System

Abstract

A system is provided.SOLUTION: A system comprising: a sensor unit configured to detect brain waves; a data preprocessing unit configured to receive the brain wave data and perform noise removal and normalization; an inference unit configured to infer a word or emotion by a machine learning model using the preprocessed data; an interface unit configured to display or output by voice an inference result by the inference unit; and an inverse transformation unit configured to generate corresponding brain wave data from the word or emotion.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] Conventional communication methods have made it difficult to communicate smoothly in real time with people who have lost the ability to speak or move their limbs. Furthermore, while there is interest in knowing what pets and other living creatures are thinking, communication between living creatures has been difficult. To solve these issues, technology that utilizes brain waves to enable communication between living creatures is needed. [Means for solving the problem]

[0005] The present invention provides a system including a sensor means for detecting electroencephalograms, a data preprocessing means for receiving the electroencephalogram data and performing noise removal and normalization, an estimation means for estimating words and emotions using a machine learning model based on the preprocessed data, an interface means for displaying or outputting the estimation results by the estimation means, and an inverse conversion means for generating corresponding electroencephalogram data from the words and emotions. This system estimates words and emotions from electroencephalogram data in real time and displays or outputs the results as audio, enabling smooth communication with people who have lost the ability to speak or move their limbs. It also enables translation between pets and other living creatures, realizing communication between living creatures that was previously difficult.

[0006] "Electroencephalograms" refer to electrical signals emitted by nerve cells in the brain.

[0007] The term "brain wave sensor means" refers to a device that detects brain waves and acquires them as digital data.

[0008] "Data preprocessing methods" refers to the process of converting collected raw data into a format suitable for machine learning models using techniques such as noise removal and normalization.

[0009] "Noise filter" refers to a technique or device that removes unwanted noise components from collected EEG data.

[0010] A "normalization algorithm" refers to a computational method that standardizes the distribution or range of data.

[0011] A "machine learning model" is an algorithm that learns specific patterns and characteristics from collected data and uses that knowledge to analyze and predict new data.

[0012] "Inference method" refers to the process of using a machine learning model to infer words and emotions from input data.

[0013] "Interface means" refers to the part that exchanges information between the system and the user, and provides information in the form of a display, audio output, or the like.

[0014] "Inverse conversion means" refers to technology that generates corresponding brain wave data based on information such as words and emotions. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[0037] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. Because the collected data is difficult to analyze in its raw form, the device sends this data to a server.

[0038] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[0039] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[0040] The device then displays the received prediction results to the user through an interface. For example, if the predicted word is "Hello," the device will display "Hello" on its screen or play it aloud using speech synthesis technology. This interface allows the user to communicate their thoughts to others in real time.

[0041] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[0042] Specific examples

[0043] Example 1: When the user thinks "Hello"

[0044] 1. The user imagines a specific word in their mind, such as "Hello."

[0045] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[0046] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0047] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0048] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[0049] Example 2: When the user says "Hello"

[0050] 1. When the user says "hello", enter the string "hello" into the terminal.

[0051] 2. The terminal sends the string data to the server.

[0052] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[0053] 4. The server sends the generated EEG data to the device.

[0054] 5. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain.

[0055] 6. The user receives the same feeling as "hello."

[0056] Through these processes, this system will enable smooth communication with people and animals who have lost the ability to speak. In the future, it may also be possible to translate between a wide variety of living creatures, opening up new forms of communication.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[0060] Step 2:

[0061] The user thinks about a specific word or emotion, such as "Hello," and the EEG sensor detects the brain waves that correspond to this thought.

[0062] Step 3:

[0063] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[0064] Step 4:

[0065] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[0066] Step 5:

[0067] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[0068] Step 6:

[0069] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[0070] Step 7:

[0071] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[0072] Step 8:

[0073] The server receives the output from the machine learning model and interprets the estimated words and sentiment. In this example, the model estimates "Hello."

[0074] Step 9:

[0075] The server sends the estimation results to the terminal, which is the step to notify the results to the user.

[0076] Step 10:

[0077] The device sends the received inference result to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[0078] Step 11:

[0079] The user can confirm the inference results through the interface, thereby recognizing that their thoughts have been accurately interpreted and communicated to others.

[0080] Inverse transformation (e.g., when a user is told "hello")

[0081] Step 1:

[0082] A situation occurs where a user says "hello." The device receives this in text form.

[0083] Step 2:

[0084] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[0085] Step 3:

[0086] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[0087] Step 4:

[0088] The server sends the generated brainwave data to the device, which is then ready to be transmitted to the user's brain.

[0089] Step 5:

[0090] The device transmits the generated brainwave data back to the brainwave sensor, which then stimulates the user's brain.

[0091] Step 6:

[0092] The user receives the transmitted EEG signal and the same sensation as saying "hello" is reproduced in the brain, giving the user the sensation of hearing the word.

[0093] Through these processing steps, this system realizes smooth communication between living organisms using brain waves.

[0094] Example 1

[0095] 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."

[0096] Previous communication systems using EEGs lacked accuracy and real-time capabilities, and in particular, the lack of noise removal and data standardization made it difficult to analyze EEG data. Furthermore, there was a lack of inverse conversion methods to convert corresponding words and emotions into EEG data. As a result, it was difficult to achieve smooth communication with people or animals who had lost the ability to speak.

[0097] 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.

[0098] In this invention, the server includes a sensor device for detecting brain waves, a data preprocessing device that receives the brain wave data and performs noise reduction and normalization, an estimation device that uses the preprocessed data to estimate words and emotions using a machine learning model, an interface device that displays or outputs the estimation results by the estimation device as audio, an inverse conversion device that generates corresponding brain wave data from the words and emotions, a terminal that collects brain wave data in real time, a communication device that transmits the collected data to the server via the Internet, and a transmission device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain. This system enables real-time analysis of brain wave data and accurate estimation of corresponding words and emotions. Furthermore, by using the inverse conversion means to convert words and emotions into brain wave data and reproducing them in the user's brain, communication without speaking is possible.

[0099] "Electroencephalograms" are electrical signals emitted by nerve cells in the brain.

[0100] A "sensor device" is a device for detecting brain waves and is used to collect electrical signals from the brain in real time.

[0101] The "data preprocessing device" is a device that performs noise removal and standardization on the electroencephalogram data received from the sensor device.

[0102] A "noise filter" is an algorithm for removing unnecessary noise components from EEG data.

[0103] A "normalization algorithm" is an algorithm for converting data into a standard format.

[0104] An "estimation device" is a device that uses preprocessed data to estimate words and emotions using a machine learning model.

[0105] A "machine learning model" is a mathematical model that learns from past datasets and infers words and emotions from new data.

[0106] An "interface device" is a device for displaying or outputting the estimation results of an estimation device as audio.

[0107] An "inverse conversion device" is a device for generating corresponding electroencephalogram data from words and emotions.

[0108] The "terminal" is a device that collects brain wave data from a sensor device and transmits it to a server.

[0109] The "communication device" is a device that allows the terminal to transmit brain wave data to a server via the Internet.

[0110] The "transmitting device" is a device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain.

[0111] MODE FOR CARRYING OUT THE INVENTION

[0112] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[0113] EEG data collection

[0114] First, the user wears an EEG sensor device, which detects electrical signals emitted by the brain's nerve cells in real time. Specifically, a sensor device such as Neurosky's MindWave is used.

[0115] Sending data

[0116] The device then collects the EEG data from the sensor device and transmits it to a server via the internet. The device can be a smartphone, computer, or other device.

[0117] Data Preprocessing

[0118] The server processes the received EEG data using a data preprocessing device. Specifically, it uses a noise filter to remove unwanted noise components and applies a normalization algorithm to standardize the data. For this purpose, the Python libraries scipy.signal and scikit-learn are used.

[0119] Data analysis and estimation

[0120] Based on the preprocessed data, the server inputs the data into a machine learning model (e.g., TensorFlow or PyTorch) to estimate words and emotions. The machine learning model is trained from a large set of historical data and makes accurate estimates based on the data provided.

[0121] Sending and displaying results

[0122] The estimation results are sent from the server to the device, which then displays or outputs the results to the user. For example, it can be played back as audio using the Google Text-to-Speech API.

[0123] Inverse transformation process

[0124] The system also includes a reverse conversion mechanism. For example, if the user receives different words or emotions, the device sends the string data to the server. The server uses a generative AI model (e.g., OpenAI's GPT-3 or GPT-4) to generate corresponding EEG data from the string, which is then sent to the device. The device then sends the generated EEG data back to the sensor device, which stimulates the user's brain.

[0125] Specific examples

[0126] Example 1: When the user thinks "Hello"

[0127] 1. The user imagines a specific word in their mind, such as "Hello."

[0128] 2. The terminal collects EEG data from the sensor device in real time and transmits it to the server.

[0129] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0130] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0131] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[0132] Example 2: When the user says "Hello"

[0133] 1. When the user says "hello", enter the string "hello" into the terminal.

[0134] 2. The terminal sends the string data to the server.

[0135] 3. The server uses the generative AI model to generate corresponding EEG data from the string.

[0136] 4. The server sends the generated EEG data to the device.

[0137] 5. The device transmits the generated brain wave data back to the sensor device, stimulating the user's brain.

[0138] 6. The user receives the same feeling as "hello."

[0139] Example prompt: "Implement a method to communicate by converting the user's thoughts into EEG data. The hardware used will be Neurosky's MindWave, and the machine learning model will be built using PyTorch."

[0140] This system will enable smooth communication between people and animals who have lost the ability to speak, and will also enable translation between a wide variety of living creatures, opening up the possibility of new forms of communication.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Step 1: Collect EEG data

[0143] The user wears an EEG sensor device. This sensor device detects electrical signals emitted by the brain's nerve cells in real time. The terminal collects EEG data from the sensor device via Bluetooth or a wired connection. The input is raw data from the sensor device. The output is EEG data collected by the terminal. Specifically, the terminal receives the signals sent from the sensor device and saves them in a stream format as "brainwave data."

[0144] Step 2: Sending data

[0145] The device sends the collected EEG data to a server via an internet connection. The input is the EEG data collected by the device. The output is the EEG data sent to the server. Specifically, the device sends the EEG data to the server using an HTTP POST request.

[0146] Step 3: Preprocessing the data

[0147] The server performs noise filtering on the received EEG data. Then, it applies a normalization algorithm to standardize the data. The input is the raw EEG data received by the server. The output is the noise-removed and standardized EEG data. Specifically, the server performs noise filtering using the Python library scipy.signal and standardizes the data using scikit-learn's StandardScaler.

[0148] Step 4: Data analysis and estimation

[0149] The server inputs the preprocessed data into a machine learning model. The model learns from past datasets and estimates the words and emotions corresponding to the EEG data. The input is the preprocessed EEG data. The output is the estimated words and emotions. Specifically, the server inputs the data into a machine learning model built using TensorFlow or PyTorch and obtains the estimated results.

[0150] Step 5: Send and view results

[0151] The server sends the estimated results to the device. The device receives the results and displays or outputs them as audio to the user through an interface device. The input is the estimated words and emotions (data sent from the server). The output is the results displayed or output as audio to the user. Specifically, the device uses the Google Text-to-Speech API or similar to play back the estimated words as audio or display them on the screen.

[0152] Step 6: Reverse transformation

[0153] When a user receives a specific word or emotion, the device sends the string of characters to the server. The server uses a generative AI model to generate corresponding brain wave data from this string of characters and sends it back to the device. The device then sends the generated brain wave data back to the sensor device, stimulating the user's brain. The input is the string of characters (the words or emotions entered by the user). The output is the corresponding brain wave data. Specifically, the server uses OpenAI's GPT-3 or GPT-4 to convert the string of characters into brain wave data, which is then sent back to the user's brain via the device.

[0154] (Application example 1)

[0155] 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."

[0156] In conventional factory production sites, workers need advanced programming knowledge and complex operations to communicate effectively with robots. Furthermore, transmitting work instructions takes time, placing a heavy burden on workers. Furthermore, there is a lack of interfaces for issuing instructions quickly and accurately. There is a need to solve these problems and achieve smoother, more efficient communication between humans and robots.

[0157] 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.

[0158] In this invention, the server includes a sensor means for detecting brain waves, a data preprocessing means for receiving the brain wave data and performing noise removal and normalization, an estimation means for estimating words and emotions using a machine learning model using the preprocessed data, an interface means for displaying or outputting the estimation results by voice, an inverse conversion means for generating corresponding brain wave data from the words and emotions, and an instruction generation means for generating work instructions based on the preprocessed data and transmitting the instructions to an external device. This enables workers to quickly and accurately issue work instructions to factory robots simply by thinking using the brain wave sensor.

[0159] The "sensor means for detecting brain waves" is a device that detects the user's brain activity and collects brain wave data.

[0160] The "data preprocessing means" is a device or method that performs processing to remove noise from collected electroencephalogram data and standardize the data.

[0161] The "estimation means" is a device or method that inputs preprocessed EEG data into a machine learning model and estimates words and emotions based on the output.

[0162] The "interface means" is a device or method for displaying or outputting the results estimated by the estimation means by voice.

[0163] The "inverse conversion means" is a device or method that generates corresponding electroencephalogram data from estimated words or emotions.

[0164] The "instruction generation means" is a device or method that generates work instructions based on the preprocessed data and the estimated results, and transmits the instructions to an external device.

[0165] An "external device" is an industrial robot or other mechanical device that receives data or instructions and performs a specific action.

[0166] This invention is a system that realizes communication between living organisms using brain waves. In particular, it aims to enable factory workers to wear smart glasses and transmit their thoughts to industrial robots as instructions. Specific embodiments of this system are described below.

[0167] 1. EEG data collection and preprocessing

[0168] The user (worker) wears an EEG sensor and engages in specific thinking, such as "pick out the next part and assemble it." This sensor detects the electrical signals emitted by the neurons in the user's brain in real time, i.e., EEG data. The device receives the data collected from this sensor. However, because EEG data is difficult to analyze in its raw form, a noise filter is first used to remove unnecessary noise components. Next, a normalization algorithm is applied to standardize the data, making it suitable for machine learning models.

[0169] 2. Estimating words and emotions

[0170] The preprocessed data is sent to a server. The server uses a generative AI model to analyze the data and estimate corresponding words and emotions. The generative AI model learns from a huge amount of past data sets and is able to make estimates with high accuracy. For example, if a user thinks, "Take out the next part and assemble it," data corresponding to that word is generated.

[0171] 3. Displaying Estimation Results and Generating Instructions

[0172] The estimated words and emotions are sent from the server to the device. The device displays the estimated results to the user through an interface. For example, if the estimated instruction is "Start assembly," the text "Start assembly" is displayed on the device screen. If the user confirms the instruction and there are no problems, the instruction is sent to an external device (industrial robot).

[0173] 4. Specific Examples

[0174] As a concrete example, imagine a worker wearing smart glasses thinking the instruction "pick out the next part and assemble it." The flow of this system is as follows:

[0175] 1. The worker thinks, "Pick out the next part and assemble it."

[0176] 2. The EEG sensor collects EEG data and transmits it to the device.

[0177] 3. The device preprocesses the data using noise filters and normalization algorithms.

[0178] 4. The preprocessed data is sent to the server and input into the generative AI model.

[0179] 5. The server estimates the words and emotions and sends the results to the device.

[0180] 6. The terminal displays "Assembly Start" and the user confirms.

[0181] 7. After confirmation, the terminal sends the instruction to the external device (industrial robot).

[0182] Prompt Sentence Examples

[0183] "Instruct the robot to pick up the next part and assemble it."

[0184] This invention enables factory workers to issue instructions to industrial robots quickly and accurately simply by thinking, without the need for complex programming knowledge or operation. Real-time communication also improves work efficiency and accuracy.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The user wears an EEG sensor and thinks, for example, "Pick out the next part and assemble it." The EEG sensor detects the electrical signals (brainwave data) from the user's brain's neurons in real time and sends that data to a device. The input is the EEG data detected in real time, and the output is the raw EEG data sent to the device.

[0188] Step 2:

[0189] The EEG data received by the device is filtered to remove unwanted noise components. A normalization algorithm is then applied to standardize the data. The input is the raw EEG data received from the sensor, and the output is the normalized data with noise removed. Specifically, the mean value of the data is subtracted and divided by the standard deviation.

[0190] Step 3:

[0191] The preprocessed data is sent to a server, which then inputs the received data into a generative AI model. The input is noise-removed and normalized EEG data, and the output is estimated words and emotions. The generative AI model uses a multi-layer neural network to learn from a huge dataset of past data.

[0192] Step 4:

[0193] The server uses the generative AI model to send estimated words and emotions to the device. The input is the words and emotions estimated by the generative AI model, and the output is the transmission of the estimated results to the device. Specifically, the output of the generative AI model is converted into JSON format and sent to the device via the network.

[0194] Step 5:

[0195] The device displays the inference results to the user through an interface. The input is the inference results sent from the server, and the output is text or audio displayed on the interface screen. For example, "Start assembly" may be displayed as text, and can also be confirmed aloud using speech synthesis technology.

[0196] Step 6:

[0197] The user checks the displayed inference results, and if there are no problems, sends instructions to an external device (industrial robot). The input is the inference results, and the output is specific instructions to the external device. Specifically, instructions are sent by pressing a button on the interface.

[0198] Step 7:

[0199] An external device (industrial robot) starts to operate based on the received instruction. The input is the specific instruction sent by the user, and the output is the actual action of the robot. For example, it executes the action "pick out the next part and assemble it."

[0200] 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.

[0201] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[0202] First, the user wears an EEG sensor. This sensor detects the electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. The collected data is raw and therefore contains a lot of noise. The device then transmits this data to a server.

[0203] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[0204] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[0205] In addition to the estimation means, the server is also equipped with an emotion engine, which further analyzes the user's brainwave data and classifies their emotional state into joy, sadness, anger, surprise, etc. The emotion engine uses a machine learning algorithm to estimate the emotional state in real time and also transmits this information to the device.

[0206] The device displays the received inference results and emotional state to the user through an interface. For example, if the inferred word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on its screen or play it in a "joy" tone using voice synthesis technology. This interface allows the user to communicate their thoughts and emotions to others in real time.

[0207] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[0208] Specific examples

[0209] Example 1: User thinks "Hello" and feels happy

[0210] 1. The user feels a sense of joy in their brain along with the specific word "Hello."

[0211] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[0212] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0213] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0214] 5. The server's emotion engine recognizes the emotion of joy.

[0215] 6. The server sends the estimation results and emotion information to the device, which then displays or speaks "Hello (joy)."

[0216] Example 2: When a user is told "hello" and feels surprised

[0217] 1. A situation occurs where a user is told "hello" and feels surprised.

[0218] 2. The terminal inputs the string data "Hello" and sends it to the server.

[0219] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[0220] 4. The server's emotion engine recognizes the emotion of surprise and encodes it into the brainwave data.

[0221] 5. The server sends the generated EEG data to the device.

[0222] 6. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain with a sense of surprise.

[0223] Through these concrete examples, this system realizes smooth communication between living organisms using brain waves and emotions.

[0224] The processing flow will be explained below.

[0225] Program processing steps

[0226] When the user thinks "Hello"

[0227] Step 1:

[0228] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[0229] Step 2:

[0230] When the user thinks about the specific word "Hello" and the emotion of joy, the EEG sensor detects the brain waves that correspond to this thought and emotion.

[0231] Step 3:

[0232] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[0233] Step 4:

[0234] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[0235] Step 5:

[0236] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[0237] Step 6:

[0238] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[0239] Step 7:

[0240] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[0241] Step 8:

[0242] The server receives the output from the machine learning model and interprets the predicted word as "Hello."

[0243] Step 9:

[0244] The server uses an emotion engine to analyze the user's emotions from the brainwave data and classify the emotion as "joy."

[0245] Step 10:

[0246] The server sends the estimation results and emotion information to the terminal. This is the step to communicate the results and emotions to the user.

[0247] Step 11:

[0248] The device sends the received estimation results and emotion information to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[0249] Step 12:

[0250] The user can confirm the estimation results and emotional information through the interface, thereby recognizing that their thoughts and emotions have been accurately interpreted and conveyed to others.

[0251] Inverse transformation (when a user is told "hello" and feels surprised)

[0252] Step 1:

[0253] The user is surprised when they hear "hello." The device receives this message in text format.

[0254] Step 2:

[0255] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[0256] Step 3:

[0257] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[0258] Step 4:

[0259] The server uses an emotion engine to recognize the emotion "surprise" and integrates this information with the brainwave data.

[0260] Step 5:

[0261] The server sends the generated EEG data to the terminal, which includes the word "hello" and emotional information about "surprise."

[0262] Step 6:

[0263] The device transmits the generated brainwave data back to the brainwave sensor, which stimulates the user's brain and reproduces words and emotions.

[0264] Step 7:

[0265] The user receives the transmitted EEG signal and the sensations of "hello" and surprise are recreated in the brain, resulting in the user experiencing the words and emotions.

[0266] Through the above processing steps, this system realizes smooth communication between living organisms using brain waves and emotions.

[0267] Example 2

[0268] 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."

[0269] Previous communication systems using EEGs had issues such as insufficient noise removal and normalization of EEG data, and low emotion recognition accuracy. Furthermore, the interfaces for accurately displaying and outputting estimated words and emotions in real time were also inadequate. Furthermore, even in communication using inverse conversion, the accuracy of the generated EEG data was an issue.

[0270] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or outputting the estimation results and emotional information by the estimation means as audio, and inverse conversion means for generating corresponding brain wave data from the words and emotions. This makes it possible to estimate words and emotions with high accuracy using normalized data with little noise, enable real-time display and audio output, and enable accurate communication through inverse conversion.

[0271] "Electroencephalograms" are weak electrical signals emitted by nerve cells in humans and animals.

[0272] "Sensor means" refers to a device or mechanism that detects brain waves in real time.

[0273] The "data preprocessing means" is a device or mechanism that performs noise removal and normalization on the received electroencephalogram data.

[0274] A "noise filter" is an algorithm or device for removing unwanted noise components from EEG data.

[0275] A "normalization algorithm" is a mathematical method for converting data into a uniform format.

[0276] The "estimation means" is a device or mechanism that estimates words and emotions using a machine learning model based on preprocessed data.

[0277] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications for new data.

[0278] An "emotion engine" is an algorithm or system that analyzes brainwave data and classifies emotional states such as joy, sadness, and anger.

[0279] The "interface means" is a device or mechanism for visually or audibly notifying the user of the estimation results and emotional information.

[0280] The "inverse conversion means" is a device or mechanism that generates corresponding electroencephalogram data from identified words or emotions.

[0281] A "generative AI model" is an artificial intelligence model that generates corresponding brainwave data or other outputs from input text data.

[0282] A "prompt" is an instruction or question that serves as input to a generative AI model.

[0283] MODE FOR CARRYING OUT THE INVENTION

[0284] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[0285] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by nerve cells, i.e., brain waves, in real time. A commercially available EEG capture device can be used as the sensor. At the same time, the device collects EEG data from the sensor. However, this data contains a lot of noise, making it unusable as is.

[0286] The device then transmits the collected EEG data to a server. This communication is encrypted using the SSL / TLS protocol to ensure security. The server can be hosted in a cloud environment, for example, to facilitate scalability and resource management. The server first applies a noise filter to the received EEG data to remove unwanted noise components. The noise filter can be a band-pass filter or a custom noise reduction algorithm.

[0287] Once the noise has been removed, the server then applies a normalization algorithm, for example, using Z-score normalization to standardize the data, ensuring that the data obtained from different users and across different measurement sessions is in a consistent format.

[0288] Based on the preprocessed data, the server inputs the data into a machine learning model, which can be a deep learning framework such as TensorFlow. This model learns from a large dataset of past data and predicts corresponding words and emotions based on the input data.

[0289] The estimation results are encrypted using the SSL / TLS protocol and sent to the device. The emotion engine on the server then further analyzes the EEG data to classify emotional states such as joy, sadness, anger, and surprise. The emotion engine also uses machine learning algorithms to estimate emotional states in real time.

[0290] The device displays the estimation results and emotion information to the user through an interface. Display can be done in the form of a web application using HTML5 and JavaScript. It is also possible to play the estimated emotion tone using speech synthesis technology. For example, if the estimated word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on the screen or play it in a "joy" tone.

[0291] The system also has a reverse conversion mechanism. For example, when communicating with other users (including pets), if a user wants to receive specific words or emotions, the device sends the string data to the server. The server uses a generative AI model to generate corresponding EEG data from the string and sends it back to the device. An example of a generative AI model is OpenAI's GPT-4. An example of a prompt sentence is, "Please generate the EEG data when the user says 'hello'."

[0292] The device then transmits the generated brainwave data back to the sensor, stimulating the user's brain and reproducing the words and emotions within the brain. This function allows users to communicate without speaking.

[0293] As described above, this system realizes highly accurate communication between living organisms using brain waves and emotional data, allowing users to smoothly convey their thoughts and emotions to others.

[0294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0295] Program processing steps

[0296] Step 1:

[0297] The user wears an EEG sensor. The sensor detects electrical signals (brain waves) emitted by the brain's neurons in real time. The input is the electrical signals emitted by the neurons, and the output is the detected raw brain wave data. Specifically, the user wears the EEG sensor on their head, and the sensor captures the electrical signals.

[0298] Step 2:

[0299] The device collects raw EEG data from the sensor in real time and sends it to the server. The input is raw EEG data from the sensor, and the output is unprocessed EEG data sent to the server. Specifically, the device takes in data from the sensor, encrypts it using SSL / TLS, and sends it to the server.

[0300] Step 3:

[0301] The server applies a noise filter to the received raw EEG data. The input is raw EEG data, and the output is clean EEG data with noise removed. Specifically, the server uses a band-pass filter or a custom noise reduction algorithm to remove noise from the EEG data.

[0302] Step 4:

[0303] The server normalizes the clean EEG data using a normalization algorithm. The input is the denoised EEG data, and the output is the normalized EEG data. Specifically, the data is converted into a consistent format using Z-score normalization.

[0304] Step 5:

[0305] The server inputs the normalized data into a machine learning model. The input is normalized EEG data, and the output is estimated words and emotions. Specifically, the data is analyzed using a deep learning framework such as TensorFlow to estimate the words and emotions the user is thinking.

[0306] Step 6:

[0307] The server sends the estimated words and emotion information to the device. The input is the estimation result from the machine learning model, and the output is the encrypted estimation result and emotion information. Specifically, the estimation result is encrypted using SSL / TLS and sent to the device.

[0308] Step 7:

[0309] The device displays the estimation results and emotional information to the user through an interface. The input is the estimation results and emotional information received from the server, and the output is the information displayed on the interface or a voice generated by speech synthesis. Specific operations include displaying the results in a web application format using HTML5 and JavaScript, and playing back a voice in a specific tone using speech synthesis technology.

[0310] Step 8:

[0311] When a user wants to receive a desired word or emotion, the device sends the string data to the server. The input is the string data entered by the user, and the output is the string data to be sent to the server. Specifically, the device takes the entered string data, encrypts it using SSL / TLS, and sends it to the server.

[0312] Step 9:

[0313] The server uses a generative AI model to generate corresponding brain wave data from input string data. The input is string data received from the terminal, and the output is generated brain wave data. In concrete terms, a prompt sentence is input into the generative AI model (for example, a general-purpose artificial intelligence model), and brain wave data is generated based on that. An example of a prompt sentence is in the format "Please generate brain wave data when the user says 'hello'."

[0314] Step 10:

[0315] The server sends the generated EEG data to the terminal. The input is the generated EEG data, and the output is the EEG data to be sent to the terminal. Specifically, the EEG data is encrypted using SSL / TLS and sent to the terminal.

[0316] Step 11:

[0317] The device then transmits the received brainwave data back to the sensor, which then stimulates the user's brain. The input is the received brainwave data, and the output is the words and emotions that are reproduced in the user's brain. Specifically, the brainwave data is transmitted back to the user's brain via the sensor, which then stimulates the user to reproduce specific words and emotions.

[0318] This processing step allows the system to convey the user's thoughts and feelings to others, and also enables communication through reverse conversion.

[0319] (Application example 2)

[0320] 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."

[0321] Currently, communication between workers and robots in factories is often carried out via physical input devices or programming, making it difficult to give intuitive and quick instructions. Furthermore, it is not possible to understand the emotions of workers and respond appropriately, which raises concerns about reduced work efficiency and stress. Furthermore, there are limited means of receiving feedback from robots in real time, making it difficult to respond quickly.

[0322] The identification processing 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 sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or audio output of the estimation results by the estimation means, inverse conversion means for generating corresponding brain wave data from the words and emotions, and means for sending instructions to a factory robot via the interface means and feeding back the robot's status and messages to the user's brain. This enables workers to intuitively issue instructions to factory robots using brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[0323] The "sensor means for detecting brain waves" is a device that detects and collects the user's brain wave data in real time.

[0324] The "data preprocessing means" refers to a device or software that removes noise and normalizes the received EEG data, converting it into a format suitable for a machine learning model.

[0325] The "estimation means" is a system or algorithm that inputs preprocessed EEG data into a machine learning model to estimate words and emotions.

[0326] The "interface means" refers to a device or software for displaying or outputting the estimation result by the estimation means to the user.

[0327] The "inverse conversion means" is a device or system that generates corresponding electroencephalogram data from words and emotions and feeds this back to the user's brain.

[0328] A "factory robot" is an automated mechanical device designed to perform manufacturing or assembly tasks.

[0329] A "server" is a central processing unit or system for processing, estimating, and feeding back EEG data.

[0330] "Noise filter" is a filtering technique for removing unnecessary noise components from EEG data.

[0331] A "normalization algorithm" is an algorithm that standardizes data and converts it into a format that can be efficiently processed by machine learning models.

[0332] A "machine learning model" is an algorithmic model that learns from past data and makes inferences and predictions based on new data.

[0333] The present invention is a system for efficiently communicating between workers and robots in a factory. Specific embodiments of the system are described below.

[0334] System configuration

[0335] 1. Sensor means for detecting brain waves:

[0336] The user wears an EEG sensor (e.g., an EEG headset) that detects the user's EEG data in real time and transmits it to a device.

[0337] 2. Data preprocessing methods:

[0338] After receiving the EEG data, the device uses a noise filter (e.g., Butterworth filter) to remove unnecessary noise, then standardizes the data using a normalization algorithm and performs preprocessing.

[0339] 3. Estimation method:

[0340] The preprocessed data is sent to a server, which uses a machine learning model (e.g., a model using TensorFlow or Keras) to analyze the data, infer words and emotions, and then uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) to classify the emotional state.

[0341] 4. Interface means:

[0342] The analysis results are sent from the server to the terminal and displayed or output to the user via the terminal's display or audio output device. At the same time, the analysis results are sent as instructions to the factory robot.

[0343] 5. Reverse transformation method:

[0344] If necessary, the server uses a generative AI model to generate corresponding brainwave data from the string data and transmits it back to the sensor via the device, allowing specific words or emotions to be fed back to the user's brain.

[0345] 6. Feedback methods:

[0346] Factory robots send their work status and messages in real time to a server, which then analyzes this information and sends it directly to the user's brain as necessary feedback.

[0347] Hardware and Software

[0348] Brainwave sensor: Brainwave detection headset (e.g., Emotiv EPOC+)

[0349] Device: Smartphone or tablet (Android or iOS device)

[0350] Server: Cloud computing service (e.g., Amazon Web Services, Google Cloud)

[0351] Machine learning models: TensorFlow, Keras

[0352] Emotion engine: Azure Cognitive Services, IBM Watson

[0353] Specific examples

[0354] Example 1: Packing instructions

[0355] 1. If the user thinks "Robot, start packing" and feels satisfied:

[0356] The EEG sensor collects EEG data and transmits it to the terminal.

[0357] Data preprocessing is performed on the terminal and then sent to the server.

[0358] Analysis and estimation are performed on the server, and instructions are sent to the robot.

[0359] The robot starts working and sends the work status to the server.

[0360] The server feeds the analysis results back to the device, stimulating the user's brain.

[0361] Prompt Sentence Examples

[0362] "When the user thinks 'Robot, start packing,' and feels satisfied, process the EEG data and send the corresponding instruction to the robot. Please provide a detailed description of the data you collected, normalized, and extrapolated."

[0363] This allows users to intuitively give instructions to factory robots using their brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1:

[0366] The user wears an EEG sensor, which detects the user's brainwaves in real time and transmits the data to the device via Bluetooth. The input is the user's brainwaves, and the output is raw EEG data.

[0367] Step 2:

[0368] The device performs noise filtering on the received EEG data. It uses a Butterworth filter to remove unwanted noise. The input is raw EEG data, and the output is pre-processed EEG data with noise removed.

[0369] Step 3:

[0370] The device normalizes the noise-filtered EEG data. It uses a normalization algorithm to standardize the data and convert it into a format suitable for the machine learning model. The input is the noise-removed EEG data, and the output is the normalized EEG data.

[0371] Step 4:

[0372] The device sends the normalized EEG data to the server. The data is securely transferred using the HTTPS protocol. The input is the normalized EEG data, and the output is the data sent to the server.

[0373] Step 5:

[0374] The server inputs the received data into a machine learning model. Using TensorFlow or Keras, the data is fed into a pre-trained model to estimate words and emotions. The input is normalized EEG data, and the output is estimated words and emotions.

[0375] Step 6:

[0376] The server uses an emotion engine to classify detailed emotional states. It analyzes and classifies emotions using Azure Cognitive Services and IBM Watson's emotion detection API. The input is the emotion estimated by the machine learning model, and the output is detailed classified emotional information.

[0377] Step 7:

[0378] The server sends the estimated words and emotion information to the terminal. At the same time, it sends the analysis results as instructions to the factory robot, which then begins the specified action. The input is the estimated words and emotion, and the output is the instructions sent to the terminal and the robot.

[0379] Step 8:

[0380] The device displays or outputs the received instructions and emotional information. The user can check the text on the display or hear the information through the audio output. The input is the estimated words and emotional information, and the output is visual or auditory feedback to the user.

[0381] Step 9:

[0382] Factory robots operate according to instructions and send work status and status information to a server in real time. The input is the instructions sent to the robot, and the output is the work status and status information.

[0383] Step 10:

[0384] The server analyzes the feedback information from the robot and sends it as stimuli to the user's brain as needed. It uses a generative AI model to generate corresponding brainwave data from the string data, which is then sent back to the brainwave sensor via the terminal. The input is the feedback information from the robot, and the output is the feedback sent to the user's brain.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] [Second embodiment]

[0389] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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."

[0401] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[0402] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. Because the collected data is difficult to analyze in its raw form, the device sends this data to a server.

[0403] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[0404] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[0405] The device then displays the received prediction results to the user through an interface. For example, if the predicted word is "Hello," the device will display "Hello" on its screen or play it aloud using speech synthesis technology. This interface allows the user to communicate their thoughts to others in real time.

[0406] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[0407] Specific examples

[0408] Example 1: When the user thinks "Hello"

[0409] 1. The user imagines a specific word in their mind, such as "Hello."

[0410] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[0411] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0412] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0413] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[0414] Example 2: When the user says "Hello"

[0415] 1. When the user says "hello", enter the string "hello" into the terminal.

[0416] 2. The terminal sends the string data to the server.

[0417] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[0418] 4. The server sends the generated EEG data to the device.

[0419] 5. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain.

[0420] 6. The user receives the same feeling as "hello."

[0421] Through these processes, this system will enable smooth communication with people and animals who have lost the ability to speak. In the future, it may also be possible to translate between a wide variety of living creatures, opening up new forms of communication.

[0422] The processing flow will be explained below.

[0423] Step 1:

[0424] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[0425] Step 2:

[0426] The user thinks about a specific word or emotion, such as "Hello," and the EEG sensor detects the brain waves that correspond to this thought.

[0427] Step 3:

[0428] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[0429] Step 4:

[0430] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[0431] Step 5:

[0432] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[0433] Step 6:

[0434] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[0435] Step 7:

[0436] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[0437] Step 8:

[0438] The server receives the output from the machine learning model and interprets the estimated words and sentiment. In this example, the model estimates "Hello."

[0439] Step 9:

[0440] The server sends the estimation results to the terminal, which is the step to notify the results to the user.

[0441] Step 10:

[0442] The device sends the received inference result to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[0443] Step 11:

[0444] The user can confirm the inference results through the interface, thereby recognizing that their thoughts have been accurately interpreted and communicated to others.

[0445] Inverse transformation (e.g., when a user is told "hello")

[0446] Step 1:

[0447] A situation occurs where a user says "hello." The device receives this in text form.

[0448] Step 2:

[0449] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[0450] Step 3:

[0451] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[0452] Step 4:

[0453] The server sends the generated brainwave data to the device, which is then ready to be transmitted to the user's brain.

[0454] Step 5:

[0455] The device transmits the generated brainwave data back to the brainwave sensor, which then stimulates the user's brain.

[0456] Step 6:

[0457] The user receives the transmitted EEG signal and the same sensation as saying "hello" is reproduced in the brain, giving the user the sensation of hearing the word.

[0458] Through these processing steps, this system realizes smooth communication between living organisms using brain waves.

[0459] Example 1

[0460] 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."

[0461] Previous communication systems using EEGs lacked accuracy and real-time capabilities, and in particular, the lack of noise removal and data standardization made it difficult to analyze EEG data. Furthermore, there was a lack of inverse conversion methods to convert corresponding words and emotions into EEG data. As a result, it was difficult to achieve smooth communication with people or animals who had lost the ability to speak.

[0462] 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.

[0463] In this invention, the server includes a sensor device for detecting brain waves, a data preprocessing device that receives the brain wave data and performs noise reduction and normalization, an estimation device that uses the preprocessed data to estimate words and emotions using a machine learning model, an interface device that displays or outputs the estimation results by the estimation device as audio, an inverse conversion device that generates corresponding brain wave data from the words and emotions, a terminal that collects brain wave data in real time, a communication device that transmits the collected data to the server via the Internet, and a transmission device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain. This system enables real-time analysis of brain wave data and accurate estimation of corresponding words and emotions. Furthermore, by using the inverse conversion means to convert words and emotions into brain wave data and reproducing them in the user's brain, communication without speaking is possible.

[0464] "Electroencephalograms" are electrical signals emitted by nerve cells in the brain.

[0465] A "sensor device" is a device for detecting brain waves and is used to collect electrical signals from the brain in real time.

[0466] The "data preprocessing device" is a device that performs noise removal and standardization on the electroencephalogram data received from the sensor device.

[0467] A "noise filter" is an algorithm for removing unnecessary noise components from EEG data.

[0468] A "normalization algorithm" is an algorithm for converting data into a standard format.

[0469] An "estimation device" is a device that uses preprocessed data to estimate words and emotions using a machine learning model.

[0470] A "machine learning model" is a mathematical model that learns from past datasets and infers words and emotions from new data.

[0471] An "interface device" is a device for displaying or outputting the estimation results of an estimation device as audio.

[0472] An "inverse conversion device" is a device for generating corresponding electroencephalogram data from words and emotions.

[0473] The "terminal" is a device that collects brain wave data from a sensor device and transmits it to a server.

[0474] The "communication device" is a device that allows the terminal to transmit brain wave data to a server via the Internet.

[0475] The "transmitting device" is a device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain.

[0476] MODE FOR CARRYING OUT THE INVENTION

[0477] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[0478] EEG data collection

[0479] First, the user wears an EEG sensor device, which detects electrical signals emitted by the brain's nerve cells in real time. Specifically, a sensor device such as Neurosky's MindWave is used.

[0480] Sending data

[0481] The device then collects the EEG data from the sensor device and transmits it to a server via the internet. The device can be a smartphone, computer, or other device.

[0482] Data Preprocessing

[0483] The server processes the received EEG data using a data preprocessing device. Specifically, it uses a noise filter to remove unwanted noise components and applies a normalization algorithm to standardize the data. For this purpose, the Python libraries scipy.signal and scikit-learn are used.

[0484] Data analysis and estimation

[0485] Based on the preprocessed data, the server inputs the data into a machine learning model (e.g., TensorFlow or PyTorch) to estimate words and emotions. The machine learning model is trained from a large set of historical data and makes accurate estimates based on the data provided.

[0486] Sending and displaying results

[0487] The estimation results are sent from the server to the device, which then displays or outputs the results to the user. For example, it can be played back as audio using the Google Text-to-Speech API.

[0488] Inverse transformation process

[0489] The system also includes a reverse conversion mechanism. For example, if the user receives different words or emotions, the device sends the string data to the server. The server uses a generative AI model (e.g., OpenAI's GPT-3 or GPT-4) to generate corresponding EEG data from the string, which is then sent to the device. The device then sends the generated EEG data back to the sensor device, which stimulates the user's brain.

[0490] Specific examples

[0491] Example 1: When the user thinks "Hello"

[0492] 1. The user imagines a specific word in their mind, such as "Hello."

[0493] 2. The terminal collects EEG data from the sensor device in real time and transmits it to the server.

[0494] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0495] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0496] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[0497] Example 2: When the user says "Hello"

[0498] 1. When the user says "hello", enter the string "hello" into the terminal.

[0499] 2. The terminal sends the string data to the server.

[0500] 3. The server uses the generative AI model to generate corresponding EEG data from the string.

[0501] 4. The server sends the generated EEG data to the device.

[0502] 5. The device transmits the generated brain wave data back to the sensor device, stimulating the user's brain.

[0503] 6. The user receives the same feeling as "hello."

[0504] Example prompt: "Implement a method to communicate by converting the user's thoughts into EEG data. The hardware used will be Neurosky's MindWave, and the machine learning model will be built using PyTorch."

[0505] This system will enable smooth communication between people and animals who have lost the ability to speak, and will also enable translation between a wide variety of living creatures, opening up the possibility of new forms of communication.

[0506] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0507] Step 1: Collect EEG data

[0508] The user wears an EEG sensor device. This sensor device detects electrical signals emitted by the brain's nerve cells in real time. The terminal collects EEG data from the sensor device via Bluetooth or a wired connection. The input is raw data from the sensor device. The output is EEG data collected by the terminal. Specifically, the terminal receives the signals sent from the sensor device and saves them in a stream format as "brainwave data."

[0509] Step 2: Sending data

[0510] The device sends the collected EEG data to a server via an internet connection. The input is the EEG data collected by the device. The output is the EEG data sent to the server. Specifically, the device sends the EEG data to the server using an HTTP POST request.

[0511] Step 3: Preprocessing the data

[0512] The server performs noise filtering on the received EEG data. Then, it applies a normalization algorithm to standardize the data. The input is the raw EEG data received by the server. The output is the noise-removed and standardized EEG data. Specifically, the server performs noise filtering using the Python library scipy.signal and standardizes the data using scikit-learn's StandardScaler.

[0513] Step 4: Data analysis and estimation

[0514] The server inputs the preprocessed data into a machine learning model. The model learns from past datasets and estimates the words and emotions corresponding to the EEG data. The input is the preprocessed EEG data. The output is the estimated words and emotions. Specifically, the server inputs the data into a machine learning model built using TensorFlow or PyTorch and obtains the estimated results.

[0515] Step 5: Send and view results

[0516] The server sends the estimated results to the device. The device receives the results and displays or outputs them as audio to the user through an interface device. The input is the estimated words and emotions (data sent from the server). The output is the results displayed or output as audio to the user. Specifically, the device uses the Google Text-to-Speech API or similar to play back the estimated words as audio or display them on the screen.

[0517] Step 6: Reverse transformation

[0518] When a user receives a specific word or emotion, the device sends the string of characters to the server. The server uses a generative AI model to generate corresponding brain wave data from this string of characters and sends it back to the device. The device then sends the generated brain wave data back to the sensor device, stimulating the user's brain. The input is the string of characters (the words or emotions entered by the user). The output is the corresponding brain wave data. Specifically, the server uses OpenAI's GPT-3 or GPT-4 to convert the string of characters into brain wave data, which is then sent back to the user's brain via the device.

[0519] (Application example 1)

[0520] 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."

[0521] In conventional factory production sites, workers need advanced programming knowledge and complex operations to communicate effectively with robots. Furthermore, transmitting work instructions takes time, placing a heavy burden on workers. Furthermore, there is a lack of interfaces for issuing instructions quickly and accurately. There is a need to solve these problems and achieve smoother, more efficient communication between humans and robots.

[0522] 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.

[0523] In this invention, the server includes a sensor means for detecting brain waves, a data preprocessing means for receiving the brain wave data and performing noise removal and normalization, an estimation means for estimating words and emotions using a machine learning model using the preprocessed data, an interface means for displaying or outputting the estimation results by voice, an inverse conversion means for generating corresponding brain wave data from the words and emotions, and an instruction generation means for generating work instructions based on the preprocessed data and transmitting the instructions to an external device. This enables workers to quickly and accurately issue work instructions to factory robots simply by thinking using the brain wave sensor.

[0524] The "sensor means for detecting brain waves" is a device that detects the user's brain activity and collects brain wave data.

[0525] The "data preprocessing means" is a device or method that performs processing to remove noise from collected electroencephalogram data and standardize the data.

[0526] The "estimation means" is a device or method that inputs preprocessed EEG data into a machine learning model and estimates words and emotions based on the output.

[0527] The "interface means" is a device or method for displaying or outputting the results estimated by the estimation means by voice.

[0528] The "inverse conversion means" is a device or method that generates corresponding electroencephalogram data from estimated words or emotions.

[0529] The "instruction generation means" is a device or method that generates work instructions based on the preprocessed data and the estimated results, and transmits the instructions to an external device.

[0530] An "external device" is an industrial robot or other mechanical device that receives data or instructions and performs a specific action.

[0531] This invention is a system that realizes communication between living organisms using brain waves. In particular, it aims to enable factory workers to wear smart glasses and transmit their thoughts to industrial robots as instructions. Specific embodiments of this system are described below.

[0532] 1. EEG data collection and preprocessing

[0533] The user (worker) wears an EEG sensor and engages in specific thinking, such as "pick out the next part and assemble it." This sensor detects the electrical signals emitted by the neurons in the user's brain in real time, i.e., EEG data. The device receives the data collected from this sensor. However, because EEG data is difficult to analyze in its raw form, a noise filter is first used to remove unnecessary noise components. Next, a normalization algorithm is applied to standardize the data, making it suitable for machine learning models.

[0534] 2. Estimating words and emotions

[0535] The preprocessed data is sent to a server. The server uses a generative AI model to analyze the data and estimate corresponding words and emotions. The generative AI model learns from a huge amount of past data sets and is able to make estimates with high accuracy. For example, if a user thinks, "Take out the next part and assemble it," data corresponding to that word is generated.

[0536] 3. Displaying Estimation Results and Generating Instructions

[0537] The estimated words and emotions are sent from the server to the device. The device displays the estimated results to the user through an interface. For example, if the estimated instruction is "Start assembly," the text "Start assembly" is displayed on the device screen. If the user confirms the instruction and there are no problems, the instruction is sent to an external device (industrial robot).

[0538] 4. Specific Examples

[0539] As a concrete example, imagine a worker wearing smart glasses thinking the instruction "pick out the next part and assemble it." The flow of this system is as follows:

[0540] 1. The worker thinks, "Pick out the next part and assemble it."

[0541] 2. The EEG sensor collects EEG data and transmits it to the device.

[0542] 3. The device preprocesses the data using noise filters and normalization algorithms.

[0543] 4. The preprocessed data is sent to the server and input into the generative AI model.

[0544] 5. The server estimates the words and emotions and sends the results to the device.

[0545] 6. The terminal displays "Assembly Start" and the user confirms.

[0546] 7. After confirmation, the terminal sends the instruction to the external device (industrial robot).

[0547] Prompt Sentence Examples

[0548] "Instruct the robot to pick up the next part and assemble it."

[0549] This invention enables factory workers to issue instructions to industrial robots quickly and accurately simply by thinking, without the need for complex programming knowledge or operation. Real-time communication also improves work efficiency and accuracy.

[0550] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0551] Step 1:

[0552] The user wears an EEG sensor and thinks, for example, "Pick out the next part and assemble it." The EEG sensor detects the electrical signals (brainwave data) from the user's brain's neurons in real time and sends that data to a device. The input is the EEG data detected in real time, and the output is the raw EEG data sent to the device.

[0553] Step 2:

[0554] The EEG data received by the device is filtered to remove unwanted noise components. A normalization algorithm is then applied to standardize the data. The input is the raw EEG data received from the sensor, and the output is the normalized data with noise removed. Specifically, the mean value of the data is subtracted and divided by the standard deviation.

[0555] Step 3:

[0556] The preprocessed data is sent to a server, which then inputs the received data into a generative AI model. The input is noise-removed and normalized EEG data, and the output is estimated words and emotions. The generative AI model uses a multi-layer neural network to learn from a huge dataset of past data.

[0557] Step 4:

[0558] The server uses the generative AI model to send estimated words and emotions to the device. The input is the words and emotions estimated by the generative AI model, and the output is the transmission of the estimated results to the device. Specifically, the output of the generative AI model is converted into JSON format and sent to the device via the network.

[0559] Step 5:

[0560] The device displays the inference results to the user through an interface. The input is the inference results sent from the server, and the output is text or audio displayed on the interface screen. For example, "Start assembly" may be displayed as text, and can also be confirmed aloud using speech synthesis technology.

[0561] Step 6:

[0562] The user checks the displayed inference results, and if there are no problems, sends instructions to an external device (industrial robot). The input is the inference results, and the output is specific instructions to the external device. Specifically, instructions are sent by pressing a button on the interface.

[0563] Step 7:

[0564] An external device (industrial robot) starts to operate based on the received instruction. The input is the specific instruction sent by the user, and the output is the actual action of the robot. For example, it executes the action "pick out the next part and assemble it."

[0565] 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.

[0566] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[0567] First, the user wears an EEG sensor. This sensor detects the electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. The collected data is raw and therefore contains a lot of noise. The device then transmits this data to a server.

[0568] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[0569] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[0570] In addition to the estimation means, the server is also equipped with an emotion engine, which further analyzes the user's brainwave data and classifies their emotional state into joy, sadness, anger, surprise, etc. The emotion engine uses a machine learning algorithm to estimate the emotional state in real time and also transmits this information to the device.

[0571] The device displays the received inference results and emotional state to the user through an interface. For example, if the inferred word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on its screen or play it in a "joy" tone using voice synthesis technology. This interface allows the user to communicate their thoughts and emotions to others in real time.

[0572] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[0573] Specific examples

[0574] Example 1: User thinks "Hello" and feels happy

[0575] 1. The user feels a sense of joy in their brain along with the specific word "Hello."

[0576] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[0577] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0578] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0579] 5. The server's emotion engine recognizes the emotion of joy.

[0580] 6. The server sends the estimation results and emotion information to the device, which then displays or speaks "Hello (joy)."

[0581] Example 2: When a user is told "hello" and feels surprised

[0582] 1. A situation occurs where a user is told "hello" and feels surprised.

[0583] 2. The terminal inputs the string data "Hello" and sends it to the server.

[0584] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[0585] 4. The server's emotion engine recognizes the emotion of surprise and encodes it into the brainwave data.

[0586] 5. The server sends the generated EEG data to the device.

[0587] 6. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain with a sense of surprise.

[0588] Through these concrete examples, this system realizes smooth communication between living organisms using brain waves and emotions.

[0589] The processing flow will be explained below.

[0590] Program processing steps

[0591] When the user thinks "Hello"

[0592] Step 1:

[0593] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[0594] Step 2:

[0595] When the user thinks about the specific word "Hello" and the emotion of joy, the EEG sensor detects the brain waves that correspond to this thought and emotion.

[0596] Step 3:

[0597] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[0598] Step 4:

[0599] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[0600] Step 5:

[0601] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[0602] Step 6:

[0603] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[0604] Step 7:

[0605] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[0606] Step 8:

[0607] The server receives the output from the machine learning model and interprets the predicted word as "Hello."

[0608] Step 9:

[0609] The server uses an emotion engine to analyze the user's emotions from the brainwave data and classify the emotion as "joy."

[0610] Step 10:

[0611] The server sends the estimation results and emotion information to the terminal. This is the step to communicate the results and emotions to the user.

[0612] Step 11:

[0613] The device sends the received estimation results and emotion information to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[0614] Step 12:

[0615] The user can confirm the estimation results and emotional information through the interface, thereby recognizing that their thoughts and emotions have been accurately interpreted and conveyed to others.

[0616] Inverse transformation (when a user is told "hello" and feels surprised)

[0617] Step 1:

[0618] The user is surprised when they hear "hello." The device receives this message in text format.

[0619] Step 2:

[0620] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[0621] Step 3:

[0622] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[0623] Step 4:

[0624] The server uses an emotion engine to recognize the emotion "surprise" and integrates this information with the brainwave data.

[0625] Step 5:

[0626] The server sends the generated EEG data to the terminal, which includes the word "hello" and emotional information about "surprise."

[0627] Step 6:

[0628] The device transmits the generated brainwave data back to the brainwave sensor, which stimulates the user's brain and reproduces words and emotions.

[0629] Step 7:

[0630] The user receives the transmitted EEG signal and the sensations of "hello" and surprise are recreated in the brain, resulting in the user experiencing the words and emotions.

[0631] Through the above processing steps, this system realizes smooth communication between living organisms using brain waves and emotions.

[0632] Example 2

[0633] 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."

[0634] Previous communication systems using EEGs had issues such as insufficient noise removal and normalization of EEG data, and low emotion recognition accuracy. Furthermore, the interfaces for accurately displaying and outputting estimated words and emotions in real time were also inadequate. Furthermore, even in communication using inverse conversion, the accuracy of the generated EEG data was an issue.

[0635] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or outputting the estimation results and emotional information by the estimation means as audio, and inverse conversion means for generating corresponding brain wave data from the words and emotions. This makes it possible to estimate words and emotions with high accuracy using normalized data with little noise, enable real-time display and audio output, and enable accurate communication through inverse conversion.

[0636] "Electroencephalograms" are weak electrical signals emitted by nerve cells in humans and animals.

[0637] "Sensor means" refers to a device or mechanism that detects brain waves in real time.

[0638] The "data preprocessing means" is a device or mechanism that performs noise removal and normalization on the received electroencephalogram data.

[0639] A "noise filter" is an algorithm or device for removing unwanted noise components from EEG data.

[0640] A "normalization algorithm" is a mathematical method for converting data into a uniform format.

[0641] The "estimation means" is a device or mechanism that estimates words and emotions using a machine learning model based on preprocessed data.

[0642] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications for new data.

[0643] An "emotion engine" is an algorithm or system that analyzes brainwave data and classifies emotional states such as joy, sadness, and anger.

[0644] The "interface means" is a device or mechanism for visually or audibly notifying the user of the estimation results and emotional information.

[0645] The "inverse conversion means" is a device or mechanism that generates corresponding electroencephalogram data from identified words or emotions.

[0646] A "generative AI model" is an artificial intelligence model that generates corresponding brainwave data or other outputs from input text data.

[0647] A "prompt" is an instruction or question that serves as input to a generative AI model.

[0648] MODE FOR CARRYING OUT THE INVENTION

[0649] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[0650] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by nerve cells, i.e., brain waves, in real time. A commercially available EEG capture device can be used as the sensor. At the same time, the device collects EEG data from the sensor. However, this data contains a lot of noise, making it unusable as is.

[0651] The device then transmits the collected EEG data to a server. This communication is encrypted using the SSL / TLS protocol to ensure security. The server can be hosted in a cloud environment, for example, to facilitate scalability and resource management. The server first applies a noise filter to the received EEG data to remove unwanted noise components. The noise filter can be a band-pass filter or a custom noise reduction algorithm.

[0652] Once the noise has been removed, the server then applies a normalization algorithm, for example, using Z-score normalization to standardize the data, ensuring that the data obtained from different users and across different measurement sessions is in a consistent format.

[0653] Based on the preprocessed data, the server inputs the data into a machine learning model, which can be a deep learning framework such as TensorFlow. This model learns from a large dataset of past data and predicts corresponding words and emotions based on the input data.

[0654] The estimation results are encrypted using the SSL / TLS protocol and sent to the device. The emotion engine on the server then further analyzes the EEG data to classify emotional states such as joy, sadness, anger, and surprise. The emotion engine also uses machine learning algorithms to estimate emotional states in real time.

[0655] The device displays the estimation results and emotion information to the user through an interface. Display can be done in the form of a web application using HTML5 and JavaScript. It is also possible to play the estimated emotion tone using speech synthesis technology. For example, if the estimated word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on the screen or play it in a "joy" tone.

[0656] The system also has a reverse conversion mechanism. For example, when communicating with other users (including pets), if a user wants to receive specific words or emotions, the device sends the string data to the server. The server uses a generative AI model to generate corresponding EEG data from the string and sends it back to the device. An example of a generative AI model is OpenAI's GPT-4. An example of a prompt sentence is, "Please generate the EEG data when the user says 'hello'."

[0657] The device then transmits the generated brainwave data back to the sensor, stimulating the user's brain and reproducing the words and emotions within the brain. This function allows users to communicate without speaking.

[0658] As described above, this system realizes highly accurate communication between living organisms using brain waves and emotional data, allowing users to smoothly convey their thoughts and emotions to others.

[0659] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0660] Program processing steps

[0661] Step 1:

[0662] The user wears an EEG sensor. The sensor detects electrical signals (brain waves) emitted by the brain's neurons in real time. The input is the electrical signals emitted by the neurons, and the output is the detected raw brain wave data. Specifically, the user wears the EEG sensor on their head, and the sensor captures the electrical signals.

[0663] Step 2:

[0664] The device collects raw EEG data from the sensor in real time and sends it to the server. The input is raw EEG data from the sensor, and the output is unprocessed EEG data sent to the server. Specifically, the device takes in data from the sensor, encrypts it using SSL / TLS, and sends it to the server.

[0665] Step 3:

[0666] The server applies a noise filter to the received raw EEG data. The input is raw EEG data, and the output is clean EEG data with noise removed. Specifically, the server uses a band-pass filter or a custom noise reduction algorithm to remove noise from the EEG data.

[0667] Step 4:

[0668] The server normalizes the clean EEG data using a normalization algorithm. The input is the denoised EEG data, and the output is the normalized EEG data. Specifically, the data is converted into a consistent format using Z-score normalization.

[0669] Step 5:

[0670] The server inputs the normalized data into a machine learning model. The input is normalized EEG data, and the output is estimated words and emotions. Specifically, the data is analyzed using a deep learning framework such as TensorFlow to estimate the words and emotions the user is thinking.

[0671] Step 6:

[0672] The server sends the estimated words and emotion information to the device. The input is the estimation result from the machine learning model, and the output is the encrypted estimation result and emotion information. Specifically, the estimation result is encrypted using SSL / TLS and sent to the device.

[0673] Step 7:

[0674] The device displays the estimation results and emotional information to the user through an interface. The input is the estimation results and emotional information received from the server, and the output is the information displayed on the interface or a voice generated by speech synthesis. Specific operations include displaying the results in a web application format using HTML5 and JavaScript, and playing back a voice in a specific tone using speech synthesis technology.

[0675] Step 8:

[0676] When a user wants to receive a desired word or emotion, the device sends the string data to the server. The input is the string data entered by the user, and the output is the string data to be sent to the server. Specifically, the device takes the entered string data, encrypts it using SSL / TLS, and sends it to the server.

[0677] Step 9:

[0678] The server uses a generative AI model to generate corresponding brain wave data from input string data. The input is string data received from the terminal, and the output is generated brain wave data. In concrete terms, a prompt sentence is input into the generative AI model (for example, a general-purpose artificial intelligence model), and brain wave data is generated based on that. An example of a prompt sentence is in the format "Please generate brain wave data when the user says 'hello'."

[0679] Step 10:

[0680] The server sends the generated EEG data to the terminal. The input is the generated EEG data, and the output is the EEG data to be sent to the terminal. Specifically, the EEG data is encrypted using SSL / TLS and sent to the terminal.

[0681] Step 11:

[0682] The device then transmits the received brainwave data back to the sensor, which then stimulates the user's brain. The input is the received brainwave data, and the output is the words and emotions that are reproduced in the user's brain. Specifically, the brainwave data is transmitted back to the user's brain via the sensor, which then stimulates the user to reproduce specific words and emotions.

[0683] This processing step allows the system to convey the user's thoughts and feelings to others, and also enables communication through reverse conversion.

[0684] (Application example 2)

[0685] 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."

[0686] Currently, communication between workers and robots in factories is often carried out via physical input devices or programming, making it difficult to give intuitive and quick instructions. Furthermore, it is not possible to understand the emotions of workers and respond appropriately, which raises concerns about reduced work efficiency and stress. Furthermore, there are limited means of receiving feedback from robots in real time, making it difficult to respond quickly.

[0687] The identification processing 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 sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or audio output of the estimation results by the estimation means, inverse conversion means for generating corresponding brain wave data from the words and emotions, and means for sending instructions to a factory robot via the interface means and feeding back the robot's status and messages to the user's brain. This enables workers to intuitively issue instructions to factory robots using brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[0688] The "sensor means for detecting brain waves" is a device that detects and collects the user's brain wave data in real time.

[0689] The "data preprocessing means" refers to a device or software that removes noise and normalizes the received EEG data, converting it into a format suitable for a machine learning model.

[0690] The "estimation means" is a system or algorithm that inputs preprocessed EEG data into a machine learning model to estimate words and emotions.

[0691] The "interface means" refers to a device or software for displaying or outputting the estimation result by the estimation means to the user.

[0692] The "inverse conversion means" is a device or system that generates corresponding electroencephalogram data from words and emotions and feeds this back to the user's brain.

[0693] A "factory robot" is an automated mechanical device designed to perform manufacturing or assembly tasks.

[0694] A "server" is a central processing unit or system for processing, estimating, and feeding back EEG data.

[0695] "Noise filter" is a filtering technique for removing unnecessary noise components from EEG data.

[0696] A "normalization algorithm" is an algorithm that standardizes data and converts it into a format that can be efficiently processed by machine learning models.

[0697] A "machine learning model" is an algorithmic model that learns from past data and makes inferences and predictions based on new data.

[0698] The present invention is a system for efficiently communicating between workers and robots in a factory. Specific embodiments of the system are described below.

[0699] System configuration

[0700] 1. Sensor means for detecting brain waves:

[0701] The user wears an EEG sensor (e.g., an EEG headset) that detects the user's EEG data in real time and transmits it to a device.

[0702] 2. Data preprocessing methods:

[0703] After receiving the EEG data, the device uses a noise filter (e.g., Butterworth filter) to remove unnecessary noise, then standardizes the data using a normalization algorithm and performs preprocessing.

[0704] 3. Estimation method:

[0705] The preprocessed data is sent to a server, which uses a machine learning model (e.g., a model using TensorFlow or Keras) to analyze the data, infer words and emotions, and then uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) to classify the emotional state.

[0706] 4. Interface means:

[0707] The analysis results are sent from the server to the terminal and displayed or output to the user via the terminal's display or audio output device. At the same time, the analysis results are sent as instructions to the factory robot.

[0708] 5. Reverse transformation method:

[0709] If necessary, the server uses a generative AI model to generate corresponding brainwave data from the string data and transmits it back to the sensor via the device, allowing specific words or emotions to be fed back to the user's brain.

[0710] 6. Feedback methods:

[0711] Factory robots send their work status and messages in real time to a server, which then analyzes this information and sends it directly to the user's brain as necessary feedback.

[0712] Hardware and Software

[0713] Brainwave sensor: Brainwave detection headset (e.g., Emotiv EPOC+)

[0714] Device: Smartphone or tablet (Android or iOS device)

[0715] Server: Cloud computing service (e.g., Amazon Web Services, Google Cloud)

[0716] Machine learning models: TensorFlow, Keras

[0717] Emotion engine: Azure Cognitive Services, IBM Watson

[0718] Specific examples

[0719] Example 1: Packing instructions

[0720] 1. If the user thinks "Robot, start packing" and feels satisfied:

[0721] The EEG sensor collects EEG data and transmits it to the terminal.

[0722] Data preprocessing is performed on the terminal and then sent to the server.

[0723] Analysis and estimation are performed on the server, and instructions are sent to the robot.

[0724] The robot starts working and sends the work status to the server.

[0725] The server feeds the analysis results back to the device, stimulating the user's brain.

[0726] Prompt Sentence Examples

[0727] "When the user thinks 'Robot, start packing,' and feels satisfied, process the EEG data and send the corresponding instruction to the robot. Please provide a detailed description of the data you collected, normalized, and extrapolated."

[0728] This allows users to intuitively give instructions to factory robots using their brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

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

[0730] Step 1:

[0731] The user wears an EEG sensor, which detects the user's brainwaves in real time and transmits the data to the device via Bluetooth. The input is the user's brainwaves, and the output is raw EEG data.

[0732] Step 2:

[0733] The device performs noise filtering on the received EEG data. It uses a Butterworth filter to remove unwanted noise. The input is raw EEG data, and the output is pre-processed EEG data with noise removed.

[0734] Step 3:

[0735] The device normalizes the noise-filtered EEG data. It uses a normalization algorithm to standardize the data and convert it into a format suitable for the machine learning model. The input is the noise-removed EEG data, and the output is the normalized EEG data.

[0736] Step 4:

[0737] The device sends the normalized EEG data to the server. The data is securely transferred using the HTTPS protocol. The input is the normalized EEG data, and the output is the data sent to the server.

[0738] Step 5:

[0739] The server inputs the received data into a machine learning model. Using TensorFlow or Keras, the data is fed into a pre-trained model to estimate words and emotions. The input is normalized EEG data, and the output is estimated words and emotions.

[0740] Step 6:

[0741] The server uses an emotion engine to classify detailed emotional states. It analyzes and classifies emotions using Azure Cognitive Services and IBM Watson's emotion detection API. The input is the emotion estimated by the machine learning model, and the output is detailed classified emotional information.

[0742] Step 7:

[0743] The server sends the estimated words and emotion information to the terminal. At the same time, it sends the analysis results as instructions to the factory robot, which then begins the specified action. The input is the estimated words and emotion, and the output is the instructions sent to the terminal and the robot.

[0744] Step 8:

[0745] The device displays or outputs the received instructions and emotional information. The user can check the text on the display or hear the information through the audio output. The input is the estimated words and emotional information, and the output is visual or auditory feedback to the user.

[0746] Step 9:

[0747] Factory robots operate according to instructions and send work status and status information to a server in real time. The input is the instructions sent to the robot, and the output is the work status and status information.

[0748] Step 10:

[0749] The server analyzes the feedback information from the robot and sends it as stimuli to the user's brain as needed. It uses a generative AI model to generate corresponding brainwave data from the string data, which is then sent back to the brainwave sensor via the terminal. The input is the feedback information from the robot, and the output is the feedback sent to the user's brain.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] [Third embodiment]

[0754] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0755] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0756] 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).

[0757] 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.

[0758] 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.

[0759] 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).

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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."

[0766] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[0767] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. Because the collected data is difficult to analyze in its raw form, the device sends this data to a server.

[0768] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[0769] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[0770] The device then displays the received prediction results to the user through an interface. For example, if the predicted word is "Hello," the device will display "Hello" on its screen or play it aloud using speech synthesis technology. This interface allows the user to communicate their thoughts to others in real time.

[0771] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[0772] Specific examples

[0773] Example 1: When the user thinks "Hello"

[0774] 1. The user imagines a specific word in their mind, such as "Hello."

[0775] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[0776] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0777] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0778] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[0779] Example 2: When the user says "Hello"

[0780] 1. When the user says "hello", enter the string "hello" into the terminal.

[0781] 2. The terminal sends the string data to the server.

[0782] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[0783] 4. The server sends the generated EEG data to the device.

[0784] 5. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain.

[0785] 6. The user receives the same feeling as "hello."

[0786] Through these processes, this system will enable smooth communication with people and animals who have lost the ability to speak. In the future, it may also be possible to translate between a wide variety of living creatures, opening up new forms of communication.

[0787] The processing flow will be explained below.

[0788] Step 1:

[0789] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[0790] Step 2:

[0791] The user thinks about a specific word or emotion, such as "Hello," and the EEG sensor detects the brain waves that correspond to this thought.

[0792] Step 3:

[0793] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[0794] Step 4:

[0795] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[0796] Step 5:

[0797] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[0798] Step 6:

[0799] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[0800] Step 7:

[0801] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[0802] Step 8:

[0803] The server receives the output from the machine learning model and interprets the estimated words and sentiment. In this example, the model estimates "Hello."

[0804] Step 9:

[0805] The server sends the estimation results to the terminal, which is the step to notify the results to the user.

[0806] Step 10:

[0807] The device sends the received inference result to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[0808] Step 11:

[0809] The user can confirm the inference results through the interface, thereby recognizing that their thoughts have been accurately interpreted and communicated to others.

[0810] Inverse transformation (e.g., when a user is told "hello")

[0811] Step 1:

[0812] A situation occurs where a user says "hello." The device receives this in text form.

[0813] Step 2:

[0814] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[0815] Step 3:

[0816] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[0817] Step 4:

[0818] The server sends the generated brainwave data to the device, which is then ready to be transmitted to the user's brain.

[0819] Step 5:

[0820] The device transmits the generated brainwave data back to the brainwave sensor, which then stimulates the user's brain.

[0821] Step 6:

[0822] The user receives the transmitted EEG signal and the same sensation as saying "hello" is reproduced in the brain, giving the user the sensation of hearing the word.

[0823] Through these processing steps, this system realizes smooth communication between living organisms using brain waves.

[0824] Example 1

[0825] 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."

[0826] Previous communication systems using EEGs lacked accuracy and real-time capabilities, and in particular, the lack of noise removal and data standardization made it difficult to analyze EEG data. Furthermore, there was a lack of inverse conversion methods to convert corresponding words and emotions into EEG data. As a result, it was difficult to achieve smooth communication with people or animals who had lost the ability to speak.

[0827] 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.

[0828] In this invention, the server includes a sensor device for detecting brain waves, a data preprocessing device that receives the brain wave data and performs noise reduction and normalization, an estimation device that uses the preprocessed data to estimate words and emotions using a machine learning model, an interface device that displays or outputs the estimation results by the estimation device as audio, an inverse conversion device that generates corresponding brain wave data from the words and emotions, a terminal that collects brain wave data in real time, a communication device that transmits the collected data to the server via the Internet, and a transmission device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain. This system enables real-time analysis of brain wave data and accurate estimation of corresponding words and emotions. Furthermore, by using the inverse conversion means to convert words and emotions into brain wave data and reproducing them in the user's brain, communication without speaking is possible.

[0829] "Electroencephalograms" are electrical signals emitted by nerve cells in the brain.

[0830] A "sensor device" is a device for detecting brain waves and is used to collect electrical signals from the brain in real time.

[0831] The "data preprocessing device" is a device that performs noise removal and standardization on the electroencephalogram data received from the sensor device.

[0832] A "noise filter" is an algorithm for removing unnecessary noise components from EEG data.

[0833] A "normalization algorithm" is an algorithm for converting data into a standard format.

[0834] An "estimation device" is a device that uses preprocessed data to estimate words and emotions using a machine learning model.

[0835] A "machine learning model" is a mathematical model that learns from past datasets and infers words and emotions from new data.

[0836] An "interface device" is a device for displaying or outputting the estimation results of an estimation device as audio.

[0837] An "inverse conversion device" is a device for generating corresponding electroencephalogram data from words and emotions.

[0838] The "terminal" is a device that collects brain wave data from a sensor device and transmits it to a server.

[0839] The "communication device" is a device that allows the terminal to transmit brain wave data to a server via the Internet.

[0840] The "transmitting device" is a device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain.

[0841] MODE FOR CARRYING OUT THE INVENTION

[0842] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[0843] EEG data collection

[0844] First, the user wears an EEG sensor device, which detects electrical signals emitted by the brain's nerve cells in real time. Specifically, a sensor device such as Neurosky's MindWave is used.

[0845] Sending data

[0846] The device then collects the EEG data from the sensor device and transmits it to a server via the internet. The device can be a smartphone, computer, or other device.

[0847] Data Preprocessing

[0848] The server processes the received EEG data using a data preprocessing device. Specifically, it uses a noise filter to remove unwanted noise components and applies a normalization algorithm to standardize the data. For this purpose, the Python libraries scipy.signal and scikit-learn are used.

[0849] Data analysis and estimation

[0850] Based on the preprocessed data, the server inputs the data into a machine learning model (e.g., TensorFlow or PyTorch) to estimate words and emotions. The machine learning model is trained from a large set of historical data and makes accurate estimates based on the data provided.

[0851] Sending and displaying results

[0852] The estimation results are sent from the server to the device, which then displays or outputs the results to the user. For example, it can be played back as audio using the Google Text-to-Speech API.

[0853] Inverse transformation process

[0854] The system also includes a reverse conversion mechanism. For example, if the user receives different words or emotions, the device sends the string data to the server. The server uses a generative AI model (e.g., OpenAI's GPT-3 or GPT-4) to generate corresponding EEG data from the string, which is then sent to the device. The device then sends the generated EEG data back to the sensor device, which stimulates the user's brain.

[0855] Specific examples

[0856] Example 1: When the user thinks "Hello"

[0857] 1. The user imagines a specific word in their mind, such as "Hello."

[0858] 2. The terminal collects EEG data from the sensor device in real time and transmits it to the server.

[0859] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0860] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0861] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[0862] Example 2: When the user says "Hello"

[0863] 1. When the user says "hello", enter the string "hello" into the terminal.

[0864] 2. The terminal sends the string data to the server.

[0865] 3. The server uses the generative AI model to generate corresponding EEG data from the string.

[0866] 4. The server sends the generated EEG data to the device.

[0867] 5. The device transmits the generated brain wave data back to the sensor device, stimulating the user's brain.

[0868] 6. The user receives the same feeling as "hello."

[0869] Example prompt: "Implement a method to communicate by converting the user's thoughts into EEG data. The hardware used will be Neurosky's MindWave, and the machine learning model will be built using PyTorch."

[0870] This system will enable smooth communication between people and animals who have lost the ability to speak, and will also enable translation between a wide variety of living creatures, opening up the possibility of new forms of communication.

[0871] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0872] Step 1: Collect EEG data

[0873] The user wears an EEG sensor device. This sensor device detects electrical signals emitted by the brain's nerve cells in real time. The terminal collects EEG data from the sensor device via Bluetooth or a wired connection. The input is raw data from the sensor device. The output is EEG data collected by the terminal. Specifically, the terminal receives the signals sent from the sensor device and saves them in a stream format as "brainwave data."

[0874] Step 2: Sending data

[0875] The device sends the collected EEG data to a server via an internet connection. The input is the EEG data collected by the device. The output is the EEG data sent to the server. Specifically, the device sends the EEG data to the server using an HTTP POST request.

[0876] Step 3: Preprocessing the data

[0877] The server performs noise filtering on the received EEG data. Then, it applies a normalization algorithm to standardize the data. The input is the raw EEG data received by the server. The output is the noise-removed and standardized EEG data. Specifically, the server performs noise filtering using the Python library scipy.signal and standardizes the data using scikit-learn's StandardScaler.

[0878] Step 4: Data analysis and estimation

[0879] The server inputs the preprocessed data into a machine learning model. The model learns from past datasets and estimates the words and emotions corresponding to the EEG data. The input is the preprocessed EEG data. The output is the estimated words and emotions. Specifically, the server inputs the data into a machine learning model built using TensorFlow or PyTorch and obtains the estimated results.

[0880] Step 5: Send and view results

[0881] The server sends the estimated results to the device. The device receives the results and displays or outputs them as audio to the user through an interface device. The input is the estimated words and emotions (data sent from the server). The output is the results displayed or output as audio to the user. Specifically, the device uses the Google Text-to-Speech API or similar to play back the estimated words as audio or display them on the screen.

[0882] Step 6: Reverse transformation

[0883] When a user receives a specific word or emotion, the device sends the string of characters to the server. The server uses a generative AI model to generate corresponding brain wave data from this string of characters and sends it back to the device. The device then sends the generated brain wave data back to the sensor device, stimulating the user's brain. The input is the string of characters (the words or emotions entered by the user). The output is the corresponding brain wave data. Specifically, the server uses OpenAI's GPT-3 or GPT-4 to convert the string of characters into brain wave data, which is then sent back to the user's brain via the device.

[0884] (Application example 1)

[0885] 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."

[0886] In conventional factory production sites, workers need advanced programming knowledge and complex operations to communicate effectively with robots. Furthermore, transmitting work instructions takes time, placing a heavy burden on workers. Furthermore, there is a lack of interfaces for issuing instructions quickly and accurately. There is a need to solve these problems and achieve smoother, more efficient communication between humans and robots.

[0887] 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.

[0888] In this invention, the server includes a sensor means for detecting brain waves, a data preprocessing means for receiving the brain wave data and performing noise removal and normalization, an estimation means for estimating words and emotions using a machine learning model using the preprocessed data, an interface means for displaying or outputting the estimation results by voice, an inverse conversion means for generating corresponding brain wave data from the words and emotions, and an instruction generation means for generating work instructions based on the preprocessed data and transmitting the instructions to an external device. This enables workers to quickly and accurately issue work instructions to factory robots simply by thinking using the brain wave sensor.

[0889] The "sensor means for detecting brain waves" is a device that detects the user's brain activity and collects brain wave data.

[0890] The "data preprocessing means" is a device or method that performs processing to remove noise from collected electroencephalogram data and standardize the data.

[0891] The "estimation means" is a device or method that inputs preprocessed EEG data into a machine learning model and estimates words and emotions based on the output.

[0892] The "interface means" is a device or method for displaying or outputting the results estimated by the estimation means by voice.

[0893] The "inverse conversion means" is a device or method that generates corresponding electroencephalogram data from estimated words or emotions.

[0894] The "instruction generation means" is a device or method that generates work instructions based on the preprocessed data and the estimated results, and transmits the instructions to an external device.

[0895] An "external device" is an industrial robot or other mechanical device that receives data or instructions and performs a specific action.

[0896] This invention is a system that realizes communication between living organisms using brain waves. In particular, it aims to enable factory workers to wear smart glasses and transmit their thoughts to industrial robots as instructions. Specific embodiments of this system are described below.

[0897] 1. EEG data collection and preprocessing

[0898] The user (worker) wears an EEG sensor and engages in specific thinking, such as "pick out the next part and assemble it." This sensor detects the electrical signals emitted by the neurons in the user's brain in real time, i.e., EEG data. The device receives the data collected from this sensor. However, because EEG data is difficult to analyze in its raw form, a noise filter is first used to remove unnecessary noise components. Next, a normalization algorithm is applied to standardize the data, making it suitable for machine learning models.

[0899] 2. Estimating words and emotions

[0900] The preprocessed data is sent to a server. The server uses a generative AI model to analyze the data and estimate corresponding words and emotions. The generative AI model learns from a huge amount of past data sets and is able to make estimates with high accuracy. For example, if a user thinks, "Take out the next part and assemble it," data corresponding to that word is generated.

[0901] 3. Displaying Estimation Results and Generating Instructions

[0902] The estimated words and emotions are sent from the server to the device. The device displays the estimated results to the user through an interface. For example, if the estimated instruction is "Start assembly," the text "Start assembly" is displayed on the device screen. If the user confirms the instruction and there are no problems, the instruction is sent to an external device (industrial robot).

[0903] 4. Specific Examples

[0904] As a concrete example, imagine a worker wearing smart glasses thinking the instruction "pick out the next part and assemble it." The flow of this system is as follows:

[0905] 1. The worker thinks, "Pick out the next part and assemble it."

[0906] 2. The EEG sensor collects EEG data and transmits it to the device.

[0907] 3. The device preprocesses the data using noise filters and normalization algorithms.

[0908] 4. The preprocessed data is sent to the server and input into the generative AI model.

[0909] 5. The server estimates the words and emotions and sends the results to the device.

[0910] 6. The terminal displays "Assembly Start" and the user confirms.

[0911] 7. After confirmation, the terminal sends the instruction to the external device (industrial robot).

[0912] Prompt Sentence Examples

[0913] "Instruct the robot to pick up the next part and assemble it."

[0914] This invention enables factory workers to issue instructions to industrial robots quickly and accurately simply by thinking, without the need for complex programming knowledge or operation. Real-time communication also improves work efficiency and accuracy.

[0915] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0916] Step 1:

[0917] The user wears an EEG sensor and thinks, for example, "Pick out the next part and assemble it." The EEG sensor detects the electrical signals (brainwave data) from the user's brain's neurons in real time and sends that data to a device. The input is the EEG data detected in real time, and the output is the raw EEG data sent to the device.

[0918] Step 2:

[0919] The EEG data received by the device is filtered to remove unwanted noise components. A normalization algorithm is then applied to standardize the data. The input is the raw EEG data received from the sensor, and the output is the normalized data with noise removed. Specifically, the mean value of the data is subtracted and divided by the standard deviation.

[0920] Step 3:

[0921] The preprocessed data is sent to a server, which then inputs the received data into a generative AI model. The input is noise-removed and normalized EEG data, and the output is estimated words and emotions. The generative AI model uses a multi-layer neural network to learn from a huge dataset of past data.

[0922] Step 4:

[0923] The server uses the generative AI model to send estimated words and emotions to the device. The input is the words and emotions estimated by the generative AI model, and the output is the transmission of the estimated results to the device. Specifically, the output of the generative AI model is converted into JSON format and sent to the device via the network.

[0924] Step 5:

[0925] The device displays the inference results to the user through an interface. The input is the inference results sent from the server, and the output is text or audio displayed on the interface screen. For example, "Start assembly" may be displayed as text, and can also be confirmed aloud using speech synthesis technology.

[0926] Step 6:

[0927] The user checks the displayed inference results, and if there are no problems, sends instructions to an external device (industrial robot). The input is the inference results, and the output is specific instructions to the external device. Specifically, instructions are sent by pressing a button on the interface.

[0928] Step 7:

[0929] An external device (industrial robot) starts to operate based on the received instruction. The input is the specific instruction sent by the user, and the output is the actual action of the robot. For example, it executes the action "pick out the next part and assemble it."

[0930] 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.

[0931] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[0932] First, the user wears an EEG sensor. This sensor detects the electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. The collected data is raw and therefore contains a lot of noise. The device then transmits this data to a server.

[0933] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[0934] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[0935] In addition to the estimation means, the server is also equipped with an emotion engine, which further analyzes the user's brainwave data and classifies their emotional state into joy, sadness, anger, surprise, etc. The emotion engine uses a machine learning algorithm to estimate the emotional state in real time and also transmits this information to the device.

[0936] The device displays the received inference results and emotional state to the user through an interface. For example, if the inferred word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on its screen or play it in a "joy" tone using voice synthesis technology. This interface allows the user to communicate their thoughts and emotions to others in real time.

[0937] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[0938] Specific examples

[0939] Example 1: User thinks "Hello" and feels happy

[0940] 1. The user feels a sense of joy in their brain along with the specific word "Hello."

[0941] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[0942] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[0943] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[0944] 5. The server's emotion engine recognizes the emotion of joy.

[0945] 6. The server sends the estimation results and emotion information to the device, which then displays or speaks "Hello (joy)."

[0946] Example 2: When a user is told "hello" and feels surprised

[0947] 1. A situation occurs where a user is told "hello" and feels surprised.

[0948] 2. The terminal inputs the string data "Hello" and sends it to the server.

[0949] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[0950] 4. The server's emotion engine recognizes the emotion of surprise and encodes it into the brainwave data.

[0951] 5. The server sends the generated EEG data to the device.

[0952] 6. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain with a sense of surprise.

[0953] Through these concrete examples, this system realizes smooth communication between living organisms using brain waves and emotions.

[0954] The processing flow will be explained below.

[0955] Program processing steps

[0956] When the user thinks "Hello"

[0957] Step 1:

[0958] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[0959] Step 2:

[0960] When the user thinks about the specific word "Hello" and the emotion of joy, the EEG sensor detects the brain waves that correspond to this thought and emotion.

[0961] Step 3:

[0962] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[0963] Step 4:

[0964] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[0965] Step 5:

[0966] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[0967] Step 6:

[0968] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[0969] Step 7:

[0970] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[0971] Step 8:

[0972] The server receives the output from the machine learning model and interprets the predicted word as "Hello."

[0973] Step 9:

[0974] The server uses an emotion engine to analyze the user's emotions from the brainwave data and classify the emotion as "joy."

[0975] Step 10:

[0976] The server sends the estimation results and emotion information to the terminal. This is the step to communicate the results and emotions to the user.

[0977] Step 11:

[0978] The device sends the received estimation results and emotion information to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[0979] Step 12:

[0980] The user can confirm the estimation results and emotional information through the interface, thereby recognizing that their thoughts and emotions have been accurately interpreted and conveyed to others.

[0981] Inverse transformation (when a user is told "hello" and feels surprised)

[0982] Step 1:

[0983] The user is surprised when they hear "hello." The device receives this message in text format.

[0984] Step 2:

[0985] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[0986] Step 3:

[0987] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[0988] Step 4:

[0989] The server uses an emotion engine to recognize the emotion "surprise" and integrates this information with the brainwave data.

[0990] Step 5:

[0991] The server sends the generated EEG data to the terminal, which includes the word "hello" and emotional information about "surprise."

[0992] Step 6:

[0993] The device transmits the generated brainwave data back to the brainwave sensor, which stimulates the user's brain and reproduces words and emotions.

[0994] Step 7:

[0995] The user receives the transmitted EEG signal and the sensations of "hello" and surprise are recreated in the brain, resulting in the user experiencing the words and emotions.

[0996] Through the above processing steps, this system realizes smooth communication between living organisms using brain waves and emotions.

[0997] Example 2

[0998] 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."

[0999] Previous communication systems using EEGs had issues such as insufficient noise removal and normalization of EEG data, and low emotion recognition accuracy. Furthermore, the interfaces for accurately displaying and outputting estimated words and emotions in real time were also inadequate. Furthermore, even in communication using inverse conversion, the accuracy of the generated EEG data was an issue.

[1000] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or outputting the estimation results and emotional information by the estimation means as audio, and inverse conversion means for generating corresponding brain wave data from the words and emotions. This makes it possible to estimate words and emotions with high accuracy using normalized data with little noise, enable real-time display and audio output, and enable accurate communication through inverse conversion.

[1001] "Electroencephalograms" are weak electrical signals emitted by nerve cells in humans and animals.

[1002] "Sensor means" refers to a device or mechanism that detects brain waves in real time.

[1003] The "data preprocessing means" is a device or mechanism that performs noise removal and normalization on the received electroencephalogram data.

[1004] A "noise filter" is an algorithm or device for removing unwanted noise components from EEG data.

[1005] A "normalization algorithm" is a mathematical method for converting data into a uniform format.

[1006] The "estimation means" is a device or mechanism that estimates words and emotions using a machine learning model based on preprocessed data.

[1007] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications for new data.

[1008] An "emotion engine" is an algorithm or system that analyzes brainwave data and classifies emotional states such as joy, sadness, and anger.

[1009] The "interface means" is a device or mechanism for visually or audibly notifying the user of the estimation results and emotional information.

[1010] The "inverse conversion means" is a device or mechanism that generates corresponding electroencephalogram data from identified words or emotions.

[1011] A "generative AI model" is an artificial intelligence model that generates corresponding brainwave data or other outputs from input text data.

[1012] A "prompt" is an instruction or question that serves as input to a generative AI model.

[1013] MODE FOR CARRYING OUT THE INVENTION

[1014] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[1015] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by nerve cells, i.e., brain waves, in real time. A commercially available EEG capture device can be used as the sensor. At the same time, the device collects EEG data from the sensor. However, this data contains a lot of noise, making it unusable as is.

[1016] The device then transmits the collected EEG data to a server. This communication is encrypted using the SSL / TLS protocol to ensure security. The server can be hosted in a cloud environment, for example, to facilitate scalability and resource management. The server first applies a noise filter to the received EEG data to remove unwanted noise components. The noise filter can be a band-pass filter or a custom noise reduction algorithm.

[1017] Once the noise has been removed, the server then applies a normalization algorithm, for example, using Z-score normalization to standardize the data, ensuring that the data obtained from different users and across different measurement sessions is in a consistent format.

[1018] Based on the preprocessed data, the server inputs the data into a machine learning model, which can be a deep learning framework such as TensorFlow. This model learns from a large dataset of past data and predicts corresponding words and emotions based on the input data.

[1019] The estimation results are encrypted using the SSL / TLS protocol and sent to the device. The emotion engine on the server then further analyzes the EEG data to classify emotional states such as joy, sadness, anger, and surprise. The emotion engine also uses machine learning algorithms to estimate emotional states in real time.

[1020] The device displays the estimation results and emotion information to the user through an interface. Display can be done in the form of a web application using HTML5 and JavaScript. It is also possible to play the estimated emotion tone using speech synthesis technology. For example, if the estimated word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on the screen or play it in a "joy" tone.

[1021] The system also has a reverse conversion mechanism. For example, when communicating with other users (including pets), if a user wants to receive specific words or emotions, the device sends the string data to the server. The server uses a generative AI model to generate corresponding EEG data from the string and sends it back to the device. An example of a generative AI model is OpenAI's GPT-4. An example of a prompt sentence is, "Please generate the EEG data when the user says 'hello'."

[1022] The device then transmits the generated brainwave data back to the sensor, stimulating the user's brain and reproducing the words and emotions within the brain. This function allows users to communicate without speaking.

[1023] As described above, this system realizes highly accurate communication between living organisms using brain waves and emotional data, allowing users to smoothly convey their thoughts and emotions to others.

[1024] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1025] Program processing steps

[1026] Step 1:

[1027] The user wears an EEG sensor. The sensor detects electrical signals (brain waves) emitted by the brain's neurons in real time. The input is the electrical signals emitted by the neurons, and the output is the detected raw brain wave data. Specifically, the user wears the EEG sensor on their head, and the sensor captures the electrical signals.

[1028] Step 2:

[1029] The device collects raw EEG data from the sensor in real time and sends it to the server. The input is raw EEG data from the sensor, and the output is unprocessed EEG data sent to the server. Specifically, the device takes in data from the sensor, encrypts it using SSL / TLS, and sends it to the server.

[1030] Step 3:

[1031] The server applies a noise filter to the received raw EEG data. The input is raw EEG data, and the output is clean EEG data with noise removed. Specifically, the server uses a band-pass filter or a custom noise reduction algorithm to remove noise from the EEG data.

[1032] Step 4:

[1033] The server normalizes the clean EEG data using a normalization algorithm. The input is the denoised EEG data, and the output is the normalized EEG data. Specifically, the data is converted into a consistent format using Z-score normalization.

[1034] Step 5:

[1035] The server inputs the normalized data into a machine learning model. The input is normalized EEG data, and the output is estimated words and emotions. Specifically, the data is analyzed using a deep learning framework such as TensorFlow to estimate the words and emotions the user is thinking.

[1036] Step 6:

[1037] The server sends the estimated words and emotion information to the device. The input is the estimation result from the machine learning model, and the output is the encrypted estimation result and emotion information. Specifically, the estimation result is encrypted using SSL / TLS and sent to the device.

[1038] Step 7:

[1039] The device displays the estimation results and emotional information to the user through an interface. The input is the estimation results and emotional information received from the server, and the output is the information displayed on the interface or a voice generated by speech synthesis. Specific operations include displaying the results in a web application format using HTML5 and JavaScript, and playing back a voice in a specific tone using speech synthesis technology.

[1040] Step 8:

[1041] When a user wants to receive a desired word or emotion, the device sends the string data to the server. The input is the string data entered by the user, and the output is the string data to be sent to the server. Specifically, the device takes the entered string data, encrypts it using SSL / TLS, and sends it to the server.

[1042] Step 9:

[1043] The server uses a generative AI model to generate corresponding brain wave data from input string data. The input is string data received from the terminal, and the output is generated brain wave data. In concrete terms, a prompt sentence is input into the generative AI model (for example, a general-purpose artificial intelligence model), and brain wave data is generated based on that. An example of a prompt sentence is in the format "Please generate brain wave data when the user says 'hello'."

[1044] Step 10:

[1045] The server sends the generated EEG data to the terminal. The input is the generated EEG data, and the output is the EEG data to be sent to the terminal. Specifically, the EEG data is encrypted using SSL / TLS and sent to the terminal.

[1046] Step 11:

[1047] The device then transmits the received brainwave data back to the sensor, which then stimulates the user's brain. The input is the received brainwave data, and the output is the words and emotions that are reproduced in the user's brain. Specifically, the brainwave data is transmitted back to the user's brain via the sensor, which then stimulates the user to reproduce specific words and emotions.

[1048] This processing step allows the system to convey the user's thoughts and feelings to others, and also enables communication through reverse conversion.

[1049] (Application example 2)

[1050] 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."

[1051] Currently, communication between workers and robots in factories is often carried out via physical input devices or programming, making it difficult to give intuitive and quick instructions. Furthermore, it is not possible to understand the emotions of workers and respond appropriately, which raises concerns about reduced work efficiency and stress. Furthermore, there are limited means of receiving feedback from robots in real time, making it difficult to respond quickly.

[1052] The identification processing 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 sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or audio output of the estimation results by the estimation means, inverse conversion means for generating corresponding brain wave data from the words and emotions, and means for sending instructions to a factory robot via the interface means and feeding back the robot's status and messages to the user's brain. This enables workers to intuitively issue instructions to factory robots using brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[1053] The "sensor means for detecting brain waves" is a device that detects and collects the user's brain wave data in real time.

[1054] The "data preprocessing means" refers to a device or software that removes noise and normalizes the received EEG data, converting it into a format suitable for a machine learning model.

[1055] The "estimation means" is a system or algorithm that inputs preprocessed EEG data into a machine learning model to estimate words and emotions.

[1056] The "interface means" refers to a device or software for displaying or outputting the estimation result by the estimation means to the user.

[1057] The "inverse conversion means" is a device or system that generates corresponding electroencephalogram data from words and emotions and feeds this back to the user's brain.

[1058] A "factory robot" is an automated mechanical device designed to perform manufacturing or assembly tasks.

[1059] A "server" is a central processing unit or system for processing, estimating, and feeding back EEG data.

[1060] "Noise filter" is a filtering technique for removing unnecessary noise components from EEG data.

[1061] A "normalization algorithm" is an algorithm that standardizes data and converts it into a format that can be efficiently processed by machine learning models.

[1062] A "machine learning model" is an algorithmic model that learns from past data and makes inferences and predictions based on new data.

[1063] The present invention is a system for efficiently communicating between workers and robots in a factory. Specific embodiments of the system are described below.

[1064] System configuration

[1065] 1. Sensor means for detecting brain waves:

[1066] The user wears an EEG sensor (e.g., an EEG headset) that detects the user's EEG data in real time and transmits it to a device.

[1067] 2. Data preprocessing methods:

[1068] After receiving the EEG data, the device uses a noise filter (e.g., Butterworth filter) to remove unnecessary noise, then standardizes the data using a normalization algorithm and performs preprocessing.

[1069] 3. Estimation method:

[1070] The preprocessed data is sent to a server, which uses a machine learning model (e.g., a model using TensorFlow or Keras) to analyze the data, infer words and emotions, and then uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) to classify the emotional state.

[1071] 4. Interface means:

[1072] The analysis results are sent from the server to the terminal and displayed or output to the user via the terminal's display or audio output device. At the same time, the analysis results are sent as instructions to the factory robot.

[1073] 5. Reverse transformation method:

[1074] If necessary, the server uses a generative AI model to generate corresponding brainwave data from the string data and transmits it back to the sensor via the device, allowing specific words or emotions to be fed back to the user's brain.

[1075] 6. Feedback methods:

[1076] Factory robots send their work status and messages in real time to a server, which then analyzes this information and sends it directly to the user's brain as necessary feedback.

[1077] Hardware and Software

[1078] Brainwave sensor: Brainwave detection headset (e.g., Emotiv EPOC+)

[1079] Device: Smartphone or tablet (Android or iOS device)

[1080] Server: Cloud computing service (e.g., Amazon Web Services, Google Cloud)

[1081] Machine learning models: TensorFlow, Keras

[1082] Emotion engine: Azure Cognitive Services, IBM Watson

[1083] Specific examples

[1084] Example 1: Packing instructions

[1085] 1. If the user thinks "Robot, start packing" and feels satisfied:

[1086] The EEG sensor collects EEG data and transmits it to the terminal.

[1087] Data preprocessing is performed on the terminal and then sent to the server.

[1088] Analysis and estimation are performed on the server, and instructions are sent to the robot.

[1089] The robot starts working and sends the work status to the server.

[1090] The server feeds the analysis results back to the device, stimulating the user's brain.

[1091] Prompt Sentence Examples

[1092] "When the user thinks 'Robot, start packing,' and feels satisfied, process the EEG data and send the corresponding instruction to the robot. Please provide a detailed description of the data you collected, normalized, and extrapolated."

[1093] This allows users to intuitively give instructions to factory robots using their brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[1094] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1095] Step 1:

[1096] The user wears an EEG sensor, which detects the user's brainwaves in real time and transmits the data to the device via Bluetooth. The input is the user's brainwaves, and the output is raw EEG data.

[1097] Step 2:

[1098] The device performs noise filtering on the received EEG data. It uses a Butterworth filter to remove unwanted noise. The input is raw EEG data, and the output is pre-processed EEG data with noise removed.

[1099] Step 3:

[1100] The device normalizes the noise-filtered EEG data. It uses a normalization algorithm to standardize the data and convert it into a format suitable for the machine learning model. The input is the noise-removed EEG data, and the output is the normalized EEG data.

[1101] Step 4:

[1102] The device sends the normalized EEG data to the server. The data is securely transferred using the HTTPS protocol. The input is the normalized EEG data, and the output is the data sent to the server.

[1103] Step 5:

[1104] The server inputs the received data into a machine learning model. Using TensorFlow or Keras, the data is fed into a pre-trained model to estimate words and emotions. The input is normalized EEG data, and the output is estimated words and emotions.

[1105] Step 6:

[1106] The server uses an emotion engine to classify detailed emotional states. It analyzes and classifies emotions using Azure Cognitive Services and IBM Watson's emotion detection API. The input is the emotion estimated by the machine learning model, and the output is detailed classified emotional information.

[1107] Step 7:

[1108] The server sends the estimated words and emotion information to the terminal. At the same time, it sends the analysis results as instructions to the factory robot, which then begins the specified action. The input is the estimated words and emotion, and the output is the instructions sent to the terminal and the robot.

[1109] Step 8:

[1110] The device displays or outputs the received instructions and emotional information. The user can check the text on the display or hear the information through the audio output. The input is the estimated words and emotional information, and the output is visual or auditory feedback to the user.

[1111] Step 9:

[1112] Factory robots operate according to instructions and send work status and status information to a server in real time. The input is the instructions sent to the robot, and the output is the work status and status information.

[1113] Step 10:

[1114] The server analyzes the feedback information from the robot and sends it as stimuli to the user's brain as needed. It uses a generative AI model to generate corresponding brainwave data from the string data, which is then sent back to the brainwave sensor via the terminal. The input is the feedback information from the robot, and the output is the feedback sent to the user's brain.

[1115] 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.

[1116] 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.

[1117] 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.

[1118] [Fourth embodiment]

[1119] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1120] 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.

[1121] 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).

[1122] 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.

[1123] 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.

[1124] 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).

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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."

[1132] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[1133] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. Because the collected data is difficult to analyze in its raw form, the device sends this data to a server.

[1134] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[1135] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[1136] The device then displays the received prediction results to the user through an interface. For example, if the predicted word is "Hello," the device will display "Hello" on its screen or play it aloud using speech synthesis technology. This interface allows the user to communicate their thoughts to others in real time.

[1137] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[1138] Specific examples

[1139] Example 1: When the user thinks "Hello"

[1140] 1. The user imagines a specific word in their mind, such as "Hello."

[1141] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[1142] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[1143] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[1144] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[1145] Example 2: When the user says "Hello"

[1146] 1. When the user says "hello", enter the string "hello" into the terminal.

[1147] 2. The terminal sends the string data to the server.

[1148] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[1149] 4. The server sends the generated EEG data to the device.

[1150] 5. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain.

[1151] 6. The user receives the same feeling as "hello."

[1152] Through these processes, this system will enable smooth communication with people and animals who have lost the ability to speak. In the future, it may also be possible to translate between a wide variety of living creatures, opening up new forms of communication.

[1153] The processing flow will be explained below.

[1154] Step 1:

[1155] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[1156] Step 2:

[1157] The user thinks about a specific word or emotion, such as "Hello," and the EEG sensor detects the brain waves that correspond to this thought.

[1158] Step 3:

[1159] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[1160] Step 4:

[1161] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[1162] Step 5:

[1163] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[1164] Step 6:

[1165] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[1166] Step 7:

[1167] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[1168] Step 8:

[1169] The server receives the output from the machine learning model and interprets the estimated words and sentiment. In this example, the model estimates "Hello."

[1170] Step 9:

[1171] The server sends the estimation results to the terminal, which is the step to notify the results to the user.

[1172] Step 10:

[1173] The device sends the received inference result to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[1174] Step 11:

[1175] The user can confirm the inference results through the interface, thereby recognizing that their thoughts have been accurately interpreted and communicated to others.

[1176] Inverse transformation (e.g., when a user is told "hello")

[1177] Step 1:

[1178] A situation occurs where a user says "hello." The device receives this in text form.

[1179] Step 2:

[1180] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[1181] Step 3:

[1182] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[1183] Step 4:

[1184] The server sends the generated brainwave data to the device, which is then ready to be transmitted to the user's brain.

[1185] Step 5:

[1186] The device transmits the generated brainwave data back to the brainwave sensor, which then stimulates the user's brain.

[1187] Step 6:

[1188] The user receives the transmitted EEG signal and the same sensation as saying "hello" is reproduced in the brain, giving the user the sensation of hearing the word.

[1189] Through these processing steps, this system realizes smooth communication between living organisms using brain waves.

[1190] Example 1

[1191] 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."

[1192] Previous communication systems using EEGs lacked accuracy and real-time capabilities, and in particular, the lack of noise removal and data standardization made it difficult to analyze EEG data. Furthermore, there was a lack of inverse conversion methods to convert corresponding words and emotions into EEG data. As a result, it was difficult to achieve smooth communication with people or animals who had lost the ability to speak.

[1193] 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.

[1194] In this invention, the server includes a sensor device for detecting brain waves, a data preprocessing device that receives the brain wave data and performs noise reduction and normalization, an estimation device that uses the preprocessed data to estimate words and emotions using a machine learning model, an interface device that displays or outputs the estimation results by the estimation device as audio, an inverse conversion device that generates corresponding brain wave data from the words and emotions, a terminal that collects brain wave data in real time, a communication device that transmits the collected data to the server via the Internet, and a transmission device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain. This system enables real-time analysis of brain wave data and accurate estimation of corresponding words and emotions. Furthermore, by using the inverse conversion means to convert words and emotions into brain wave data and reproducing them in the user's brain, communication without speaking is possible.

[1195] "Electroencephalograms" are electrical signals emitted by nerve cells in the brain.

[1196] A "sensor device" is a device for detecting brain waves and is used to collect electrical signals from the brain in real time.

[1197] The "data preprocessing device" is a device that performs noise removal and standardization on the electroencephalogram data received from the sensor device.

[1198] A "noise filter" is an algorithm for removing unnecessary noise components from EEG data.

[1199] A "normalization algorithm" is an algorithm for converting data into a standard format.

[1200] An "estimation device" is a device that uses preprocessed data to estimate words and emotions using a machine learning model.

[1201] A "machine learning model" is a mathematical model that learns from past datasets and infers words and emotions from new data.

[1202] An "interface device" is a device for displaying or outputting the estimation results of an estimation device as audio.

[1203] An "inverse conversion device" is a device for generating corresponding electroencephalogram data from words and emotions.

[1204] The "terminal" is a device that collects brain wave data from a sensor device and transmits it to a server.

[1205] The "communication device" is a device that allows the terminal to transmit brain wave data to a server via the Internet.

[1206] The "transmitting device" is a device that transmits the generated brain wave data back to the sensor device and stimulates the user's brain.

[1207] MODE FOR CARRYING OUT THE INVENTION

[1208] The present invention is a system for realizing communication between living organisms using electroencephalograms. Specific embodiments of the system will be described below.

[1209] EEG data collection

[1210] First, the user wears an EEG sensor device, which detects electrical signals emitted by the brain's nerve cells in real time. Specifically, a sensor device such as Neurosky's MindWave is used.

[1211] Sending data

[1212] The device then collects the EEG data from the sensor device and transmits it to a server via the internet. The device can be a smartphone, computer, or other device.

[1213] Data Preprocessing

[1214] The server processes the received EEG data using a data preprocessing device. Specifically, it uses a noise filter to remove unwanted noise components and applies a normalization algorithm to standardize the data. For this purpose, the Python libraries scipy.signal and scikit-learn are used.

[1215] Data analysis and estimation

[1216] Based on the preprocessed data, the server inputs the data into a machine learning model (e.g., TensorFlow or PyTorch) to estimate words and emotions. The machine learning model is trained from a large set of historical data and makes accurate estimates based on the data provided.

[1217] Sending and displaying results

[1218] The estimation results are sent from the server to the device, which then displays or outputs the results to the user. For example, it can be played back as audio using the Google Text-to-Speech API.

[1219] Inverse transformation process

[1220] The system also includes a reverse conversion mechanism. For example, if the user receives different words or emotions, the device sends the string data to the server. The server uses a generative AI model (e.g., OpenAI's GPT-3 or GPT-4) to generate corresponding EEG data from the string, which is then sent to the device. The device then sends the generated EEG data back to the sensor device, which stimulates the user's brain.

[1221] Specific examples

[1222] Example 1: When the user thinks "Hello"

[1223] 1. The user imagines a specific word in their mind, such as "Hello."

[1224] 2. The terminal collects EEG data from the sensor device in real time and transmits it to the server.

[1225] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[1226] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[1227] 5. The server sends the estimation result to the device, which then displays or speaks "Hello."

[1228] Example 2: When the user says "Hello"

[1229] 1. When the user says "hello", enter the string "hello" into the terminal.

[1230] 2. The terminal sends the string data to the server.

[1231] 3. The server uses the generative AI model to generate corresponding EEG data from the string.

[1232] 4. The server sends the generated EEG data to the device.

[1233] 5. The device transmits the generated brain wave data back to the sensor device, stimulating the user's brain.

[1234] 6. The user receives the same feeling as "hello."

[1235] Example prompt: "Implement a method to communicate by converting the user's thoughts into EEG data. The hardware used will be Neurosky's MindWave, and the machine learning model will be built using PyTorch."

[1236] This system will enable smooth communication between people and animals who have lost the ability to speak, and will also enable translation between a wide variety of living creatures, opening up the possibility of new forms of communication.

[1237] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1238] Step 1: Collect EEG data

[1239] The user wears an EEG sensor device. This sensor device detects electrical signals emitted by the brain's nerve cells in real time. The terminal collects EEG data from the sensor device via Bluetooth or a wired connection. The input is raw data from the sensor device. The output is EEG data collected by the terminal. Specifically, the terminal receives the signals sent from the sensor device and saves them in a stream format as "brainwave data."

[1240] Step 2: Sending data

[1241] The device sends the collected EEG data to a server via an internet connection. The input is the EEG data collected by the device. The output is the EEG data sent to the server. Specifically, the device sends the EEG data to the server using an HTTP POST request.

[1242] Step 3: Preprocessing the data

[1243] The server performs noise filtering on the received EEG data. Then, it applies a normalization algorithm to standardize the data. The input is the raw EEG data received by the server. The output is the noise-removed and standardized EEG data. Specifically, the server performs noise filtering using the Python library scipy.signal and standardizes the data using scikit-learn's StandardScaler.

[1244] Step 4: Data analysis and estimation

[1245] The server inputs the preprocessed data into a machine learning model. The model learns from past datasets and estimates the words and emotions corresponding to the EEG data. The input is the preprocessed EEG data. The output is the estimated words and emotions. Specifically, the server inputs the data into a machine learning model built using TensorFlow or PyTorch and obtains the estimated results.

[1246] Step 5: Send and view results

[1247] The server sends the estimated results to the device. The device receives the results and displays or outputs them as audio to the user through an interface device. The input is the estimated words and emotions (data sent from the server). The output is the results displayed or output as audio to the user. Specifically, the device uses the Google Text-to-Speech API or similar to play back the estimated words as audio or display them on the screen.

[1248] Step 6: Reverse transformation

[1249] When a user receives a specific word or emotion, the device sends the string of characters to the server. The server uses a generative AI model to generate corresponding brain wave data from this string of characters and sends it back to the device. The device then sends the generated brain wave data back to the sensor device, stimulating the user's brain. The input is the string of characters (the words or emotions entered by the user). The output is the corresponding brain wave data. Specifically, the server uses OpenAI's GPT-3 or GPT-4 to convert the string of characters into brain wave data, which is then sent back to the user's brain via the device.

[1250] (Application example 1)

[1251] 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."

[1252] In conventional factory production sites, workers need advanced programming knowledge and complex operations to communicate effectively with robots. Furthermore, transmitting work instructions takes time, placing a heavy burden on workers. Furthermore, there is a lack of interfaces for issuing instructions quickly and accurately. There is a need to solve these problems and achieve smoother, more efficient communication between humans and robots.

[1253] 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.

[1254] In this invention, the server includes a sensor means for detecting brain waves, a data preprocessing means for receiving the brain wave data and performing noise removal and normalization, an estimation means for estimating words and emotions using a machine learning model using the preprocessed data, an interface means for displaying or outputting the estimation results by voice, an inverse conversion means for generating corresponding brain wave data from the words and emotions, and an instruction generation means for generating work instructions based on the preprocessed data and transmitting the instructions to an external device. This enables workers to quickly and accurately issue work instructions to factory robots simply by thinking using the brain wave sensor.

[1255] The "sensor means for detecting brain waves" is a device that detects the user's brain activity and collects brain wave data.

[1256] The "data preprocessing means" is a device or method that performs processing to remove noise from collected electroencephalogram data and standardize the data.

[1257] The "estimation means" is a device or method that inputs preprocessed EEG data into a machine learning model and estimates words and emotions based on the output.

[1258] The "interface means" is a device or method for displaying or outputting the results estimated by the estimation means by voice.

[1259] The "inverse conversion means" is a device or method that generates corresponding electroencephalogram data from estimated words or emotions.

[1260] The "instruction generation means" is a device or method that generates work instructions based on the preprocessed data and the estimated results, and transmits the instructions to an external device.

[1261] An "external device" is an industrial robot or other mechanical device that receives data or instructions and performs a specific action.

[1262] This invention is a system that realizes communication between living organisms using brain waves. In particular, it aims to enable factory workers to wear smart glasses and transmit their thoughts to industrial robots as instructions. Specific embodiments of this system are described below.

[1263] 1. EEG data collection and preprocessing

[1264] The user (worker) wears an EEG sensor and engages in specific thinking, such as "pick out the next part and assemble it." This sensor detects the electrical signals emitted by the neurons in the user's brain in real time, i.e., EEG data. The device receives the data collected from this sensor. However, because EEG data is difficult to analyze in its raw form, a noise filter is first used to remove unnecessary noise components. Next, a normalization algorithm is applied to standardize the data, making it suitable for machine learning models.

[1265] 2. Estimating words and emotions

[1266] The preprocessed data is sent to a server. The server uses a generative AI model to analyze the data and estimate corresponding words and emotions. The generative AI model learns from a huge amount of past data sets and is able to make estimates with high accuracy. For example, if a user thinks, "Take out the next part and assemble it," data corresponding to that word is generated.

[1267] 3. Displaying Estimation Results and Generating Instructions

[1268] The estimated words and emotions are sent from the server to the device. The device displays the estimated results to the user through an interface. For example, if the estimated instruction is "Start assembly," the text "Start assembly" is displayed on the device screen. If the user confirms the instruction and there are no problems, the instruction is sent to an external device (industrial robot).

[1269] 4. Specific Examples

[1270] As a concrete example, imagine a worker wearing smart glasses thinking the instruction "pick out the next part and assemble it." The flow of this system is as follows:

[1271] 1. The worker thinks, "Pick out the next part and assemble it."

[1272] 2. The EEG sensor collects EEG data and transmits it to the device.

[1273] 3. The device preprocesses the data using noise filters and normalization algorithms.

[1274] 4. The preprocessed data is sent to the server and input into the generative AI model.

[1275] 5. The server estimates the words and emotions and sends the results to the device.

[1276] 6. The terminal displays "Assembly Start" and the user confirms.

[1277] 7. After confirmation, the terminal sends the instruction to the external device (industrial robot).

[1278] Prompt Sentence Examples

[1279] "Instruct the robot to pick up the next part and assemble it."

[1280] This invention enables factory workers to issue instructions to industrial robots quickly and accurately simply by thinking, without the need for complex programming knowledge or operation. Real-time communication also improves work efficiency and accuracy.

[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1282] Step 1:

[1283] The user wears an EEG sensor and thinks, for example, "Pick out the next part and assemble it." The EEG sensor detects the electrical signals (brainwave data) from the user's brain's neurons in real time and sends that data to a device. The input is the EEG data detected in real time, and the output is the raw EEG data sent to the device.

[1284] Step 2:

[1285] The EEG data received by the device is filtered to remove unwanted noise components. A normalization algorithm is then applied to standardize the data. The input is the raw EEG data received from the sensor, and the output is the normalized data with noise removed. Specifically, the mean value of the data is subtracted and divided by the standard deviation.

[1286] Step 3:

[1287] The preprocessed data is sent to a server, which then inputs the received data into a generative AI model. The input is noise-removed and normalized EEG data, and the output is estimated words and emotions. The generative AI model uses a multi-layer neural network to learn from a huge dataset of past data.

[1288] Step 4:

[1289] The server uses the generative AI model to send estimated words and emotions to the device. The input is the words and emotions estimated by the generative AI model, and the output is the transmission of the estimated results to the device. Specifically, the output of the generative AI model is converted into JSON format and sent to the device via the network.

[1290] Step 5:

[1291] The device displays the inference results to the user through an interface. The input is the inference results sent from the server, and the output is text or audio displayed on the interface screen. For example, "Start assembly" may be displayed as text, and can also be confirmed aloud using speech synthesis technology.

[1292] Step 6:

[1293] The user checks the displayed inference results, and if there are no problems, sends instructions to an external device (industrial robot). The input is the inference results, and the output is specific instructions to the external device. Specifically, instructions are sent by pressing a button on the interface.

[1294] Step 7:

[1295] An external device (industrial robot) starts to operate based on the received instruction. The input is the specific instruction sent by the user, and the output is the actual action of the robot. For example, it executes the action "pick out the next part and assemble it."

[1296] 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.

[1297] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[1298] First, the user wears an EEG sensor. This sensor detects the electrical signals emitted by the brain's nerve cells, or brain waves, in real time. At the same time, the device collects EEG data from the sensor. The collected data is raw and therefore contains a lot of noise. The device then transmits this data to a server.

[1299] The server processes the received EEG data using a noise filter to remove unwanted noise components (data cleaning), and then applies a normalization algorithm to standardize the data, making it suitable for machine learning models.

[1300] Based on the pre-processed data, the server inputs the data into a machine learning model. This model learns from a huge dataset of past data and predicts the corresponding words and emotions based on the input data. The prediction results are sent from the server to the device.

[1301] In addition to the estimation means, the server is also equipped with an emotion engine, which further analyzes the user's brainwave data and classifies their emotional state into joy, sadness, anger, surprise, etc. The emotion engine uses a machine learning algorithm to estimate the emotional state in real time and also transmits this information to the device.

[1302] The device displays the received inference results and emotional state to the user through an interface. For example, if the inferred word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on its screen or play it in a "joy" tone using voice synthesis technology. This interface allows the user to communicate their thoughts and emotions to others in real time.

[1303] The system also has a reverse conversion mechanism. For example, when communicating with another user (including a pet), once the desired words or emotions are identified, the device sends the string of characters to the server. The server uses a generation AI to generate corresponding brainwave data from the string of characters and sends it back to the device. The device then sends the generated brainwave data back to the sensor, stimulating the user's brain and recreating the words and emotions within the brain. This function allows users to communicate without speaking.

[1304] Specific examples

[1305] Example 1: User thinks "Hello" and feels happy

[1306] 1. The user feels a sense of joy in their brain along with the specific word "Hello."

[1307] 2. The device collects brainwave data from the sensor in real time and sends it to the server.

[1308] 3. The server processes the received data with a noise filter and normalizes it with a normalization algorithm.

[1309] 4. The server inputs the preprocessed data into the machine learning model and infers "Hello."

[1310] 5. The server's emotion engine recognizes the emotion of joy.

[1311] 6. The server sends the estimation results and emotion information to the device, which then displays or speaks "Hello (joy)."

[1312] Example 2: When a user is told "hello" and feels surprised

[1313] 1. A situation occurs where a user is told "hello" and feels surprised.

[1314] 2. The terminal inputs the string data "Hello" and sends it to the server.

[1315] 3. The server uses generation AI to generate corresponding brainwave data from the string.

[1316] 4. The server's emotion engine recognizes the emotion of surprise and encodes it into the brainwave data.

[1317] 5. The server sends the generated EEG data to the device.

[1318] 6. The device transmits the generated brainwave data back to the sensor, stimulating the user's brain with a sense of surprise.

[1319] Through these concrete examples, this system realizes smooth communication between living organisms using brain waves and emotions.

[1320] The processing flow will be explained below.

[1321] Program processing steps

[1322] When the user thinks "Hello"

[1323] Step 1:

[1324] The user wears the EEG sensor, which prepares the user's brainwave data to be collected in real time.

[1325] Step 2:

[1326] When the user thinks about the specific word "Hello" and the emotion of joy, the EEG sensor detects the brain waves that correspond to this thought and emotion.

[1327] Step 3:

[1328] The device collects EEG data in real time from the EEG sensor. The collected data is raw and contains a lot of noise.

[1329] Step 4:

[1330] The device then transmits the collected brainwave data to a server, typically via a cloud communication protocol over the internet.

[1331] Step 5:

[1332] The EEG data received by the server is processed using a data pre-processing means, which first removes noise components from the EEG data using a noise filter.

[1333] Step 6:

[1334] The server uses a normalization algorithm to standardize the data, which is then converted into a format suitable for machine learning models.

[1335] Step 7:

[1336] The server feeds the preprocessed EEG data into a machine learning model, which is trained to use past data to predict corresponding words and emotions from the current input data.

[1337] Step 8:

[1338] The server receives the output from the machine learning model and interprets the predicted word as "Hello."

[1339] Step 9:

[1340] The server uses an emotion engine to analyze the user's emotions from the brainwave data and classify the emotion as "joy."

[1341] Step 10:

[1342] The server sends the estimation results and emotion information to the terminal. This is the step to communicate the results and emotions to the user.

[1343] Step 11:

[1344] The device sends the received estimation results and emotion information to a display interface, for example, displaying "Hello" on the user's screen or outputting it as voice.

[1345] Step 12:

[1346] The user can confirm the estimation results and emotional information through the interface, thereby recognizing that their thoughts and emotions have been accurately interpreted and conveyed to others.

[1347] Inverse transformation (when a user is told "hello" and feels surprised)

[1348] Step 1:

[1349] The user is surprised when they hear "hello." The device receives this message in text format.

[1350] Step 2:

[1351] The device sends the string data "Hello" to the server. The server prepares to process the received data.

[1352] Step 3:

[1353] The server uses generative AI to generate corresponding EEG data from the string data, a process based on a trained generative model.

[1354] Step 4:

[1355] The server uses an emotion engine to recognize the emotion "surprise" and integrates this information with the brainwave data.

[1356] Step 5:

[1357] The server sends the generated EEG data to the terminal, which includes the word "hello" and emotional information about "surprise."

[1358] Step 6:

[1359] The device transmits the generated brainwave data back to the brainwave sensor, which stimulates the user's brain and reproduces words and emotions.

[1360] Step 7:

[1361] The user receives the transmitted EEG signal and the sensations of "hello" and surprise are recreated in the brain, resulting in the user experiencing the words and emotions.

[1362] Through the above processing steps, this system realizes smooth communication between living organisms using brain waves and emotions.

[1363] Example 2

[1364] 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."

[1365] Previous communication systems using EEGs had issues such as insufficient noise removal and normalization of EEG data, and low emotion recognition accuracy. Furthermore, the interfaces for accurately displaying and outputting estimated words and emotions in real time were also inadequate. Furthermore, even in communication using inverse conversion, the accuracy of the generated EEG data was an issue.

[1366] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or outputting the estimation results and emotional information by the estimation means as audio, and inverse conversion means for generating corresponding brain wave data from the words and emotions. This makes it possible to estimate words and emotions with high accuracy using normalized data with little noise, enable real-time display and audio output, and enable accurate communication through inverse conversion.

[1367] "Electroencephalograms" are weak electrical signals emitted by nerve cells in humans and animals.

[1368] "Sensor means" refers to a device or mechanism that detects brain waves in real time.

[1369] The "data preprocessing means" is a device or mechanism that performs noise removal and normalization on the received electroencephalogram data.

[1370] A "noise filter" is an algorithm or device for removing unwanted noise components from EEG data.

[1371] A "normalization algorithm" is a mathematical method for converting data into a uniform format.

[1372] The "estimation means" is a device or mechanism that estimates words and emotions using a machine learning model based on preprocessed data.

[1373] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications for new data.

[1374] An "emotion engine" is an algorithm or system that analyzes brainwave data and classifies emotional states such as joy, sadness, and anger.

[1375] The "interface means" is a device or mechanism for visually or audibly notifying the user of the estimation results and emotional information.

[1376] The "inverse conversion means" is a device or mechanism that generates corresponding electroencephalogram data from identified words or emotions.

[1377] A "generative AI model" is an artificial intelligence model that generates corresponding brainwave data or other outputs from input text data.

[1378] A "prompt" is an instruction or question that serves as input to a generative AI model.

[1379] MODE FOR CARRYING OUT THE INVENTION

[1380] The present invention aims to provide a system for realizing communication between living organisms using electroencephalograms, and to accurately recognize the emotions of a user by combining it with an emotion engine. Specific embodiments of the system are described below.

[1381] First, the user wears an EEG sensor. This sensor detects electrical signals emitted by nerve cells, i.e., brain waves, in real time. A commercially available EEG capture device can be used as the sensor. At the same time, the device collects EEG data from the sensor. However, this data contains a lot of noise, making it unusable as is.

[1382] The device then transmits the collected EEG data to a server. This communication is encrypted using the SSL / TLS protocol to ensure security. The server can be hosted in a cloud environment, for example, to facilitate scalability and resource management. The server first applies a noise filter to the received EEG data to remove unwanted noise components. The noise filter can be a band-pass filter or a custom noise reduction algorithm.

[1383] Once the noise has been removed, the server then applies a normalization algorithm, for example, using Z-score normalization to standardize the data, ensuring that the data obtained from different users and across different measurement sessions is in a consistent format.

[1384] Based on the preprocessed data, the server inputs the data into a machine learning model, which can be a deep learning framework such as TensorFlow. This model learns from a large dataset of past data and predicts corresponding words and emotions based on the input data.

[1385] The estimation results are encrypted using the SSL / TLS protocol and sent to the device. The emotion engine on the server then further analyzes the EEG data to classify emotional states such as joy, sadness, anger, and surprise. The emotion engine also uses machine learning algorithms to estimate emotional states in real time.

[1386] The device displays the estimation results and emotion information to the user through an interface. Display can be done in the form of a web application using HTML5 and JavaScript. It is also possible to play the estimated emotion tone using speech synthesis technology. For example, if the estimated word is "Hello" and the emotion engine recognizes the emotion "joy," the device will display "Hello (joy)" on the screen or play it in a "joy" tone.

[1387] The system also has a reverse conversion mechanism. For example, when communicating with other users (including pets), if a user wants to receive specific words or emotions, the device sends the string data to the server. The server uses a generative AI model to generate corresponding EEG data from the string and sends it back to the device. An example of a generative AI model is OpenAI's GPT-4. An example of a prompt sentence is, "Please generate the EEG data when the user says 'hello'."

[1388] The device then transmits the generated brainwave data back to the sensor, stimulating the user's brain and reproducing the words and emotions within the brain. This function allows users to communicate without speaking.

[1389] As described above, this system realizes highly accurate communication between living organisms using brain waves and emotional data, allowing users to smoothly convey their thoughts and emotions to others.

[1390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1391] Program processing steps

[1392] Step 1:

[1393] The user wears an EEG sensor. The sensor detects electrical signals (brain waves) emitted by the brain's neurons in real time. The input is the electrical signals emitted by the neurons, and the output is the detected raw brain wave data. Specifically, the user wears the EEG sensor on their head, and the sensor captures the electrical signals.

[1394] Step 2:

[1395] The device collects raw EEG data from the sensor in real time and sends it to the server. The input is raw EEG data from the sensor, and the output is unprocessed EEG data sent to the server. Specifically, the device takes in data from the sensor, encrypts it using SSL / TLS, and sends it to the server.

[1396] Step 3:

[1397] The server applies a noise filter to the received raw EEG data. The input is raw EEG data, and the output is clean EEG data with noise removed. Specifically, the server uses a band-pass filter or a custom noise reduction algorithm to remove noise from the EEG data.

[1398] Step 4:

[1399] The server normalizes the clean EEG data using a normalization algorithm. The input is the denoised EEG data, and the output is the normalized EEG data. Specifically, the data is converted into a consistent format using Z-score normalization.

[1400] Step 5:

[1401] The server inputs the normalized data into a machine learning model. The input is normalized EEG data, and the output is estimated words and emotions. Specifically, the data is analyzed using a deep learning framework such as TensorFlow to estimate the words and emotions the user is thinking.

[1402] Step 6:

[1403] The server sends the estimated words and emotion information to the device. The input is the estimation result from the machine learning model, and the output is the encrypted estimation result and emotion information. Specifically, the estimation result is encrypted using SSL / TLS and sent to the device.

[1404] Step 7:

[1405] The device displays the estimation results and emotional information to the user through an interface. The input is the estimation results and emotional information received from the server, and the output is the information displayed on the interface or a voice generated by speech synthesis. Specific operations include displaying the results in a web application format using HTML5 and JavaScript, and playing back a voice in a specific tone using speech synthesis technology.

[1406] Step 8:

[1407] When a user wants to receive a desired word or emotion, the device sends the string data to the server. The input is the string data entered by the user, and the output is the string data to be sent to the server. Specifically, the device takes the entered string data, encrypts it using SSL / TLS, and sends it to the server.

[1408] Step 9:

[1409] The server uses a generative AI model to generate corresponding brain wave data from input string data. The input is string data received from the terminal, and the output is generated brain wave data. In concrete terms, a prompt sentence is input into the generative AI model (for example, a general-purpose artificial intelligence model), and brain wave data is generated based on that. An example of a prompt sentence is in the format "Please generate brain wave data when the user says 'hello'."

[1410] Step 10:

[1411] The server sends the generated EEG data to the terminal. The input is the generated EEG data, and the output is the EEG data to be sent to the terminal. Specifically, the EEG data is encrypted using SSL / TLS and sent to the terminal.

[1412] Step 11:

[1413] The device then transmits the received brainwave data back to the sensor, which then stimulates the user's brain. The input is the received brainwave data, and the output is the words and emotions that are reproduced in the user's brain. Specifically, the brainwave data is transmitted back to the user's brain via the sensor, which then stimulates the user to reproduce specific words and emotions.

[1414] This processing step allows the system to convey the user's thoughts and feelings to others, and also enables communication through reverse conversion.

[1415] (Application example 2)

[1416] 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."

[1417] Currently, communication between workers and robots in factories is often carried out via physical input devices or programming, making it difficult to give intuitive and quick instructions. Furthermore, it is not possible to understand the emotions of workers and respond appropriately, which raises concerns about reduced work efficiency and stress. Furthermore, there are limited means of receiving feedback from robots in real time, making it difficult to respond quickly.

[1418] The identification processing 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 sensor means for detecting brain waves, data preprocessing means for receiving the brain wave data and performing noise removal and normalization, estimation means for estimating words and emotions using a machine learning model using the preprocessed data, interface means for displaying or audio output of the estimation results by the estimation means, inverse conversion means for generating corresponding brain wave data from the words and emotions, and means for sending instructions to a factory robot via the interface means and feeding back the robot's status and messages to the user's brain. This enables workers to intuitively issue instructions to factory robots using brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[1419] The "sensor means for detecting brain waves" is a device that detects and collects the user's brain wave data in real time.

[1420] The "data preprocessing means" refers to a device or software that removes noise and normalizes the received EEG data, converting it into a format suitable for a machine learning model.

[1421] The "estimation means" is a system or algorithm that inputs preprocessed EEG data into a machine learning model to estimate words and emotions.

[1422] The "interface means" refers to a device or software for displaying or outputting the estimation result by the estimation means to the user.

[1423] The "inverse conversion means" is a device or system that generates corresponding electroencephalogram data from words and emotions and feeds this back to the user's brain.

[1424] A "factory robot" is an automated mechanical device designed to perform manufacturing or assembly tasks.

[1425] A "server" is a central processing unit or system for processing, estimating, and feeding back EEG data.

[1426] "Noise filter" is a filtering technique for removing unnecessary noise components from EEG data.

[1427] A "normalization algorithm" is an algorithm that standardizes data and converts it into a format that can be efficiently processed by machine learning models.

[1428] A "machine learning model" is an algorithmic model that learns from past data and makes inferences and predictions based on new data.

[1429] The present invention is a system for efficiently communicating between workers and robots in a factory. Specific embodiments of the system are described below.

[1430] System configuration

[1431] 1. Sensor means for detecting brain waves:

[1432] The user wears an EEG sensor (e.g., an EEG headset) that detects the user's EEG data in real time and transmits it to a device.

[1433] 2. Data preprocessing methods:

[1434] After receiving the EEG data, the device uses a noise filter (e.g., Butterworth filter) to remove unnecessary noise, then standardizes the data using a normalization algorithm and performs preprocessing.

[1435] 3. Estimation method:

[1436] The preprocessed data is sent to a server, which uses a machine learning model (e.g., a model using TensorFlow or Keras) to analyze the data, infer words and emotions, and then uses an emotion engine (e.g., Azure Cognitive Services or IBM Watson) to classify the emotional state.

[1437] 4. Interface means:

[1438] The analysis results are sent from the server to the terminal and displayed or output to the user via the terminal's display or audio output device. At the same time, the analysis results are sent as instructions to the factory robot.

[1439] 5. Reverse transformation method:

[1440] If necessary, the server uses a generative AI model to generate corresponding brainwave data from the string data and transmits it back to the sensor via the device, allowing specific words or emotions to be fed back to the user's brain.

[1441] 6. Feedback methods:

[1442] Factory robots send their work status and messages in real time to a server, which then analyzes this information and sends it directly to the user's brain as necessary feedback.

[1443] Hardware and Software

[1444] Brainwave sensor: Brainwave detection headset (e.g., Emotiv EPOC+)

[1445] Device: Smartphone or tablet (Android or iOS device)

[1446] Server: Cloud computing service (e.g., Amazon Web Services, Google Cloud)

[1447] Machine learning models: TensorFlow, Keras

[1448] Emotion engine: Azure Cognitive Services, IBM Watson

[1449] Specific examples

[1450] Example 1: Packing instructions

[1451] 1. If the user thinks "Robot, start packing" and feels satisfied:

[1452] The EEG sensor collects EEG data and transmits it to the terminal.

[1453] Data preprocessing is performed on the terminal and then sent to the server.

[1454] Analysis and estimation are performed on the server, and instructions are sent to the robot.

[1455] The robot starts working and sends the work status to the server.

[1456] The server feeds the analysis results back to the device, stimulating the user's brain.

[1457] Prompt Sentence Examples

[1458] "When the user thinks 'Robot, start packing,' and feels satisfied, process the EEG data and send the corresponding instruction to the robot. Please provide a detailed description of the data you collected, normalized, and extrapolated."

[1459] This allows users to intuitively give instructions to factory robots using their brain waves and receive feedback from the robots in real time, which is expected to improve work efficiency and reduce stress.

[1460] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1461] Step 1:

[1462] The user wears an EEG sensor, which detects the user's brainwaves in real time and transmits the data to the device via Bluetooth. The input is the user's brainwaves, and the output is raw EEG data.

[1463] Step 2:

[1464] The device performs noise filtering on the received EEG data. It uses a Butterworth filter to remove unwanted noise. The input is raw EEG data, and the output is pre-processed EEG data with noise removed.

[1465] Step 3:

[1466] The device normalizes the noise-filtered EEG data. It uses a normalization algorithm to standardize the data and convert it into a format suitable for the machine learning model. The input is the noise-removed EEG data, and the output is the normalized EEG data.

[1467] Step 4:

[1468] The device sends the normalized EEG data to the server. The data is securely transferred using the HTTPS protocol. The input is the normalized EEG data, and the output is the data sent to the server.

[1469] Step 5:

[1470] The server inputs the received data into a machine learning model. Using TensorFlow or Keras, the data is fed into a pre-trained model to estimate words and emotions. The input is normalized EEG data, and the output is estimated words and emotions.

[1471] Step 6:

[1472] The server uses an emotion engine to classify detailed emotional states. It analyzes and classifies emotions using Azure Cognitive Services and IBM Watson's emotion detection API. The input is the emotion estimated by the machine learning model, and the output is detailed classified emotional information.

[1473] Step 7:

[1474] The server sends the estimated words and emotion information to the terminal. At the same time, it sends the analysis results as instructions to the factory robot, which then begins the specified action. The input is the estimated words and emotion, and the output is the instructions sent to the terminal and the robot.

[1475] Step 8:

[1476] The device displays or outputs the received instructions and emotional information. The user can check the text on the display or hear the information through the audio output. The input is the estimated words and emotional information, and the output is visual or auditory feedback to the user.

[1477] Step 9:

[1478] Factory robots operate according to instructions and send work status and status information to a server in real time. The input is the instructions sent to the robot, and the output is the work status and status information.

[1479] Step 10:

[1480] The server analyzes the feedback information from the robot and sends it as stimuli to the user's brain as needed. It uses a generative AI model to generate corresponding brainwave data from the string data, which is then sent back to the brainwave sensor via the terminal. The input is the feedback information from the robot, and the output is the feedback sent to the user's brain.

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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).

[1488] 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.

[1489] 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."

[1490] 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.

[1491] 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).

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] 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.

[1502] The following is further disclosed regarding the above embodiment.

[1503] (Claim 1)

[1504] sensor means for detecting brain waves;

[1505] a data pre-processing means for receiving the electroencephalogram data and performing noise removal and normalization;

[1506] an estimation means for estimating words and emotions using a machine learning model using the preprocessed data;

[1507] an interface means for displaying or outputting by voice the estimation result by the estimation means;

[1508] an inverse conversion means for generating corresponding electroencephalogram data from the words and emotions;

[1509] A system including:

[1510] (Claim 2)

[1511] 2. The system of claim 1, wherein the data preprocessing means removes noise from the EEG data using a noise filter and standardizes the data using a normalization algorithm.

[1512] (Claim 3)

[1513] 2. The system according to claim 1, wherein the estimation means inputs the electroencephalogram data into a machine learning model and obtains estimated words and emotions from the output thereof.

[1514] "Example 1"

[1515] (Claim 1)

[1516] a sensor device for detecting brain waves;

[1517] a data preprocessing device that receives the electroencephalogram data and performs noise removal and normalization;

[1518] an estimation device that estimates words and emotions using a machine learning model using the preprocessed data;

[1519] an interface device that displays or outputs an estimation result by the estimation device;

[1520] an inverse transformation device that generates corresponding electroencephalogram data from the words and emotions;

[1521] A terminal that collects brainwave data in real time,

[1522] a communication device that transmits the collected data to a server via the Internet;

[1523] a transmitting device that transmits the generated electroencephalogram data back to the sensor device to stimulate the user's brain;

[1524] A system including:

[1525] (Claim 2)

[1526] 10. The system of claim 1, wherein the data preprocessing device uses a noise filter to remove noise from the EEG data and a normalization algorithm to standardize the data.

[1527] (Claim 3)

[1528] 2. The system according to claim 1, wherein the estimation device inputs the electroencephalogram data into a machine learning model and obtains estimated words and emotions from the output.

[1529] "Application Example 1"

[1530] (Claim 1)

[1531] sensor means for detecting brain waves;

[1532] a data pre-processing means for receiving the electroencephalogram data and performing noise removal and normalization;

[1533] an estimation means for estimating words and emotions using a machine learning model using the preprocessed data;

[1534] an interface means for displaying or outputting by voice the estimation result by the estimation means;

[1535] an inverse conversion means for generating corresponding electroencephalogram data from the words and emotions;

[1536] an instruction generation means for generating work instructions based on the preprocessed data and transmitting the instructions to an external device;

[1537] A system including:

[1538] (Claim 2)

[1539] 2. The system of claim 1, wherein the data preprocessing means removes noise from the EEG data using a noise filter and standardizes the data using a normalization algorithm.

[1540] (Claim 3)

[1541] 2. The system according to claim 1, wherein the estimation means inputs the electroencephalogram data into a machine learning model and obtains estimated words and emotions from the output thereof.

[1542] (Claim 4)

[1543] 2. The system according to claim 1, wherein the instruction generating means generates appropriate work instructions based on the estimated words and emotions, and transmits the instructions to an industrial robot.

[1544] "Example 2: Combining Emotion Engines"

[1545] (Claim 1)

[1546] sensor means for detecting brain waves;

[1547] a data pre-processing means for receiving the electroencephalogram data and performing noise removal and normalization;

[1548] an estimation means for estimating words and emotions using a machine learning model using the preprocessed data;

[1549] an interface means for displaying or outputting by voice the estimation result and emotion information by the estimation means;

[1550] an inverse conversion means for generating corresponding electroencephalogram data from the words and emotions;

[1551] A system including:

[1552] (Claim 2)

[1553] 2. The system of claim 1, wherein the data preprocessing means removes noise from the EEG data using a noise filter and standardizes the data using a normalization algorithm.

[1554] (Claim 3)

[1555] 2. The system according to claim 1, wherein the estimation means inputs the electroencephalogram data into a machine learning model, and classifies estimated words and emotions based on the output of the model using an emotion engine.

[1556] "Application example 2 when combining emotion engines"

[1557] (Claim 1)

[1558] sensor means for detecting brain waves;

[1559] a data pre-processing means for receiving the electroencephalogram data and performing noise removal and normalization;

[1560] an estimation means for estimating words and emotions using a machine learning model using the preprocessed data;

[1561] an interface means for displaying or outputting by voice the estimation result by the estimation means;

[1562] an inverse conversion means for generating corresponding electroencephalogram data from the words and emotions;

[1563] a means for transmitting instructions to the factory robot through the interface means and feeding back the status and messages of the robot to the user's brain;

[1564] A system including:

[1565] (Claim 2)

[1566] 2. The system of claim 1, wherein the data preprocessing means removes noise from the EEG data using a noise filter and standardizes the data using a normalization algorithm.

[1567] (Claim 3)

[1568] The system of claim 1, wherein the estimation means inputs the EEG data into a machine learning model and obtains estimated words and emotions from the output, which include instructions to a factory robot and feedback from the robot. [Explanation of symbols]

[1569] 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. sensor means for detecting brain waves; a data pre-processing means for receiving the electroencephalogram data and performing noise removal and normalization; an estimation means for estimating words and emotions using a machine learning model using the preprocessed data; an interface means for displaying or outputting by voice the estimation result by the estimation means; an inverse conversion means for generating corresponding electroencephalogram data from the words and emotions; A system including:

2. 2. The system of claim 1, wherein the data preprocessing means uses a noise filter to remove noise from the electroencephalogram data and a normalization algorithm to standardize the data.

3. The system according to claim 1 , wherein the estimation means inputs the electroencephalogram data into a machine learning model and obtains estimated words and emotions from the output thereof.

Images