example 1

[0069] 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."

[0070] In online action games, it is difficult for users to share information with team members quickly and accurately without interrupting the game. In particular, there are problems with delays and recognition errors in the process of converting voice input into text and generating appropriate sentences.

[0071] 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.

[0072] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a prompt sentence based on the extracted keywords and generating a sentence using a generative AI model, and means for displaying the generated sentence on a user interface, thereby enabling a user to quickly and accurately share information with team members without interrupting operations.

[0073] The "means for receiving voice input" is a function for receiving voice uttered by the user via the device's microphone or the like.

[0074] The "means for converting voice input into text" is a function that analyzes received voice data and converts the content into a corresponding text format.

[0075] "Means for extracting keywords from character strings" is a function that selects important words and phrases from the converted text data.

[0076] "Means for generating prompt sentences and generating sentences using a generative AI model" refers to a function that creates specific instruction sentences based on extracted keywords, inputs these instruction sentences into an AI model, and generates natural-looking sentences.

[0077] "Means for displaying the generated text on a user interface" refers to a function for displaying the generated text data on an in-game chat or other display interface.

[0078] A "speech recognition engine" is software or algorithms used to analyze received voice data and convert it into text form.

[0079] A "generative AI engine" is an artificial intelligence model or algorithm used to generate natural-sounding sentences from given text data and keywords.

[0080] MODE FOR CARRYING OUT THE INVENTION

[0081] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0082] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device. The voice data received by the device is converted into a string of characters using the device's built-in voice recognition engine (e.g., voice recognition API). This voice recognition engine analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0083] The converted text data is then sent from the device to the server, which analyzes the received text data and uses a natural language processing (NLP) engine (e.g., spaCy or NLTK) to extract important keywords from the text. In this case, the keywords "enemy" and "left" are extracted.

[0084] Based on the extracted keywords, the server generates a prompt sentence. This prompt sentence is given to a generative AI engine (e.g., a generative AI model) to generate natural and appropriate sentences. For example, based on the extracted keywords "enemy" and "left," a sentence such as "The enemy is on your left" is generated.

[0085] The generated text is sent from the server to the device, which then displays it in the user interface, specifically the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0086] As a concrete example, consider a user playing an online first-person shooter (FPS) game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into text data and sends it to the server. The server extracts the keywords "enemy" and "left" from the text, and the generative AI model generates the sentence "enemy is on the left." Finally, the generated text is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0087] An example of a prompt sentence might be:

[0088] Keywords: enemy, left

[0089] Background information: Generate a short description based on information the user hears during the game.

[0090] This system provides an environment in which users can share information efficiently and accurately without interrupting gameplay.

[0091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0092] Step 1:

[0093] The user provides voice input. During the game, the user speaks simple commands such as "enemy, left" into the device's microphone. This is the input.

[0094] Step 2:

[0095] The device receives voice input and converts the speech to text. The input voice data is received by the device's microphone and then passed to a speech recognition engine (e.g., a speech recognition API). The speech recognition engine analyzes the voice waveform and outputs corresponding text data, such as "enemy, left."

[0096] Step 3:

[0097] The terminal sends the converted text data to the server. The converted text data is securely sent to the server using HTTPS. This sent text data becomes input and processing on the server begins.

[0098] Step 4:

[0099] The server parses the string and extracts keywords. The server passes the received text data to a natural language processing engine (e.g. spaCy or NLTK). This engine parses the text data and extracts important keywords such as "enemy" and "left". This is the output of the extracted keywords.

[0100] Step 5:

[0101] The server generates a prompt sentence based on the extracted keywords and sends it to the generative AI model. The server uses the extracted keywords to create a prompt sentence (e.g., "Keywords: enemy, left. Generate an appropriate warning sentence in the game environment") and sends this prompt sentence to the generative AI model (e.g., generative AI engine). This prompt sentence becomes the input.

[0102] Step 6:

[0103] The generative AI model generates an appropriate sentence. Based on the prompt, the generative AI model generates a natural sentence such as "The enemy is on your left." This is the output of the generated sentence.

[0104] Step 7:

[0105] The server sends the generated text to the terminal. The server returns the generated text to the terminal. This text becomes the input, and the terminal resumes processing.

[0106] Step 8:

[0107] The device displays the received text on the user interface. The device displays the received text in the in-game chat, allowing all team members of the user to receive the information quickly and accurately. This is the final output.

[0108] (Application example 1)

[0109] 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."

[0110] In existing virtual stores, users must enter product-related questions by text or select from limited options, making it difficult to communicate quickly and naturally. Furthermore, voice inquiries are often not processed in real time, limiting the shopping experience. This issue needs to be resolved.

[0111] 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.

[0112] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, and means for displaying the generated sentence, thereby enabling a user to ask a question about a product by voice and receive a quick and natural answer.

[0113] The "means for receiving voice input from the user" is a mechanism for obtaining voice uttered by the user as digital data using a microphone or its interface.

[0114] The "means for converting received speech input into text" refers to the process of converting the acquired speech data into a corresponding text format using a language model and a speech recognition engine.

[0115] "Means for extracting keywords from strings of characters" is a natural language processing technique for identifying and extracting specific important words and phrases from the converted text.

[0116] "Means for generating sentences based on extracted keywords" refers to the process of using the obtained keyword information to construct natural and meaningful sentences using a generation algorithm model.

[0117] "Means for displaying the generated text" refers to an interface or device that visually or audibly presents the generated text to the user.

[0118] A "natural language processing engine" is a software component used to analyze text data, understand its meaning, extract keywords, and more.

[0119] A "generative algorithm model" is a machine learning model for generating appropriate sentences based on given keyword information.

[0120] The "virtual store chat function" is a system that allows text-based communication between users and the store in an online virtual store.

[0121] "Voice function" refers to the technology and function for conveying generated text and other information to the user by voice.

[0122] The present invention relates to a system that allows a user to ask questions about products in a virtual store by voice input. A specific embodiment of this system will be described below.

[0123] First, the device used by the user is a smartphone, tablet, or computer, which is equipped with a microphone and allows the user to input voice data.

[0124] The device has a means for receiving user voice input. Once the voice input is received, the device uses a speech recognition engine (e.g., Google Speech-to-Text API or IBM Watson Speech to Text) to convert the speech into text. The voice data is converted into text data in real time.

[0125] This text data is then sent to a server, which analyzes it and extracts keywords using a natural language processing (NLP) engine. For example, a voice input such as "What size is this dress?" is converted into text data such as "What size is this dress?", and the keywords "dress" and "size" are extracted based on this.

[0126] Based on the extracted keywords, the server uses a generative algorithm model (such as OpenAI GPT-3) to generate appropriate sentences that respond to the user's question, such as "This dress is available in sizes S, M, and L."

[0127] The generated text is sent from the server to the device, which then displays or reads it to the user either through the virtual store's chat function or audibly using a text-to-speech (TTS) engine.

[0128] Examples:

[0129] For example, suppose a user asks a question in a virtual store, "What material is this shirt made of?" A microphone captures the voice, and the speech data is converted into text by a speech recognition engine. The text data, "What material is this shirt made of?" is sent to the server, and an NLP engine extracts the keywords "shirt" and "material." A generative algorithm model uses the prompt sentence to generate the sentence, "This shirt is 100% cotton." Finally, this sentence is displayed in the virtual store's chat function or read aloud by a TTS engine and provided to the user.

[0130] Example prompt sentence:

[0131] "Customer Question: What is this shirt made of? Generate an appropriate answer."

[0132] The system allows users to ask product questions using natural voice input and receive quick and accurate answers, significantly improving the shopping experience in virtual stores.

[0133] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0134] Step 1:

[0135] Users speak their questions into a microphone on their virtual store device (smartphone, tablet, or computer), and this voice input is captured through the device's microphone.

[0136] Input: User's voice input (e.g., "What material is this shirt made of?")

[0137] Output: Captured audio data

[0138] Step 2:

[0139] The device sends the captured voice data to a speech recognition engine (e.g., Google Speech-to-Text API) to convert the voice data into text. The engine analyzes the voice waveform and generates corresponding text data.

[0140] Input: Audio data

[0141] Output: Text data (e.g., "What material is this shirt made of?")

[0142] Step 3:

[0143] The device sends the generated text data to the server, which then analyzes the text data using a natural language processing (NLP) engine to extract keywords.

[0144] Input: Text data

[0145] Output: Extracted keywords (e.g. "shirt", "material")

[0146] Step 4:

[0147] The server sends a prompt based on the extracted keywords to a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer. The generative AI model creates logical and natural sentences based on the given keywords and prompt.

[0148] Input: Extracted keywords, prompt sentence

[0149] Output: Generated sentence (e.g. "This shirt is 100% cotton")

[0150] Step 5:

[0151] The generated text is sent from the server to the terminal, which then presents it to the user via the chat function of the virtual store or a text-to-speech (TTS) engine.

[0152] Input: Generated sentence

[0153] Output: Display or audio response to user (e.g., displayed in chat or played as "This shirt is 100% cotton")

[0154] This process allows users to ask product questions using voice input and receive quick, natural answers in real time, significantly improving the shopping experience in virtual stores.

[0155] 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.

[0156] The present invention provides a system that allows users to efficiently share information through voice input in an online action game and provides information by recognizing emotions. Specific embodiments of this system are described below.

[0157] First, the user speaks into the device's microphone. The user gives a specific command, such as "enemy, left." This voice input is received by the device and converted into a string of characters by the device's voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, such as "enemy, left." This string of characters is then sent from the device to the server.

[0158] The server analyzes the received text data and extracts keywords such as "enemy" and "left" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if the user says "enemy, left" in a tense voice, the emotion engine will recognize the emotion as "tension."

[0159] The keywords and the recognized emotions are input into a generative AI model, which generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "enemy" and "left" and the emotion "tension," it generates a sentence such as "I'm nervous, the enemy is on my left."

[0160] The generated text is sent from the server to the device, where it is displayed in the in-game chat. Furthermore, by simultaneously displaying emotional information, the user's intentions and state are more accurately conveyed to team members.

[0161] As a concrete example, consider a user playing an online FPS game. The user spots an enemy and says "enemy, left" into the microphone in a tense voice. This utterance is converted into text data "enemy, left" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, enemy is on the left." Finally, this sentence is displayed in the device's in-game chat, accompanied by emotional information, so all team members can receive this important information along with the speaker's emotions.

[0162] Through the above process, the system provides an environment in which users can share information more efficiently and accurately, and communicate their intentions and status to other players in the game.

[0163] The processing flow will be explained below.

[0164] Step 1:

[0165] The user speaks into the microphone of the device.

[0166] Action: The user verbally utters the specific command "enemy, left."

[0167] Step 2:

[0168] The device receives voice input and converts the voice into text using a voice recognition system.

[0169] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0170] Step 3:

[0171] The terminal transmits the generated text data to the server.

[0172] Operation: The device sends a request to send text data to the server over the network.

[0173] Step 4:

[0174] The server analyzes the received text data and extracts keywords from the string.

[0175] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0176] Step 5:

[0177] The server uses an emotion engine to recognize the user's emotion from the voice data.

[0178] How it works: The server's emotion engine analyzes the voice data and recognizes emotions such as "tension" and "excitement."

[0179] Step 6:

[0180] The server sends input data to the generative AI model based on the extracted keywords and recognized emotions.

[0181] How it works: The server formats the keywords "enemy" and "left" and the emotional information "tension" and sends a request to the API of the generative AI model.

[0182] Step 7:

[0183] Generative AI generates appropriate sentences.

[0184] How it works: The generative AI model generates the sentence "I'm nervous, the enemy is on my left" based on the keywords and emotional information sent.

[0185] Step 8:

[0186] The server sends the generated text to the terminal.

[0187] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0188] Step 9:

[0189] The text and emotional information received by the device will be displayed in the in-game chat.

[0190] What it does: The game client on your device displays the received text and emotion information in the chat window, allowing team members to view this information.

[0191] This series of processing steps allows users to notify team members of their status and share information efficiently and accurately.

[0192] Example 2

[0193] 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."

[0194] In online action games, there is a lack of efficient and accurate means for users to share information through voice input. Furthermore, information transmission does not take into account the user's emotional state, resulting in a problem of in-game communication not proceeding smoothly.

[0195] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for recognizing emotions based on the extracted keywords, means for generating natural sentences based on the emotions and keywords, and means for displaying the generated sentences in an in-game chat. This allows users to share information efficiently and accurately through voice input, and by adding emotional information, smooth communication within the game is possible.

[0196] A "user" is someone who uses the system to play online games.

[0197] "Means for receiving voice input" refers to a microphone and corresponding hardware and software for receiving the user's voice as digital data.

[0198] A "means for converting speech to text" refers to a system or module for converting received speech data into text data using a speech recognition engine.

[0199] "Keyword extraction methods" refers to natural language processing (NLP) techniques for identifying important words and phrases from text data.

[0200] "Means for recognizing emotions" refers to algorithms or emotion engines that analyze the features of a user's voice and estimate emotions such as tension, joy, or anger.

[0201] The "means for generating natural-sentence text" refers to a generative AI model for generating appropriate text based on extracted keywords and emotional information.

[0202] The "means for displaying in the in-game chat" refers to a UI module for displaying the generated text and emotion information in the chat window of the game application.

[0203] The present invention provides a system that allows users to efficiently share information through voice input in an online game and provides information by recognizing emotions. A specific embodiment of this system will be described below.

[0204] System Overview

[0205] The entire system consists of the device (terminal) on which the user plays the game, the server that analyzes and processes the audio, and the game application that displays the generated information.

[0206] 1. Receiving voice input

[0207] While playing an online game, a user speaks commands into a microphone, for example, "enemy, left."

[0208] 2. Converting voice data to text

[0209] The device's voice recognition system uses the Google Speech-to-Text API or similar to convert the user's voice into digital data (a string of characters), which may take the form of "enemy, left."

[0210] 3. Sending text data to the server

[0211] The device then sends the converted text data to the server over the network, using a secure protocol such as HTTPS.

[0212] 4. Keyword extraction

[0213] The server analyzes the received text data and uses NLP (natural language processing) technology to extract the keywords "enemy" and "left."

[0214] 5. Emotion recognition

[0215] The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features such as voice data and recognizes the user's emotion (e.g., nervousness).

[0216] 6. Natural language generation

[0217] The extracted keywords and recognized emotions are input to a generative AI model (e.g., OpenAI GPT-3) on the server, using the following prompt:

[0218] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[0219] The generative AI model generates natural sentences such as "I'm nervous, the enemy is on my left."

[0220] 7. Sending the generated text to the terminal

[0221] The server sends the generated text to the device, again using a secure protocol such as HTTPS for communication.

[0222] 8. In-game chat display

[0223] The device displays the received text and emotional information on the in-game chat screen, thereby communicating the user's spoken information and emotional state to other players.

[0224] Specific examples

[0225] Below is a concrete example of using this system. Suppose a user is playing an online FPS game. The user spots an enemy and says "enemy, left" in a nervous voice. This voice is received by the device's microphone, converted into text data "enemy, left," and sent to the server. The server extracts the keywords "enemy" and "left," and the emotion engine recognizes "tension." The generative AI model generates the sentence "I'm nervous, the enemy is on my left," which is then displayed in the in-game chat. This allows all team members to instantly understand the enemy's location and the user's emotional state.

[0226] This process allows the system to efficiently and accurately share information through voice input, and by adding emotional information, it achieves smooth communication within the game.

[0227] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0228] Step 1:

[0229] While playing an online game, a user says into a microphone, "Enemy, left."

[0230] Specific operation: The microphone collects the user's voice waveform, converts it into digital data, and sends it to the terminal.

[0231] Input and Output: The input is the user's voice data, and the output is the digital voice data.

[0232] Step 2:

[0233] The terminal's voice recognition system (voice recognition engine) is used to convert the received voice data into text data.

[0234] Specific operation: Calls a speech recognition engine such as the Google Speech-to-Text API and generates a string from the audio waveform data.

[0235] Input and output: The input is digital voice data, and the output is text data such as "enemy, left."

[0236] Step 3:

[0237] The terminal transmits the generated text data to the server via the network.

[0238] Specific operation: The terminal's network module divides the text data into packets and sends them to the server using the HTTPS protocol.

[0239] Input and Output: The input is the text data "enemy, left", and the output is the text data sent to the server.

[0240] Step 4:

[0241] The server analyzes the received text data and extracts keywords using natural language processing (NLP) technology.

[0242] Specific operation: The server's NLP module performs morphological analysis of the string and identifies the important keywords "enemy" and "left."

[0243] Input and Output: The input is the text data arriving at the server, and the output is the extracted keywords "enemy" and "left."

[0244] Step 5:

[0245] The server uses an emotion engine to recognize emotions from the user's voice.

[0246] Specific operation: The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features (pitch, tone, speed, etc.) from the voice data and estimates the emotion (e.g., "tension").

[0247] Input and Output: The input is the voice data, and the output is the recognized emotion "tension."

[0248] Step 6:

[0249] The server generates natural-sounding sentences using a generative AI model (e.g., OpenAI GPT-3) based on the extracted keywords and recognized emotions.

[0250] Specific operation: The following prompt sentence is input into the generative AI model to generate a sentence.

[0251] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[0252] Input and output: The input is the keywords "enemy" and "left" and the emotion "tension", and the output is the generated sentence "I'm tense, the enemy is on my left".

[0253] Step 7:

[0254] The server transmits the generated text to the terminal via the network.

[0255] Specific operation: The server's network module divides the generated text into packets and sends them to the terminal using the HTTPS protocol.

[0256] Input and output: The input is the generated sentence "I'm nervous, the enemy is on my left", and the output is the text data sent to the terminal.

[0257] Step 8:

[0258] The device displays the received text and emotional information in the in-game chat.

[0259] Specific behavior: The device's game application displays the text "Tension, enemy on the left" and an emoticon in the chat window.

[0260] Input and Output: Input is received text data and emotion information, output is information displayed on the in-game chat screen.

[0261] (Application example 2)

[0262] 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."

[0263] In the past, work management and problem reporting in factories were mainly done manually, which not only placed a heavy burden on workers but also created a high risk of delays in information transmission and misunderstandings.In addition, there was no means of communication that took into account the emotions and tension of workers, which led to problems such as reduced work efficiency and delayed response to problems.

[0264] The identification process by the identification 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 receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, means for displaying the generated sentence on an output device, and means for recognizing the user's emotions and providing information. This makes it possible to share information efficiently and accurately, reducing the burden on workers and enabling quick problem resolution.

[0265] "User" refers to a person who uses the system.

[0266] A "means for receiving voice input" is a device or software function for capturing voice information from a user.

[0267] "Means for converting into character string" refers to a process for converting received voice information into text data.

[0268] "Keyword extraction means" is a technique for extracting important words and phrases from text data.

[0269] "Means for generating sentences" refers to a technology that creates natural sentences based on extracted keywords.

[0270] "Means for displaying on an output device" refers to a function for visually presenting the generated text to the user.

[0271] "Means for recognizing emotions and providing information" is a technology that analyzes emotions from the user's voice and generates an appropriate response based on that information.

[0272] "Production system" refers to the entire system for managing and transmitting information about the production process.

[0273] The present invention is a system that enables factory workers to efficiently share information through voice input and also recognizes emotions to provide information. Specific embodiments of this system will be described below.

[0274] First, the user speaks into the microphone of the device. For example, they might say, "Line 1, abnormal." This voice input is received by the device and converted into a string of characters by the voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, for example, "Line 1, abnormal." This string data is then sent from the device to the server.

[0275] The server analyzes the received text data and extracts keywords such as "Line 1" and "Abnormal" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if a user says "Line 1, abnormal" in a tense voice, the emotion engine will recognize the emotion as "tension."

[0276] The keywords and the recognized emotions are input into a generative AI model, which then generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "Line 1" and "Abnormal" and the emotion "Tense," it generates a sentence such as "I'm nervous, there's an abnormality in Line 1."

[0277] The generated sentences are sent from the server to the terminals, which then display them on their output devices, allowing all workers to receive this important information along with the speaker's emotions.

[0278] As a concrete example, let's consider a scenario in a factory. A user discovers an abnormality on the production line and says "Line 1, abnormal" in a tense voice into the microphone. This statement is converted into text data "Line 1, abnormal" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, there's an abnormality on Line 1." Finally, this sentence is displayed on the terminal's output device, accompanied by emotional information, allowing all workers to share this information quickly and accurately.

[0279] An example of a prompt is:

[0280] "Line 1 abnormal, emotion is tension."

[0281] This allows the system to provide an environment where users can efficiently and accurately share information and communicate their intentions and status to other workers in the work environment.

[0282] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0283] Step 1:

[0284] The user inputs voice into the microphone. This input is a specific instruction, such as "Line 1, abnormal." The input data is collected by the terminal as a voice signal.

[0285] Step 2:

[0286] The device converts the collected voice signal into text data using a voice recognition system (e.g., the SpeechRecognition library). The input here is the voice signal, and the output is text data (e.g., "Line 1, abnormal"). The device temporarily stores this text data.

[0287] Step 3:

[0288] The terminal sends the converted text data to the server. The input here is the text data generated in step 2, and the output is the transfer to the server. The text data is sent to the server via the network.

[0289] Step 4:

[0290] The server analyzes the received text data and extracts keywords using a keyword extraction module (e.g., a natural language processing engine). The input here is the text data, and the output is the extracted keywords (e.g., "Line 1" and "Abnormal"). The server stores the keywords as variables.

[0291] Step 5:

[0292] The server recognizes emotions from the user's voice using an emotion engine (e.g., a transformers pipeline for emotion analysis). The input here is the audio signal or text data obtained in step 2, and the output is the recognized emotion (e.g., "tension"). The server stores the emotion information as a variable.

[0293] Step 6:

[0294] The server inputs the extracted keywords and recognized emotions into a generative AI model (e.g., GPT-2) to generate natural-sounding sentences. The input here is keywords and emotion information, and the output is a generated sentence (e.g., "I'm nervous, there's something wrong with line 1"). The generative AI model uses "Line 1 is abnormal, the emotion is nervous" as the prompt sentence.

[0295] Step 7:

[0296] The generated text is sent from the server to the terminal. The input here is the generated text, and the output is transfer to the terminal. The text data is sent to the terminal via the network.

[0297] Step 8:

[0298] The terminal displays the received text on an output device (e.g., a monitor or speaker). Here, the input is the generated text, and the output is visual or audio feedback to the user. Specific actions include displaying the text on a monitor or playing it aloud through a speaker.

[0299] 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.

[0300] 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.

[0301] 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.

[0302] [Second embodiment]

[0303] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0304] 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.

[0305] 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).

[0306] 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.

[0307] 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.

[0308] 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).

[0309] 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.

[0310] 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.

[0311] 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.

[0312] 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.

[0313] 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.

[0314] 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."

[0315] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0316] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device.

[0317] The device then converts the received voice input into text. This conversion is performed using the device's built-in voice recognition system. The voice recognition system analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0318] The converted string is sent from the device to the server. The server analyzes the received text data and extracts keywords from the string. Specifically, it uses natural language processing (NLP) algorithms to detect important words and phrases. In this case, the keywords "enemy" and "left" are extracted.

[0319] Once the keywords are extracted, the server uses a generative AI model to generate sentences based on these keywords. The generative AI model generates natural and appropriate sentences based on the given keywords and background information. For example, sentence generation based on the extracted keywords "enemy" and "left" would generate a sentence such as "The enemy is on your left."

[0320] The generated text is sent from the server to the device, which then displays it in the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0321] As a concrete example, consider a user playing an online FPS game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into a string and sends it to the server. The server extracts keywords from the string, and a generative AI model generates the sentence "enemy on the left." Finally, the generated sentence is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0322] As a result, this system provides an environment in which users can share information efficiently and clearly without letting go of their controllers.

[0323] The processing flow will be explained below.

[0324] Step 1:

[0325] The user speaks into the microphone of the device.

[0326] Action: The user verbally utters the specific command "enemy, left."

[0327] Step 2:

[0328] The device receives voice input and converts the voice into text using a voice recognition system.

[0329] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0330] Step 3:

[0331] The terminal transmits the generated text data to the server.

[0332] Operation: The device sends a request to send text data to the server over the network.

[0333] Step 4:

[0334] The server analyzes the received text data and extracts keywords from the string.

[0335] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0336] Step 5:

[0337] The server sends input data to the generative AI model based on the extracted keywords.

[0338] How it works: The server formats the keywords and necessary contextual information and sends a request to the generation AI's API.

[0339] Step 6:

[0340] Generative AI generates appropriate sentences.

[0341] How it works: The generative AI model generates the sentence "The enemy is on your left" based on the keywords and context information provided.

[0342] Step 7:

[0343] The server sends the generated text to the terminal.

[0344] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0345] Step 8:

[0346] The text received by the device will be displayed in the in-game chat.

[0347] What it does: The game client on the device displays the received text in a chat window, allowing the user's teammates to view this information.

[0348] This series of processing steps allows users to share information efficiently and smoothly progress through game play.

[0349] Example 1

[0350] 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."

[0351] In online action games, it is difficult for users to share information with team members quickly and accurately without interrupting the game. In particular, there are problems with delays and recognition errors in the process of converting voice input into text and generating appropriate sentences.

[0352] 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.

[0353] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a prompt sentence based on the extracted keywords and generating a sentence using a generative AI model, and means for displaying the generated sentence on a user interface, thereby enabling a user to quickly and accurately share information with team members without interrupting operations.

[0354] The "means for receiving voice input" is a function for receiving voice uttered by the user via the device's microphone or the like.

[0355] The "means for converting voice input into text" is a function that analyzes received voice data and converts the content into a corresponding text format.

[0356] "Means for extracting keywords from character strings" is a function that selects important words and phrases from the converted text data.

[0357] "Means for generating prompt sentences and generating sentences using a generative AI model" refers to a function that creates specific instruction sentences based on extracted keywords, inputs these instruction sentences into an AI model, and generates natural-looking sentences.

[0358] "Means for displaying the generated text on a user interface" refers to a function for displaying the generated text data on an in-game chat or other display interface.

[0359] A "speech recognition engine" is software or algorithms used to analyze received voice data and convert it into text form.

[0360] A "generative AI engine" is an artificial intelligence model or algorithm used to generate natural-sounding sentences from given text data and keywords.

[0361] MODE FOR CARRYING OUT THE INVENTION

[0362] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0363] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device. The voice data received by the device is converted into a string of characters using the device's built-in voice recognition engine (e.g., voice recognition API). This voice recognition engine analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0364] The converted text data is then sent from the device to the server, which analyzes the received text data and uses a natural language processing (NLP) engine (e.g., spaCy or NLTK) to extract important keywords from the text. In this case, the keywords "enemy" and "left" are extracted.

[0365] Based on the extracted keywords, the server generates a prompt sentence. This prompt sentence is given to a generative AI engine (e.g., a generative AI model) to generate natural and appropriate sentences. For example, based on the extracted keywords "enemy" and "left," a sentence such as "The enemy is on your left" is generated.

[0366] The generated text is sent from the server to the device, which then displays it in the user interface, specifically the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0367] As a concrete example, consider a user playing an online first-person shooter (FPS) game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into text data and sends it to the server. The server extracts the keywords "enemy" and "left" from the text, and the generative AI model generates the sentence "enemy is on the left." Finally, the generated text is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0368] An example of a prompt sentence might be:

[0369] Keywords: enemy, left

[0370] Background information: Generate a short description based on information the user hears during the game.

[0371] This system provides an environment in which users can share information efficiently and accurately without interrupting gameplay.

[0372] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0373] Step 1:

[0374] The user provides voice input. During the game, the user speaks simple commands such as "enemy, left" into the device's microphone. This is the input.

[0375] Step 2:

[0376] The device receives voice input and converts the speech to text. The input voice data is received by the device's microphone and then passed to a speech recognition engine (e.g., a speech recognition API). The speech recognition engine analyzes the voice waveform and outputs corresponding text data, such as "enemy, left."

[0377] Step 3:

[0378] The terminal sends the converted text data to the server. The converted text data is securely sent to the server using HTTPS. This sent text data becomes input and processing on the server begins.

[0379] Step 4:

[0380] The server parses the string and extracts keywords. The server passes the received text data to a natural language processing engine (e.g. spaCy or NLTK). This engine parses the text data and extracts important keywords such as "enemy" and "left". This is the output of the extracted keywords.

[0381] Step 5:

[0382] The server generates a prompt sentence based on the extracted keywords and sends it to the generative AI model. The server uses the extracted keywords to create a prompt sentence (e.g., "Keywords: enemy, left. Generate an appropriate warning sentence in the game environment") and sends this prompt sentence to the generative AI model (e.g., generative AI engine). This prompt sentence becomes the input.

[0383] Step 6:

[0384] The generative AI model generates an appropriate sentence. Based on the prompt, the generative AI model generates a natural sentence such as "The enemy is on your left." This is the output of the generated sentence.

[0385] Step 7:

[0386] The server sends the generated text to the terminal. The server returns the generated text to the terminal. This text becomes the input, and the terminal resumes processing.

[0387] Step 8:

[0388] The device displays the received text on the user interface. The device displays the received text in the in-game chat, allowing all team members of the user to receive the information quickly and accurately. This is the final output.

[0389] (Application example 1)

[0390] 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."

[0391] In existing virtual stores, users must enter product-related questions by text or select from limited options, making it difficult to communicate quickly and naturally. Furthermore, voice inquiries are often not processed in real time, limiting the shopping experience. This issue needs to be resolved.

[0392] 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.

[0393] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, and means for displaying the generated sentence, thereby enabling a user to ask a question about a product by voice and receive a quick and natural answer.

[0394] The "means for receiving voice input from the user" is a mechanism for obtaining voice uttered by the user as digital data using a microphone or its interface.

[0395] The "means for converting received speech input into text" refers to the process of converting the acquired speech data into a corresponding text format using a language model and a speech recognition engine.

[0396] "Means for extracting keywords from strings of characters" is a natural language processing technique for identifying and extracting specific important words and phrases from the converted text.

[0397] "Means for generating sentences based on extracted keywords" refers to the process of using the obtained keyword information to construct natural and meaningful sentences using a generation algorithm model.

[0398] "Means for displaying the generated text" refers to an interface or device that visually or audibly presents the generated text to the user.

[0399] A "natural language processing engine" is a software component used to analyze text data, understand its meaning, extract keywords, and more.

[0400] A "generative algorithm model" is a machine learning model for generating appropriate sentences based on given keyword information.

[0401] The "virtual store chat function" is a system that allows text-based communication between users and the store in an online virtual store.

[0402] "Voice function" refers to the technology and function for conveying generated text and other information to the user by voice.

[0403] The present invention relates to a system that allows a user to ask questions about products in a virtual store by voice input. A specific embodiment of this system will be described below.

[0404] First, the device used by the user is a smartphone, tablet, or computer, which is equipped with a microphone and allows the user to input voice data.

[0405] The device has a means for receiving user voice input. Once the voice input is received, the device uses a speech recognition engine (e.g., Google Speech-to-Text API or IBM Watson Speech to Text) to convert the speech into text. The voice data is converted into text data in real time.

[0406] This text data is then sent to a server, which analyzes it and extracts keywords using a natural language processing (NLP) engine. For example, a voice input such as "What size is this dress?" is converted into text data such as "What size is this dress?", and the keywords "dress" and "size" are extracted based on this.

[0407] Based on the extracted keywords, the server uses a generative algorithm model (such as OpenAI GPT-3) to generate appropriate sentences that respond to the user's question, such as "This dress is available in sizes S, M, and L."

[0408] The generated text is sent from the server to the device, which then displays or reads it to the user either through the virtual store's chat function or audibly using a text-to-speech (TTS) engine.

[0409] Examples:

[0410] For example, suppose a user asks a question in a virtual store, "What material is this shirt made of?" A microphone captures the voice, and the speech data is converted into text by a speech recognition engine. The text data, "What material is this shirt made of?" is sent to the server, and an NLP engine extracts the keywords "shirt" and "material." A generative algorithm model uses the prompt sentence to generate the sentence, "This shirt is 100% cotton." Finally, this sentence is displayed in the virtual store's chat function or read aloud by a TTS engine and provided to the user.

[0411] Example prompt sentence:

[0412] "Customer Question: What is this shirt made of? Generate an appropriate answer."

[0413] The system allows users to ask product questions using natural voice input and receive quick and accurate answers, significantly improving the shopping experience in virtual stores.

[0414] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0415] Step 1:

[0416] Users speak their questions into a microphone on their virtual store device (smartphone, tablet, or computer), and this voice input is captured through the device's microphone.

[0417] Input: User's voice input (e.g., "What material is this shirt made of?")

[0418] Output: Captured audio data

[0419] Step 2:

[0420] The device sends the captured voice data to a speech recognition engine (e.g., Google Speech-to-Text API) to convert the voice data into text. The engine analyzes the voice waveform and generates corresponding text data.

[0421] Input: Audio data

[0422] Output: Text data (e.g., "What material is this shirt made of?")

[0423] Step 3:

[0424] The device sends the generated text data to the server, which then analyzes the text data using a natural language processing (NLP) engine to extract keywords.

[0425] Input: Text data

[0426] Output: Extracted keywords (e.g. "shirt", "material")

[0427] Step 4:

[0428] The server sends a prompt based on the extracted keywords to a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer. The generative AI model creates logical and natural sentences based on the given keywords and prompt.

[0429] Input: Extracted keywords, prompt sentence

[0430] Output: Generated sentence (e.g. "This shirt is 100% cotton")

[0431] Step 5:

[0432] The generated text is sent from the server to the terminal, which then presents it to the user via the chat function of the virtual store or a text-to-speech (TTS) engine.

[0433] Input: Generated sentence

[0434] Output: Display or audio response to user (e.g., displayed in chat or played as "This shirt is 100% cotton")

[0435] This process allows users to ask product questions using voice input and receive quick, natural answers in real time, significantly improving the shopping experience in virtual stores.

[0436] 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.

[0437] The present invention provides a system that allows users to efficiently share information through voice input in an online action game and provides information by recognizing emotions. Specific embodiments of this system are described below.

[0438] First, the user speaks into the device's microphone. The user gives a specific command, such as "enemy, left." This voice input is received by the device and converted into a string of characters by the device's voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, such as "enemy, left." This string of characters is then sent from the device to the server.

[0439] The server analyzes the received text data and extracts keywords such as "enemy" and "left" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if the user says "enemy, left" in a tense voice, the emotion engine will recognize the emotion as "tension."

[0440] The keywords and the recognized emotions are input into a generative AI model, which generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "enemy" and "left" and the emotion "tension," it generates a sentence such as "I'm nervous, the enemy is on my left."

[0441] The generated text is sent from the server to the device, where it is displayed in the in-game chat. Furthermore, by simultaneously displaying emotional information, the user's intentions and state are more accurately conveyed to team members.

[0442] As a concrete example, consider a user playing an online FPS game. The user spots an enemy and says "enemy, left" into the microphone in a tense voice. This utterance is converted into text data "enemy, left" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, enemy is on the left." Finally, this sentence is displayed in the device's in-game chat, accompanied by emotional information, so all team members can receive this important information along with the speaker's emotions.

[0443] Through the above process, the system provides an environment in which users can share information more efficiently and accurately, and communicate their intentions and status to other players in the game.

[0444] The processing flow will be explained below.

[0445] Step 1:

[0446] The user speaks into the microphone of the device.

[0447] Action: The user verbally utters the specific command "enemy, left."

[0448] Step 2:

[0449] The device receives voice input and converts the voice into text using a voice recognition system.

[0450] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0451] Step 3:

[0452] The terminal transmits the generated text data to the server.

[0453] Operation: The device sends a request to send text data to the server over the network.

[0454] Step 4:

[0455] The server analyzes the received text data and extracts keywords from the string.

[0456] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0457] Step 5:

[0458] The server uses an emotion engine to recognize the user's emotion from the voice data.

[0459] How it works: The server's emotion engine analyzes the voice data and recognizes emotions such as "tension" and "excitement."

[0460] Step 6:

[0461] The server sends input data to the generative AI model based on the extracted keywords and recognized emotions.

[0462] How it works: The server formats the keywords "enemy" and "left" and the emotional information "tension" and sends a request to the API of the generative AI model.

[0463] Step 7:

[0464] Generative AI generates appropriate sentences.

[0465] How it works: The generative AI model generates the sentence "I'm nervous, the enemy is on my left" based on the keywords and emotional information sent.

[0466] Step 8:

[0467] The server sends the generated text to the terminal.

[0468] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0469] Step 9:

[0470] The text and emotional information received by the device will be displayed in the in-game chat.

[0471] What it does: The game client on your device displays the received text and emotion information in the chat window, allowing team members to view this information.

[0472] This series of processing steps allows users to notify team members of their status and share information efficiently and accurately.

[0473] Example 2

[0474] 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."

[0475] In online action games, there is a lack of efficient and accurate means for users to share information through voice input. Furthermore, information transmission does not take into account the user's emotional state, resulting in a problem of in-game communication not proceeding smoothly.

[0476] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for recognizing emotions based on the extracted keywords, means for generating natural sentences based on the emotions and keywords, and means for displaying the generated sentences in an in-game chat. This allows users to share information efficiently and accurately through voice input, and by adding emotional information, smooth communication within the game is possible.

[0477] A "user" is someone who uses the system to play online games.

[0478] "Means for receiving voice input" refers to a microphone and corresponding hardware and software for receiving the user's voice as digital data.

[0479] A "means for converting speech to text" refers to a system or module for converting received speech data into text data using a speech recognition engine.

[0480] "Keyword extraction methods" refers to natural language processing (NLP) techniques for identifying important words and phrases from text data.

[0481] "Means for recognizing emotions" refers to algorithms or emotion engines that analyze the features of a user's voice and estimate emotions such as tension, joy, or anger.

[0482] The "means for generating natural-sentence text" refers to a generative AI model for generating appropriate text based on extracted keywords and emotional information.

[0483] The "means for displaying in the in-game chat" refers to a UI module for displaying the generated text and emotion information in the chat window of the game application.

[0484] The present invention provides a system that allows users to efficiently share information through voice input in an online game and provides information by recognizing emotions. A specific embodiment of this system will be described below.

[0485] System Overview

[0486] The entire system consists of the device (terminal) on which the user plays the game, the server that analyzes and processes the audio, and the game application that displays the generated information.

[0487] 1. Receiving voice input

[0488] While playing an online game, a user speaks commands into a microphone, for example, "enemy, left."

[0489] 2. Converting voice data to text

[0490] The device's voice recognition system uses the Google Speech-to-Text API or similar to convert the user's voice into digital data (a string of characters), which may take the form of "enemy, left."

[0491] 3. Sending text data to the server

[0492] The device then sends the converted text data to the server over the network, using a secure protocol such as HTTPS.

[0493] 4. Keyword extraction

[0494] The server analyzes the received text data and uses NLP (natural language processing) technology to extract the keywords "enemy" and "left."

[0495] 5. Emotion recognition

[0496] The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features such as voice data and recognizes the user's emotion (e.g., nervousness).

[0497] 6. Natural language generation

[0498] The extracted keywords and recognized emotions are input to a generative AI model (e.g., OpenAI GPT-3) on the server, using the following prompt:

[0499] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[0500] The generative AI model generates natural sentences such as "I'm nervous, the enemy is on my left."

[0501] 7. Sending the generated text to the terminal

[0502] The server sends the generated text to the device, again using a secure protocol such as HTTPS for communication.

[0503] 8. In-game chat display

[0504] The device displays the received text and emotional information on the in-game chat screen, thereby communicating the user's spoken information and emotional state to other players.

[0505] Specific examples

[0506] Below is a concrete example of using this system. Suppose a user is playing an online FPS game. The user spots an enemy and says "enemy, left" in a nervous voice. This voice is received by the device's microphone, converted into text data "enemy, left," and sent to the server. The server extracts the keywords "enemy" and "left," and the emotion engine recognizes "tension." The generative AI model generates the sentence "I'm nervous, the enemy is on my left," which is then displayed in the in-game chat. This allows all team members to instantly understand the enemy's location and the user's emotional state.

[0507] This process allows the system to efficiently and accurately share information through voice input, and by adding emotional information, it achieves smooth communication within the game.

[0508] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0509] Step 1:

[0510] While playing an online game, a user says into a microphone, "Enemy, left."

[0511] Specific operation: The microphone collects the user's voice waveform, converts it into digital data, and sends it to the terminal.

[0512] Input and Output: The input is the user's voice data, and the output is the digital voice data.

[0513] Step 2:

[0514] The terminal's voice recognition system (voice recognition engine) is used to convert the received voice data into text data.

[0515] Specific operation: Calls a speech recognition engine such as the Google Speech-to-Text API and generates a string from the audio waveform data.

[0516] Input and output: The input is digital voice data, and the output is text data such as "enemy, left."

[0517] Step 3:

[0518] The terminal transmits the generated text data to the server via the network.

[0519] Specific operation: The terminal's network module divides the text data into packets and sends them to the server using the HTTPS protocol.

[0520] Input and Output: The input is the text data "enemy, left", and the output is the text data sent to the server.

[0521] Step 4:

[0522] The server analyzes the received text data and extracts keywords using natural language processing (NLP) technology.

[0523] Specific operation: The server's NLP module performs morphological analysis of the string and identifies the important keywords "enemy" and "left."

[0524] Input and Output: The input is the text data arriving at the server, and the output is the extracted keywords "enemy" and "left."

[0525] Step 5:

[0526] The server uses an emotion engine to recognize emotions from the user's voice.

[0527] Specific operation: The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features (pitch, tone, speed, etc.) from the voice data and estimates the emotion (e.g., "tension").

[0528] Input and Output: The input is the voice data, and the output is the recognized emotion "tension."

[0529] Step 6:

[0530] The server generates natural-sounding sentences using a generative AI model (e.g., OpenAI GPT-3) based on the extracted keywords and recognized emotions.

[0531] Specific operation: The following prompt sentence is input into the generative AI model to generate a sentence.

[0532] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[0533] Input and output: The input is the keywords "enemy" and "left" and the emotion "tension", and the output is the generated sentence "I'm tense, the enemy is on my left".

[0534] Step 7:

[0535] The server transmits the generated text to the terminal via the network.

[0536] Specific operation: The server's network module divides the generated text into packets and sends them to the terminal using the HTTPS protocol.

[0537] Input and output: The input is the generated sentence "I'm nervous, the enemy is on my left", and the output is the text data sent to the terminal.

[0538] Step 8:

[0539] The device displays the received text and emotional information in the in-game chat.

[0540] Specific behavior: The device's game application displays the text "Tension, enemy on the left" and an emoticon in the chat window.

[0541] Input and Output: Input is received text data and emotion information, output is information displayed on the in-game chat screen.

[0542] (Application example 2)

[0543] 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."

[0544] In the past, work management and problem reporting in factories were mainly done manually, which not only placed a heavy burden on workers but also created a high risk of delays in information transmission and misunderstandings.In addition, there was no means of communication that took into account the emotions and tension of workers, which led to problems such as reduced work efficiency and delayed response to problems.

[0545] The identification process by the identification 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 receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, means for displaying the generated sentence on an output device, and means for recognizing the user's emotions and providing information. This makes it possible to share information efficiently and accurately, reducing the burden on workers and enabling quick problem resolution.

[0546] "User" refers to a person who uses the system.

[0547] A "means for receiving voice input" is a device or software function for capturing voice information from a user.

[0548] "Means for converting into character string" refers to a process for converting received voice information into text data.

[0549] "Keyword extraction means" is a technique for extracting important words and phrases from text data.

[0550] "Means for generating sentences" refers to a technology that creates natural sentences based on extracted keywords.

[0551] "Means for displaying on an output device" refers to a function for visually presenting the generated text to the user.

[0552] "Means for recognizing emotions and providing information" is a technology that analyzes emotions from the user's voice and generates an appropriate response based on that information.

[0553] "Production system" refers to the entire system for managing and transmitting information about the production process.

[0554] The present invention is a system that enables factory workers to efficiently share information through voice input and also recognizes emotions to provide information. Specific embodiments of this system will be described below.

[0555] First, the user speaks into the microphone of the device. For example, they might say, "Line 1, abnormal." This voice input is received by the device and converted into a string of characters by the voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, for example, "Line 1, abnormal." This string data is then sent from the device to the server.

[0556] The server analyzes the received text data and extracts keywords such as "Line 1" and "Abnormal" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if a user says "Line 1, abnormal" in a tense voice, the emotion engine will recognize the emotion as "tension."

[0557] The keywords and the recognized emotions are input into a generative AI model, which then generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "Line 1" and "Abnormal" and the emotion "Tense," it generates a sentence such as "I'm nervous, there's an abnormality in Line 1."

[0558] The generated sentences are sent from the server to the terminals, which then display them on their output devices, allowing all workers to receive this important information along with the speaker's emotions.

[0559] As a concrete example, let's consider a scenario in a factory. A user discovers an abnormality on the production line and says "Line 1, abnormal" in a tense voice into the microphone. This statement is converted into text data "Line 1, abnormal" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, there's an abnormality on Line 1." Finally, this sentence is displayed on the terminal's output device, accompanied by emotional information, allowing all workers to share this information quickly and accurately.

[0560] An example of a prompt is:

[0561] "Line 1 abnormal, emotion is tension."

[0562] This allows the system to provide an environment where users can efficiently and accurately share information and communicate their intentions and status to other workers in the work environment.

[0563] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0564] Step 1:

[0565] The user inputs voice into the microphone. This input is a specific instruction, such as "Line 1, abnormal." The input data is collected by the terminal as a voice signal.

[0566] Step 2:

[0567] The device converts the collected voice signal into text data using a voice recognition system (e.g., the SpeechRecognition library). The input here is the voice signal, and the output is text data (e.g., "Line 1, abnormal"). The device temporarily stores this text data.

[0568] Step 3:

[0569] The terminal sends the converted text data to the server. The input here is the text data generated in step 2, and the output is the transfer to the server. The text data is sent to the server via the network.

[0570] Step 4:

[0571] The server analyzes the received text data and extracts keywords using a keyword extraction module (e.g., a natural language processing engine). The input here is the text data, and the output is the extracted keywords (e.g., "Line 1" and "Abnormal"). The server stores the keywords as variables.

[0572] Step 5:

[0573] The server recognizes emotions from the user's voice using an emotion engine (e.g., a transformers pipeline for emotion analysis). The input here is the audio signal or text data obtained in step 2, and the output is the recognized emotion (e.g., "tension"). The server stores the emotion information as a variable.

[0574] Step 6:

[0575] The server inputs the extracted keywords and recognized emotions into a generative AI model (e.g., GPT-2) to generate natural-sounding sentences. The input here is keywords and emotion information, and the output is a generated sentence (e.g., "I'm nervous, there's something wrong with line 1"). The generative AI model uses "Line 1 is abnormal, the emotion is nervous" as the prompt sentence.

[0576] Step 7:

[0577] The generated text is sent from the server to the terminal. The input here is the generated text, and the output is transfer to the terminal. The text data is sent to the terminal via the network.

[0578] Step 8:

[0579] The terminal displays the received text on an output device (e.g., a monitor or speaker). Here, the input is the generated text, and the output is visual or audio feedback to the user. Specific actions include displaying the text on a monitor or playing it aloud through a speaker.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] [Third embodiment]

[0584] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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."

[0596] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0597] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device.

[0598] The device then converts the received voice input into text. This conversion is performed using the device's built-in voice recognition system. The voice recognition system analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0599] The converted string is sent from the device to the server. The server analyzes the received text data and extracts keywords from the string. Specifically, it uses natural language processing (NLP) algorithms to detect important words and phrases. In this case, the keywords "enemy" and "left" are extracted.

[0600] Once the keywords are extracted, the server uses a generative AI model to generate sentences based on these keywords. The generative AI model generates natural and appropriate sentences based on the given keywords and background information. For example, sentence generation based on the extracted keywords "enemy" and "left" would generate a sentence such as "The enemy is on your left."

[0601] The generated text is sent from the server to the device, which then displays it in the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0602] As a concrete example, consider a user playing an online FPS game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into a string and sends it to the server. The server extracts keywords from the string, and a generative AI model generates the sentence "enemy on the left." Finally, the generated sentence is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0603] As a result, this system provides an environment in which users can share information efficiently and clearly without letting go of their controllers.

[0604] The processing flow will be explained below.

[0605] Step 1:

[0606] The user speaks into the microphone of the device.

[0607] Action: The user verbally utters the specific command "enemy, left."

[0608] Step 2:

[0609] The device receives voice input and converts the voice into text using a voice recognition system.

[0610] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0611] Step 3:

[0612] The terminal transmits the generated text data to the server.

[0613] Operation: The device sends a request to send text data to the server over the network.

[0614] Step 4:

[0615] The server analyzes the received text data and extracts keywords from the string.

[0616] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0617] Step 5:

[0618] The server sends input data to the generative AI model based on the extracted keywords.

[0619] How it works: The server formats the keywords and necessary contextual information and sends a request to the generation AI's API.

[0620] Step 6:

[0621] Generative AI generates appropriate sentences.

[0622] How it works: The generative AI model generates the sentence "The enemy is on your left" based on the keywords and context information provided.

[0623] Step 7:

[0624] The server sends the generated text to the terminal.

[0625] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0626] Step 8:

[0627] The text received by the device will be displayed in the in-game chat.

[0628] What it does: The game client on the device displays the received text in a chat window, allowing the user's teammates to view this information.

[0629] This series of processing steps allows users to share information efficiently and smoothly progress through game play.

[0630] Example 1

[0631] 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."

[0632] In online action games, it is difficult for users to share information with team members quickly and accurately without interrupting the game. In particular, there are problems with delays and recognition errors in the process of converting voice input into text and generating appropriate sentences.

[0633] 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.

[0634] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a prompt sentence based on the extracted keywords and generating a sentence using a generative AI model, and means for displaying the generated sentence on a user interface, thereby enabling a user to quickly and accurately share information with team members without interrupting operations.

[0635] The "means for receiving voice input" is a function for receiving voice uttered by the user via the device's microphone or the like.

[0636] The "means for converting voice input into text" is a function that analyzes received voice data and converts the content into a corresponding text format.

[0637] "Means for extracting keywords from character strings" is a function that selects important words and phrases from the converted text data.

[0638] "Means for generating prompt sentences and generating sentences using a generative AI model" refers to a function that creates specific instruction sentences based on extracted keywords, inputs these instruction sentences into an AI model, and generates natural-looking sentences.

[0639] "Means for displaying the generated text on a user interface" refers to a function for displaying the generated text data on an in-game chat or other display interface.

[0640] A "speech recognition engine" is software or algorithms used to analyze received voice data and convert it into text form.

[0641] A "generative AI engine" is an artificial intelligence model or algorithm used to generate natural-sounding sentences from given text data and keywords.

[0642] MODE FOR CARRYING OUT THE INVENTION

[0643] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0644] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device. The voice data received by the device is converted into a string of characters using the device's built-in voice recognition engine (e.g., voice recognition API). This voice recognition engine analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0645] The converted text data is then sent from the device to the server, which analyzes the received text data and uses a natural language processing (NLP) engine (e.g., spaCy or NLTK) to extract important keywords from the text. In this case, the keywords "enemy" and "left" are extracted.

[0646] Based on the extracted keywords, the server generates a prompt sentence. This prompt sentence is given to a generative AI engine (e.g., a generative AI model) to generate natural and appropriate sentences. For example, based on the extracted keywords "enemy" and "left," a sentence such as "The enemy is on your left" is generated.

[0647] The generated text is sent from the server to the device, which then displays it in the user interface, specifically the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0648] As a concrete example, consider a user playing an online first-person shooter (FPS) game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into text data and sends it to the server. The server extracts the keywords "enemy" and "left" from the text, and the generative AI model generates the sentence "enemy is on the left." Finally, the generated text is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0649] An example of a prompt sentence might be:

[0650] Keywords: enemy, left

[0651] Background information: Generate a short description based on information the user hears during the game.

[0652] This system provides an environment in which users can share information efficiently and accurately without interrupting gameplay.

[0653] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0654] Step 1:

[0655] The user provides voice input. During the game, the user speaks simple commands such as "enemy, left" into the device's microphone. This is the input.

[0656] Step 2:

[0657] The device receives voice input and converts the speech to text. The input voice data is received by the device's microphone and then passed to a speech recognition engine (e.g., a speech recognition API). The speech recognition engine analyzes the voice waveform and outputs corresponding text data, such as "enemy, left."

[0658] Step 3:

[0659] The terminal sends the converted text data to the server. The converted text data is securely sent to the server using HTTPS. This sent text data becomes input and processing on the server begins.

[0660] Step 4:

[0661] The server parses the string and extracts keywords. The server passes the received text data to a natural language processing engine (e.g. spaCy or NLTK). This engine parses the text data and extracts important keywords such as "enemy" and "left". This is the output of the extracted keywords.

[0662] Step 5:

[0663] The server generates a prompt sentence based on the extracted keywords and sends it to the generative AI model. The server uses the extracted keywords to create a prompt sentence (e.g., "Keywords: enemy, left. Generate an appropriate warning sentence in the game environment") and sends this prompt sentence to the generative AI model (e.g., generative AI engine). This prompt sentence becomes the input.

[0664] Step 6:

[0665] The generative AI model generates an appropriate sentence. Based on the prompt, the generative AI model generates a natural sentence such as "The enemy is on your left." This is the output of the generated sentence.

[0666] Step 7:

[0667] The server sends the generated text to the terminal. The server returns the generated text to the terminal. This text becomes the input, and the terminal resumes processing.

[0668] Step 8:

[0669] The device displays the received text on the user interface. The device displays the received text in the in-game chat, allowing all team members of the user to receive the information quickly and accurately. This is the final output.

[0670] (Application example 1)

[0671] 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."

[0672] In existing virtual stores, users must enter product-related questions by text or select from limited options, making it difficult to communicate quickly and naturally. Furthermore, voice inquiries are often not processed in real time, limiting the shopping experience. This issue needs to be resolved.

[0673] 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.

[0674] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, and means for displaying the generated sentence, thereby enabling a user to ask a question about a product by voice and receive a quick and natural answer.

[0675] The "means for receiving voice input from the user" is a mechanism for obtaining voice uttered by the user as digital data using a microphone or its interface.

[0676] The "means for converting received speech input into text" refers to the process of converting the acquired speech data into a corresponding text format using a language model and a speech recognition engine.

[0677] "Means for extracting keywords from strings of characters" is a natural language processing technique for identifying and extracting specific important words and phrases from the converted text.

[0678] "Means for generating sentences based on extracted keywords" refers to the process of using the obtained keyword information to construct natural and meaningful sentences using a generation algorithm model.

[0679] "Means for displaying the generated text" refers to an interface or device that visually or audibly presents the generated text to the user.

[0680] A "natural language processing engine" is a software component used to analyze text data, understand its meaning, extract keywords, and more.

[0681] A "generative algorithm model" is a machine learning model for generating appropriate sentences based on given keyword information.

[0682] The "virtual store chat function" is a system that allows text-based communication between users and the store in an online virtual store.

[0683] "Voice function" refers to the technology and function for conveying generated text and other information to the user by voice.

[0684] The present invention relates to a system that allows a user to ask questions about products in a virtual store by voice input. A specific embodiment of this system will be described below.

[0685] First, the device used by the user is a smartphone, tablet, or computer, which is equipped with a microphone and allows the user to input voice data.

[0686] The device has a means for receiving user voice input. Once the voice input is received, the device uses a speech recognition engine (e.g., Google Speech-to-Text API or IBM Watson Speech to Text) to convert the speech into text. The voice data is converted into text data in real time.

[0687] This text data is then sent to a server, which analyzes it and extracts keywords using a natural language processing (NLP) engine. For example, a voice input such as "What size is this dress?" is converted into text data such as "What size is this dress?", and the keywords "dress" and "size" are extracted based on this.

[0688] Based on the extracted keywords, the server uses a generative algorithm model (such as OpenAI GPT-3) to generate appropriate sentences that respond to the user's question, such as "This dress is available in sizes S, M, and L."

[0689] The generated text is sent from the server to the device, which then displays or reads it to the user either through the virtual store's chat function or audibly using a text-to-speech (TTS) engine.

[0690] Examples:

[0691] For example, suppose a user asks a question in a virtual store, "What material is this shirt made of?" A microphone captures the voice, and the speech data is converted into text by a speech recognition engine. The text data, "What material is this shirt made of?" is sent to the server, and an NLP engine extracts the keywords "shirt" and "material." A generative algorithm model uses the prompt sentence to generate the sentence, "This shirt is 100% cotton." Finally, this sentence is displayed in the virtual store's chat function or read aloud by a TTS engine and provided to the user.

[0692] Example prompt sentence:

[0693] "Customer Question: What is this shirt made of? Generate an appropriate answer."

[0694] The system allows users to ask product questions using natural voice input and receive quick and accurate answers, significantly improving the shopping experience in virtual stores.

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] Users speak their questions into a microphone on their virtual store device (smartphone, tablet, or computer), and this voice input is captured through the device's microphone.

[0698] Input: User's voice input (e.g., "What material is this shirt made of?")

[0699] Output: Captured audio data

[0700] Step 2:

[0701] The device sends the captured voice data to a speech recognition engine (e.g., Google Speech-to-Text API) to convert the voice data into text. The engine analyzes the voice waveform and generates corresponding text data.

[0702] Input: Audio data

[0703] Output: Text data (e.g., "What material is this shirt made of?")

[0704] Step 3:

[0705] The device sends the generated text data to the server, which then analyzes the text data using a natural language processing (NLP) engine to extract keywords.

[0706] Input: Text data

[0707] Output: Extracted keywords (e.g. "shirt", "material")

[0708] Step 4:

[0709] The server sends a prompt based on the extracted keywords to a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer. The generative AI model creates logical and natural sentences based on the given keywords and prompt.

[0710] Input: Extracted keywords, prompt sentence

[0711] Output: Generated sentence (e.g. "This shirt is 100% cotton")

[0712] Step 5:

[0713] The generated text is sent from the server to the terminal, which then presents it to the user via the chat function of the virtual store or a text-to-speech (TTS) engine.

[0714] Input: Generated sentence

[0715] Output: Display or audio response to user (e.g., displayed in chat or played as "This shirt is 100% cotton")

[0716] This process allows users to ask product questions using voice input and receive quick, natural answers in real time, significantly improving the shopping experience in virtual stores.

[0717] 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.

[0718] The present invention provides a system that allows users to efficiently share information through voice input in an online action game and provides information by recognizing emotions. Specific embodiments of this system are described below.

[0719] First, the user speaks into the device's microphone. The user gives a specific command, such as "enemy, left." This voice input is received by the device and converted into a string of characters by the device's voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, such as "enemy, left." This string of characters is then sent from the device to the server.

[0720] The server analyzes the received text data and extracts keywords such as "enemy" and "left" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if the user says "enemy, left" in a tense voice, the emotion engine will recognize the emotion as "tension."

[0721] The keywords and the recognized emotions are input into a generative AI model, which generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "enemy" and "left" and the emotion "tension," it generates a sentence such as "I'm nervous, the enemy is on my left."

[0722] The generated text is sent from the server to the device, where it is displayed in the in-game chat. Furthermore, by simultaneously displaying emotional information, the user's intentions and state are more accurately conveyed to team members.

[0723] As a concrete example, consider a user playing an online FPS game. The user spots an enemy and says "enemy, left" into the microphone in a tense voice. This utterance is converted into text data "enemy, left" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, enemy is on the left." Finally, this sentence is displayed in the device's in-game chat, accompanied by emotional information, so all team members can receive this important information along with the speaker's emotions.

[0724] Through the above process, the system provides an environment in which users can share information more efficiently and accurately, and communicate their intentions and status to other players in the game.

[0725] The processing flow will be explained below.

[0726] Step 1:

[0727] The user speaks into the microphone of the device.

[0728] Action: The user verbally utters the specific command "enemy, left."

[0729] Step 2:

[0730] The device receives voice input and converts the voice into text using a voice recognition system.

[0731] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0732] Step 3:

[0733] The terminal transmits the generated text data to the server.

[0734] Operation: The device sends a request to send text data to the server over the network.

[0735] Step 4:

[0736] The server analyzes the received text data and extracts keywords from the string.

[0737] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0738] Step 5:

[0739] The server uses an emotion engine to recognize the user's emotion from the voice data.

[0740] How it works: The server's emotion engine analyzes the voice data and recognizes emotions such as "tension" and "excitement."

[0741] Step 6:

[0742] The server sends input data to the generative AI model based on the extracted keywords and recognized emotions.

[0743] How it works: The server formats the keywords "enemy" and "left" and the emotional information "tension" and sends a request to the API of the generative AI model.

[0744] Step 7:

[0745] Generative AI generates appropriate sentences.

[0746] How it works: The generative AI model generates the sentence "I'm nervous, the enemy is on my left" based on the keywords and emotional information sent.

[0747] Step 8:

[0748] The server sends the generated text to the terminal.

[0749] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0750] Step 9:

[0751] The text and emotional information received by the device will be displayed in the in-game chat.

[0752] What it does: The game client on your device displays the received text and emotion information in the chat window, allowing team members to view this information.

[0753] This series of processing steps allows users to notify team members of their status and share information efficiently and accurately.

[0754] Example 2

[0755] 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."

[0756] In online action games, there is a lack of efficient and accurate means for users to share information through voice input. Furthermore, information transmission does not take into account the user's emotional state, resulting in a problem of in-game communication not proceeding smoothly.

[0757] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for recognizing emotions based on the extracted keywords, means for generating natural sentences based on the emotions and keywords, and means for displaying the generated sentences in an in-game chat. This allows users to share information efficiently and accurately through voice input, and by adding emotional information, smooth communication within the game is possible.

[0758] A "user" is someone who uses the system to play online games.

[0759] "Means for receiving voice input" refers to a microphone and corresponding hardware and software for receiving the user's voice as digital data.

[0760] A "means for converting speech to text" refers to a system or module for converting received speech data into text data using a speech recognition engine.

[0761] "Keyword extraction methods" refers to natural language processing (NLP) techniques for identifying important words and phrases from text data.

[0762] "Means for recognizing emotions" refers to algorithms or emotion engines that analyze the features of a user's voice and estimate emotions such as tension, joy, or anger.

[0763] The "means for generating natural-sentence text" refers to a generative AI model for generating appropriate text based on extracted keywords and emotional information.

[0764] The "means for displaying in the in-game chat" refers to a UI module for displaying the generated text and emotion information in the chat window of the game application.

[0765] The present invention provides a system that allows users to efficiently share information through voice input in an online game and provides information by recognizing emotions. A specific embodiment of this system will be described below.

[0766] System Overview

[0767] The entire system consists of the device (terminal) on which the user plays the game, the server that analyzes and processes the audio, and the game application that displays the generated information.

[0768] 1. Receiving voice input

[0769] While playing an online game, a user speaks commands into a microphone, for example, "enemy, left."

[0770] 2. Converting voice data to text

[0771] The device's voice recognition system uses the Google Speech-to-Text API or similar to convert the user's voice into digital data (a string of characters), which may take the form of "enemy, left."

[0772] 3. Sending text data to the server

[0773] The device then sends the converted text data to the server over the network, using a secure protocol such as HTTPS.

[0774] 4. Keyword extraction

[0775] The server analyzes the received text data and uses NLP (natural language processing) technology to extract the keywords "enemy" and "left."

[0776] 5. Emotion recognition

[0777] The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features such as voice data and recognizes the user's emotion (e.g., nervousness).

[0778] 6. Natural language generation

[0779] The extracted keywords and recognized emotions are input to a generative AI model (e.g., OpenAI GPT-3) on the server, using the following prompt:

[0780] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[0781] The generative AI model generates natural sentences such as "I'm nervous, the enemy is on my left."

[0782] 7. Sending the generated text to the terminal

[0783] The server sends the generated text to the device, again using a secure protocol such as HTTPS for communication.

[0784] 8. In-game chat display

[0785] The device displays the received text and emotional information on the in-game chat screen, thereby communicating the user's spoken information and emotional state to other players.

[0786] Specific examples

[0787] Below is a concrete example of using this system. Suppose a user is playing an online FPS game. The user spots an enemy and says "enemy, left" in a nervous voice. This voice is received by the device's microphone, converted into text data "enemy, left," and sent to the server. The server extracts the keywords "enemy" and "left," and the emotion engine recognizes "tension." The generative AI model generates the sentence "I'm nervous, the enemy is on my left," which is then displayed in the in-game chat. This allows all team members to instantly understand the enemy's location and the user's emotional state.

[0788] This process allows the system to efficiently and accurately share information through voice input, and by adding emotional information, it achieves smooth communication within the game.

[0789] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0790] Step 1:

[0791] While playing an online game, a user says into a microphone, "Enemy, left."

[0792] Specific operation: The microphone collects the user's voice waveform, converts it into digital data, and sends it to the terminal.

[0793] Input and Output: The input is the user's voice data, and the output is the digital voice data.

[0794] Step 2:

[0795] The terminal's voice recognition system (voice recognition engine) is used to convert the received voice data into text data.

[0796] Specific operation: Calls a speech recognition engine such as the Google Speech-to-Text API and generates a string from the audio waveform data.

[0797] Input and output: The input is digital voice data, and the output is text data such as "enemy, left."

[0798] Step 3:

[0799] The terminal transmits the generated text data to the server via the network.

[0800] Specific operation: The terminal's network module divides the text data into packets and sends them to the server using the HTTPS protocol.

[0801] Input and Output: The input is the text data "enemy, left", and the output is the text data sent to the server.

[0802] Step 4:

[0803] The server analyzes the received text data and extracts keywords using natural language processing (NLP) technology.

[0804] Specific operation: The server's NLP module performs morphological analysis of the string and identifies the important keywords "enemy" and "left."

[0805] Input and Output: The input is the text data arriving at the server, and the output is the extracted keywords "enemy" and "left."

[0806] Step 5:

[0807] The server uses an emotion engine to recognize emotions from the user's voice.

[0808] Specific operation: The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features (pitch, tone, speed, etc.) from the voice data and estimates the emotion (e.g., "tension").

[0809] Input and Output: The input is the voice data, and the output is the recognized emotion "tension."

[0810] Step 6:

[0811] The server generates natural-sounding sentences using a generative AI model (e.g., OpenAI GPT-3) based on the extracted keywords and recognized emotions.

[0812] Specific operation: The following prompt sentence is input into the generative AI model to generate a sentence.

[0813] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[0814] Input and output: The input is the keywords "enemy" and "left" and the emotion "tension", and the output is the generated sentence "I'm tense, the enemy is on my left".

[0815] Step 7:

[0816] The server transmits the generated text to the terminal via the network.

[0817] Specific operation: The server's network module divides the generated text into packets and sends them to the terminal using the HTTPS protocol.

[0818] Input and output: The input is the generated sentence "I'm nervous, the enemy is on my left", and the output is the text data sent to the terminal.

[0819] Step 8:

[0820] The device displays the received text and emotional information in the in-game chat.

[0821] Specific behavior: The device's game application displays the text "Tension, enemy on the left" and an emoticon in the chat window.

[0822] Input and Output: Input is received text data and emotion information, output is information displayed on the in-game chat screen.

[0823] (Application example 2)

[0824] 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."

[0825] In the past, work management and problem reporting in factories were mainly done manually, which not only placed a heavy burden on workers but also created a high risk of delays in information transmission and misunderstandings.In addition, there was no means of communication that took into account the emotions and tension of workers, which led to problems such as reduced work efficiency and delayed response to problems.

[0826] The identification process by the identification 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 receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, means for displaying the generated sentence on an output device, and means for recognizing the user's emotions and providing information. This makes it possible to share information efficiently and accurately, reducing the burden on workers and enabling quick problem resolution.

[0827] "User" refers to a person who uses the system.

[0828] A "means for receiving voice input" is a device or software function for capturing voice information from a user.

[0829] "Means for converting into character string" refers to a process for converting received voice information into text data.

[0830] "Keyword extraction means" is a technique for extracting important words and phrases from text data.

[0831] "Means for generating sentences" refers to a technology that creates natural sentences based on extracted keywords.

[0832] "Means for displaying on an output device" refers to a function for visually presenting the generated text to the user.

[0833] "Means for recognizing emotions and providing information" is a technology that analyzes emotions from the user's voice and generates an appropriate response based on that information.

[0834] "Production system" refers to the entire system for managing and transmitting information about the production process.

[0835] The present invention is a system that enables factory workers to efficiently share information through voice input and also recognizes emotions to provide information. Specific embodiments of this system will be described below.

[0836] First, the user speaks into the microphone of the device. For example, they might say, "Line 1, abnormal." This voice input is received by the device and converted into a string of characters by the voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, for example, "Line 1, abnormal." This string data is then sent from the device to the server.

[0837] The server analyzes the received text data and extracts keywords such as "Line 1" and "Abnormal" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if a user says "Line 1, abnormal" in a tense voice, the emotion engine will recognize the emotion as "tension."

[0838] The keywords and the recognized emotions are input into a generative AI model, which then generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "Line 1" and "Abnormal" and the emotion "Tense," it generates a sentence such as "I'm nervous, there's an abnormality in Line 1."

[0839] The generated sentences are sent from the server to the terminals, which then display them on their output devices, allowing all workers to receive this important information along with the speaker's emotions.

[0840] As a concrete example, let's consider a scenario in a factory. A user discovers an abnormality on the production line and says "Line 1, abnormal" in a tense voice into the microphone. This statement is converted into text data "Line 1, abnormal" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, there's an abnormality on Line 1." Finally, this sentence is displayed on the terminal's output device, accompanied by emotional information, allowing all workers to share this information quickly and accurately.

[0841] An example of a prompt is:

[0842] "Line 1 abnormal, emotion is tension."

[0843] This allows the system to provide an environment where users can efficiently and accurately share information and communicate their intentions and status to other workers in the work environment.

[0844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0845] Step 1:

[0846] The user inputs voice into the microphone. This input is a specific instruction, such as "Line 1, abnormal." The input data is collected by the terminal as a voice signal.

[0847] Step 2:

[0848] The device converts the collected voice signal into text data using a voice recognition system (e.g., the SpeechRecognition library). The input here is the voice signal, and the output is text data (e.g., "Line 1, abnormal"). The device temporarily stores this text data.

[0849] Step 3:

[0850] The terminal sends the converted text data to the server. The input here is the text data generated in step 2, and the output is the transfer to the server. The text data is sent to the server via the network.

[0851] Step 4:

[0852] The server analyzes the received text data and extracts keywords using a keyword extraction module (e.g., a natural language processing engine). The input here is the text data, and the output is the extracted keywords (e.g., "Line 1" and "Abnormal"). The server stores the keywords as variables.

[0853] Step 5:

[0854] The server recognizes emotions from the user's voice using an emotion engine (e.g., a transformers pipeline for emotion analysis). The input here is the audio signal or text data obtained in step 2, and the output is the recognized emotion (e.g., "tension"). The server stores the emotion information as a variable.

[0855] Step 6:

[0856] The server inputs the extracted keywords and recognized emotions into a generative AI model (e.g., GPT-2) to generate natural-sounding sentences. The input here is keywords and emotion information, and the output is a generated sentence (e.g., "I'm nervous, there's something wrong with line 1"). The generative AI model uses "Line 1 is abnormal, the emotion is nervous" as the prompt sentence.

[0857] Step 7:

[0858] The generated text is sent from the server to the terminal. The input here is the generated text, and the output is transfer to the terminal. The text data is sent to the terminal via the network.

[0859] Step 8:

[0860] The terminal displays the received text on an output device (e.g., a monitor or speaker). Here, the input is the generated text, and the output is visual or audio feedback to the user. Specific actions include displaying the text on a monitor or playing it aloud through a speaker.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] [Fourth embodiment]

[0865] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0866] 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.

[0867] 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).

[0868] 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.

[0869] 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.

[0870] 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).

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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."

[0878] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0879] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device.

[0880] The device then converts the received voice input into text. This conversion is performed using the device's built-in voice recognition system. The voice recognition system analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0881] The converted string is sent from the device to the server. The server analyzes the received text data and extracts keywords from the string. Specifically, it uses natural language processing (NLP) algorithms to detect important words and phrases. In this case, the keywords "enemy" and "left" are extracted.

[0882] Once the keywords are extracted, the server uses a generative AI model to generate sentences based on these keywords. The generative AI model generates natural and appropriate sentences based on the given keywords and background information. For example, sentence generation based on the extracted keywords "enemy" and "left" would generate a sentence such as "The enemy is on your left."

[0883] The generated text is sent from the server to the device, which then displays it in the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0884] As a concrete example, consider a user playing an online FPS game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into a string and sends it to the server. The server extracts keywords from the string, and a generative AI model generates the sentence "enemy on the left." Finally, the generated sentence is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0885] As a result, this system provides an environment in which users can share information efficiently and clearly without letting go of their controllers.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] The user speaks into the microphone of the device.

[0889] Action: The user verbally utters the specific command "enemy, left."

[0890] Step 2:

[0891] The device receives voice input and converts the voice into text using a voice recognition system.

[0892] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[0893] Step 3:

[0894] The terminal transmits the generated text data to the server.

[0895] Operation: The device sends a request to send text data to the server over the network.

[0896] Step 4:

[0897] The server analyzes the received text data and extracts keywords from the string.

[0898] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[0899] Step 5:

[0900] The server sends input data to the generative AI model based on the extracted keywords.

[0901] How it works: The server formats the keywords and necessary contextual information and sends a request to the generation AI's API.

[0902] Step 6:

[0903] Generative AI generates appropriate sentences.

[0904] How it works: The generative AI model generates the sentence "The enemy is on your left" based on the keywords and context information provided.

[0905] Step 7:

[0906] The server sends the generated text to the terminal.

[0907] Operation: The server returns the generated text data to the terminal as an HTTP response.

[0908] Step 8:

[0909] The text received by the device will be displayed in the in-game chat.

[0910] What it does: The game client on the device displays the received text in a chat window, allowing the user's teammates to view this information.

[0911] This series of processing steps allows users to share information efficiently and smoothly progress through game play.

[0912] Example 1

[0913] 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."

[0914] In online action games, it is difficult for users to share information with team members quickly and accurately without interrupting the game. In particular, there are problems with delays and recognition errors in the process of converting voice input into text and generating appropriate sentences.

[0915] 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.

[0916] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a prompt sentence based on the extracted keywords and generating a sentence using a generative AI model, and means for displaying the generated sentence on a user interface, thereby enabling a user to quickly and accurately share information with team members without interrupting operations.

[0917] The "means for receiving voice input" is a function for receiving voice uttered by the user via the device's microphone or the like.

[0918] The "means for converting voice input into text" is a function that analyzes received voice data and converts the content into a corresponding text format.

[0919] "Means for extracting keywords from character strings" is a function that selects important words and phrases from the converted text data.

[0920] "Means for generating prompt sentences and generating sentences using a generative AI model" refers to a function that creates specific instruction sentences based on extracted keywords, inputs these instruction sentences into an AI model, and generates natural-looking sentences.

[0921] "Means for displaying the generated text on a user interface" refers to a function for displaying the generated text data on an in-game chat or other display interface.

[0922] A "speech recognition engine" is software or algorithms used to analyze received voice data and convert it into text form.

[0923] A "generative AI engine" is an artificial intelligence model or algorithm used to generate natural-sounding sentences from given text data and keywords.

[0924] MODE FOR CARRYING OUT THE INVENTION

[0925] The present invention provides a system for enabling users to efficiently share information via voice input in an online action game. Specific embodiments of this system will be described below.

[0926] First, the user speaks into the device's microphone. This voice input is often a simple command such as "enemy, left." This voice input is received by the device. The voice data received by the device is converted into a string of characters using the device's built-in voice recognition engine (e.g., voice recognition API). This voice recognition engine analyzes the voice waveform and generates corresponding text data. For example, the voice input "enemy, left" is directly converted into the text data "enemy, left."

[0927] The converted text data is then sent from the device to the server, which analyzes the received text data and uses a natural language processing (NLP) engine (e.g., spaCy or NLTK) to extract important keywords from the text. In this case, the keywords "enemy" and "left" are extracted.

[0928] Based on the extracted keywords, the server generates a prompt sentence. This prompt sentence is given to a generative AI engine (e.g., a generative AI model) to generate natural and appropriate sentences. For example, based on the extracted keywords "enemy" and "left," a sentence such as "The enemy is on your left" is generated.

[0929] The generated text is sent from the server to the device, which then displays it in the user interface, specifically the in-game chat, allowing users to quickly and clearly share important information with their teammates.

[0930] As a concrete example, consider a user playing an online first-person shooter (FPS) game. When the user spots an enemy, they say "enemy, left" into the microphone. The device converts this utterance into text data and sends it to the server. The server extracts the keywords "enemy" and "left" from the text, and the generative AI model generates the sentence "enemy is on the left." Finally, the generated text is displayed in the device's in-game chat, allowing all of the user's team members to instantly receive this information.

[0931] An example of a prompt sentence might be:

[0932] Keywords: enemy, left

[0933] Background information: Generate a short description based on information the user hears during the game.

[0934] This system provides an environment in which users can share information efficiently and accurately without interrupting gameplay.

[0935] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0936] Step 1:

[0937] The user provides voice input. During the game, the user speaks simple commands such as "enemy, left" into the device's microphone. This is the input.

[0938] Step 2:

[0939] The device receives voice input and converts the speech to text. The input voice data is received by the device's microphone and then passed to a speech recognition engine (e.g., a speech recognition API). The speech recognition engine analyzes the voice waveform and outputs corresponding text data, such as "enemy, left."

[0940] Step 3:

[0941] The terminal sends the converted text data to the server. The converted text data is securely sent to the server using HTTPS. This sent text data becomes input and processing on the server begins.

[0942] Step 4:

[0943] The server parses the string and extracts keywords. The server passes the received text data to a natural language processing engine (e.g. spaCy or NLTK). This engine parses the text data and extracts important keywords such as "enemy" and "left". This is the output of the extracted keywords.

[0944] Step 5:

[0945] The server generates a prompt sentence based on the extracted keywords and sends it to the generative AI model. The server uses the extracted keywords to create a prompt sentence (e.g., "Keywords: enemy, left. Generate an appropriate warning sentence in the game environment") and sends this prompt sentence to the generative AI model (e.g., generative AI engine). This prompt sentence becomes the input.

[0946] Step 6:

[0947] The generative AI model generates an appropriate sentence. Based on the prompt, the generative AI model generates a natural sentence such as "The enemy is on your left." This is the output of the generated sentence.

[0948] Step 7:

[0949] The server sends the generated text to the terminal. The server returns the generated text to the terminal. This text becomes the input, and the terminal resumes processing.

[0950] Step 8:

[0951] The device displays the received text on the user interface. The device displays the received text in the in-game chat, allowing all team members of the user to receive the information quickly and accurately. This is the final output.

[0952] (Application example 1)

[0953] 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."

[0954] In existing virtual stores, users must enter product-related questions by text or select from limited options, making it difficult to communicate quickly and naturally. Furthermore, voice inquiries are often not processed in real time, limiting the shopping experience. This issue needs to be resolved.

[0955] 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.

[0956] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, and means for displaying the generated sentence, thereby enabling a user to ask a question about a product by voice and receive a quick and natural answer.

[0957] The "means for receiving voice input from the user" is a mechanism for obtaining voice uttered by the user as digital data using a microphone or its interface.

[0958] The "means for converting received speech input into text" refers to the process of converting the acquired speech data into a corresponding text format using a language model and a speech recognition engine.

[0959] "Means for extracting keywords from strings of characters" is a natural language processing technique for identifying and extracting specific important words and phrases from the converted text.

[0960] "Means for generating sentences based on extracted keywords" refers to the process of using the obtained keyword information to construct natural and meaningful sentences using a generation algorithm model.

[0961] "Means for displaying the generated text" refers to an interface or device that visually or audibly presents the generated text to the user.

[0962] A "natural language processing engine" is a software component used to analyze text data, understand its meaning, extract keywords, and more.

[0963] A "generative algorithm model" is a machine learning model for generating appropriate sentences based on given keyword information.

[0964] The "virtual store chat function" is a system that allows text-based communication between users and the store in an online virtual store.

[0965] "Voice function" refers to the technology and function for conveying generated text and other information to the user by voice.

[0966] The present invention relates to a system that allows a user to ask questions about products in a virtual store by voice input. A specific embodiment of this system will be described below.

[0967] First, the device used by the user is a smartphone, tablet, or computer, which is equipped with a microphone and allows the user to input voice data.

[0968] The device has a means for receiving user voice input. Once the voice input is received, the device uses a speech recognition engine (e.g., Google Speech-to-Text API or IBM Watson Speech to Text) to convert the speech into text. The voice data is converted into text data in real time.

[0969] This text data is then sent to a server, which analyzes it and extracts keywords using a natural language processing (NLP) engine. For example, a voice input such as "What size is this dress?" is converted into text data such as "What size is this dress?", and the keywords "dress" and "size" are extracted based on this.

[0970] Based on the extracted keywords, the server uses a generative algorithm model (such as OpenAI GPT-3) to generate appropriate sentences that respond to the user's question, such as "This dress is available in sizes S, M, and L."

[0971] The generated text is sent from the server to the device, which then displays or reads it to the user either through the virtual store's chat function or audibly using a text-to-speech (TTS) engine.

[0972] Examples:

[0973] For example, suppose a user asks a question in a virtual store, "What material is this shirt made of?" A microphone captures the voice, and the speech data is converted into text by a speech recognition engine. The text data, "What material is this shirt made of?" is sent to the server, and an NLP engine extracts the keywords "shirt" and "material." A generative algorithm model uses the prompt sentence to generate the sentence, "This shirt is 100% cotton." Finally, this sentence is displayed in the virtual store's chat function or read aloud by a TTS engine and provided to the user.

[0974] Example prompt sentence:

[0975] "Customer Question: What is this shirt made of? Generate an appropriate answer."

[0976] The system allows users to ask product questions using natural voice input and receive quick and accurate answers, significantly improving the shopping experience in virtual stores.

[0977] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0978] Step 1:

[0979] Users speak their questions into a microphone on their virtual store device (smartphone, tablet, or computer), and this voice input is captured through the device's microphone.

[0980] Input: User's voice input (e.g., "What material is this shirt made of?")

[0981] Output: Captured audio data

[0982] Step 2:

[0983] The device sends the captured voice data to a speech recognition engine (e.g., Google Speech-to-Text API) to convert the voice data into text. The engine analyzes the voice waveform and generates corresponding text data.

[0984] Input: Audio data

[0985] Output: Text data (e.g., "What material is this shirt made of?")

[0986] Step 3:

[0987] The device sends the generated text data to the server, which then analyzes the text data using a natural language processing (NLP) engine to extract keywords.

[0988] Input: Text data

[0989] Output: Extracted keywords (e.g. "shirt", "material")

[0990] Step 4:

[0991] The server sends a prompt based on the extracted keywords to a generative AI model (e.g., OpenAI GPT-3) to generate an appropriate answer. The generative AI model creates logical and natural sentences based on the given keywords and prompt.

[0992] Input: Extracted keywords, prompt sentence

[0993] Output: Generated sentence (e.g. "This shirt is 100% cotton")

[0994] Step 5:

[0995] The generated text is sent from the server to the terminal, which then presents it to the user via the chat function of the virtual store or a text-to-speech (TTS) engine.

[0996] Input: Generated sentence

[0997] Output: Display or audio response to user (e.g., displayed in chat or played as "This shirt is 100% cotton")

[0998] This process allows users to ask product questions using voice input and receive quick, natural answers in real time, significantly improving the shopping experience in virtual stores.

[0999] 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.

[1000] The present invention provides a system that allows users to efficiently share information through voice input in an online action game and provides information by recognizing emotions. Specific embodiments of this system are described below.

[1001] First, the user speaks into the device's microphone. The user gives a specific command, such as "enemy, left." This voice input is received by the device and converted into a string of characters by the device's voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, such as "enemy, left." This string of characters is then sent from the device to the server.

[1002] The server analyzes the received text data and extracts keywords such as "enemy" and "left" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if the user says "enemy, left" in a tense voice, the emotion engine will recognize the emotion as "tension."

[1003] The keywords and the recognized emotions are input into a generative AI model, which generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "enemy" and "left" and the emotion "tension," it generates a sentence such as "I'm nervous, the enemy is on my left."

[1004] The generated text is sent from the server to the device, where it is displayed in the in-game chat. Furthermore, by simultaneously displaying emotional information, the user's intentions and state are more accurately conveyed to team members.

[1005] As a concrete example, consider a user playing an online FPS game. The user spots an enemy and says "enemy, left" into the microphone in a tense voice. This utterance is converted into text data "enemy, left" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, enemy is on the left." Finally, this sentence is displayed in the device's in-game chat, accompanied by emotional information, so all team members can receive this important information along with the speaker's emotions.

[1006] Through the above process, the system provides an environment in which users can share information more efficiently and accurately, and communicate their intentions and status to other players in the game.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] The user speaks into the microphone of the device.

[1010] Action: The user verbally utters the specific command "enemy, left."

[1011] Step 2:

[1012] The device receives voice input and converts the voice into text using a voice recognition system.

[1013] How it works: The device's voice recognition engine analyzes the voice waveform and generates the text data "enemy, left."

[1014] Step 3:

[1015] The terminal transmits the generated text data to the server.

[1016] Operation: The device sends a request to send text data to the server over the network.

[1017] Step 4:

[1018] The server analyzes the received text data and extracts keywords from the string.

[1019] How it works: The server's keyword extraction module uses a natural language processing algorithm to extract the keywords "enemy" and "left."

[1020] Step 5:

[1021] The server uses an emotion engine to recognize the user's emotion from the voice data.

[1022] How it works: The server's emotion engine analyzes the voice data and recognizes emotions such as "tension" and "excitement."

[1023] Step 6:

[1024] The server sends input data to the generative AI model based on the extracted keywords and recognized emotions.

[1025] How it works: The server formats the keywords "enemy" and "left" and the emotional information "tension" and sends a request to the API of the generative AI model.

[1026] Step 7:

[1027] Generative AI generates appropriate sentences.

[1028] How it works: The generative AI model generates the sentence "I'm nervous, the enemy is on my left" based on the keywords and emotional information sent.

[1029] Step 8:

[1030] The server sends the generated text to the terminal.

[1031] Operation: The server returns the generated text data to the terminal as an HTTP response.

[1032] Step 9:

[1033] The text and emotional information received by the device will be displayed in the in-game chat.

[1034] What it does: The game client on your device displays the received text and emotion information in the chat window, allowing team members to view this information.

[1035] This series of processing steps allows users to notify team members of their status and share information efficiently and accurately.

[1036] Example 2

[1037] 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."

[1038] In online action games, there is a lack of efficient and accurate means for users to share information through voice input. Furthermore, information transmission does not take into account the user's emotional state, resulting in a problem of in-game communication not proceeding smoothly.

[1039] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for recognizing emotions based on the extracted keywords, means for generating natural sentences based on the emotions and keywords, and means for displaying the generated sentences in an in-game chat. This allows users to share information efficiently and accurately through voice input, and by adding emotional information, smooth communication within the game is possible.

[1040] A "user" is someone who uses the system to play online games.

[1041] "Means for receiving voice input" refers to a microphone and corresponding hardware and software for receiving the user's voice as digital data.

[1042] A "means for converting speech to text" refers to a system or module for converting received speech data into text data using a speech recognition engine.

[1043] "Keyword extraction methods" refers to natural language processing (NLP) techniques for identifying important words and phrases from text data.

[1044] "Means for recognizing emotions" refers to algorithms or emotion engines that analyze the features of a user's voice and estimate emotions such as tension, joy, or anger.

[1045] The "means for generating natural-sentence text" refers to a generative AI model for generating appropriate text based on extracted keywords and emotional information.

[1046] The "means for displaying in the in-game chat" refers to a UI module for displaying the generated text and emotion information in the chat window of the game application.

[1047] The present invention provides a system that allows users to efficiently share information through voice input in an online game and provides information by recognizing emotions. A specific embodiment of this system will be described below.

[1048] System Overview

[1049] The entire system consists of the device (terminal) on which the user plays the game, the server that analyzes and processes the audio, and the game application that displays the generated information.

[1050] 1. Receiving voice input

[1051] While playing an online game, a user speaks commands into a microphone, for example, "enemy, left."

[1052] 2. Converting voice data to text

[1053] The device's voice recognition system uses the Google Speech-to-Text API or similar to convert the user's voice into digital data (a string of characters), which may take the form of "enemy, left."

[1054] 3. Sending text data to the server

[1055] The device then sends the converted text data to the server over the network, using a secure protocol such as HTTPS.

[1056] 4. Keyword extraction

[1057] The server analyzes the received text data and uses NLP (natural language processing) technology to extract the keywords "enemy" and "left."

[1058] 5. Emotion recognition

[1059] The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features such as voice data and recognizes the user's emotion (e.g., nervousness).

[1060] 6. Natural language generation

[1061] The extracted keywords and recognized emotions are input to a generative AI model (e.g., OpenAI GPT-3) on the server, using the following prompt:

[1062] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[1063] The generative AI model generates natural sentences such as "I'm nervous, the enemy is on my left."

[1064] 7. Sending the generated text to the terminal

[1065] The server sends the generated text to the device, again using a secure protocol such as HTTPS for communication.

[1066] 8. In-game chat display

[1067] The device displays the received text and emotional information on the in-game chat screen, thereby communicating the user's spoken information and emotional state to other players.

[1068] Specific examples

[1069] Below is a concrete example of using this system. Suppose a user is playing an online FPS game. The user spots an enemy and says "enemy, left" in a nervous voice. This voice is received by the device's microphone, converted into text data "enemy, left," and sent to the server. The server extracts the keywords "enemy" and "left," and the emotion engine recognizes "tension." The generative AI model generates the sentence "I'm nervous, the enemy is on my left," which is then displayed in the in-game chat. This allows all team members to instantly understand the enemy's location and the user's emotional state.

[1070] This process allows the system to efficiently and accurately share information through voice input, and by adding emotional information, it achieves smooth communication within the game.

[1071] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1072] Step 1:

[1073] While playing an online game, a user says into a microphone, "Enemy, left."

[1074] Specific operation: The microphone collects the user's voice waveform, converts it into digital data, and sends it to the terminal.

[1075] Input and Output: The input is the user's voice data, and the output is the digital voice data.

[1076] Step 2:

[1077] The terminal's voice recognition system (voice recognition engine) is used to convert the received voice data into text data.

[1078] Specific operation: Calls a speech recognition engine such as the Google Speech-to-Text API and generates a string from the audio waveform data.

[1079] Input and output: The input is digital voice data, and the output is text data such as "enemy, left."

[1080] Step 3:

[1081] The terminal transmits the generated text data to the server via the network.

[1082] Specific operation: The terminal's network module divides the text data into packets and sends them to the server using the HTTPS protocol.

[1083] Input and Output: The input is the text data "enemy, left", and the output is the text data sent to the server.

[1084] Step 4:

[1085] The server analyzes the received text data and extracts keywords using natural language processing (NLP) technology.

[1086] Specific operation: The server's NLP module performs morphological analysis of the string and identifies the important keywords "enemy" and "left."

[1087] Input and Output: The input is the text data arriving at the server, and the output is the extracted keywords "enemy" and "left."

[1088] Step 5:

[1089] The server uses an emotion engine to recognize emotions from the user's voice.

[1090] Specific operation: The server's emotion engine (e.g., IBM Watson Tone Analyzer) analyzes features (pitch, tone, speed, etc.) from the voice data and estimates the emotion (e.g., "tension").

[1091] Input and Output: The input is the voice data, and the output is the recognized emotion "tension."

[1092] Step 6:

[1093] The server generates natural-sounding sentences using a generative AI model (e.g., OpenAI GPT-3) based on the extracted keywords and recognized emotions.

[1094] Specific operation: The following prompt sentence is input into the generative AI model to generate a sentence.

[1095] Example prompt: "Generate natural-sounding sentences based on the text data 'enemy, left' and the emotion 'tension'."

[1096] Input and output: The input is the keywords "enemy" and "left" and the emotion "tension", and the output is the generated sentence "I'm tense, the enemy is on my left".

[1097] Step 7:

[1098] The server transmits the generated text to the terminal via the network.

[1099] Specific operation: The server's network module divides the generated text into packets and sends them to the terminal using the HTTPS protocol.

[1100] Input and output: The input is the generated sentence "I'm nervous, the enemy is on my left", and the output is the text data sent to the terminal.

[1101] Step 8:

[1102] The device displays the received text and emotional information in the in-game chat.

[1103] Specific behavior: The device's game application displays the text "Tension, enemy on the left" and an emoticon in the chat window.

[1104] Input and Output: Input is received text data and emotion information, output is information displayed on the in-game chat screen.

[1105] (Application example 2)

[1106] 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."

[1107] In the past, work management and problem reporting in factories were mainly done manually, which not only placed a heavy burden on workers but also created a high risk of delays in information transmission and misunderstandings.In addition, there was no means of communication that took into account the emotions and tension of workers, which led to problems such as reduced work efficiency and delayed response to problems.

[1108] The identification process by the identification 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 receiving voice input from a user, means for converting the received voice input into a character string, means for extracting keywords from the character string, means for generating a sentence based on the extracted keywords, means for displaying the generated sentence on an output device, and means for recognizing the user's emotions and providing information. This makes it possible to share information efficiently and accurately, reducing the burden on workers and enabling quick problem resolution.

[1109] "User" refers to a person who uses the system.

[1110] A "means for receiving voice input" is a device or software function for capturing voice information from a user.

[1111] "Means for converting into character string" refers to a process for converting received voice information into text data.

[1112] "Keyword extraction means" is a technique for extracting important words and phrases from text data.

[1113] "Means for generating sentences" refers to a technology that creates natural sentences based on extracted keywords.

[1114] "Means for displaying on an output device" refers to a function for visually presenting the generated text to the user.

[1115] "Means for recognizing emotions and providing information" is a technology that analyzes emotions from the user's voice and generates an appropriate response based on that information.

[1116] "Production system" refers to the entire system for managing and transmitting information about the production process.

[1117] The present invention is a system that enables factory workers to efficiently share information through voice input and also recognizes emotions to provide information. Specific embodiments of this system will be described below.

[1118] First, the user speaks into the microphone of the device. For example, they might say, "Line 1, abnormal." This voice input is received by the device and converted into a string of characters by the voice recognition system. The voice recognition system analyzes the voice waveform and generates text data, for example, "Line 1, abnormal." This string data is then sent from the device to the server.

[1119] The server analyzes the received text data and extracts keywords such as "Line 1" and "Abnormal" using a keyword extraction module. The server is also connected to an emotion engine, which recognizes emotions from the user's voice. For example, if a user says "Line 1, abnormal" in a tense voice, the emotion engine will recognize the emotion as "tension."

[1120] The keywords and the recognized emotions are input into a generative AI model, which then generates natural-sounding sentences based on the keywords and emotions. For example, based on the keywords "Line 1" and "Abnormal" and the emotion "Tense," it generates a sentence such as "I'm nervous, there's an abnormality in Line 1."

[1121] The generated sentences are sent from the server to the terminals, which then display them on their output devices, allowing all workers to receive this important information along with the speaker's emotions.

[1122] As a concrete example, let's consider a scenario in a factory. A user discovers an abnormality on the production line and says "Line 1, abnormal" in a tense voice into the microphone. This statement is converted into text data "Line 1, abnormal" and sent to the server. The server extracts keywords, the emotion engine recognizes "tension," and the generative AI model generates the sentence "I'm nervous, there's an abnormality on Line 1." Finally, this sentence is displayed on the terminal's output device, accompanied by emotional information, allowing all workers to share this information quickly and accurately.

[1123] An example of a prompt is:

[1124] "Line 1 abnormal, emotion is tension."

[1125] This allows the system to provide an environment where users can efficiently and accurately share information and communicate their intentions and status to other workers in the work environment.

[1126] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1127] Step 1:

[1128] The user inputs voice into the microphone. This input is a specific instruction, such as "Line 1, abnormal." The input data is collected by the terminal as a voice signal.

[1129] Step 2:

[1130] The device converts the collected voice signal into text data using a voice recognition system (e.g., the SpeechRecognition library). The input here is the voice signal, and the output is text data (e.g., "Line 1, abnormal"). The device temporarily stores this text data.

[1131] Step 3:

[1132] The terminal sends the converted text data to the server. The input here is the text data generated in step 2, and the output is the transfer to the server. The text data is sent to the server via the network.

[1133] Step 4:

[1134] The server analyzes the received text data and extracts keywords using a keyword extraction module (e.g., a natural language processing engine). The input here is the text data, and the output is the extracted keywords (e.g., "Line 1" and "Abnormal"). The server stores the keywords as variables.

[1135] Step 5:

[1136] The server recognizes emotions from the user's voice using an emotion engine (e.g., a transformers pipeline for emotion analysis). The input here is the audio signal or text data obtained in step 2, and the output is the recognized emotion (e.g., "tension"). The server stores the emotion information as a variable.

[1137] Step 6:

[1138] The server inputs the extracted keywords and recognized emotions into a generative AI model (e.g., GPT-2) to generate natural-sounding sentences. The input here is keywords and emotion information, and the output is a generated sentence (e.g., "I'm nervous, there's something wrong with line 1"). The generative AI model uses "Line 1 is abnormal, the emotion is nervous" as the prompt sentence.

[1139] Step 7:

[1140] The generated text is sent from the server to the terminal. The input here is the generated text, and the output is transfer to the terminal. The text data is sent to the terminal via the network.

[1141] Step 8:

[1142] The terminal displays the received text on an output device (e.g., a monitor or speaker). Here, the input is the generated text, and the output is visual or audio feedback to the user. Specific actions include displaying the text on a monitor or playing it aloud through a speaker.

[1143] 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.

[1144] 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.

[1145] 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.

[1146] 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.

[1147] 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.

[1148] 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.

[1149] 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).

[1150] 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.

[1151] 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."

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] The following is further disclosed regarding the above embodiment.

[1165] (Claim 1)

[1166] means for receiving voice input from a user;

[1167] means for converting received speech input into text;

[1168] a means for extracting keywords from a string;

[1169] A means for generating sentences based on the extracted keywords;

[1170] a means for displaying the generated text in an in-game chat;

[1171] A system including:

[1172] (Claim 2)

[1173] 2. The system according to claim 1, wherein the means for converting the voice input into a string of characters uses a natural language processing engine.

[1174] (Claim 3)

[1175] The system of claim 1, wherein the means for generating sentences based on extracted keywords uses a generative AI model.

[1176] "Example 1"

[1177] (Claim 1)

[1178] means for receiving voice input from a user;

[1179] means for converting received speech input into text;

[1180] a means for extracting keywords from a string;

[1181] A means for generating a prompt sentence based on the extracted keywords and generating a sentence using a generative AI model;

[1182] means for displaying the generated sentence on a user interface;

[1183] A system including:

[1184] (Claim 2)

[1185] 2. The system according to claim 1, wherein the means for converting the voice input into a string of characters uses a voice recognition engine.

[1186] (Claim 3)

[1187] The system of claim 1, wherein the means for generating a prompt sentence based on the extracted keywords and generating a sentence using a generative AI model uses a generative AI engine.

[1188] "Application Example 1"

[1189] (Claim 1)

[1190] means for receiving voice input from a user;

[1191] means for converting received speech input into text;

[1192] a means for extracting keywords from a string;

[1193] A means for generating sentences based on the extracted keywords;

[1194] a means for displaying the generated text;

[1195] A system including:

[1196] (Claim 2)

[1197] 2. The system according to claim 1, wherein the means for converting the voice input into a string of characters uses a natural language processing engine.

[1198] (Claim 3)

[1199] 2. The system according to claim 1, wherein the means for generating sentences based on the extracted keywords uses a generation algorithm model.

[1200] (Claim 4)

[1201] 2. The system according to claim 1, further comprising means for displaying the generated text using a chat function or a voice function of the virtual store.

[1202] "Example 2: Combining Emotion Engines"

[1203] (Claim 1)

[1204] means for receiving voice input from a user;

[1205] means for converting received speech input into text;

[1206] a means for extracting keywords from a string;

[1207] A means for recognizing emotions based on extracted keywords;

[1208] A method for generating natural sentences based on emotions and keywords,

[1209] a means for displaying the generated text in an in-game chat;

[1210] A system including:

[1211] (Claim 2)

[1212] 2. The system according to claim 1, wherein the means for converting the voice input into a string of characters uses a voice recognition engine.

[1213] (Claim 3)

[1214] The system of claim 1, wherein the means for generating natural-looking sentences based on emotions and keywords uses a generative AI model.

[1215] "Application example 2 when combining emotion engines"

[1216] (Claim 1)

[1217] means for receiving voice input from a user;

[1218] means for converting received speech input into text;

[1219] a means for extracting keywords from a string;

[1220] A means for generating sentences based on the extracted keywords;

[1221] means for displaying the generated text on an output device;

[1222] means for recognizing a user's emotions and providing information;

[1223] Production systems including.

[1224] (Claim 2)

[1225] 2. The production system according to claim 1, wherein the means for converting the voice input into a character string uses a natural language processing engine.

[1226] (Claim 3)

[1227] 2. The production system according to claim 1, wherein the means for generating sentences based on extracted keywords uses a generative AI model. [Explanation of symbols]

[1228] 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. means for receiving voice input from a user; means for converting received speech input into text; a means for extracting keywords from a string; A means for generating sentences based on the extracted keywords; a means for displaying the generated text in an in-game chat; A system including:

2. 2. The system of claim 1, wherein the means for converting the speech input into a string of characters uses a natural language processing engine.

3. 2. The system according to claim 1, wherein the means for generating sentences based on extracted keywords uses a generative AI model.

Images