System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining speech; means for converting the obtained speech into text data; means for performing sentiment analysis on the converted text data; means for converting negative expressions into positive expressions; means for converting the converted positive text data into speech data; and means for playing the converted speech data to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In everyday environments such as the workplace and home, there is a problem known as "emotional contagion," where the anger or bad mood of others negatively affects one's own mood and productivity. This problem can spread negative emotions and reduce the productivity of the entire team. In particular, angry or bad comments can have a negative impact on people who are not directly present. To solve this problem, a method is needed to properly process surrounding audio information and remove or convert negative expressions. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means: a system including means for acquiring speech, means for converting the acquired speech into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into speech data, and means for playing the converted speech data to a user. In this system, the sentiment analysis means analyzes the text data using a generative model, and the means for converting speech into text data uses a speech recognition API. This allows the user to receive only positive speech information, allowing them to continue working in a comfortable environment while maintaining their productivity.

[0006] "Means for acquiring audio" refers to a device or function that detects surrounding audio and records it as digital audio data.

[0007] "Means for converting into text data" refers to software or services for converting acquired voice data into text format.

[0008] "Sentiment analysis methods" refers to generative models and algorithms that analyze text data and identify emotions from its context and vocabulary.

[0009] "Means of converting negative expressions into positive expressions" refers to systems or software that have the ability to automatically replace negative text determined through sentiment analysis with positive content.

[0010] "Means for converting into audio data" refers to speech synthesis technology and services for reconverting text data into speech data.

[0011] The "means for playing back to the user" refers to an audio output device such as an earphone or speaker that plays back audio data to the user.

[0012] A "generative model" refers to an algorithm or model that uses machine learning and natural language processing to analyze text data and determine emotions, etc.

[0013] "Speech Recognition API" means an external service or tool that provides a programmatic interface for converting speech to text. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system that captures sounds around a user and processes them in real time. The system includes earphones (terminals) worn by the user and a server that receives and processes audio data from the user.

[0036] System Configuration

[0037] 1. Terminal

[0038] Audio collection: Obtains audio around the user through a microphone.

[0039] Data transmission: The acquired audio data is sent to the server.

[0040] Play Audio: Plays the processed audio sent from the server to the user.

[0041] 2. Server

[0042] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[0043] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[0044] Text transformation: Transform identified negative expressions into positive ones.

[0045] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[0046] Data transmission: The converted audio data is sent back to the device.

[0047] Example

[0048] The user's working environment in the office

[0049] A user is wearing earphones and working in an office.

[0050] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0051] The device transmits the audio data to the server in real time.

[0052] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0053] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0054] The server transforms negative statements into positive statements (e.g., "It would be great if you could help me complete this task").

[0055] The server converts the converted positive text into speech and sends it to the device.

[0056] The device plays a positive sound to the user.

[0057] In this way, users can hear negative sounds occurring in the workplace converted into positive sounds, allowing them to work comfortably while maintaining productivity.

[0058] Technical effects

[0059] This system prevents stress and loss of productivity by providing only positive information to users without blocking out surrounding audio information. In addition, because the system operates in real time, users can always work in an optimized audio environment.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[0063] Step 2:

[0064] The device converts the captured audio data into a byte stream and sends it to a server over the Internet in real time.

[0065] Step 3:

[0066] The server sends the received audio data to the Google Speech-to-Text API, which converts the audio into text data, which becomes a sentence like "Why isn't this finished yet?"

[0067] Step 4:

[0068] The server uses the generative AI model to perform sentiment analysis on the text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[0069] Step 5:

[0070] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0071] Step 6:

[0072] The server then passes the converted positive text to text-to-speech software, which converts it back into speech data, generating a speech that says, "It would be great if you could help me complete this task."

[0073] Step 7:

[0074] The server converts the generated positive voice data into a packet format and transmits it to the terminal via the Internet.

[0075] Step 8:

[0076] The device plays the received positive voice data to the user, who can hear the positive message through the earphone.

[0077] Step 9:

[0078] By listening to positive audio, users can focus on their work and daily life without being negatively influenced.

[0079] Example 1

[0080] 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."

[0081] In modern workplaces and social environments, negative audio information is a common problem, causing stress and reducing productivity. However, conventional technologies do not adequately provide a means to not only block out surrounding audio information, but also to convert negative audio into positive audio in real time.

[0082] 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.

[0083] In this invention, the server includes means for acquiring voice, means for transmitting the acquired voice to data, means for converting the acquired voice to text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into sound data, and means for playing the converted sound data to the user. This makes it possible to convert negative voices in the surrounding area into positive voices in real time, thereby reducing stress for the user and improving productivity.

[0084] The "means for acquiring sound" is a means for collecting sound around the user using a device such as a microphone.

[0085] The "transmission means for converting the acquired voice into data" is a means for transmitting the collected voice data to a server via an appropriate communication means (for example, Wi-Fi or Bluetooth).

[0086] The "means for converting the acquired voice into text data" refers to a means for using a voice recognition technique to convert the received voice data into character data.

[0087] "Means for sentiment analysis of converted text data" refers to means for analyzing emotions contained in text data using an AI model or the like, and identifying emotions such as negative or positive.

[0088] "Means for converting negative expressions into positive expressions" refers to a means for replacing negative expressions identified through sentiment analysis with positive expressions using rule-based logic and natural language processing technology.

[0089] The "means for converting the converted positive text data into sound data" refers to a means for converting the positive text data into sound data again using a voice synthesis technique.

[0090] The "means for reproducing the converted sound data to the user" refers to a means for providing the converted sound data to the user through audio equipment such as earphones or speakers.

[0091] The present invention is a system for capturing sounds around a user and processing them in real time. The system includes a sound collection device (terminal) and a server that receives and processes the collected sound data.

[0092] System Configuration

[0093] 1. Terminal

[0094] Sound collection: A microphone built into the earphones worn by the user collects sounds around the user with high sensitivity, such as conversations in an office or environmental sounds.

[0095] Data transmission: The collected voice data is sent to a server via Wi-Fi or Bluetooth. This data transmission is done in real time, so it is important to act without delay.

[0096] 2. Server

[0097] Speech Recognition: The server uses speech recognition technology such as the Google Speech-to-Text API to convert the voice data sent from the device into text data. For example, the speech "Why isn't this finished yet?" is converted into text.

[0098] Sentiment analysis: A generative AI model is used to analyze the sentiment of the converted text data, identifying negative expressions within the text. The AI ​​model used is a common model that provides natural language processing techniques.

[0099] Text transformation: Negative expressions identified through sentiment analysis are transformed into positive ones through rule-based text transformation routines, for example, transforming "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0100] Speech synthesis: The converted positive text is converted back into voice data using the Google Text-to-Speech API, etc. This produces clear, natural-sounding speech for the user.

[0101] Data transmission: The converted audio data is sent back to the device via Wi-Fi or Bluetooth.

[0102] 3. Terminal

[0103] Audio playback: The terminal can play the converted positive audio data to the user through the earphone speaker.

[0104] Specific examples

[0105] For example, imagine a user working in an office. While working with earphones in, the user receives negative feedback from their boss, such as "Why haven't you finished this yet?" The system works as follows:

[0106] 1. The device picks up the boss's remarks through the microphone.

[0107] 2. The device sends the acquired audio data to the server.

[0108] 3. The server converts the audio data into text data using the Google Speech-to-Text API.

[0109] 4. The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[0110] 5. The server translates "Why isn't this finished yet?" into a positive phrase like "It would be great if you could help me finish this task."

[0111] 6. The server uses the Google Text-to-Speech API to convert the converted positive text back into audio data.

[0112] 7. The server sends the converted audio data back to the device.

[0113] 8. The device plays the converted positive audio data to the user through the earphone speaker.

[0114] An example of a prompt sentence is "Why isn't this finished yet?" By collecting and processing this speech data, users can hear a positive message such as "I'd appreciate it if you could help me complete this task." This can help users feel less stressed at work and improve their productivity.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: Audio Collection:

[0117] The device picks up the user's surrounding sounds using a microphone built into the earphones. During this process, the high-sensitivity microphone picks up surrounding conversations and environmental sounds (e.g., "Why isn't this finished yet?").

[0118] Input: Live sounds from the user's surroundings.

[0119] Output: Collected audio data.

[0120] Step 2: Send data:

[0121] The device transmits the captured audio data to a server in real time, encrypted using Wi-Fi or Bluetooth protocols.

[0122] Input: Collected audio data.

[0123] Output: The audio data sent to the server.

[0124] Step 3: Voice Recognition:

[0125] The server uses a speech recognition API (for example, Google Speech-to-Text API) to convert the received voice data into text data. In this process, speech such as "Why isn't this finished yet?" is converted into text.

[0126] Input: The audio data sent to the server.

[0127] Output: The converted text data.

[0128] Step 4: Sentiment Analysis:

[0129] The server uses a generative AI model to perform sentiment analysis on the text data, identifying negative expressions in the text (e.g., "Why isn't this finished yet?").

[0130] Input: The converted text data.

[0131] Output: Sentiment analysis result (negative / positive).

[0132] Step 5: Text conversion:

[0133] The server converts negative expressions into positive ones based on sentiment analysis, in the process replacing "Why isn't this finished yet?" with "It would be great if you could help me finish this task."

[0134] Input: Sentiment analysis results and converted text data.

[0135] Output: The converted positive text data.

[0136] Step 6: Speech synthesis:

[0137] The server converts the positive text data back into audio data using text-to-speech software (e.g., Google Text-to-Speech API).

[0138] Input: Transformed positive text data.

[0139] Output: Retranscoded audio data.

[0140] Step 7: Send data:

[0141] The server then sends the audio data back to the device in real time, where it is encrypted and transmitted over Wi-Fi or Bluetooth.

[0142] Input: Retranscoded audio data.

[0143] Output: The audio data sent to the device.

[0144] Step 8: Audio playback:

[0145] The device plays the converted positive voice data to the user through the earphone speaker, and the user can clearly hear the converted positive message (e.g., "It would be helpful if you could help me complete this task").

[0146] Input: Audio data sent to the device.

[0147] Output: Positive speech that is played to the user.

[0148] (Application example 1)

[0149] 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."

[0150] In high-stress environments such as factories, workers can receive negative instructions and feedback directly from managers, which increases their mental burden and reduces productivity. In such environments, smooth communication is important, and a system is needed that can convert negative expressions into positive ones.

[0151] 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.

[0152] In this invention, the server includes means for acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for providing the converted voice data to workers in the factory in real time. This allows workers to hear voice converted into positive expressions without receiving negative feedback, thereby reducing mental stress and improving productivity.

[0153] "Means for acquiring audio" refers to a device or system that collects environmental sounds around the user and converts them into digital signals.

[0154] "Means for converting captured speech into text data" refers to the process or technology for converting speech data into text data, typically using speech recognition software or an API.

[0155] "Means for sentiment analysis of converted text data" refers to technology that analyzes the content of text data and identifies the emotions and sensibilities contained therein, and uses generative models and natural language processing.

[0156] "Methods of transforming negative expressions into positive expressions" refers to techniques or processes that transform negative expressions identified through sentiment analysis into positive, forward-looking expressions.

[0157] "Means for converting converted positive text data into voice data" refers to a technology or system that converts text data converted into positive expressions back into voice data.

[0158] "Means for playing the converted audio data to the user" refers to a device or system that outputs the converted audio data to the user so that it can be heard.

[0159] "Means for providing the converted positive voice data to factory workers in real time" refers to technology or systems for immediately transmitting and playing the converted positive voice data to factory workers with as little delay as possible.

[0160] This invention is a system that facilitates communication between workers and managers in a factory, allowing workers to hear voices converted into positive expressions without receiving negative feedback. The specific form of this system is shown below.

[0161] 1. How to get audio:

[0162] The system uses earphones with a microphone to capture audio from the user's surroundings in the factory. These earphones are intended to be worn by workers at all times. This voice capture function is activated when the user receives instructions or feedback from the manager.

[0163] 2. Means for converting the captured audio into text data:

[0164] The captured voice data is sent to a server, where it is converted into text data using the Google Speech-to-Text API. This conversion process is done in real time, so the data can proceed to the next step without delay.

[0165] 3. Means of sentiment analysis on converted text data:

[0166] The server performs sentiment analysis on the converted text data using the Google Cloud Natural Language API to determine whether it contains negative sentiment. This process checks whether the instructions or feedback are negative.

[0167] 4. Ways to transform negative statements into positive ones:

[0168] If the sentiment analysis identifies a negative response, the server uses a generative AI model to convert the negative portion of the text into a positive one, using the T5 model from the Transformers library and a prompt sentence to generate a positive response.

[0169] Example prompt sentence:

[0170] Transform the following negative sentences into positive ones:

[0171] Why haven't you finished this job yet?

[0172] 5. Means for converting the converted positive text data into audio data:

[0173] The converted positive text data is then converted back into audio data using the Google Cloud Text-to-Speech API, which generates audio data that is then sent to the user's earphones.

[0174] 6. Means for playing the converted audio data to the user:

[0175] Finally, the earphones play the converted positive voice data back to the user, allowing the worker to hear the positively converted voice without receiving direct negative feedback.

[0176] For example, if a worker on a factory painting line receives negative feedback such as, "Why haven't you finished this job yet?", the system will convert this into a positive response such as, "Shall I help you finish this job?" This will reduce stress for the worker and increase productivity.

[0177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0178] Step 1:

[0179] Audio capture by device

[0180] Input: Sound from the user's surroundings in the factory

[0181] How it works: The user wears earphones with a microphone and captures surrounding sounds in real time.

[0182] Output: Captured audio data

[0183] Step 2:

[0184] Converting audio data to text

[0185] Input: Captured audio data

[0186] How it works: Voice data is sent to a server, which then converts it into text using the Google Speech-to-Text API. It uses speech recognition technology to represent human speech as a string of characters.

[0187] Output: Text data

[0188] Step 3:

[0189] Sentiment analysis of text data

[0190] Input: Converted text data

[0191] How it works: The server uses the Google Cloud Natural Language API on the text data to analyze the content of the text and determine whether it contains negative sentiment. It then uses a generative model to calculate a sentiment score for the text.

[0192] Output: Sentiment score of the text and whether it contains negative expressions

[0193] Step 4:

[0194] Transforming negative expressions into positive ones

[0195] Input: Sentiment analysis results (if negative expressions are identified)

[0196] How it works: The server uses a generative AI model to convert text data that has been identified as negative by sentiment analysis into positive expressions. Specifically, it uses the T5 model from the Transformers library and performs the conversion based on the following prompt sentence:

[0197] Example prompt: "Transform the following negative sentences into positive ones: Why haven't you finished this work yet?"

[0198] Output: Positively converted text data

[0199] Step 5:

[0200] Speech conversion of positive text data

[0201] Input: Positively converted text data

[0202] How it works: The server uses the Google Cloud Text-to-Speech API to convert the positive text data into audio data, using appropriate speech synthesis technology to convert the text into natural-sounding speech.

[0203] Output: Converted positive speech data

[0204] Step 6:

[0205] Playing audio to the user

[0206] Input: Transduced positive speech data

[0207] How it works: The device receives the converted positive voice data and plays it through the user's earphones, allowing the user to hear the voice converted into positive expressions in real time.

[0208] Output: A positive voice that the user hears

[0209] 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.

[0210] The present invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes voice data from the user, and an emotion engine that recognizes the user's emotions.

[0211] System Configuration

[0212] 1. Terminal

[0213] Audio collection: Obtains audio around the user through a microphone.

[0214] Data transmission: The acquired audio data is sent to the server.

[0215] User emotion collection: Analyze the user's voice patterns and biometric signals using an emotion engine.

[0216] Play Audio: Plays the processed audio sent from the server to the user.

[0217] 2. Server

[0218] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[0219] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[0220] Text transformation: Transform identified negative expressions into positive ones.

[0221] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[0222] Data transmission: The converted audio data is sent back to the device.

[0223] 3. Emotion Engine

[0224] Biosignal analysis: Measures the user's heart rate, electrodermal activity, etc. to analyze the user's emotional state.

[0225] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[0226] Example

[0227] The user's working environment in the office

[0228] A user is wearing earphones and working in an office.

[0229] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0230] The device transmits the audio data to the server in real time.

[0231] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[0232] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0233] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0234] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0235] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[0236] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[0237] Technical effects

[0238] This system prevents stress and loss of productivity by providing only positive information to the user without blocking out surrounding audio information. It also uses an emotion engine to grasp the user's current emotional state and provide optimal feedback accordingly, allowing users to work in a real-time optimized audio environment.

[0239] The processing flow will be explained below.

[0240] Step 1:

[0241] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[0242] Step 2:

[0243] The device converts the voice data it acquires in real time into a digital format and transmits it to a server via a network.

[0244] Step 3:

[0245] The device uses an emotion engine to analyze bio-signals such as the user's heart rate, electrodermal activity, and vocal tone to recognize the user's emotional state in real time.

[0246] Step 4:

[0247] The server sends the received voice data to the Google Speech-to-Text API, which converts the voice data into text data. For example, the text data generated is "Why isn't this finished yet?"

[0248] Step 5:

[0249] The server uses the generative AI model to perform sentiment analysis on the converted text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[0250] Step 6:

[0251] The server translates negative statements into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0252] Step 7:

[0253] The server uses text-to-speech software to generate audio data to convert the positive text into speech, generating a speech that reads, "It would be great if you could help me complete this task."

[0254] Step 8:

[0255] The server transmits the generated positive voice data to the terminal via the Internet.

[0256] Step 9:

[0257] The device plays the received positive voice data through the user's earphone, allowing the user to hear the positive message through the earphone.

[0258] Step 10:

[0259] Users can listen to positive voices, avoiding negative influences and continuing to concentrate on their work or daily life. In addition, the system monitors the user's emotional state in real time and provides feedback accordingly, maintaining an optimal working environment.

[0260] As a result, the present invention constantly monitors the user's emotional state and converts negative sounds from the surrounding environment into positive ones and plays them back, thereby reducing the user's stress and improving work efficiency.

[0261] Example 2

[0262] 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."

[0263] In modern society, many people experience stress due to negative voices and expressions in the workplace and in public places. This environment can have a negative impact on users' mental health and productivity. Furthermore, the lack of a system that can instantly convert negative feedback into positive ones makes it difficult for users to obtain positive information in real time.

[0264] 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 transmitting acquired voice data to the server, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for playing the converted voice data to the user. This allows the user to convert negative voices around them into positive information in real time and receive it, which is expected to reduce stress and improve productivity.

[0265] "User" refers to an individual who uses the system.

[0266] "Ambient audio" refers to all audio data occurring in the user's surrounding environment.

[0267] A "terminal" is a device worn by a user, and refers to a hardware device that has functions such as acquiring, transmitting, and playing audio.

[0268] "Audio data" refers to audio information converted into a digital signal.

[0269] "Server" refers to a computer system for processing audio data.

[0270] "Biological signals" refers to physiological data obtained from the human body, such as a user's heart rate or electrodermal activity.

[0271] "Emotion engine" refers to software or hardware functionality that analyzes bio-signals and audio data to identify a user's emotional state.

[0272] "Text data" refers to digital data that has been converted from voice data into text information.

[0273] "Sentiment analysis" refers to the process of identifying emotions from the content of text data, and classifying and evaluating those emotions.

[0274] A "generative model" refers to an AI model used for natural language processing, etc., that has the ability to provide appropriate responses or conversions to specific inputs.

[0275] "Conversion means" refers to a method or device for converting particular data into a different data format.

[0276] "Speech recognition API" refers to a program interface for converting voice data into text data.

[0277] "Text-to-speech software" refers to software that has the function of converting text data into audio data and reading it aloud.

[0278] This invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes the sound data, and an emotion engine that recognizes the user's emotions.

[0279] System Configuration

[0280] 1. Terminal

[0281] Audio collection: The device captures the user's surroundings through a microphone, allowing it to collect audio data tailored to the user's surroundings.

[0282] Data transmission: The device transmits the captured audio data to the server in real time. Data transmission requires a high-speed and stable connection.

[0283] User emotion collection: The device analyzes the user's biometric signals (heart rate, electrodermal activity, etc.) using an emotion engine, which then identifies the user's current emotional state.

[0284] Audio playback: The device plays the processed audio data sent from the server to the user. The audio played is the converted positive audio.

[0285] 2. Server

[0286] Speech recognition: The server converts the voice data received from the device into text data using the Google Speech-to-Text API, etc., and obtains voice as text information with high accuracy.

[0287] Sentiment analysis: The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[0288] Text transformation: The server transforms identified negative phrases into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0289] Speech synthesis: The server converts the converted positive text back into speech data using text-to-speech software.

[0290] Data transmission: The server sends the converted audio data back to the device.

[0291] 3. Emotion Engine

[0292] Biosignal analysis: The device measures the user's heart rate and electrodermal activity to analyze the user's emotional state.

[0293] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[0294] Specific examples

[0295] The user's working environment in the office

[0296] A user is wearing earphones and working in an office.

[0297] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0298] The device transmits the audio data to the server in real time.

[0299] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[0300] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0301] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0302] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0303] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[0304] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[0305] Prompt Sentence Examples

[0306] "My boss yells, 'Why isn't this finished yet?'"

[0307] This system allows users to convert negative voices around them into positive information in real time, which is expected to reduce stress and improve productivity.

[0308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0309] Program processing flow

[0310] Step 1:

[0311] The user puts on a compatible earphone, which is equipped with a microphone and biometric sensors, and is ready to capture ambient sounds and the user's biometric data.

[0312] Step 2:

[0313] The device uses a built-in microphone to collect the user's surrounding sounds in real time. The input is environmental sounds and conversational voices, which are then converted into digital form. Specifically, analog audio signals are encoded into digital data.

[0314] Step 3:

[0315] The voice data acquired by the device is sent to the server in real time. The voice data as input is transferred to the server via the network. The communication requires a high-speed and stable connection.

[0316] Step 4:

[0317] The device uses built-in sensors to acquire biometric signals such as the user's heart rate and electrodermal activity. The biometric data is then sent to an emotion engine to analyze the user's emotional state. Specifically, changes in heart rate and electrodermal activity are monitored in real time and the data is transmitted digitally.

[0318] Step 5:

[0319] The server converts the voice data received from the device into text data using the Google Speech-to-Text API. The input is digital voice data, and the output is analyzed text data. Specifically, a speech recognition algorithm is run on the server to convert the acquired digital voice signal into an appropriate string of characters.

[0320] Step 6:

[0321] The server performs sentiment analysis on the text data using a generative AI model. The input is the converted text data, and the output is the results of identifying negative expressions. Specifically, natural language processing techniques are used to analyze the sentiment within the text and detect negative keywords and phrases.

[0322] Step 7:

[0323] The server converts negative expressions into positive ones. The input is negative text data identified through sentiment analysis, and the output is the converted positive text data. Specifically, it uses a generative AI model to replace it with an appropriate positive phrase.

[0324] Step 8:

[0325] The server reconverts the positive text data into voice data using text-to-speech software. The input is positive text data, and the output is synthesized positive voice data. Specifically, the server uses text-to-speech software to convert the data into natural voice.

[0326] Step 9:

[0327] The server sends the converted voice data to the terminal. The input is the synthesized positive voice data, and the output is the voice data sent to the terminal. This allows the user to receive a positive message.

[0328] Step 10:

[0329] The terminal plays the positive voice data sent from the server to the user. The input is the positive voice data, and the output is the voice played to the user through the earphone. Specifically, the converted positive voice is played using the earphone speaker.

[0330] As a result, this system instantly converts negative voices around the user into positive voices, enabling productivity to be improved and stress to be reduced.

[0331] (Application example 2)

[0332] 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."

[0333] When employees in physical stores receive negative comments from customers while serving them, the emotional damage can have a negative impact on work efficiency and customer satisfaction. There is a need for a method that allows employees to convert negative words and expressions into positive ones in real time, thereby smoothing interactions with customers and improving customer satisfaction.

[0334] 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 acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, means for playing the converted voice data to the user, and means for collecting surrounding voices, converting negative expressions into positive expressions in real time, and providing the converted voice data to the user, thereby optimizing the user's emotional state. This enables employees in physical stores to convert negative expressions into positive expressions through dialogue with customers, thereby improving the efficiency of customer service operations and customer satisfaction.

[0335] The "means for acquiring sound" is a function for collecting surrounding sound through a sound collecting device such as a microphone.

[0336] The "means for converting acquired voice into text data" is a function that converts acquired voice data into character information (text data) using voice recognition technology.

[0337] "Means for sentiment analysis of converted text data" refers to a function that uses sentiment analysis software, such as a generative model, to analyze sentiment within the text data and identify its content.

[0338] The "means for converting negative expressions into positive expressions" is an algorithm or software that converts the analyzed negative expressions into positive expressions.

[0339] "Means for converting converted positive text data into audio data" refers to the function of converting positive text data into audio data using text-to-speech software.

[0340] The "means for playing back converted audio data to the user" is a function for playing back processed audio data to the user through earphones or speakers.

[0341] "Means for optimizing the user's emotional state by collecting surrounding sounds, converting negative expressions into positive ones in real time, and providing them to the user" is a function that manages the user's emotional state and mental stress by monitoring the audio environment around the user, instantly converting statements that may cause negative emotions into positive ones, and providing them to the user.

[0342] The present invention provides a system for converting negative expressions into positive ones in real time during customer interactions, thereby optimizing the emotional state of employees. The system includes a means for acquiring voice, a means for converting the acquired voice into text data, a means for sentiment analysis of the converted text data, a means for converting negative expressions into positive ones, a means for converting the converted positive text data into voice data, a means for playing the converted voice data to a user, and a means for optimizing the emotional state of the user by collecting surrounding voices and providing positive information in real time.

[0343] The functions of the system and the hardware and software used will be specifically described below.

[0344] 1. Audio acquisition method

[0345] The smart glasses use built-in microphones to collect ambient sounds, enabling real-time sound collection.

[0346] 2. Means of converting voice to text data

[0347] Using a speech recognition API (e.g., Google Speech-to-Text API), the collected speech is converted into text data, which allows the speech data to be converted into analyzable text data.

[0348] 3. Sentiment Analysis Methods for Text Data

[0349] Generative AI models (e.g., Hugging Face Transformers sentiment analysis pipeline) are used to analyze sentiment within text data and identify negative expressions.

[0350] 4. A way to transform negative statements into positive ones

[0351] The identified negative text is converted into positive text through a conversion algorithm or a dedicated API, which allows for conversion into positive expressions.

[0352] 5. A means of converting positive text data into audio data

[0353] The positive text data is converted into audio data using the Google Cloud Text-to-Speech API, which then provides the converted positive text data to the user in an appropriate audio format.

[0354] 6. A means of playing audio data to the user

[0355] The converted positive voice data is played back to the user using the built-in speaker of the smart glasses, allowing the user to hear the positive information in real time.

[0356] 7. User Emotion Optimization

[0357] By collecting surrounding sounds, converting negative expressions into positive ones in real time, and playing them back, the system optimizes the user's emotional state in real time, helping users reduce stress and improve work efficiency.

[0358] Specific examples

[0359] For example, if an employee in a physical store is serving a customer face-to-face and the customer says, "I don't like this product," the system collects the voice, converts it into text, and recognizes it as a negative comment.The system then converts the negative comment into a more positive expression, such as, "We'll suggest some improvements, so please let us know your thoughts," and reconverts it into voice data to be conveyed to the employee.

[0360] Prompt Sentence Examples

[0361] Negative comments:

[0362] "Why didn't you like this product?"

[0363] Positive transformation:

[0364] "Please let me know your thoughts so I can suggest some improvements."

[0365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0366] Step 1:

[0367] The microphone on the device (smart glasses) is used to collect the conversational voice between the user and the customer in real time. The input is the surrounding sound, and the output is the voice data.

[0368] Step 2:

[0369] The collected voice data is sent from the terminal to the server. The input is the voice data sent from the terminal, and the output is the voice data transferred to the server.

[0370] Step 3:

[0371] The received voice data is converted into text data using the server's speech recognition API (e.g., Google Speech-to-Text API). The input is the voice data transferred to the server, and the output is text data.

[0372] Step 4:

[0373] The server's sentiment analysis method is used to analyze the sentiment in the transformed text data. A generative AI model (e.g., Hugging Face Transformers) is used to identify negative expressions. The input is the text data, and the output is a negative or positive sentiment label.

[0374] Step 5:

[0375] The server uses a text transformation algorithm or API to transform the identified negative text into positive text. The input is text data containing negative expressions, and the output is text data containing positive expressions.

[0376] Step 6:

[0377] The converted positive text data is converted into speech data using the Google Cloud Text-to-Speech API on the server. The input is text data containing positive expressions, and the output is positive speech data.

[0378] Step 7:

[0379] The converted positive voice data is sent from the server to the terminal. The input is the positive voice data on the server, and the output is the positive voice data sent to the terminal.

[0380] Step 8:

[0381] Uses the device's speaker to play positive voice data to the user. The input is the positive voice data sent to the device, and the output is the positive voice played to the user.

[0382] This allows users to receive positive information in real time, reducing stress when dealing with customers.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] [Second embodiment]

[0387] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0388] 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.

[0389] 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).

[0390] 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.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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."

[0399] The present invention is a system that captures sounds around a user and processes them in real time. The system includes earphones (terminals) worn by the user and a server that receives and processes audio data from the user.

[0400] System Configuration

[0401] 1. Terminal

[0402] Audio collection: Obtains audio around the user through a microphone.

[0403] Data transmission: The acquired audio data is sent to the server.

[0404] Play Audio: Plays the processed audio sent from the server to the user.

[0405] 2. Server

[0406] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[0407] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[0408] Text transformation: Transform identified negative expressions into positive ones.

[0409] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[0410] Data transmission: The converted audio data is sent back to the device.

[0411] Example

[0412] The user's working environment in the office

[0413] A user is wearing earphones and working in an office.

[0414] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0415] The device transmits the audio data to the server in real time.

[0416] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0417] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0418] The server transforms negative statements into positive statements (e.g., "It would be great if you could help me complete this task").

[0419] The server converts the converted positive text into speech and sends it to the device.

[0420] The device plays a positive sound to the user.

[0421] In this way, users can hear negative sounds occurring in the workplace converted into positive sounds, allowing them to work comfortably while maintaining productivity.

[0422] Technical effects

[0423] This system prevents stress and loss of productivity by providing only positive information to users without blocking out surrounding audio information. In addition, because the system operates in real time, users can always work in an optimized audio environment.

[0424] The processing flow will be explained below.

[0425] Step 1:

[0426] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[0427] Step 2:

[0428] The device converts the captured audio data into a byte stream and sends it to a server over the Internet in real time.

[0429] Step 3:

[0430] The server sends the received audio data to the Google Speech-to-Text API, which converts the audio into text data, which becomes a sentence like "Why isn't this finished yet?"

[0431] Step 4:

[0432] The server uses the generative AI model to perform sentiment analysis on the text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[0433] Step 5:

[0434] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0435] Step 6:

[0436] The server then passes the converted positive text to text-to-speech software, which converts it back into speech data, generating a speech that says, "It would be great if you could help me complete this task."

[0437] Step 7:

[0438] The server converts the generated positive voice data into a packet format and transmits it to the terminal via the Internet.

[0439] Step 8:

[0440] The device plays the received positive voice data to the user, who can hear the positive message through the earphone.

[0441] Step 9:

[0442] By listening to positive audio, users can focus on their work and daily life without being negatively influenced.

[0443] Example 1

[0444] 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."

[0445] In modern workplaces and social environments, negative audio information is a common problem, causing stress and reducing productivity. However, conventional technologies do not adequately provide a means to not only block out surrounding audio information, but also to convert negative audio into positive audio in real time.

[0446] 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.

[0447] In this invention, the server includes means for acquiring voice, means for transmitting the acquired voice to data, means for converting the acquired voice to text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into sound data, and means for playing the converted sound data to the user. This makes it possible to convert negative voices in the surrounding area into positive voices in real time, thereby reducing stress for the user and improving productivity.

[0448] The "means for acquiring sound" is a means for collecting sound around the user using a device such as a microphone.

[0449] The "transmission means for converting the acquired voice into data" is a means for transmitting the collected voice data to a server via an appropriate communication means (for example, Wi-Fi or Bluetooth).

[0450] The "means for converting acquired voice into text data" refers to a means for using voice recognition technology to convert received voice data into character data.

[0451] "Means for sentiment analysis of converted text data" refers to means for analyzing emotions contained in text data using an AI model or the like, and identifying emotions such as negative or positive.

[0452] "Means for converting negative expressions into positive expressions" refers to a means for replacing negative expressions identified through sentiment analysis with positive expressions using rule-based logic and natural language processing technology.

[0453] The "means for converting the converted positive text data into sound data" refers to a means for converting the positive text data into sound data again using a voice synthesis technique.

[0454] The "means for reproducing the converted sound data to the user" refers to a means for providing the converted sound data to the user through audio equipment such as earphones or speakers.

[0455] The present invention is a system for capturing sounds around a user and processing them in real time. The system includes a sound collection device (terminal) and a server that receives and processes the collected sound data.

[0456] System Configuration

[0457] 1. Terminal

[0458] Sound collection: A microphone built into the earphones worn by the user collects sounds around the user with high sensitivity, such as conversations in an office or environmental sounds.

[0459] Data transmission: The collected voice data is sent to a server via Wi-Fi or Bluetooth. This data transmission is done in real time, so it is important to act without delay.

[0460] 2. Server

[0461] Speech Recognition: The server uses speech recognition technology such as the Google Speech-to-Text API to convert the voice data sent from the device into text data. For example, the speech "Why isn't this finished yet?" is converted into text.

[0462] Sentiment analysis: A generative AI model is used to analyze the sentiment of the converted text data, identifying negative expressions within the text. The AI ​​model used is a common model that provides natural language processing techniques.

[0463] Text transformation: Negative expressions identified through sentiment analysis are transformed into positive ones through rule-based text transformation routines, for example, transforming "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0464] Speech synthesis: The converted positive text is converted back into voice data using the Google Text-to-Speech API, etc. This produces clear, natural-sounding speech for the user.

[0465] Data transmission: The converted audio data is sent back to the device via Wi-Fi or Bluetooth.

[0466] 3. Terminal

[0467] Audio playback: The terminal can play the converted positive audio data to the user through the earphone speaker.

[0468] Specific examples

[0469] For example, imagine a user working in an office. While working with earphones in, the user receives negative feedback from their boss, such as "Why haven't you finished this yet?" The system works as follows:

[0470] 1. The device picks up the boss's remarks through the microphone.

[0471] 2. The device sends the acquired audio data to the server.

[0472] 3. The server converts the audio data into text data using the Google Speech-to-Text API.

[0473] 4. The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[0474] 5. The server translates "Why isn't this finished yet?" into a positive phrase like "It would be great if you could help me finish this task."

[0475] 6. The server uses the Google Text-to-Speech API to convert the converted positive text back into audio data.

[0476] 7. The server sends the converted audio data back to the device.

[0477] 8. The device plays the converted positive audio data to the user through the earphone speaker.

[0478] An example of a prompt sentence is "Why isn't this finished yet?" By collecting and processing this speech data, users can hear a positive message such as "I'd appreciate it if you could help me complete this task." This can help users feel less stressed at work and improve their productivity.

[0479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0480] Step 1: Audio Collection:

[0481] The device picks up the user's surrounding sounds using a microphone built into the earphones. During this process, the high-sensitivity microphone picks up surrounding conversations and environmental sounds (e.g., "Why isn't this finished yet?").

[0482] Input: Live sounds from the user's surroundings.

[0483] Output: Collected audio data.

[0484] Step 2: Send data:

[0485] The device transmits the captured audio data to a server in real time, encrypted using Wi-Fi or Bluetooth protocols.

[0486] Input: Collected audio data.

[0487] Output: The audio data sent to the server.

[0488] Step 3: Voice Recognition:

[0489] The server uses a speech recognition API (for example, Google Speech-to-Text API) to convert the received voice data into text data. In this process, speech such as "Why isn't this finished yet?" is converted into text.

[0490] Input: The audio data sent to the server.

[0491] Output: The converted text data.

[0492] Step 4: Sentiment Analysis:

[0493] The server uses a generative AI model to perform sentiment analysis on the text data, identifying negative expressions in the text (e.g., "Why isn't this finished yet?").

[0494] Input: The converted text data.

[0495] Output: Sentiment analysis result (negative / positive).

[0496] Step 5: Text conversion:

[0497] The server converts negative expressions into positive ones based on sentiment analysis, and in the process, "Why isn't this finished yet?" becomes "It would be great if you could help me finish this task."

[0498] Input: Sentiment analysis results and converted text data.

[0499] Output: The converted positive text data.

[0500] Step 6: Speech synthesis:

[0501] The server converts the positive text data back into audio data using text-to-speech software (e.g., Google Text-to-Speech API).

[0502] Input: Transformed positive text data.

[0503] Output: Retranscoded audio data.

[0504] Step 7: Send data:

[0505] The server then sends the audio data back to the device in real time, where it is encrypted and transmitted over Wi-Fi or Bluetooth.

[0506] Input: Retranscoded audio data.

[0507] Output: The audio data sent to the device.

[0508] Step 8: Audio playback:

[0509] The device plays the converted positive voice data to the user through the earphone speaker, and the user can clearly hear the converted positive message (e.g., "It would be helpful if you could help me complete this task").

[0510] Input: Audio data sent to the device.

[0511] Output: Positive speech that is played to the user.

[0512] (Application example 1)

[0513] 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."

[0514] In high-stress environments such as factories, workers can receive negative instructions and feedback directly from managers, which increases their mental burden and reduces productivity. In such environments, smooth communication is important, and a system is needed that can convert negative expressions into positive ones.

[0515] 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.

[0516] In this invention, the server includes means for acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for providing the converted voice data to workers in the factory in real time. This allows workers to hear voice converted into positive expressions without receiving negative feedback, thereby reducing mental stress and improving productivity.

[0517] "Means for acquiring audio" refers to a device or system that collects environmental sounds around the user and converts them into digital signals.

[0518] "Means for converting captured speech into text data" refers to the process or technology for converting speech data into text data, typically using speech recognition software or an API.

[0519] "Means for sentiment analysis of converted text data" refers to technology that analyzes the content of text data and identifies the emotions and sensibilities contained therein, and uses generative models and natural language processing.

[0520] "Methods of transforming negative expressions into positive expressions" refers to techniques or processes that transform negative expressions identified through sentiment analysis into positive, forward-looking expressions.

[0521] "Means for converting converted positive text data into voice data" refers to a technology or system that converts text data converted into positive expressions back into voice data.

[0522] "Means for playing the converted audio data to the user" refers to a device or system that outputs the converted audio data to the user so that it can be heard.

[0523] "Means for providing the converted positive voice data to factory workers in real time" refers to technology or systems for immediately transmitting and playing the converted positive voice data to factory workers with as little delay as possible.

[0524] This invention is a system that facilitates communication between workers and managers in a factory, allowing workers to hear voices converted into positive expressions without receiving negative feedback. The specific form of this system is shown below.

[0525] 1. How to get audio:

[0526] The system uses earphones with a microphone to capture audio from the user's surroundings in the factory. These earphones are intended to be worn by workers at all times. This voice capture function is activated when the user receives instructions or feedback from the manager.

[0527] 2. Means for converting the captured audio into text data:

[0528] The captured voice data is sent to a server, where it is converted into text data using the Google Speech-to-Text API. This conversion process is done in real time, so the data can proceed to the next step without delay.

[0529] 3. Means of sentiment analysis on converted text data:

[0530] The server performs sentiment analysis on the converted text data using the Google Cloud Natural Language API to determine whether it contains negative sentiment. This process checks whether the instructions or feedback are negative.

[0531] 4. Ways to transform negative statements into positive ones:

[0532] If the sentiment analysis identifies a negative response, the server uses a generative AI model to convert the negative portion of the text into a positive one, using the T5 model from the Transformers library and a prompt sentence to generate a positive response.

[0533] Example prompt sentence:

[0534] Transform the following negative sentences into positive ones:

[0535] Why haven't you finished this job yet?

[0536] 5. Means for converting the converted positive text data into audio data:

[0537] The converted positive text data is then converted back into audio data using the Google Cloud Text-to-Speech API, which generates audio data that is then sent to the user's earphones.

[0538] 6. Means for playing the converted audio data to the user:

[0539] Finally, the earphones play the converted positive voice data back to the user, allowing the worker to hear the positively converted voice without receiving direct negative feedback.

[0540] For example, if a worker on a factory painting line receives negative feedback such as, "Why haven't you finished this job yet?", the system will convert this into a positive response such as, "Shall I help you finish this job?" This will reduce stress for the worker and increase productivity.

[0541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0542] Step 1:

[0543] Audio capture by device

[0544] Input: Sound from the user's surroundings in the factory

[0545] How it works: The user wears earphones with a microphone and captures surrounding sounds in real time.

[0546] Output: Captured audio data

[0547] Step 2:

[0548] Converting audio data to text

[0549] Input: Captured audio data

[0550] How it works: Voice data is sent to a server, which then converts it into text using the Google Speech-to-Text API. It uses speech recognition technology to represent human speech as a string of characters.

[0551] Output: Text data

[0552] Step 3:

[0553] Sentiment analysis of text data

[0554] Input: Converted text data

[0555] How it works: The server uses the Google Cloud Natural Language API on the text data to analyze the content of the text and determine whether it contains negative sentiment. It then uses a generative model to calculate a sentiment score for the text.

[0556] Output: Sentiment score of the text and whether it contains negative expressions

[0557] Step 4:

[0558] Transforming negative expressions into positive ones

[0559] Input: Sentiment analysis results (if negative expressions are identified)

[0560] How it works: The server uses a generative AI model to convert text data that has been identified as negative by sentiment analysis into positive expressions. Specifically, it uses the T5 model from the Transformers library and performs the conversion based on the following prompt sentence:

[0561] Example prompt: "Transform the following negative sentences into positive ones: Why haven't you finished this work yet?"

[0562] Output: Positively converted text data

[0563] Step 5:

[0564] Speech conversion of positive text data

[0565] Input: Positively converted text data

[0566] How it works: The server uses the Google Cloud Text-to-Speech API to convert the positive text data into audio data, using appropriate speech synthesis technology to convert the text into natural-sounding speech.

[0567] Output: Converted positive speech data

[0568] Step 6:

[0569] Playing audio to the user

[0570] Input: Transduced positive speech data

[0571] How it works: The device receives the converted positive voice data and plays it through the user's earphones, allowing the user to hear the voice converted into positive expressions in real time.

[0572] Output: A positive voice that the user hears

[0573] 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.

[0574] The present invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes voice data from the user, and an emotion engine that recognizes the user's emotions.

[0575] System Configuration

[0576] 1. Terminal

[0577] Audio collection: Obtains audio around the user through a microphone.

[0578] Data transmission: The acquired audio data is sent to the server.

[0579] User emotion collection: Analyze the user's voice patterns and biometric signals using an emotion engine.

[0580] Play Audio: Plays the processed audio sent from the server to the user.

[0581] 2. Server

[0582] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[0583] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[0584] Text transformation: Transform identified negative expressions into positive ones.

[0585] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[0586] Data transmission: The converted audio data is sent back to the device.

[0587] 3. Emotion Engine

[0588] Biosignal analysis: Measures the user's heart rate, electrodermal activity, etc. to analyze the user's emotional state.

[0589] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[0590] Example

[0591] The user's working environment in the office

[0592] A user is wearing earphones and working in an office.

[0593] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0594] The device transmits the audio data to the server in real time.

[0595] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[0596] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0597] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0598] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0599] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[0600] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[0601] Technical effects

[0602] This system prevents stress and loss of productivity by providing only positive information to the user without blocking out surrounding audio information. It also uses an emotion engine to grasp the user's current emotional state and provide optimal feedback accordingly, allowing users to work in a real-time optimized audio environment.

[0603] The processing flow will be explained below.

[0604] Step 1:

[0605] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[0606] Step 2:

[0607] The device converts the voice data it acquires in real time into a digital format and transmits it to a server via a network.

[0608] Step 3:

[0609] The device uses an emotion engine to analyze bio-signals such as the user's heart rate, electrodermal activity, and vocal tone to recognize the user's emotional state in real time.

[0610] Step 4:

[0611] The server sends the received voice data to the Google Speech-to-Text API, which converts the voice data into text data. For example, the text data generated is "Why isn't this finished yet?"

[0612] Step 5:

[0613] The server uses the generative AI model to perform sentiment analysis on the converted text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[0614] Step 6:

[0615] The server translates negative statements into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0616] Step 7:

[0617] The server uses text-to-speech software to generate audio data to convert the positive text into speech, generating a speech that reads, "It would be great if you could help me complete this task."

[0618] Step 8:

[0619] The server transmits the generated positive voice data to the terminal via the Internet.

[0620] Step 9:

[0621] The device plays the received positive voice data through the user's earphone, allowing the user to hear the positive message through the earphone.

[0622] Step 10:

[0623] Users can listen to positive voices, avoiding negative influences and continuing to concentrate on their work or daily life. In addition, the system monitors the user's emotional state in real time and provides feedback accordingly, maintaining an optimal working environment.

[0624] As a result, the present invention constantly monitors the user's emotional state and converts negative sounds from the surrounding environment into positive ones and plays them back, thereby reducing the user's stress and improving work efficiency.

[0625] Example 2

[0626] 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."

[0627] In modern society, many people experience stress due to negative voices and expressions in the workplace and in public places. This environment can have a negative impact on users' mental health and productivity. Furthermore, the lack of a system that can instantly convert negative feedback into positive ones makes it difficult for users to obtain positive information in real time.

[0628] 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 transmitting acquired voice data to the server, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for playing the converted voice data to the user. This allows the user to convert negative voices around them into positive information in real time and receive it, which is expected to reduce stress and improve productivity.

[0629] "User" refers to an individual who uses the system.

[0630] "Ambient audio" refers to all audio data occurring in the user's surrounding environment.

[0631] A "terminal" is a device worn by a user, and refers to a hardware device that has functions such as acquiring, transmitting, and playing audio.

[0632] "Audio data" refers to audio information converted into a digital signal.

[0633] "Server" refers to a computer system for processing audio data.

[0634] "Biological signals" refers to physiological data obtained from the human body, such as a user's heart rate or electrodermal activity.

[0635] "Emotion engine" refers to software or hardware functionality that analyzes bio-signals and audio data to identify a user's emotional state.

[0636] "Text data" refers to digital data that has been converted from voice data into text information.

[0637] "Sentiment analysis" refers to the process of identifying emotions from the content of text data, and classifying and evaluating those emotions.

[0638] A "generative model" refers to an AI model used for natural language processing, etc., that has the ability to provide appropriate responses or conversions to specific inputs.

[0639] "Conversion means" refers to a method or device for converting particular data into a different data format.

[0640] "Speech recognition API" refers to a program interface for converting voice data into text data.

[0641] "Text-to-speech software" refers to software that has the function of converting text data into audio data and reading it aloud.

[0642] This invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes the sound data, and an emotion engine that recognizes the user's emotions.

[0643] System Configuration

[0644] 1. Terminal

[0645] Audio collection: The device captures the user's surroundings through a microphone, allowing it to collect audio data tailored to the user's surroundings.

[0646] Data transmission: The device transmits the captured audio data to the server in real time. Data transmission requires a high-speed and stable connection.

[0647] User emotion collection: The device analyzes the user's biometric signals (heart rate, electrodermal activity, etc.) using an emotion engine, which then identifies the user's current emotional state.

[0648] Audio playback: The device plays the processed audio data sent from the server to the user. The audio played is the converted positive audio.

[0649] 2. Server

[0650] Speech recognition: The server converts the voice data received from the device into text data using the Google Speech-to-Text API, etc., and obtains voice as text information with high accuracy.

[0651] Sentiment analysis: The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[0652] Text transformation: The server transforms identified negative phrases into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0653] Speech synthesis: The server converts the converted positive text back into speech data using text-to-speech software.

[0654] Data transmission: The server sends the converted audio data back to the device.

[0655] 3. Emotion Engine

[0656] Biosignal analysis: The device measures the user's heart rate and electrodermal activity to analyze the user's emotional state.

[0657] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[0658] Specific examples

[0659] The user's working environment in the office

[0660] A user is wearing earphones and working in an office.

[0661] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0662] The device transmits the audio data to the server in real time.

[0663] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[0664] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0665] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0666] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0667] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[0668] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[0669] Prompt Sentence Examples

[0670] "My boss yells, 'Why isn't this finished yet?'"

[0671] This system allows users to convert negative voices around them into positive information in real time, which is expected to reduce stress and improve productivity.

[0672] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0673] Program processing flow

[0674] Step 1:

[0675] The user puts on a compatible earphone, which is equipped with a microphone and biometric sensors, and is ready to capture ambient sounds and the user's biometric data.

[0676] Step 2:

[0677] The device uses a built-in microphone to collect the user's surrounding sounds in real time. The input is environmental sounds and conversational voices, which are then converted into digital form. Specifically, analog audio signals are encoded into digital data.

[0678] Step 3:

[0679] The voice data acquired by the device is sent to the server in real time. The voice data as input is transferred to the server via the network. The communication requires a high-speed and stable connection.

[0680] Step 4:

[0681] The device uses built-in sensors to acquire biometric signals such as the user's heart rate and electrodermal activity. The biometric data is then sent to an emotion engine to analyze the user's emotional state. Specifically, changes in heart rate and electrodermal activity are monitored in real time and the data is transmitted digitally.

[0682] Step 5:

[0683] The server converts the voice data received from the device into text data using the Google Speech-to-Text API. The input is digital voice data, and the output is analyzed text data. Specifically, a speech recognition algorithm is run on the server to convert the acquired digital voice signal into an appropriate string of characters.

[0684] Step 6:

[0685] The server performs sentiment analysis on the text data using a generative AI model. The input is the converted text data, and the output is the results of identifying negative expressions. Specifically, natural language processing techniques are used to analyze the sentiment within the text and detect negative keywords and phrases.

[0686] Step 7:

[0687] The server converts negative expressions into positive ones. The input is negative text data identified through sentiment analysis, and the output is the converted positive text data. Specifically, it uses a generative AI model to replace it with an appropriate positive phrase.

[0688] Step 8:

[0689] The server reconverts the positive text data into voice data using text-to-speech software. The input is positive text data, and the output is synthesized positive voice data. Specifically, the server uses text-to-speech software to convert the data into natural voice.

[0690] Step 9:

[0691] The server sends the converted voice data to the terminal. The input is the synthesized positive voice data, and the output is the voice data sent to the terminal. This allows the user to receive a positive message.

[0692] Step 10:

[0693] The terminal plays the positive voice data sent from the server to the user. The input is the positive voice data, and the output is the voice played to the user through the earphone. Specifically, the converted positive voice is played using the earphone speaker.

[0694] As a result, this system instantly converts negative voices around the user into positive voices, enabling productivity to be improved and stress to be reduced.

[0695] (Application example 2)

[0696] 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."

[0697] When employees in physical stores receive negative comments from customers while serving them, the emotional damage can have a negative impact on work efficiency and customer satisfaction. There is a need for a method that allows employees to convert negative words and expressions into positive ones in real time, thereby smoothing interactions with customers and improving customer satisfaction.

[0698] 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 acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, means for playing the converted voice data to the user, and means for collecting surrounding voices, converting negative expressions into positive expressions in real time, and providing the converted voice data to the user, thereby optimizing the user's emotional state. This enables employees in physical stores to convert negative expressions into positive expressions through dialogue with customers, thereby improving the efficiency of customer service operations and customer satisfaction.

[0699] The "means for acquiring sound" is a function for collecting surrounding sound through a sound collecting device such as a microphone.

[0700] The "means for converting acquired voice into text data" is a function that converts acquired voice data into character information (text data) using voice recognition technology.

[0701] "Means for sentiment analysis of converted text data" refers to a function that uses sentiment analysis software, such as a generative model, to analyze sentiment within the text data and identify its content.

[0702] The "means for converting negative expressions into positive expressions" is an algorithm or software that converts the analyzed negative expressions into positive expressions.

[0703] "Means for converting converted positive text data into audio data" refers to the function of converting positive text data into audio data using text-to-speech software.

[0704] The "means for playing back converted audio data to the user" is a function for playing back processed audio data to the user through earphones or speakers.

[0705] "Means for optimizing the user's emotional state by collecting surrounding sounds, converting negative expressions into positive ones in real time, and providing them to the user" is a function that manages the user's emotional state and mental stress by monitoring the audio environment around the user, instantly converting statements that may cause negative emotions into positive ones, and providing them to the user.

[0706] The present invention provides a system for converting negative expressions into positive ones in real time during customer interactions, thereby optimizing the emotional state of employees. The system includes a means for acquiring voice, a means for converting the acquired voice into text data, a means for sentiment analysis of the converted text data, a means for converting negative expressions into positive ones, a means for converting the converted positive text data into voice data, a means for playing the converted voice data to a user, and a means for optimizing the emotional state of the user by collecting surrounding voices and providing positive information in real time.

[0707] The functions of the system and the hardware and software used will be specifically described below.

[0708] 1. Audio acquisition method

[0709] The smart glasses use built-in microphones to collect ambient sounds, enabling real-time sound collection.

[0710] 2. Means of converting voice to text data

[0711] Using a speech recognition API (e.g., Google Speech-to-Text API), the collected speech is converted into text data, which allows the speech data to be converted into analyzable text data.

[0712] 3. Sentiment Analysis Methods for Text Data

[0713] Generative AI models (e.g., Hugging Face Transformers sentiment analysis pipeline) are used to analyze sentiment within text data and identify negative expressions.

[0714] 4. A way to transform negative statements into positive ones

[0715] The identified negative text is converted into positive text through a conversion algorithm or a dedicated API, which allows for conversion into positive expressions.

[0716] 5. A means of converting positive text data into audio data

[0717] The positive text data is converted into audio data using the Google Cloud Text-to-Speech API, which then provides the converted positive text data to the user in an appropriate audio format.

[0718] 6. A means of playing audio data to the user

[0719] The converted positive voice data is played back to the user using the built-in speaker of the smart glasses, allowing the user to hear the positive information in real time.

[0720] 7. User Emotion Optimization

[0721] By collecting surrounding sounds, converting negative expressions into positive ones in real time, and playing them back, the system optimizes the user's emotional state in real time, helping users reduce stress and improve work efficiency.

[0722] Specific examples

[0723] For example, if an employee in a physical store is serving a customer face-to-face and the customer says, "I don't like this product," the system collects the voice, converts it into text, and recognizes it as a negative comment.The system then converts the negative comment into a more positive expression, such as, "We'll suggest some improvements, so please let us know your thoughts," and reconverts it into voice data to be conveyed to the employee.

[0724] Prompt Sentence Examples

[0725] Negative comments:

[0726] "Why didn't you like this product?"

[0727] Positive transformation:

[0728] "Please let me know your thoughts so I can suggest some improvements."

[0729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0730] Step 1:

[0731] The microphone on the device (smart glasses) is used to collect the conversational voice between the user and the customer in real time. The input is the surrounding sound, and the output is the voice data.

[0732] Step 2:

[0733] The collected voice data is sent from the terminal to the server. The input is the voice data sent from the terminal, and the output is the voice data transferred to the server.

[0734] Step 3:

[0735] The received voice data is converted into text data using the server's speech recognition API (e.g., Google Speech-to-Text API). The input is the voice data transferred to the server, and the output is text data.

[0736] Step 4:

[0737] The server's sentiment analysis method is used to analyze the sentiment in the transformed text data. A generative AI model (e.g., Hugging Face Transformers) is used to identify negative expressions. The input is the text data, and the output is a negative or positive sentiment label.

[0738] Step 5:

[0739] The server uses a text transformation algorithm or API to transform the identified negative text into positive text. The input is text data containing negative expressions, and the output is text data containing positive expressions.

[0740] Step 6:

[0741] The converted positive text data is converted into speech data using the Google Cloud Text-to-Speech API on the server. The input is text data containing positive expressions, and the output is positive speech data.

[0742] Step 7:

[0743] The converted positive voice data is sent from the server to the terminal. The input is the positive voice data on the server, and the output is the positive voice data sent to the terminal.

[0744] Step 8:

[0745] Uses the device's speaker to play positive voice data to the user. The input is the positive voice data sent to the device, and the output is the positive voice played to the user.

[0746] This allows users to receive positive information in real time, reducing stress when dealing with customers.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] [Third embodiment]

[0751] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0752] 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.

[0753] 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).

[0754] 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.

[0755] 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.

[0756] 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).

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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."

[0763] The present invention is a system that captures sounds around a user and processes them in real time. The system includes earphones (terminals) worn by the user and a server that receives and processes audio data from the user.

[0764] System Configuration

[0765] 1. Terminal

[0766] Audio collection: Obtains audio around the user through a microphone.

[0767] Data transmission: The acquired audio data is sent to the server.

[0768] Play Audio: Plays the processed audio sent from the server to the user.

[0769] 2. Server

[0770] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[0771] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[0772] Text transformation: Transform identified negative expressions into positive ones.

[0773] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[0774] Data transmission: The converted audio data is sent back to the device.

[0775] Example

[0776] The user's working environment in the office

[0777] A user is wearing earphones and working in an office.

[0778] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0779] The device transmits the audio data to the server in real time.

[0780] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0781] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0782] The server transforms negative statements into positive statements (e.g., "It would be great if you could help me complete this task").

[0783] The server converts the converted positive text into speech and sends it to the device.

[0784] The device plays a positive sound to the user.

[0785] In this way, users can hear negative sounds occurring in the workplace converted into positive sounds, allowing them to work comfortably while maintaining productivity.

[0786] Technical effects

[0787] This system prevents stress and loss of productivity by providing only positive information to users without blocking out surrounding audio information. In addition, because the system operates in real time, users can always work in an optimized audio environment.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[0791] Step 2:

[0792] The device converts the captured audio data into a byte stream and sends it to a server over the Internet in real time.

[0793] Step 3:

[0794] The server sends the received audio data to the Google Speech-to-Text API, which converts the audio into text data, which becomes a sentence like "Why isn't this finished yet?"

[0795] Step 4:

[0796] The server uses the generative AI model to perform sentiment analysis on the text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[0797] Step 5:

[0798] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0799] Step 6:

[0800] The server then passes the converted positive text to text-to-speech software, which converts it back into speech data, generating a speech that says, "It would be great if you could help me complete this task."

[0801] Step 7:

[0802] The server converts the generated positive voice data into a packet format and transmits it to the terminal via the Internet.

[0803] Step 8:

[0804] The device plays the received positive voice data to the user, who can hear the positive message through the earphone.

[0805] Step 9:

[0806] By listening to positive audio, users can focus on their work and daily life without being negatively influenced.

[0807] Example 1

[0808] 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."

[0809] In modern workplaces and social environments, negative audio information is a common problem, causing stress and reducing productivity. However, conventional technologies do not adequately provide a means to not only block out surrounding audio information, but also to convert negative audio into positive audio in real time.

[0810] 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.

[0811] In this invention, the server includes means for acquiring voice, means for transmitting the acquired voice to data, means for converting the acquired voice to text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into sound data, and means for playing the converted sound data to the user. This makes it possible to convert negative voices in the surrounding area into positive voices in real time, thereby reducing stress for the user and improving productivity.

[0812] The "means for acquiring sound" is a means for collecting sound around the user using a device such as a microphone.

[0813] The "transmission means for converting the acquired voice into data" is a means for transmitting the collected voice data to a server via an appropriate communication means (for example, Wi-Fi or Bluetooth).

[0814] The "means for converting the acquired voice into text data" refers to a means for using a voice recognition technique to convert the received voice data into character data.

[0815] "Means for sentiment analysis of converted text data" refers to means for analyzing emotions contained in text data using an AI model or the like, and identifying emotions such as negative or positive.

[0816] "Means for converting negative expressions into positive expressions" refers to a means for replacing negative expressions identified through sentiment analysis with positive expressions using rule-based logic and natural language processing technology.

[0817] The "means for converting the converted positive text data into sound data" refers to a means for converting the positive text data into sound data again using a voice synthesis technique.

[0818] The "means for reproducing the converted sound data to the user" refers to a means for providing the converted sound data to the user through audio equipment such as earphones or speakers.

[0819] The present invention is a system for capturing sounds around a user and processing them in real time. The system includes a sound collection device (terminal) and a server that receives and processes the collected sound data.

[0820] System Configuration

[0821] 1. Terminal

[0822] Sound collection: A microphone built into the earphones worn by the user collects sounds around the user with high sensitivity, such as conversations in an office or environmental sounds.

[0823] Data transmission: The collected voice data is sent to a server via Wi-Fi or Bluetooth. This data transmission is done in real time, so it is important to act without delay.

[0824] 2. Server

[0825] Speech Recognition: The server uses speech recognition technology such as the Google Speech-to-Text API to convert the voice data sent from the device into text data. For example, the speech "Why isn't this finished yet?" is converted into text.

[0826] Sentiment analysis: A generative AI model is used to analyze the sentiment of the converted text data, identifying negative expressions within the text. The AI ​​model used is a common model that provides natural language processing techniques.

[0827] Text transformation: Negative expressions identified through sentiment analysis are transformed into positive ones through rule-based text transformation routines, for example, transforming "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0828] Speech synthesis: The converted positive text is converted back into voice data using the Google Text-to-Speech API, etc. This produces clear, natural-sounding speech for the user.

[0829] Data transmission: The converted audio data is sent back to the device via Wi-Fi or Bluetooth.

[0830] 3. Terminal

[0831] Audio playback: The terminal can play the converted positive audio data to the user through the earphone speaker.

[0832] Specific examples

[0833] For example, imagine a user working in an office. While working with earphones in, the user receives negative feedback from their boss, such as "Why haven't you finished this yet?" The system works as follows:

[0834] 1. The device picks up the boss's remarks through the microphone.

[0835] 2. The device sends the acquired audio data to the server.

[0836] 3. The server converts the audio data into text data using the Google Speech-to-Text API.

[0837] 4. The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[0838] 5. The server translates "Why isn't this finished yet?" into a positive phrase like "It would be great if you could help me finish this task."

[0839] 6. The server uses the Google Text-to-Speech API to convert the converted positive text back into audio data.

[0840] 7. The server sends the converted audio data back to the device.

[0841] 8. The device plays the converted positive audio data to the user through the earphone speaker.

[0842] An example of a prompt sentence is "Why isn't this finished yet?" By collecting and processing this speech data, users can hear a positive message such as "I'd appreciate it if you could help me complete this task." This can help users feel less stressed at work and improve their productivity.

[0843] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0844] Step 1: Audio Collection:

[0845] The device picks up the user's surrounding sounds using a microphone built into the earphones. During this process, the high-sensitivity microphone picks up surrounding conversations and environmental sounds (e.g., "Why isn't this finished yet?").

[0846] Input: Live sounds from the user's surroundings.

[0847] Output: Collected audio data.

[0848] Step 2: Send data:

[0849] The device transmits the captured audio data to a server in real time, encrypted using Wi-Fi or Bluetooth protocols.

[0850] Input: Collected audio data.

[0851] Output: The audio data sent to the server.

[0852] Step 3: Voice Recognition:

[0853] The server uses a speech recognition API (for example, Google Speech-to-Text API) to convert the received voice data into text data. In this process, speech such as "Why isn't this finished yet?" is converted into text.

[0854] Input: The audio data sent to the server.

[0855] Output: The converted text data.

[0856] Step 4: Sentiment Analysis:

[0857] The server uses a generative AI model to perform sentiment analysis on the text data, identifying negative expressions in the text (e.g., "Why isn't this finished yet?").

[0858] Input: The converted text data.

[0859] Output: Sentiment analysis result (negative / positive).

[0860] Step 5: Text conversion:

[0861] The server converts negative expressions into positive ones based on sentiment analysis, in the process replacing "Why isn't this finished yet?" with "It would be great if you could help me finish this task."

[0862] Input: Sentiment analysis results and converted text data.

[0863] Output: The converted positive text data.

[0864] Step 6: Speech synthesis:

[0865] The server converts the positive text data back into audio data using text-to-speech software (e.g., Google Text-to-Speech API).

[0866] Input: Transformed positive text data.

[0867] Output: Retranscoded audio data.

[0868] Step 7: Send data:

[0869] The server then sends the audio data back to the device in real time, where it is encrypted and transmitted over Wi-Fi or Bluetooth.

[0870] Input: Retranscoded audio data.

[0871] Output: The audio data sent to the device.

[0872] Step 8: Audio playback:

[0873] The device plays the converted positive voice data to the user through the earphone speaker, and the user can clearly hear the converted positive message (e.g., "It would be helpful if you could help me complete this task").

[0874] Input: Audio data sent to the device.

[0875] Output: Positive speech that is played to the user.

[0876] (Application example 1)

[0877] 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."

[0878] In high-stress environments such as factories, workers can receive negative instructions and feedback directly from managers, which increases their mental burden and reduces productivity. In such environments, smooth communication is important, and a system is needed that can convert negative expressions into positive ones.

[0879] 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.

[0880] In this invention, the server includes means for acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for providing the converted voice data to workers in the factory in real time. This allows workers to hear voice converted into positive expressions without receiving negative feedback, thereby reducing mental stress and improving productivity.

[0881] "Means for acquiring audio" refers to a device or system that collects environmental sounds around the user and converts them into digital signals.

[0882] "Means for converting captured speech into text data" refers to the process or technology for converting speech data into text data, typically using speech recognition software or an API.

[0883] "Means for sentiment analysis of converted text data" refers to technology that analyzes the content of text data and identifies the emotions and sensibilities contained therein, and uses generative models and natural language processing.

[0884] "Methods of transforming negative expressions into positive expressions" refers to techniques or processes that transform negative expressions identified through sentiment analysis into positive, forward-looking expressions.

[0885] "Means for converting converted positive text data into voice data" refers to a technology or system that converts text data converted into positive expressions back into voice data.

[0886] "Means for playing the converted audio data to the user" refers to a device or system that outputs the converted audio data to the user so that it can be heard.

[0887] "Means for providing the converted positive voice data to factory workers in real time" refers to technology or systems for immediately transmitting and playing the converted positive voice data to factory workers with as little delay as possible.

[0888] This invention is a system that facilitates communication between workers and managers in a factory, allowing workers to hear voices converted into positive expressions without receiving negative feedback. The specific form of this system is shown below.

[0889] 1. How to get audio:

[0890] The system uses earphones with a microphone to capture audio from the user's surroundings in the factory. These earphones are intended to be worn by workers at all times. This voice capture function is activated when the user receives instructions or feedback from the manager.

[0891] 2. Means for converting the captured audio into text data:

[0892] The captured voice data is sent to a server, where it is converted into text data using the Google Speech-to-Text API. This conversion process is done in real time, so the data can proceed to the next step without delay.

[0893] 3. Means of sentiment analysis on converted text data:

[0894] The server performs sentiment analysis on the converted text data using the Google Cloud Natural Language API to determine whether it contains negative sentiment. This process checks whether the instructions or feedback are negative.

[0895] 4. Ways to transform negative statements into positive ones:

[0896] If the sentiment analysis identifies a negative response, the server uses a generative AI model to convert the negative portion of the text into a positive one, using the T5 model from the Transformers library and a prompt sentence to generate a positive response.

[0897] Example prompt sentence:

[0898] Transform the following negative sentences into positive ones:

[0899] Why haven't you finished this job yet?

[0900] 5. Means for converting the converted positive text data into audio data:

[0901] The converted positive text data is then converted back into audio data using the Google Cloud Text-to-Speech API, which generates audio data that is then sent to the user's earphones.

[0902] 6. Means for playing the converted audio data to the user:

[0903] Finally, the earphones play the converted positive voice data back to the user, allowing the worker to hear the positively converted voice without receiving direct negative feedback.

[0904] For example, if a worker on a factory painting line receives negative feedback such as, "Why haven't you finished this job yet?", the system will convert this into a positive response such as, "Shall I help you finish this job?" This will reduce stress for the worker and increase productivity.

[0905] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0906] Step 1:

[0907] Audio capture by device

[0908] Input: Sound from the user's surroundings in the factory

[0909] How it works: The user wears earphones with a microphone and captures surrounding sounds in real time.

[0910] Output: Captured audio data

[0911] Step 2:

[0912] Converting audio data to text

[0913] Input: Captured audio data

[0914] How it works: Voice data is sent to a server, which then converts it into text using the Google Speech-to-Text API. It uses speech recognition technology to represent human speech as a string of characters.

[0915] Output: Text data

[0916] Step 3:

[0917] Sentiment analysis of text data

[0918] Input: Converted text data

[0919] How it works: The server uses the Google Cloud Natural Language API on the text data to analyze the content of the text and determine whether it contains negative sentiment. It then uses a generative model to calculate a sentiment score for the text.

[0920] Output: Sentiment score of the text and whether it contains negative expressions

[0921] Step 4:

[0922] Transforming negative expressions into positive ones

[0923] Input: Sentiment analysis results (if negative expressions are identified)

[0924] How it works: The server uses a generative AI model to convert text data that has been identified as negative by sentiment analysis into positive expressions. Specifically, it uses the T5 model from the Transformers library and performs the conversion based on the following prompt sentence:

[0925] Example prompt: "Transform the following negative sentences into positive ones: Why haven't you finished this work yet?"

[0926] Output: Positively converted text data

[0927] Step 5:

[0928] Speech conversion of positive text data

[0929] Input: Positively converted text data

[0930] How it works: The server uses the Google Cloud Text-to-Speech API to convert the positive text data into audio data, using appropriate speech synthesis technology to convert the text into natural-sounding speech.

[0931] Output: Converted positive speech data

[0932] Step 6:

[0933] Playing audio to the user

[0934] Input: Transduced positive speech data

[0935] How it works: The device receives the converted positive voice data and plays it through the user's earphones, allowing the user to hear the voice converted into positive expressions in real time.

[0936] Output: A positive voice that the user hears

[0937] 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.

[0938] The present invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes voice data from the user, and an emotion engine that recognizes the user's emotions.

[0939] System Configuration

[0940] 1. Terminal

[0941] Audio collection: Obtains audio around the user through a microphone.

[0942] Data transmission: The acquired audio data is sent to the server.

[0943] User emotion collection: Analyze the user's voice patterns and biometric signals using an emotion engine.

[0944] Play Audio: Plays the processed audio sent from the server to the user.

[0945] 2. Server

[0946] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[0947] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[0948] Text transformation: Transform identified negative expressions into positive ones.

[0949] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[0950] Data transmission: The converted audio data is sent back to the device.

[0951] 3. Emotion Engine

[0952] Biosignal analysis: Measures the user's heart rate, electrodermal activity, etc. to analyze the user's emotional state.

[0953] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[0954] Example

[0955] The user's working environment in the office

[0956] A user is wearing earphones and working in an office.

[0957] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[0958] The device transmits the audio data to the server in real time.

[0959] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[0960] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[0961] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[0962] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0963] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[0964] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[0965] Technical effects

[0966] This system prevents stress and loss of productivity by providing only positive information to the user without blocking out surrounding audio information. It also uses an emotion engine to grasp the user's current emotional state and provide optimal feedback accordingly, allowing users to work in a real-time optimized audio environment.

[0967] The processing flow will be explained below.

[0968] Step 1:

[0969] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[0970] Step 2:

[0971] The device converts the voice data it acquires in real time into a digital format and transmits it to a server via a network.

[0972] Step 3:

[0973] The device uses an emotion engine to analyze bio-signals such as the user's heart rate, electrodermal activity, and vocal tone to recognize the user's emotional state in real time.

[0974] Step 4:

[0975] The server sends the received voice data to the Google Speech-to-Text API, which converts the voice data into text data. For example, the text data generated is "Why isn't this finished yet?"

[0976] Step 5:

[0977] The server uses the generative AI model to perform sentiment analysis on the converted text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[0978] Step 6:

[0979] The server translates negative statements into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[0980] Step 7:

[0981] The server uses text-to-speech software to generate audio data to convert the positive text into speech, generating a speech that reads, "It would be great if you could help me complete this task."

[0982] Step 8:

[0983] The server transmits the generated positive voice data to the terminal via the Internet.

[0984] Step 9:

[0985] The device plays the received positive voice data through the user's earphone, allowing the user to hear the positive message through the earphone.

[0986] Step 10:

[0987] Users can listen to positive voices, avoiding negative influences and continuing to concentrate on their work or daily life. In addition, the system monitors the user's emotional state in real time and provides feedback accordingly, maintaining an optimal working environment.

[0988] As a result, the present invention constantly monitors the user's emotional state and converts negative sounds from the surrounding environment into positive ones and plays them back, thereby reducing the user's stress and improving work efficiency.

[0989] Example 2

[0990] 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."

[0991] In modern society, many people experience stress due to negative voices and expressions in the workplace and in public places. This environment can have a negative impact on users' mental health and productivity. Furthermore, the lack of a system that can instantly convert negative feedback into positive ones makes it difficult for users to obtain positive information in real time.

[0992] 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 transmitting acquired voice data to the server, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for playing the converted voice data to the user. This allows the user to convert negative voices around them into positive information in real time and receive it, which is expected to reduce stress and improve productivity.

[0993] "User" refers to an individual who uses the system.

[0994] "Ambient audio" refers to all audio data occurring in the user's surrounding environment.

[0995] A "terminal" is a device worn by a user, and refers to a hardware device that has functions such as acquiring, transmitting, and playing audio.

[0996] "Audio data" refers to audio information converted into a digital signal.

[0997] "Server" refers to a computer system for processing audio data.

[0998] "Biological signals" refers to physiological data obtained from the human body, such as a user's heart rate or electrodermal activity.

[0999] "Emotion engine" refers to software or hardware functionality that analyzes bio-signals and audio data to identify a user's emotional state.

[1000] "Text data" refers to digital data that has been converted from voice data into text information.

[1001] "Sentiment analysis" refers to the process of identifying emotions from the content of text data, and classifying and evaluating those emotions.

[1002] A "generative model" refers to an AI model used for natural language processing, etc., that has the ability to provide appropriate responses or conversions to specific inputs.

[1003] "Conversion means" refers to a method or device for converting particular data into a different data format.

[1004] "Speech recognition API" refers to a program interface for converting voice data into text data.

[1005] "Text-to-speech software" refers to software that has the function of converting text data into audio data and reading it aloud.

[1006] This invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes the sound data, and an emotion engine that recognizes the user's emotions.

[1007] System Configuration

[1008] 1. Terminal

[1009] Audio collection: The device captures the user's surroundings through a microphone, allowing it to collect audio data tailored to the user's surroundings.

[1010] Data transmission: The device transmits the captured audio data to the server in real time. Data transmission requires a high-speed and stable connection.

[1011] User emotion collection: The device analyzes the user's biometric signals (heart rate, electrodermal activity, etc.) using an emotion engine, which then identifies the user's current emotional state.

[1012] Audio playback: The device plays the processed audio data sent from the server to the user. The audio played is the converted positive audio.

[1013] 2. Server

[1014] Speech recognition: The server converts the voice data received from the device into text data using the Google Speech-to-Text API, etc., and obtains voice as text information with high accuracy.

[1015] Sentiment analysis: The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[1016] Text transformation: The server transforms identified negative phrases into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1017] Speech synthesis: The server converts the converted positive text back into speech data using text-to-speech software.

[1018] Data transmission: The server sends the converted audio data back to the device.

[1019] 3. Emotion Engine

[1020] Biosignal analysis: The device measures the user's heart rate and electrodermal activity to analyze the user's emotional state.

[1021] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[1022] Specific examples

[1023] The user's working environment in the office

[1024] A user is wearing earphones and working in an office.

[1025] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[1026] The device transmits the audio data to the server in real time.

[1027] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[1028] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[1029] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[1030] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1031] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[1032] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[1033] Prompt Sentence Examples

[1034] "My boss yells, 'Why isn't this finished yet?'"

[1035] This system allows users to convert negative voices around them into positive information in real time, which is expected to reduce stress and improve productivity.

[1036] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1037] Program processing flow

[1038] Step 1:

[1039] The user puts on a compatible earphone, which is equipped with a microphone and biometric sensors, and is ready to capture ambient sounds and the user's biometric data.

[1040] Step 2:

[1041] The device uses a built-in microphone to collect the user's surrounding sounds in real time. The input is environmental sounds and conversational voices, which are then converted into digital form. Specifically, analog audio signals are encoded into digital data.

[1042] Step 3:

[1043] The voice data acquired by the device is sent to the server in real time. The voice data as input is transferred to the server via the network. The communication requires a high-speed and stable connection.

[1044] Step 4:

[1045] The device uses built-in sensors to acquire biometric signals such as the user's heart rate and electrodermal activity. The biometric data is then sent to an emotion engine to analyze the user's emotional state. Specifically, changes in heart rate and electrodermal activity are monitored in real time and the data is transmitted digitally.

[1046] Step 5:

[1047] The server converts the voice data received from the device into text data using the Google Speech-to-Text API. The input is digital voice data, and the output is analyzed text data. Specifically, a speech recognition algorithm is run on the server to convert the acquired digital voice signal into an appropriate string of characters.

[1048] Step 6:

[1049] The server performs sentiment analysis on the text data using a generative AI model. The input is the converted text data, and the output is the results of identifying negative expressions. Specifically, natural language processing techniques are used to analyze the sentiment within the text and detect negative keywords and phrases.

[1050] Step 7:

[1051] The server converts negative expressions into positive ones. The input is negative text data identified through sentiment analysis, and the output is the converted positive text data. Specifically, it uses a generative AI model to replace it with an appropriate positive phrase.

[1052] Step 8:

[1053] The server reconverts the positive text data into voice data using text-to-speech software. The input is positive text data, and the output is synthesized positive voice data. Specifically, the server uses text-to-speech software to convert the data into natural voice.

[1054] Step 9:

[1055] The server sends the converted voice data to the terminal. The input is the synthesized positive voice data, and the output is the voice data sent to the terminal. This allows the user to receive a positive message.

[1056] Step 10:

[1057] The terminal plays the positive voice data sent from the server to the user. The input is the positive voice data, and the output is the voice played to the user through the earphone. Specifically, the converted positive voice is played using the earphone speaker.

[1058] As a result, this system instantly converts negative voices around the user into positive voices, enabling productivity to be improved and stress to be reduced.

[1059] (Application example 2)

[1060] 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."

[1061] When employees in physical stores receive negative comments from customers while serving them, the emotional damage can have a negative impact on work efficiency and customer satisfaction. There is a need for a method that allows employees to convert negative words and expressions into positive ones in real time, thereby smoothing interactions with customers and improving customer satisfaction.

[1062] 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 acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, means for playing the converted voice data to the user, and means for collecting surrounding voices, converting negative expressions into positive expressions in real time, and providing the converted voice data to the user, thereby optimizing the user's emotional state. This enables employees in physical stores to convert negative expressions into positive expressions through dialogue with customers, thereby improving the efficiency of customer service operations and customer satisfaction.

[1063] The "means for acquiring sound" is a function for collecting surrounding sound through a sound collecting device such as a microphone.

[1064] The "means for converting acquired voice into text data" is a function that converts acquired voice data into character information (text data) using voice recognition technology.

[1065] "Means for sentiment analysis of converted text data" refers to a function that uses sentiment analysis software, such as a generative model, to analyze sentiment within the text data and identify its content.

[1066] The "means for converting negative expressions into positive expressions" is an algorithm or software that converts the analyzed negative expressions into positive expressions.

[1067] "Means for converting converted positive text data into audio data" refers to the function of converting positive text data into audio data using text-to-speech software.

[1068] The "means for playing back converted audio data to the user" is a function for playing back processed audio data to the user through earphones or speakers.

[1069] "Means for optimizing the user's emotional state by collecting surrounding sounds, converting negative expressions into positive ones in real time, and providing them to the user" is a function that manages the user's emotional state and mental stress by monitoring the audio environment around the user, instantly converting statements that may cause negative emotions into positive ones, and providing them to the user.

[1070] The present invention provides a system for converting negative expressions into positive ones in real time during customer interactions, thereby optimizing the emotional state of employees. The system includes a means for acquiring voice, a means for converting the acquired voice into text data, a means for sentiment analysis of the converted text data, a means for converting negative expressions into positive ones, a means for converting the converted positive text data into voice data, a means for playing the converted voice data to a user, and a means for optimizing the emotional state of the user by collecting surrounding voices and providing positive information in real time.

[1071] The functions of the system and the hardware and software used will be specifically described below.

[1072] 1. Audio acquisition method

[1073] The smart glasses use built-in microphones to collect ambient sounds, enabling real-time sound collection.

[1074] 2. Means of converting voice to text data

[1075] Using a speech recognition API (e.g., Google Speech-to-Text API), the collected speech is converted into text data, which allows the speech data to be converted into analyzable text data.

[1076] 3. Sentiment Analysis Methods for Text Data

[1077] Generative AI models (e.g., Hugging Face Transformers sentiment analysis pipeline) are used to analyze sentiment within text data and identify negative expressions.

[1078] 4. A way to transform negative statements into positive ones

[1079] The identified negative text is converted into positive text through a conversion algorithm or a dedicated API, which allows for conversion into positive expressions.

[1080] 5. A means of converting positive text data into audio data

[1081] The positive text data is converted into audio data using the Google Cloud Text-to-Speech API, which then provides the converted positive text data to the user in an appropriate audio format.

[1082] 6. A means of playing audio data to the user

[1083] The converted positive voice data is played back to the user using the built-in speaker of the smart glasses, allowing the user to hear the positive information in real time.

[1084] 7. User Emotion Optimization

[1085] By collecting surrounding sounds, converting negative expressions into positive ones in real time, and playing them back, the system optimizes the user's emotional state in real time, helping users reduce stress and improve work efficiency.

[1086] Specific examples

[1087] For example, if an employee in a physical store is serving a customer face-to-face and the customer says, "I don't like this product," the system collects the voice, converts it into text, and recognizes it as a negative comment.The system then converts the negative comment into a more positive expression, such as, "We'll suggest some improvements, so please let us know your thoughts," and reconverts it into voice data to be conveyed to the employee.

[1088] Prompt Sentence Examples

[1089] Negative comments:

[1090] "Why didn't you like this product?"

[1091] Positive transformation:

[1092] "Please let me know your thoughts so I can suggest some improvements."

[1093] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1094] Step 1:

[1095] The microphone on the device (smart glasses) is used to collect the conversational voice between the user and the customer in real time. The input is the surrounding sound, and the output is the voice data.

[1096] Step 2:

[1097] The collected voice data is sent from the terminal to the server. The input is the voice data sent from the terminal, and the output is the voice data transferred to the server.

[1098] Step 3:

[1099] The received voice data is converted into text data using the server's speech recognition API (e.g., Google Speech-to-Text API). The input is the voice data transferred to the server, and the output is text data.

[1100] Step 4:

[1101] The server's sentiment analysis method is used to analyze the sentiment in the transformed text data. A generative AI model (e.g., Hugging Face Transformers) is used to identify negative expressions. The input is the text data, and the output is a negative or positive sentiment label.

[1102] Step 5:

[1103] The server uses a text transformation algorithm or API to transform the identified negative text into positive text. The input is text data containing negative expressions, and the output is text data containing positive expressions.

[1104] Step 6:

[1105] The converted positive text data is converted into speech data using the Google Cloud Text-to-Speech API on the server. The input is text data containing positive expressions, and the output is positive speech data.

[1106] Step 7:

[1107] The converted positive voice data is sent from the server to the terminal. The input is the positive voice data on the server, and the output is the positive voice data sent to the terminal.

[1108] Step 8:

[1109] Uses the device's speaker to play positive voice data to the user. The input is the positive voice data sent to the device, and the output is the positive voice played to the user.

[1110] This allows users to receive positive information in real time, reducing stress when dealing with customers.

[1111] 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.

[1112] 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.

[1113] 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.

[1114] [Fourth embodiment]

[1115] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1116] 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.

[1117] 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).

[1118] 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.

[1119] 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.

[1120] 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).

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] 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."

[1128] The present invention is a system that captures sounds around a user and processes them in real time. The system includes earphones (terminals) worn by the user and a server that receives and processes audio data from the user.

[1129] System Configuration

[1130] 1. Terminal

[1131] Audio collection: Obtains audio around the user through a microphone.

[1132] Data transmission: The acquired audio data is sent to the server.

[1133] Play Audio: Plays the processed audio sent from the server to the user.

[1134] 2. Server

[1135] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[1136] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[1137] Text transformation: Transform identified negative expressions into positive ones.

[1138] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[1139] Data transmission: The converted audio data is sent back to the device.

[1140] Example

[1141] The user's working environment in the office

[1142] A user is wearing earphones and working in an office.

[1143] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[1144] The device transmits the audio data to the server in real time.

[1145] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[1146] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[1147] The server transforms negative statements into positive statements (e.g., "It would be great if you could help me complete this task").

[1148] The server converts the converted positive text into speech and sends it to the device.

[1149] The device plays a positive sound to the user.

[1150] In this way, users can hear negative sounds occurring in the workplace converted into positive sounds, allowing them to work comfortably while maintaining productivity.

[1151] Technical effects

[1152] This system prevents stress and loss of productivity by providing only positive information to users without blocking out surrounding audio information. In addition, because the system operates in real time, users can always work in an optimized audio environment.

[1153] The processing flow will be explained below.

[1154] Step 1:

[1155] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[1156] Step 2:

[1157] The device converts the captured audio data into a byte stream and sends it to a server over the Internet in real time.

[1158] Step 3:

[1159] The server sends the received voice data to the Google Speech-to-Text API, which converts the voice into text data, which becomes a sentence like "Why isn't this finished yet?"

[1160] Step 4:

[1161] The server uses the generative AI model to perform sentiment analysis on the text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[1162] Step 5:

[1163] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1164] Step 6:

[1165] The server then passes the converted positive text to text-to-speech software, which converts it back into speech data, generating a speech that says, "It would be great if you could help me complete this task."

[1166] Step 7:

[1167] The server converts the generated positive voice data into a packet format and transmits it to the terminal via the Internet.

[1168] Step 8:

[1169] The device plays the received positive voice data to the user, who can hear the positive message through the earphone.

[1170] Step 9:

[1171] By listening to positive audio, users can focus on their work and daily life without being negatively influenced.

[1172] Example 1

[1173] 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."

[1174] In modern workplaces and social environments, negative audio information is a common problem, causing stress and reducing productivity. However, conventional technologies do not adequately provide a means to not only block out surrounding audio information, but also to convert negative audio into positive audio in real time.

[1175] 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.

[1176] In this invention, the server includes means for acquiring voice, means for transmitting the acquired voice to data, means for converting the acquired voice to text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into sound data, and means for playing the converted sound data to the user. This makes it possible to convert negative voices in the surrounding area into positive voices in real time, thereby reducing stress for the user and improving productivity.

[1177] The "means for acquiring sound" is a means for collecting sound around the user using a device such as a microphone.

[1178] The "transmission means for converting the acquired voice into data" is a means for transmitting the collected voice data to a server via an appropriate communication means (for example, Wi-Fi or Bluetooth).

[1179] The "means for converting acquired voice into text data" refers to a means for using voice recognition technology to convert received voice data into character data.

[1180] "Means for sentiment analysis of converted text data" refers to means for analyzing emotions contained in text data using an AI model or the like, and identifying emotions such as negative or positive.

[1181] "Means for converting negative expressions into positive expressions" refers to a means for replacing negative expressions identified through sentiment analysis with positive expressions using rule-based logic and natural language processing technology.

[1182] The "means for converting the converted positive text data into sound data" refers to a means for converting the positive text data into sound data again using a voice synthesis technique.

[1183] The "means for reproducing the converted sound data to the user" refers to a means for providing the converted sound data to the user through audio equipment such as earphones or speakers.

[1184] The present invention is a system for capturing sounds around a user and processing them in real time. The system includes a sound collection device (terminal) and a server that receives and processes the collected sound data.

[1185] System Configuration

[1186] 1. Terminal

[1187] Sound collection: A microphone built into the earphones worn by the user collects sounds around the user with high sensitivity, such as conversations in an office or environmental sounds.

[1188] Data transmission: The collected voice data is sent to a server via Wi-Fi or Bluetooth. This data transmission is done in real time, so it is important to act without delay.

[1189] 2. Server

[1190] Speech Recognition: The server uses speech recognition technology such as the Google Speech-to-Text API to convert the voice data sent from the device into text data. For example, the speech "Why isn't this finished yet?" is converted into text.

[1191] Sentiment analysis: A generative AI model is used to analyze the sentiment of the converted text data, identifying negative expressions within the text. The AI ​​model used is a common model that provides natural language processing techniques.

[1192] Text transformation: Negative expressions identified through sentiment analysis are transformed into positive ones through rule-based text transformation routines, for example, transforming "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1193] Speech synthesis: The converted positive text is converted back into voice data using the Google Text-to-Speech API, etc. This produces clear, natural-sounding speech for the user.

[1194] Data transmission: The converted audio data is sent back to the device via Wi-Fi or Bluetooth.

[1195] 3. Terminal

[1196] Audio playback: The terminal can play the converted positive audio data to the user through the earphone speaker.

[1197] Specific examples

[1198] For example, imagine a user working in an office. While working with earphones in, the user receives negative feedback from their boss, such as "Why haven't you finished this yet?" The system works as follows:

[1199] 1. The device picks up the boss's remarks through the microphone.

[1200] 2. The device sends the acquired audio data to the server.

[1201] 3. The server converts the audio data into text data using the Google Speech-to-Text API.

[1202] 4. The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[1203] 5. The server translates "Why isn't this finished yet?" into a positive phrase like "It would be great if you could help me finish this task."

[1204] 6. The server uses the Google Text-to-Speech API to convert the converted positive text back into audio data.

[1205] 7. The server sends the converted audio data back to the device.

[1206] 8. The device plays the converted positive audio data to the user through the earphone speaker.

[1207] An example of a prompt sentence is "Why isn't this finished yet?" By collecting and processing this speech data, users can hear a positive message such as "I'd appreciate it if you could help me complete this task." This can help users feel less stressed at work and improve their productivity.

[1208] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1209] Step 1: Audio Collection:

[1210] The device picks up the user's surrounding sounds using a microphone built into the earphones. During this process, the high-sensitivity microphone picks up surrounding conversations and environmental sounds (e.g., "Why isn't this finished yet?").

[1211] Input: Live sounds from the user's surroundings.

[1212] Output: Collected audio data.

[1213] Step 2: Send data:

[1214] The device transmits the captured audio data to a server in real time, encrypted using Wi-Fi or Bluetooth protocols.

[1215] Input: Collected audio data.

[1216] Output: The audio data sent to the server.

[1217] Step 3: Voice Recognition:

[1218] The server uses a speech recognition API (for example, Google Speech-to-Text API) to convert the received voice data into text data. In this process, speech such as "Why isn't this finished yet?" is converted into text.

[1219] Input: The audio data sent to the server.

[1220] Output: The converted text data.

[1221] Step 4: Sentiment Analysis:

[1222] The server uses a generative AI model to perform sentiment analysis on the text data, identifying negative expressions in the text (e.g., "Why isn't this finished yet?").

[1223] Input: The converted text data.

[1224] Output: Sentiment analysis result (negative / positive).

[1225] Step 5: Text conversion:

[1226] The server converts negative expressions into positive ones based on sentiment analysis, in the process replacing "Why isn't this finished yet?" with "It would be great if you could help me finish this task."

[1227] Input: Sentiment analysis results and converted text data.

[1228] Output: The converted positive text data.

[1229] Step 6: Speech synthesis:

[1230] The server converts the positive text data back into audio data using text-to-speech software (e.g., Google Text-to-Speech API).

[1231] Input: Transformed positive text data.

[1232] Output: Retranscoded audio data.

[1233] Step 7: Send data:

[1234] The server then sends the audio data back to the device in real time, where it is encrypted and transmitted over Wi-Fi or Bluetooth.

[1235] Input: Retranscoded audio data.

[1236] Output: The audio data sent to the device.

[1237] Step 8: Audio playback:

[1238] The device plays the converted positive voice data to the user through the earphone speaker, and the user can clearly hear the converted positive message (e.g., "It would be helpful if you could help me complete this task").

[1239] Input: Audio data sent to the device.

[1240] Output: Positive speech that is played to the user.

[1241] (Application example 1)

[1242] 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."

[1243] In high-stress environments such as factories, workers can receive negative instructions and feedback directly from managers, which increases their mental burden and reduces productivity. In such environments, smooth communication is important, and a system is needed that can convert negative expressions into positive ones.

[1244] 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.

[1245] In this invention, the server includes means for acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for providing the converted voice data to workers in the factory in real time. This allows workers to hear voice converted into positive expressions without receiving negative feedback, thereby reducing mental stress and improving productivity.

[1246] "Means for acquiring audio" refers to a device or system that collects environmental sounds around the user and converts them into digital signals.

[1247] "Means for converting captured speech into text data" refers to the process or technology for converting speech data into text data, typically using speech recognition software or an API.

[1248] "Means for sentiment analysis of converted text data" refers to technology that analyzes the content of text data and identifies the emotions and sensibilities contained therein, and uses generative models and natural language processing.

[1249] "Methods of transforming negative expressions into positive expressions" refers to techniques or processes that transform negative expressions identified through sentiment analysis into positive, forward-looking expressions.

[1250] "Means for converting converted positive text data into voice data" refers to a technology or system that converts text data converted into positive expressions back into voice data.

[1251] "Means for playing the converted audio data to the user" refers to a device or system that outputs the converted audio data to the user so that it can be heard.

[1252] "Means for providing the converted positive voice data to factory workers in real time" refers to technology or systems for immediately transmitting and playing the converted positive voice data to factory workers with as little delay as possible.

[1253] This invention is a system that facilitates communication between workers and managers in a factory, allowing workers to hear voices converted into positive expressions without receiving negative feedback. The specific form of this system is shown below.

[1254] 1. How to get audio:

[1255] The system uses earphones with a microphone to capture audio from the user's surroundings in the factory. These earphones are intended to be worn by workers at all times. This voice capture function is activated when the user receives instructions or feedback from the manager.

[1256] 2. Means for converting the captured audio into text data:

[1257] The captured voice data is sent to a server, where it is converted into text data using the Google Speech-to-Text API. This conversion process is done in real time, so the data can proceed to the next step without delay.

[1258] 3. Means of sentiment analysis on converted text data:

[1259] The server performs sentiment analysis on the converted text data using the Google Cloud Natural Language API to determine whether it contains negative sentiment. This process checks whether the instructions or feedback are negative.

[1260] 4. Ways to transform negative statements into positive ones:

[1261] If the sentiment analysis identifies a negative response, the server uses a generative AI model to convert the negative portion of the text into a positive one, using the T5 model from the Transformers library and a prompt sentence to generate a positive response.

[1262] Example prompt sentence:

[1263] Transform the following negative sentences into positive ones:

[1264] Why haven't you finished this job yet?

[1265] 5. Means for converting the converted positive text data into audio data:

[1266] The converted positive text data is then converted back into audio data using the Google Cloud Text-to-Speech API, which generates audio data that is then sent to the user's earphones.

[1267] 6. Means for playing the converted audio data to the user:

[1268] Finally, the earphones play the converted positive voice data back to the user, allowing the worker to hear the positively converted voice without receiving direct negative feedback.

[1269] For example, if a worker on a factory painting line receives negative feedback such as, "Why haven't you finished this job yet?", the system will convert this into a positive response such as, "Shall I help you finish this job?" This will reduce stress for the worker and increase productivity.

[1270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1271] Step 1:

[1272] Audio capture by device

[1273] Input: Sound from the user's surroundings in the factory

[1274] How it works: The user wears earphones with a microphone and captures surrounding sounds in real time.

[1275] Output: Captured audio data

[1276] Step 2:

[1277] Converting audio data to text

[1278] Input: Captured audio data

[1279] How it works: Voice data is sent to a server, which then converts it into text using the Google Speech-to-Text API. It uses speech recognition technology to represent human speech as a string of characters.

[1280] Output: Text data

[1281] Step 3:

[1282] Sentiment analysis of text data

[1283] Input: Converted text data

[1284] How it works: The server uses the Google Cloud Natural Language API on the text data to analyze the content of the text and determine whether it contains negative sentiment. It then uses a generative model to calculate a sentiment score for the text.

[1285] Output: Sentiment score of the text and whether it contains negative expressions

[1286] Step 4:

[1287] Transforming negative expressions into positive ones

[1288] Input: Sentiment analysis results (if negative expressions are identified)

[1289] How it works: The server uses a generative AI model to convert text data that has been identified as negative by sentiment analysis into positive expressions. Specifically, it uses the T5 model from the Transformers library and performs the conversion based on the following prompt sentence:

[1290] Example prompt: "Transform the following negative sentences into positive ones: Why haven't you finished this work yet?"

[1291] Output: Positively converted text data

[1292] Step 5:

[1293] Speech conversion of positive text data

[1294] Input: Positively converted text data

[1295] How it works: The server uses the Google Cloud Text-to-Speech API to convert the positive text data into audio data, using appropriate speech synthesis technology to convert the text into natural-sounding speech.

[1296] Output: Converted positive speech data

[1297] Step 6:

[1298] Playing audio to the user

[1299] Input: Transduced positive speech data

[1300] How it works: The device receives the converted positive voice data and plays it through the user's earphones, allowing the user to hear the voice converted into positive expressions in real time.

[1301] Output: A positive voice that the user hears

[1302] 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.

[1303] The present invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes voice data from the user, and an emotion engine that recognizes the user's emotions.

[1304] System Configuration

[1305] 1. Terminal

[1306] Audio collection: Obtains audio around the user through a microphone.

[1307] Data transmission: The acquired audio data is sent to the server.

[1308] User emotion collection: Analyze the user's voice patterns and biometric signals using an emotion engine.

[1309] Play Audio: Plays the processed audio sent from the server to the user.

[1310] 2. Server

[1311] Speech recognition: Using the Google Speech-to-Text API or similar, received voice data is converted into text data.

[1312] Sentiment analysis: Use generative AI models to analyze the sentiment of text and identify negative expressions.

[1313] Text transformation: Transform identified negative expressions into positive ones.

[1314] Speech synthesis: The converted positive text is converted back into voice data using text-to-speech software.

[1315] Data transmission: The converted audio data is sent back to the device.

[1316] 3. Emotion Engine

[1317] Biosignal analysis: Measures the user's heart rate, electrodermal activity, etc. to analyze the user's emotional state.

[1318] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[1319] Example

[1320] The user's working environment in the office

[1321] A user is wearing earphones and working in an office.

[1322] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[1323] The device transmits the audio data to the server in real time.

[1324] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[1325] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[1326] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[1327] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1328] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[1329] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[1330] Technical effects

[1331] This system prevents stress and loss of productivity by providing only positive information to the user without blocking out surrounding audio information. It also uses an emotion engine to grasp the user's current emotional state and provide optimal feedback accordingly, allowing users to work in a real-time optimized audio environment.

[1332] The processing flow will be explained below.

[1333] Step 1:

[1334] The device picks up the user's surrounding sounds in real time through a microphone, capturing environmental sounds and conversations in the office, home, etc.

[1335] Step 2:

[1336] The device converts the voice data it acquires in real time into a digital format and transmits it to a server via a network.

[1337] Step 3:

[1338] The device uses an emotion engine to analyze bio-signals such as the user's heart rate, electrodermal activity, and vocal tone to recognize the user's emotional state in real time.

[1339] Step 4:

[1340] The server sends the received voice data to the Google Speech-to-Text API, which converts the voice data into text data. For example, the text data generated is "Why isn't this finished yet?"

[1341] Step 5:

[1342] The server uses the generative AI model to perform sentiment analysis on the converted text data, determining whether the text is negative (e.g., determining that it is a negative comment).

[1343] Step 6:

[1344] The server translates negative statements into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1345] Step 7:

[1346] The server uses text-to-speech software to generate audio data to convert the positive text into speech, generating a speech that reads, "It would be great if you could help me complete this task."

[1347] Step 8:

[1348] The server transmits the generated positive voice data to the terminal via the Internet.

[1349] Step 9:

[1350] The device plays the received positive voice data through the user's earphone, allowing the user to hear the positive message through the earphone.

[1351] Step 10:

[1352] Users can listen to positive voices, avoiding negative influences and continuing to concentrate on their work or daily life. In addition, the system monitors the user's emotional state in real time and provides feedback accordingly, maintaining an optimal working environment.

[1353] As a result, the present invention constantly monitors the user's emotional state and converts negative sounds from the surrounding environment into positive ones and plays them back, thereby reducing the user's stress and improving work efficiency.

[1354] Example 2

[1355] 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."

[1356] In modern society, many people experience stress due to negative voices and expressions in the workplace and in public places. This environment can have a negative impact on users' mental health and productivity. Furthermore, the lack of a system that can instantly convert negative feedback into positive ones makes it difficult for users to obtain positive information in real time.

[1357] 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 transmitting acquired voice data to the server, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, and means for playing the converted voice data to the user. This allows the user to convert negative voices around them into positive information in real time and receive it, which is expected to reduce stress and improve productivity.

[1358] "User" refers to an individual who uses the system.

[1359] "Ambient audio" refers to all audio data occurring in the user's surrounding environment.

[1360] A "terminal" is a device worn by a user, and refers to a hardware device that has functions such as acquiring, transmitting, and playing audio.

[1361] "Audio data" refers to audio information converted into a digital signal.

[1362] "Server" refers to a computer system for processing audio data.

[1363] "Biological signals" refers to physiological data obtained from the human body, such as a user's heart rate or electrodermal activity.

[1364] "Emotion engine" refers to software or hardware functionality that analyzes bio-signals and audio data to identify a user's emotional state.

[1365] "Text data" refers to digital data that has been converted from voice data into text information.

[1366] "Sentiment analysis" refers to the process of identifying emotions from the content of text data, and classifying and evaluating those emotions.

[1367] A "generative model" refers to an AI model used for natural language processing, etc., that has the ability to provide appropriate responses or conversions to specific inputs.

[1368] "Conversion means" refers to a method or device for converting particular data into a different data format.

[1369] "Speech recognition API" refers to a program interface for converting voice data into text data.

[1370] "Text-to-speech software" refers to software that has the function of converting text data into audio data and reading it aloud.

[1371] This invention is a system that acquires sounds around a user and processes them in real time. This system includes earphones (terminals) worn by the user, a server that receives and processes the sound data, and an emotion engine that recognizes the user's emotions.

[1372] System Configuration

[1373] 1. Terminal

[1374] Audio collection: The device captures the user's surroundings through a microphone, allowing it to collect audio data tailored to the user's surroundings.

[1375] Data transmission: The device transmits the captured audio data to the server in real time. Data transmission requires a high-speed and stable connection.

[1376] User emotion collection: The device analyzes the user's biometric signals (heart rate, electrodermal activity, etc.) using an emotion engine, which then identifies the user's current emotional state.

[1377] Audio playback: The device plays the processed audio data sent from the server to the user. The audio played is the converted positive audio.

[1378] 2. Server

[1379] Speech recognition: The server converts the voice data received from the device into text data using the Google Speech-to-Text API, etc., and obtains voice as text information with high accuracy.

[1380] Sentiment analysis: The server uses a generative AI model to analyze the sentiment of the text and identify negative expressions.

[1381] Text transformation: The server transforms identified negative phrases into positive ones, for example, "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1382] Speech synthesis: The server converts the converted positive text back into speech data using text-to-speech software.

[1383] Data transmission: The server sends the converted audio data back to the device.

[1384] 3. Emotion Engine

[1385] Biosignal analysis: The device measures the user's heart rate and electrodermal activity to analyze the user's emotional state.

[1386] Voice analysis: Analyzes the tone and rhythm of the user's voice to recognize their emotional state.

[1387] Specific examples

[1388] The user's working environment in the office

[1389] A user is wearing earphones and working in an office.

[1390] The device picks up ambient audio (e.g., "Why isn't this finished yet?") through the microphone.

[1391] The device transmits the audio data to the server in real time.

[1392] The device uses an emotion engine to monitor the user's heart rate and tone of voice to recognize their current emotional state.

[1393] The server converts the speech into text (e.g., "Why isn't this finished yet?") using the Google Speech-to-Text API.

[1394] The server uses a generative AI model to analyze the sentiment of the text and identify it as negative (e.g., "negative remarks").

[1395] The server transforms negative text into a positive expression, in this case "Why isn't this finished yet?" into "It would be great if you could help me finish this task."

[1396] The server converts the converted positive text back into audio using text-to-speech software and sends it to the device.

[1397] The device will play a positive sound to the user, who can then hear the positive message through the earphones.

[1398] Prompt Sentence Examples

[1399] "My boss yells, 'Why isn't this finished yet?'"

[1400] This system allows users to convert negative voices around them into positive information in real time, which is expected to reduce stress and improve productivity.

[1401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1402] Program processing flow

[1403] Step 1:

[1404] The user puts on a compatible earphone, which is equipped with a microphone and biometric sensors, and is ready to capture ambient sounds and the user's biometric data.

[1405] Step 2:

[1406] The device uses a built-in microphone to collect the user's surrounding sounds in real time. The input is environmental sounds and conversational voices, which are then converted into digital form. Specifically, analog audio signals are encoded into digital data.

[1407] Step 3:

[1408] The voice data acquired by the device is sent to the server in real time. The voice data as input is transferred to the server via the network. The communication requires a high-speed and stable connection.

[1409] Step 4:

[1410] The device uses built-in sensors to acquire biometric signals such as the user's heart rate and electrodermal activity. The biometric data is then sent to an emotion engine to analyze the user's emotional state. Specifically, changes in heart rate and electrodermal activity are monitored in real time and the data is transmitted digitally.

[1411] Step 5:

[1412] The server converts the voice data received from the device into text data using the Google Speech-to-Text API. The input is digital voice data, and the output is analyzed text data. Specifically, a speech recognition algorithm is run on the server to convert the acquired digital voice signal into an appropriate string of characters.

[1413] Step 6:

[1414] The server performs sentiment analysis on the text data using a generative AI model. The input is the converted text data, and the output is the results of identifying negative expressions. Specifically, natural language processing techniques are used to analyze the sentiment within the text and detect negative keywords and phrases.

[1415] Step 7:

[1416] The server converts negative expressions into positive ones. The input is negative text data identified through sentiment analysis, and the output is the converted positive text data. Specifically, it uses a generative AI model to replace it with an appropriate positive phrase.

[1417] Step 8:

[1418] The server reconverts the positive text data into voice data using text-to-speech software. The input is positive text data, and the output is synthesized positive voice data. Specifically, the server uses text-to-speech software to convert the data into natural voice.

[1419] Step 9:

[1420] The server sends the converted voice data to the terminal. The input is the synthesized positive voice data, and the output is the voice data sent to the terminal. This allows the user to receive a positive message.

[1421] Step 10:

[1422] The terminal plays the positive voice data sent from the server to the user. The input is the positive voice data, and the output is the voice played to the user through the earphone. Specifically, the converted positive voice is played using the earphone speaker.

[1423] As a result, this system instantly converts negative voices around the user into positive voices, enabling productivity to be improved and stress to be reduced.

[1424] (Application example 2)

[1425] 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."

[1426] When employees in physical stores receive negative comments from customers while serving them, the emotional damage can have a negative impact on work efficiency and customer satisfaction. There is a need for a method that allows employees to convert negative words and expressions into positive ones in real time, thereby smoothing interactions with customers and improving customer satisfaction.

[1427] 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 acquiring voice, means for converting the acquired voice into text data, means for sentiment analysis of the converted text data, means for converting negative expressions into positive expressions, means for converting the converted positive text data into voice data, means for playing the converted voice data to the user, and means for collecting surrounding voices, converting negative expressions into positive expressions in real time, and providing the converted voice data to the user, thereby optimizing the user's emotional state. This enables employees in physical stores to convert negative expressions into positive expressions through dialogue with customers, thereby improving the efficiency of customer service operations and customer satisfaction.

[1428] The "means for acquiring sound" is a function for collecting surrounding sound through a sound collecting device such as a microphone.

[1429] The "means for converting acquired voice into text data" is a function that converts acquired voice data into character information (text data) using voice recognition technology.

[1430] "Means for sentiment analysis of converted text data" refers to a function that uses sentiment analysis software, such as a generative model, to analyze sentiment within the text data and identify its content.

[1431] The "means for converting negative expressions into positive expressions" is an algorithm or software that converts the analyzed negative expressions into positive expressions.

[1432] "Means for converting converted positive text data into audio data" refers to the function of converting positive text data into audio data using text-to-speech software.

[1433] The "means for playing back converted audio data to the user" is a function for playing back processed audio data to the user through earphones or speakers.

[1434] "Means for optimizing the user's emotional state by collecting surrounding sounds, converting negative expressions into positive ones in real time, and providing them to the user" is a function that manages the user's emotional state and mental stress by monitoring the audio environment around the user, instantly converting statements that may cause negative emotions into positive ones, and providing them to the user.

[1435] The present invention provides a system for converting negative expressions into positive ones in real time during customer interactions, thereby optimizing the emotional state of employees. The system includes a means for acquiring voice, a means for converting the acquired voice into text data, a means for sentiment analysis of the converted text data, a means for converting negative expressions into positive ones, a means for converting the converted positive text data into voice data, a means for playing the converted voice data to a user, and a means for optimizing the emotional state of the user by collecting surrounding voices and providing positive information in real time.

[1436] The functions of the system and the hardware and software used will be specifically described below.

[1437] 1. Audio acquisition method

[1438] The smart glasses use built-in microphones to collect ambient sounds, enabling real-time sound collection.

[1439] 2. Means of converting voice to text data

[1440] Using a speech recognition API (e.g., Google Speech-to-Text API), the collected speech is converted into text data, which allows the speech data to be converted into analyzable text data.

[1441] 3. Sentiment Analysis Methods for Text Data

[1442] Generative AI models (e.g., Hugging Face Transformers sentiment analysis pipeline) are used to analyze sentiment within text data and identify negative expressions.

[1443] 4. A way to transform negative statements into positive ones

[1444] The identified negative text is converted into positive text through a conversion algorithm or a dedicated API, which allows for conversion into positive expressions.

[1445] 5. A means of converting positive text data into audio data

[1446] The positive text data is converted into audio data using the Google Cloud Text-to-Speech API, which then provides the converted positive text data to the user in an appropriate audio format.

[1447] 6. A means of playing audio data to the user

[1448] The converted positive voice data is played back to the user using the built-in speaker of the smart glasses, allowing the user to hear the positive information in real time.

[1449] 7. User Emotion Optimization

[1450] By collecting surrounding sounds, converting negative expressions into positive ones in real time, and playing them back, the system optimizes the user's emotional state in real time, helping users reduce stress and improve work efficiency.

[1451] Specific examples

[1452] For example, if an employee in a physical store is serving a customer face-to-face and the customer says, "I don't like this product," the system collects the voice, converts it into text, and recognizes it as a negative comment.The system then converts the negative comment into a more positive expression, such as, "We'll suggest some improvements, so please let us know your thoughts," and reconverts it into voice data to be conveyed to the employee.

[1453] Prompt Sentence Examples

[1454] Negative comments:

[1455] "Why didn't you like this product?"

[1456] Positive transformation:

[1457] "Please let me know your thoughts so I can suggest some improvements."

[1458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1459] Step 1:

[1460] The microphone on the device (smart glasses) is used to collect the conversational voice between the user and the customer in real time. The input is the surrounding sound, and the output is the voice data.

[1461] Step 2:

[1462] The collected voice data is sent from the terminal to the server. The input is the voice data sent from the terminal, and the output is the voice data transferred to the server.

[1463] Step 3:

[1464] The received voice data is converted into text data using the server's speech recognition API (e.g., Google Speech-to-Text API). The input is the voice data transferred to the server, and the output is text data.

[1465] Step 4:

[1466] The server's sentiment analysis method is used to analyze the sentiment in the transformed text data. A generative AI model (e.g., Hugging Face Transformers) is used to identify negative expressions. The input is the text data, and the output is a negative or positive sentiment label.

[1467] Step 5:

[1468] The server uses a text transformation algorithm or API to transform the identified negative text into positive text. The input is text data containing negative expressions, and the output is text data containing positive expressions.

[1469] Step 6:

[1470] The converted positive text data is converted into speech data using the Google Cloud Text-to-Speech API on the server. The input is text data containing positive expressions, and the output is positive speech data.

[1471] Step 7:

[1472] The converted positive voice data is sent from the server to the terminal. The input is the positive voice data on the server, and the output is the positive voice data sent to the terminal.

[1473] Step 8:

[1474] Uses the device's speaker to play positive voice data to the user. The input is the positive voice data sent to the device, and the output is the positive voice played to the user.

[1475] This allows users to receive positive information in real time, reducing stress when dealing with customers.

[1476] 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.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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).

[1483] 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.

[1484] 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."

[1485] 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.

[1486] 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).

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] The following is further disclosed regarding the above embodiment.

[1498] (Claim 1)

[1499] a means for acquiring audio;

[1500] means for converting the acquired voice into text data;

[1501] means for sentiment analyzing the converted text data;

[1502] A way to transform negative expressions into positive ones,

[1503] means for converting the converted positive text data into audio data;

[1504] means for playing the converted audio data to a user;

[1505] A system including:

[1506] (Claim 2)

[1507] 10. The system of claim 1, wherein the sentiment analysis means analyzes the text data using a generative model.

[1508] (Claim 3)

[1509] 2. The system according to claim 1, wherein the means for converting speech into text data uses a speech recognition API.

[1510] "Example 1"

[1511] (Claim 1)

[1512] a means for acquiring audio;

[1513] a transmitting means for converting the acquired voice into data;

[1514] means for converting the acquired voice into text data;

[1515] means for sentiment analyzing the converted text data;

[1516] A way to transform negative expressions into positive ones,

[1517] means for converting the converted positive text data into sound data;

[1518] means for playing the converted sound data to a user;

[1519] A system including:

[1520] (Claim 2)

[1521] 10. The system of claim 1, wherein the sentiment analysis means analyzes the text data using a generative model.

[1522] (Claim 3)

[1523] 2. The system of claim 1, wherein the means for converting speech into text data uses speech recognition technology.

[1524] "Application Example 1"

[1525] (Claim 1)

[1526] a means for acquiring audio;

[1527] means for converting the acquired voice into text data;

[1528] means for sentiment analyzing the converted text data;

[1529] A way to transform negative expressions into positive ones,

[1530] means for converting the converted positive text data into audio data;

[1531] means for playing the converted audio data to a user;

[1532] A means of providing the converted positive voice data to workers in the factory in real time;

[1533] A system including:

[1534] (Claim 2)

[1535] 10. The system of claim 1, wherein the sentiment analysis means analyzes the text data using a generative model.

[1536] (Claim 3)

[1537] 2. The system according to claim 1, wherein the means for converting speech into text data uses a speech recognition API.

[1538] "Example 2: Combining Emotion Engines"

[1539] (Claim 1)

[1540] means for acquiring sounds around the user;

[1541] means for transmitting the acquired voice data to a server;

[1542] means for analyzing a user's biosignal to recognize the user's emotional state;

[1543] means for converting the acquired voice into text data;

[1544] means for sentiment analyzing the converted text data;

[1545] A way to transform negative expressions into positive ones,

[1546] means for converting the converted positive text data into audio data;

[1547] means for playing the converted audio data to a user;

[1548] A system including:

[1549] (Claim 2)

[1550] 10. The system of claim 1, wherein the sentiment analysis means analyzes the text data using a generative model.

[1551] (Claim 3)

[1552] 2. The system according to claim 1, wherein the means for converting speech into text data uses a speech recognition API.

[1553] "Application example 2 when combining emotion engines"

[1554] (Claim 1)

[1555] a means for acquiring audio;

[1556] means for converting the acquired voice into text data;

[1557] means for sentiment analyzing the converted text data;

[1558] A way to transform negative expressions into positive ones,

[1559] means for converting the converted positive text data into audio data;

[1560] means for playing the converted audio data to a user;

[1561] A means for optimizing the emotional state of a user by collecting surrounding sounds, converting negative expressions into positive ones in real time, and providing the collected sounds to the user;

[1562] A system including:

[1563] (Claim 2)

[1564] 10. The system of claim 1, wherein the sentiment analysis means analyzes the text data using a generative model.

[1565] (Claim 3)

[1566] 2. The system according to claim 1, wherein the means for converting speech into text data uses a speech recognition API. [Explanation of symbols]

[1567] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for acquiring audio; means for converting the acquired voice into text data; means for sentiment analyzing the converted text data; A way to transform negative expressions into positive ones, means for converting the converted positive text data into audio data; means for playing the converted audio data to a user; A system including:

2. 10. The system of claim 1, wherein the sentiment analysis means analyzes the text data using a generative model.

3. 2. The system according to claim 1, wherein the means for converting speech into text data uses a speech recognition API.

Images