system

Abstract

The system according to this embodiment aims to support global communication by translating user statements into another language in real time. [Solution] The system according to the embodiment comprises a speech recognition unit, a translation unit, an output unit, and a provision unit. The speech recognition unit recognizes the user's speech. The translation unit translates the speech recognized by the speech recognition unit. The output unit outputs the speech translated by the translation unit. The provision unit provides the speech translated by the translation unit to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to translate voice into another language in real time, and global communication cannot be smoothly performed.

[0005] The system according to the embodiment aims to translate a user's utterance into another language in real time and support global communication.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a speech recognition unit, a translation unit, an output unit, and a provision unit. The speech recognition unit recognizes the user's speech. The translation unit translates the speech recognized by the speech recognition unit. The output unit outputs the speech translated by the translation unit. The provision unit provides the speech translated by the translation unit to the user. [Effects of the Invention]

[0007] The system according to this embodiment can translate user statements into another language in real time, thereby supporting global communication. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that translates a user's voice into another language in real time, supporting global communication. This AI agent system translates a user's voice into another language in real time, supporting global communication. Users can convert their voice into a selected language, enabling real-time conversation. Specifically, it combines speech recognition technology and instant translation technology to instantly translate the user's statements into another language. The AI ​​agent learns from the user's language usage patterns to improve translation accuracy. It is a cloud-based service, offering scalability and ease of access. Target users include those in multilingual communities, professionals conducting international business, and educational institutions that value intercultural exchange. For example, the AI ​​agent system recognizes the user's voice in real time and translates it instantly. For instance, if a user speaks in English, the AI ​​agent system recognizes the speech and instantly translates it into Japanese. Furthermore, the AI ​​agent system learns the user's language usage patterns to improve translation accuracy. For example, it learns frequently used phrases and words and incorporates them into subsequent translations. Because it is a cloud-based service, users can access it from anywhere simply by connecting to the internet. For example, it is envisioned for use in business meetings and international events. This will enable the AI ​​agent system to improve communication speed, enhance language understanding, and expand user participation. The AI ​​agent system can translate user statements in real time, supporting global communication.

[0029] The AI ​​agent system according to this embodiment comprises a speech recognition unit, a translation unit, an output unit, and a provision unit. The speech recognition unit recognizes the user's speech. For example, the speech recognition unit collects the user's speech using a microphone and converts it into text data using speech recognition technology. The speech recognition unit can analyze the speech data using AI and accurately recognize the content of the speech. For example, the speech recognition unit removes background noise using noise cancellation technology to clearly recognize the content of the speech. The speech recognition unit can also adjust its recognition algorithm according to the speed and rhythm of the user's speech. For example, if the user speaks quickly, the speech recognition unit speeds up the recognition algorithm to accommodate this. The translation unit translates the speech recognized by the speech recognition unit. The translation unit can translate the text data into other languages ​​using AI. For example, the translation unit translates what the user says in English into Japanese. The translation unit can also learn the user's language usage patterns to improve translation accuracy. For example, the translation unit learns phrases and words that the user frequently uses and reflects them in subsequent translations. The output unit outputs the speech translated by the translation unit. The output unit can generate audio data using AI and provide it to the user. For example, the output unit converts translated text data into audio data using speech synthesis technology and outputs it through the speaker. The output unit can also optimize the audio quality according to the acoustic characteristics of the user's device. For example, the output unit adjusts the audio quality according to the speaker characteristics of a smartphone. The delivery unit provides the user with the audio translated by the translation unit. The delivery unit can estimate the user's emotions using AI and adjust the delivery method. For example, if the delivery unit is nervous, it will provide the information in a calm manner. The delivery unit can also select the optimal delivery timing by referring to the user's past usage history. For example, if the delivery unit has received information at a specific time in the past, it will provide the information at that time. As a result, the AI ​​agent system according to this embodiment can translate user statements in real time and support global communication.

[0030] The speech recognition unit recognizes the user's speech. For example, the speech recognition unit collects the user's voice using a microphone and converts it into text data using speech recognition technology. Specifically, the speech recognition unit uses a high-sensitivity microphone to clearly collect the user's voice, and the collected voice data is processed using noise cancellation technology to remove background noise. This allows the speech recognition unit to clearly recognize the content of the speech. Furthermore, the speech recognition unit uses AI to analyze the voice data and accurately recognize the content of the speech. The AI ​​uses deep learning technology to extract features from the voice data and identify phonemes and words. For example, the speech recognition unit can adjust its recognition algorithm according to the speed and rhythm of the user's speech. If the user speaks quickly, the recognition algorithm is accelerated to accommodate this, and conversely, if the user speaks slowly, the algorithm is adjusted to ensure accurate recognition. In addition, the speech recognition unit learns from a variety of voice data in advance so that it can handle differences in the user's pronunciation and accent. This allows the speech recognition unit to accurately recognize the speech of users who speak different languages ​​or dialects. Furthermore, the speech recognition unit can process voice data in real time and convert it into text data without delay. This allows users to communicate smoothly.

[0031] The translation unit translates the speech recognized by the speech recognition unit. The translation unit can also translate text data into other languages ​​using AI. Specifically, the translation unit uses neural machine translation (NMT) technology to translate text data with high accuracy. NMT utilizes deep learning to provide natural translations that consider context and meaning. For example, when translating what a user says in English into Japanese, the translation unit selects appropriate words and phrases according to the context. The translation unit can also learn the user's language usage patterns to improve translation accuracy. By learning frequently used phrases and words and incorporating them into subsequent translations, it provides more natural and accurate translations. Furthermore, the translation unit learns relevant data in advance to handle specialized terminology and industry-specific expressions. This enables it to provide highly accurate translations even in business and technical conversations. The translation unit also performs real-time translations, allowing users to continue communicating smoothly. For example, it can instantly translate user statements during meetings or phone conversations and convey them to the other party. In this way, the translation unit supports smooth communication across language barriers.

[0032] The output unit outputs the audio translated by the translation unit. The output unit can generate audio data using AI and provide it to the user. Specifically, the output unit uses text-to-speech (TTS) technology to convert the translated text data into natural-sounding audio. TTS technology utilizes deep learning to generate audio with natural intonation and intonation. For example, the output unit converts the translated text data into audio data and outputs it through the speaker. The output unit can also optimize the audio quality according to the acoustic characteristics of the user's device. For example, it can adjust the audio quality according to the speaker characteristics of a smartphone to provide clear and easy-to-understand audio. Furthermore, the output unit can adjust the tone and speed of the audio according to the user's preferences. For example, if the user prefers a calm tone, it will adjust and generate the audio accordingly. The output unit also supports multiple languages ​​and can output audio in the language selected by the user. This allows the output unit to provide the user with natural and easy-to-understand audio, supporting smooth communication.

[0033] The delivery unit provides users with audio translated by the translation unit. The delivery unit can use AI to estimate the user's emotions and adjust the delivery method accordingly. Specifically, the delivery unit estimates emotions from the user's facial expressions, tone of voice, and content of speech, and delivers information in an appropriate manner. For example, if the user is nervous, the information will be delivered in a calm manner. The AI ​​analyzes the user's emotions in real time using emotion recognition technology and adjusts the delivery method accordingly. The delivery unit can also select the optimal delivery timing by referring to the user's past usage history. For example, if the user has received information at a specific time in the past, the information will be delivered at that time. Furthermore, the delivery unit can customize the information delivery method according to the user's preferences. For example, if the user prefers visual information, the information will be delivered using text and images; if the user prefers auditory information, the information will be delivered via audio. The delivery unit can also collect user feedback and continuously improve the accuracy and effectiveness of the delivery method. This allows the delivery unit to deliver information to users in the most optimal way and improve user satisfaction.

[0034] The AI ​​agent system further includes a learning unit that learns the user's language usage patterns. The learning unit can use AI to learn the user's language usage patterns and improve translation accuracy. For example, the learning unit learns frequently used phrases and words by the user and incorporates them into future translations. The learning unit can also use AI to analyze the user's utterances and extract language usage patterns. For example, if the user frequently uses a particular grammatical structure, the learning unit learns that pattern and improves translation accuracy. The learning unit can also use AI to analyze the tone and rhythm of the user's utterances and learn language usage patterns. For example, if the user speaks in a particular tone, the learning unit learns that tone and improves translation accuracy. In this way, learning the user's language usage patterns improves translation accuracy.

[0035] The speech recognition unit can analyze background noise in response to the user's speech and optimize noise cancellation. For example, if the user is in a noisy environment, the speech recognition unit can analyze the background noise in real time and apply noise cancellation to clearly recognize the speech. If the user is in a quiet environment, the speech recognition unit can also analyze the background noise and adjust the noise cancellation intensity to recognize natural speech. If the user is moving, the speech recognition unit can also detect changes in background noise in real time and dynamically adjust noise cancellation. This allows for clear recognition of speech by analyzing background noise and optimizing noise cancellation. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input background noise data into a generating AI and have the generating AI perform noise cancellation optimization.

[0036] The speech recognition unit can adjust its recognition algorithm according to the user's speaking speed and rhythm during speech recognition. For example, if the user speaks quickly, the speech recognition unit can detect the speaking speed in real time and speed up the recognition algorithm accordingly. If the user speaks slowly, the speech recognition unit can also analyze the rhythm of the speech and optimize the recognition algorithm for accurate recognition. If the user speaks with an irregular rhythm, the speech recognition unit can learn the speech pattern and dynamically adjust the recognition algorithm. This improves recognition accuracy by adjusting the recognition algorithm according to the speaking speed and rhythm. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input speech speed data into a generating AI and have the generating AI perform the adjustment of the recognition algorithm.

[0037] The speech recognition unit can correct dialects and accents based on the user's geographical location information during speech recognition. For example, if the user is in a specific region, the speech recognition unit corrects the dialect and accent of that region based on the geographical location information. If the user moves to a different region, the speech recognition unit can acquire new geographical location information and dynamically correct the dialect and accent. If the user is in an international environment, the speech recognition unit can correct multiple dialects and accents based on the geographical location information. This improves recognition accuracy by correcting dialects and accents based on geographical location information. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input geographical location data into a generating AI and have the generating AI perform the dialect and accent correction.

[0038] The speech recognition unit can analyze the user's social media activity during speech recognition and prioritize the recognition of specific terms and phrases. For example, the speech recognition unit can analyze and prioritize the recognition of terms and phrases that the user frequently uses on social media. If the user is talking about a specific topic, the speech recognition unit can also prioritize the recognition of relevant terms and phrases based on their social media activity. If the user uses new terms or phrases, the speech recognition unit can also analyze their social media activity in real time and update their recognition algorithm. This improves recognition accuracy by analyzing social media activity and prioritizing the recognition of specific terms and phrases. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or not. For example, the speech recognition unit can input social media data into a generating AI and have the generating AI perform the priority recognition of specific terms and phrases.

[0039] The translation unit can select the most appropriate translation by considering the context of the statement during the translation process. For example, if the user is speaking in a business meeting, the translation unit will select formal expressions considering the context. If the user is having a casual conversation, the translation unit can also select relaxed expressions considering the context. If the user is talking about a technical topic, the translation unit can also appropriately translate technical terms considering the context. This improves the accuracy of the translation by selecting the most appropriate translation by considering the context of the statement. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input contextual data of the statement into a generating AI and have the generating AI perform the selection of the most appropriate translation.

[0040] The translation unit can appropriately translate specialized terminology according to the user's field of expertise during translation. For example, if the user is a medical expert, the translation unit will appropriately translate medical terminology. If the user is a legal expert, the translation unit can also appropriately translate legal terminology. If the user is an engineering expert, the translation unit can also appropriately translate technical terminology. This improves the accuracy of the translation by appropriately translating specialized terminology according to the user's field of expertise. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input specialized terminology data into a generating AI and have the generating AI perform the translation of the specialized terminology.

[0041] The translation unit can provide consistent translations by referring to the user's past translation history during the translation process. For example, the translation unit can refer to translation expressions previously used by the user to provide consistent translations. The translation unit can also consistently use certain terms if the user has used them in the past. The translation unit can also refer to contexts in which the user has previously translated and provide consistent translations in similar contexts. This improves translation accuracy by providing consistent translations by referring to past translation history. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input past translation history data into a generating AI and have the generating AI perform consistent translations.

[0042] The translation unit can select appropriate expressions while considering the user's cultural background during translation. For example, if the user belongs to a specific cultural sphere, the translation unit will select expressions appropriate to that culture. If the user is speaking with someone from a different cultural sphere, the translation unit can also select appropriate expressions considering both cultures. If the user is speaking in an international setting, the translation unit can also select culturally neutral expressions. By selecting appropriate expressions while considering cultural background, the accuracy of the translation is improved. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input cultural background data into a generating AI and have the generating AI perform the selection of appropriate expressions.

[0043] The output unit can optimize the audio quality according to the acoustic characteristics of the user's device when outputting. For example, if the user is using a smartphone, the output unit can optimize the audio quality according to the speaker characteristics of the device. If the user is using headphones, the output unit can also optimize the audio quality according to the acoustic characteristics of the headphones. If the user is using the device in a car, the output unit can also optimize the audio quality according to the acoustic characteristics of the car. This provides better audio by optimizing the audio quality according to the acoustic characteristics of the device. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the device's acoustic characteristic data into a generating AI and have the generating AI perform the optimization of the audio quality.

[0044] The output unit can adjust the frequency band of the audio based on the user's auditory characteristics during output. For example, if the user has difficulty hearing high frequencies, the output unit can adjust the frequency band of the audio to emphasize the high frequencies. If the user has difficulty hearing low frequencies, the output unit can also adjust the frequency band of the audio to emphasize the low frequencies. If the user is sensitive to a particular frequency band, the output unit can adjust that frequency band to provide a more comfortable audio experience. In this way, by adjusting the frequency band of the audio based on auditory characteristics, a more appropriate audio is provided. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's auditory characteristics data into a generating AI and have the generating AI perform the adjustment of the audio frequency band.

[0045] The output unit can analyze the user's ambient noise and set the optimal volume when outputting. For example, if the user is in a noisy environment, the output unit can analyze the ambient noise and automatically increase the volume. If the user is in a quiet environment, the output unit can also analyze the ambient noise and automatically decrease the volume. If the user is moving, the output unit can analyze changes in ambient noise in real time and dynamically adjust the volume. This allows for more appropriate audio to be provided by analyzing ambient noise and setting the optimal volume. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input ambient noise data into a generating AI and have the generating AI set the optimal volume.

[0046] The output unit can apply a power-saving mode when outputting, taking into account the battery status of the user's device. For example, if the battery of the user's device is low, the output unit will apply a power-saving mode to optimize audio output. The output unit can also output audio in normal mode when the user's device is charging. The output unit can also monitor the battery status of the user's device in real time and apply a power-saving mode as needed. This allows for extending battery life by applying a power-saving mode while considering the device's battery status. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input battery status data to a generating AI and have the generating AI execute the application of a power-saving mode.

[0047] The service provider can select the optimal delivery timing by referring to the user's past usage history at the time of delivery. For example, if the service provider has received information during a specific time period in the past, it will provide the information during that time period. If the service provider has received information under specific circumstances in the past, it can also provide the information under similar circumstances. The service provider can also analyze the user's past usage history and select the optimal delivery timing. By selecting the optimal delivery timing by referring to past usage history, information can be provided to the user at the most opportune time. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input past usage history data into a generating AI and have the generating AI select the optimal delivery timing.

[0048] The information delivery unit can customize the delivery method according to the user's current activity status at the time of delivery. For example, if the user is exercising, the information delivery unit can provide information via voice. If the user is working, the information delivery unit can also provide information via text. If the user is resting, the information delivery unit can also provide information via visuals. In this way, by customizing the delivery method according to the current activity status, information can be delivered in the most optimal way for the user. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or without AI. For example, the information delivery unit can input current activity status data into a generating AI and have the generating AI perform the customization of the delivery method.

[0049] The information delivery unit can select the optimal delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the information delivery unit can provide information according to the characteristics of the device. If the user is using a tablet, the information delivery unit can also provide information optimized for a larger screen. If the user is using a smartwatch, the information delivery unit can also provide concise and highly visible information. In this way, by selecting the optimal delivery method considering device information, information can be delivered in the most optimal way for the user. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or without AI. For example, the information delivery unit can input device information data into a generating AI and have the generating AI select the optimal delivery method.

[0050] The data delivery unit can optimize the efficiency of data transfer by considering the user's network conditions at the time of delivery. For example, if the user is connected to a high-speed network, the data delivery unit can deliver high-quality data quickly. If the user is connected to a low-speed network, the data delivery unit can also compress the data and deliver it efficiently. The data delivery unit can also monitor the user's network conditions in real time and select the optimal data transfer method. This enables efficient information delivery by optimizing the efficiency of data transfer by considering the network conditions. Some or all of the above processing in the data delivery unit may be performed using AI, for example, or without AI. For example, the data delivery unit can input network condition data into a generating AI and have the generating AI perform the optimization of data transfer efficiency.

[0051] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal learning algorithm. The learning unit can also adjust the learning algorithm based on patterns obtained from past learning data. The learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. As a result, the accuracy of learning is improved by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0052] The learning unit can update the learning content by reflecting user feedback during the learning process. For example, the learning unit can collect user feedback and incorporate it into the learning content. The learning unit can also adjust the learning algorithm based on user feedback. The learning unit can also analyze user feedback and optimize the learning content. This improves the accuracy of learning by updating the learning content in accordance with user feedback. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user feedback data into a generating AI and have the generating AI perform the update of the learning content.

[0053] The learning unit can weight the training data based on user usage during training. For example, the learning unit can weight the training data based on features that the user frequently uses. The learning unit can also weight the training data based on data that the user uses in specific situations. The learning unit can also analyze user usage and perform optimal training data weighting. This improves the accuracy of training by weighting the training data based on usage. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input usage data into a generating AI and have the generating AI perform the training data weighting.

[0054] The learning unit can optimize the learning algorithm during learning by taking into account the user's device information. For example, if the user is using a smartphone, the learning unit optimizes the learning algorithm according to the device's characteristics. If the user is using a tablet, the learning unit can also apply a learning algorithm optimized for a larger screen. If the user is using a smartwatch, the learning unit can also adjust the learning algorithm according to the device's characteristics. This improves the accuracy of learning by optimizing the learning algorithm while considering device information. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input device information data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The speech recognition unit can analyze background noise from the user's speech and optimize noise cancellation. For example, if the user is in a noisy environment, it can analyze the background noise in real time and apply noise cancellation to clearly recognize the speech. If the user is in a quiet environment, it can also analyze the background noise and adjust the intensity of noise cancellation to recognize natural speech. If the user is moving, it can detect changes in background noise in real time and dynamically adjust noise cancellation. This allows for clear recognition of speech by analyzing background noise and optimizing noise cancellation.

[0057] The speech recognition unit can adjust its recognition algorithm according to the user's speaking speed and rhythm. For example, if the user speaks quickly, it can detect the speaking speed in real time and speed up the recognition algorithm accordingly. If the user speaks slowly, it can analyze the rhythm of the speech and optimize the recognition algorithm for accurate recognition. If the user speaks with an irregular rhythm, it can learn the speech patterns and dynamically adjust the recognition algorithm. In this way, the recognition accuracy is improved by adjusting the recognition algorithm according to the speaking speed and rhythm.

[0058] The speech recognition unit can correct dialects and accents based on the user's geographical location information. For example, if the user is in a specific region, it corrects and recognizes the dialect and accent of that region based on the geographical location information. If the user moves to a different region, it can acquire new geographical location information and dynamically correct the dialect and accent. If the user is in an international environment, it can correct and recognize multiple dialects and accents based on the geographical location information. As a result, recognition accuracy is improved by correcting dialects and accents based on geographical location information.

[0059] The speech recognition unit can analyze the user's social media activity and prioritize the recognition of specific terms and phrases. For example, it can analyze and prioritize the recognition of terms and phrases that the user frequently uses on social media. If the user is talking about a specific topic, it can also prioritize the recognition of relevant terms and phrases based on their social media activity. If the user uses new terms or phrases, it can analyze their social media activity in real time and update the recognition algorithm. This improves recognition accuracy by analyzing social media activity and prioritizing the recognition of specific terms and phrases.

[0060] The translation department can select the most appropriate translation by considering the context of the statement. For example, if the user is speaking in a business meeting, it will select formal expressions considering the context. If the user is having a casual conversation, it can also select relaxed expressions considering the context. If the user is talking about a technical topic, it can also appropriately translate technical terms considering the context. This improves the accuracy of the translation by selecting the most appropriate translation based on the context of the statement.

[0061] The translation department can appropriately translate specialized terminology according to the user's field of expertise. For example, if the user is a medical expert, it can appropriately translate medical terminology. If the user is a legal expert, it can appropriately translate legal terminology. If the user is an engineering expert, it can appropriately translate technical terminology. This improves the accuracy of the translation by appropriately translating specialized terminology according to the user's field of expertise.

[0062] The output unit can optimize audio quality according to the acoustic characteristics of the user's device during output. For example, if the user is using a smartphone, the audio quality can be optimized according to the device's speaker characteristics. If the user is using headphones, the audio quality can also be optimized according to the headphones' acoustic characteristics. If the user is using it in a car, the audio quality can also be optimized according to the car's acoustic characteristics. This optimizes audio quality according to the device's acoustic characteristics, resulting in better sound quality.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The speech recognition unit recognizes the user's speech. For example, the speech recognition unit collects the user's voice using a microphone and converts it into text data using speech recognition technology. The speech recognition unit can analyze the voice data using AI and accurately recognize the content of the speech. For example, the speech recognition unit removes background noise using noise cancellation technology to clearly recognize the content of the speech. The speech recognition unit can also adjust the recognition algorithm according to the speed and rhythm of the user's speech. For example, if the user speaks quickly, the speech recognition unit speeds up the recognition algorithm to accommodate this. Step 2: The translation unit translates the speech recognized by the speech recognition unit. The translation unit can use AI to translate text data into other languages. For example, the translation unit can translate what a user says in English into Japanese. The translation unit can also learn the user's language usage patterns to improve translation accuracy. For example, the translation unit can learn frequently used phrases and words from the user and incorporate them into future translations. Step 3: The output unit outputs the audio translated by the translation unit. The output unit can generate audio data using AI and provide it to the user. For example, the output unit can convert the translated text data into audio data using speech synthesis technology and output it through the speaker. The output unit can also optimize the audio quality according to the acoustic characteristics of the user's device. For example, the output unit can adjust the audio quality according to the speaker characteristics of a smartphone. Step 4: The delivery unit provides the user with the audio translated by the translation unit. The delivery unit can use AI to estimate the user's emotions and adjust the delivery method accordingly. For example, if the user is nervous, the delivery unit will deliver the information in a calm manner. The delivery unit can also refer to the user's past usage history to select the optimal delivery timing. For example, if the delivery unit has received information at a specific time in the past, it will deliver the information at that time.

[0065] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that translates a user's voice into another language in real time, supporting global communication. This AI agent system translates a user's voice into another language in real time, supporting global communication. Users can convert their voice into a selected language, enabling real-time conversation. Specifically, it combines speech recognition technology and instant translation technology to instantly translate the user's statements into another language. The AI ​​agent learns from the user's language usage patterns to improve translation accuracy. It is a cloud-based service, offering scalability and ease of access. Target users include those in multilingual communities, professionals conducting international business, and educational institutions that value intercultural exchange. For example, the AI ​​agent system recognizes the user's voice in real time and translates it instantly. For instance, if a user speaks in English, the AI ​​agent system recognizes the speech and instantly translates it into Japanese. Furthermore, the AI ​​agent system learns the user's language usage patterns to improve translation accuracy. For example, it learns frequently used phrases and words and incorporates them into subsequent translations. Because it is a cloud-based service, users can access it from anywhere simply by connecting to the internet. For example, it is envisioned for use in business meetings and international events. This will enable the AI ​​agent system to improve communication speed, enhance language understanding, and expand user participation. The AI ​​agent system can translate user statements in real time, supporting global communication.

[0066] The AI ​​agent system according to this embodiment comprises a speech recognition unit, a translation unit, an output unit, and a provision unit. The speech recognition unit recognizes the user's speech. For example, the speech recognition unit collects the user's speech using a microphone and converts it into text data using speech recognition technology. The speech recognition unit can analyze the speech data using AI and accurately recognize the content of the speech. For example, the speech recognition unit removes background noise using noise cancellation technology to clearly recognize the content of the speech. The speech recognition unit can also adjust its recognition algorithm according to the speed and rhythm of the user's speech. For example, if the user speaks quickly, the speech recognition unit speeds up the recognition algorithm to accommodate this. The translation unit translates the speech recognized by the speech recognition unit. The translation unit can translate the text data into other languages ​​using AI. For example, the translation unit translates what the user says in English into Japanese. The translation unit can also learn the user's language usage patterns to improve translation accuracy. For example, the translation unit learns phrases and words that the user frequently uses and reflects them in subsequent translations. The output unit outputs the speech translated by the translation unit. The output unit can generate audio data using AI and provide it to the user. For example, the output unit converts translated text data into audio data using speech synthesis technology and outputs it through the speaker. The output unit can also optimize the audio quality according to the acoustic characteristics of the user's device. For example, the output unit adjusts the audio quality according to the speaker characteristics of a smartphone. The delivery unit provides the user with the audio translated by the translation unit. The delivery unit can estimate the user's emotions using AI and adjust the delivery method. For example, if the delivery unit is nervous, it will provide the information in a calm manner. The delivery unit can also select the optimal delivery timing by referring to the user's past usage history. For example, if the delivery unit has received information at a specific time in the past, it will provide the information at that time. As a result, the AI ​​agent system according to this embodiment can translate user statements in real time and support global communication.

[0067] The speech recognition unit recognizes the user's speech. For example, the speech recognition unit collects the user's voice using a microphone and converts it into text data using speech recognition technology. Specifically, the speech recognition unit uses a high-sensitivity microphone to clearly collect the user's voice, and the collected voice data is processed using noise cancellation technology to remove background noise. This allows the speech recognition unit to clearly recognize the content of the speech. Furthermore, the speech recognition unit uses AI to analyze the voice data and accurately recognize the content of the speech. The AI ​​uses deep learning technology to extract features from the voice data and identify phonemes and words. For example, the speech recognition unit can adjust its recognition algorithm according to the speed and rhythm of the user's speech. If the user speaks quickly, the recognition algorithm is accelerated to accommodate this, and conversely, if the user speaks slowly, the algorithm is adjusted to ensure accurate recognition. In addition, the speech recognition unit learns from a variety of voice data in advance so that it can handle differences in the user's pronunciation and accent. This allows the speech recognition unit to accurately recognize the speech of users who speak different languages ​​or dialects. Furthermore, the speech recognition unit can process voice data in real time and convert it into text data without delay. This allows users to communicate smoothly.

[0068] The translation unit translates the speech recognized by the speech recognition unit. The translation unit can also translate text data into other languages ​​using AI. Specifically, the translation unit uses neural machine translation (NMT) technology to translate text data with high accuracy. NMT utilizes deep learning to provide natural translations that consider context and meaning. For example, when translating what a user says in English into Japanese, the translation unit selects appropriate words and phrases according to the context. The translation unit can also learn the user's language usage patterns to improve translation accuracy. By learning frequently used phrases and words and incorporating them into subsequent translations, it provides more natural and accurate translations. Furthermore, the translation unit learns relevant data in advance to handle specialized terminology and industry-specific expressions. This enables it to provide highly accurate translations even in business and technical conversations. The translation unit also performs real-time translations, allowing users to continue communicating smoothly. For example, it can instantly translate user statements during meetings or phone conversations and convey them to the other party. In this way, the translation unit supports smooth communication across language barriers.

[0069] The output unit outputs the audio translated by the translation unit. The output unit can generate audio data using AI and provide it to the user. Specifically, the output unit uses text-to-speech (TTS) technology to convert the translated text data into natural-sounding audio. TTS technology utilizes deep learning to generate audio with natural intonation and intonation. For example, the output unit converts the translated text data into audio data and outputs it through the speaker. The output unit can also optimize the audio quality according to the acoustic characteristics of the user's device. For example, it can adjust the audio quality according to the speaker characteristics of a smartphone to provide clear and easy-to-understand audio. Furthermore, the output unit can adjust the tone and speed of the audio according to the user's preferences. For example, if the user prefers a calm tone, it will adjust and generate the audio accordingly. The output unit also supports multiple languages ​​and can output audio in the language selected by the user. This allows the output unit to provide the user with natural and easy-to-understand audio, supporting smooth communication.

[0070] The delivery unit provides users with audio translated by the translation unit. The delivery unit can use AI to estimate the user's emotions and adjust the delivery method accordingly. Specifically, the delivery unit estimates emotions from the user's facial expressions, tone of voice, and content of speech, and delivers information in an appropriate manner. For example, if the user is nervous, the information will be delivered in a calm manner. The AI ​​analyzes the user's emotions in real time using emotion recognition technology and adjusts the delivery method accordingly. The delivery unit can also select the optimal delivery timing by referring to the user's past usage history. For example, if the user has received information at a specific time in the past, the information will be delivered at that time. Furthermore, the delivery unit can customize the information delivery method according to the user's preferences. For example, if the user prefers visual information, the information will be delivered using text and images; if the user prefers auditory information, the information will be delivered via audio. The delivery unit can also collect user feedback and continuously improve the accuracy and effectiveness of the delivery method. This allows the delivery unit to deliver information to users in the most optimal way and improve user satisfaction.

[0071] The AI ​​agent system further includes a learning unit that learns the user's language usage patterns. The learning unit can use AI to learn the user's language usage patterns and improve translation accuracy. For example, the learning unit learns frequently used phrases and words by the user and incorporates them into future translations. The learning unit can also use AI to analyze the user's utterances and extract language usage patterns. For example, if the user frequently uses a particular grammatical structure, the learning unit learns that pattern and improves translation accuracy. The learning unit can also use AI to analyze the tone and rhythm of the user's utterances and learn language usage patterns. For example, if the user speaks in a particular tone, the learning unit learns that tone and improves translation accuracy. In this way, learning the user's language usage patterns improves translation accuracy.

[0072] The speech recognition unit can estimate the user's emotions and adjust the accuracy of speech recognition based on the estimated emotions. For example, if the user is nervous, the speech recognition unit can use an emotion engine to analyze the tone and rhythm of the user's speech to improve recognition accuracy. If the user is relaxed, the speech recognition unit can also use an emotion engine to recognize natural speech and optimize accuracy. If the user is excited, the speech recognition unit can use an emotion engine to handle a fast speaking speed and maintain recognition accuracy. In this way, recognition accuracy is improved by adjusting the accuracy of speech recognition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input user speech data into a generative AI and have the generative AI perform emotion estimation.

[0073] The speech recognition unit can analyze background noise in response to the user's speech and optimize noise cancellation. For example, if the user is in a noisy environment, the speech recognition unit can analyze the background noise in real time and apply noise cancellation to clearly recognize the speech. If the user is in a quiet environment, the speech recognition unit can also analyze the background noise and adjust the noise cancellation intensity to recognize natural speech. If the user is moving, the speech recognition unit can also detect changes in background noise in real time and dynamically adjust noise cancellation. This allows for clear recognition of speech by analyzing background noise and optimizing noise cancellation. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input background noise data into a generating AI and have the generating AI perform noise cancellation optimization.

[0074] The speech recognition unit can adjust its recognition algorithm according to the user's speaking speed and rhythm during speech recognition. For example, if the user speaks quickly, the speech recognition unit can detect the speaking speed in real time and speed up the recognition algorithm accordingly. If the user speaks slowly, the speech recognition unit can also analyze the rhythm of the speech and optimize the recognition algorithm for accurate recognition. If the user speaks with an irregular rhythm, the speech recognition unit can learn the speech pattern and dynamically adjust the recognition algorithm. This improves recognition accuracy by adjusting the recognition algorithm according to the speaking speed and rhythm. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input speech speed data into a generating AI and have the generating AI perform the adjustment of the recognition algorithm.

[0075] The speech recognition unit can estimate the user's emotions and determine the priority of speech recognition based on the estimated emotions. For example, if the user is in an urgent situation, the speech recognition unit can use the emotion engine to estimate the user's emotions and prioritize the recognition of their speech. If the user is relaxed, the speech recognition unit can also use the emotion engine to recognize speech with normal priority. If the user is agitated, the speech recognition unit can use the emotion engine to determine the importance of speech and adjust the priority. This allows important speech to be recognized preferentially by determining the priority of speech recognition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input user speech data into a generative AI and have the generative AI perform emotion estimation.

[0076] The speech recognition unit can correct dialects and accents based on the user's geographical location information during speech recognition. For example, if the user is in a specific region, the speech recognition unit corrects the dialect and accent of that region based on the geographical location information. If the user moves to a different region, the speech recognition unit can acquire new geographical location information and dynamically correct the dialect and accent. If the user is in an international environment, the speech recognition unit can correct multiple dialects and accents based on the geographical location information. This improves recognition accuracy by correcting dialects and accents based on geographical location information. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can input geographical location data into a generating AI and have the generating AI perform the dialect and accent correction.

[0077] The speech recognition unit can analyze the user's social media activity during speech recognition and prioritize the recognition of specific terms and phrases. For example, the speech recognition unit can analyze and prioritize the recognition of terms and phrases that the user frequently uses on social media. If the user is talking about a specific topic, the speech recognition unit can also prioritize the recognition of relevant terms and phrases based on their social media activity. If the user uses new terms or phrases, the speech recognition unit can also analyze their social media activity in real time and update their recognition algorithm. This improves recognition accuracy by analyzing social media activity and prioritizing the recognition of specific terms and phrases. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or not. For example, the speech recognition unit can input social media data into a generating AI and have the generating AI perform the priority recognition of specific terms and phrases.

[0078] The translation unit can estimate the user's emotions and adjust the translation's expression based on the estimated emotions. For example, if the user is angry, the translation unit can use an emotion engine to select an expression that softens the emotion. If the user is sad, the translation unit can also use an emotion engine to select a gentle expression. If the user is happy, the translation unit can also use an emotion engine to select a cheerful expression. By adjusting the translation's expression according to the user's emotions, a more appropriate translation is provided. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input user utterance data into a generative AI and have the generative AI perform emotion estimation.

[0079] The translation unit can select the most appropriate translation by considering the context of the statement during the translation process. For example, if the user is speaking in a business meeting, the translation unit will select formal expressions considering the context. If the user is having a casual conversation, the translation unit can also select relaxed expressions considering the context. If the user is talking about a technical topic, the translation unit can also appropriately translate technical terms considering the context. This improves the accuracy of the translation by selecting the most appropriate translation by considering the context of the statement. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input contextual data of the statement into a generating AI and have the generating AI perform the selection of the most appropriate translation.

[0080] The translation unit can appropriately translate specialized terminology according to the user's field of expertise during translation. For example, if the user is a medical expert, the translation unit will appropriately translate medical terminology. If the user is a legal expert, the translation unit can also appropriately translate legal terminology. If the user is an engineering expert, the translation unit can also appropriately translate technical terminology. This improves the accuracy of the translation by appropriately translating specialized terminology according to the user's field of expertise. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input specialized terminology data into a generating AI and have the generating AI perform the translation of the specialized terminology.

[0081] The translation unit can estimate the user's emotions and adjust the tone of the translation based on the estimated emotions. For example, if the user is angry, the translation unit can use an emotion engine to soften the tone. If the user is sad, the translation unit can also use an emotion engine to make the tone gentler. If the user is happy, the translation unit can also use an emotion engine to make the tone brighter. By adjusting the tone of the translation according to the user's emotions, a more appropriate translation is provided. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input user speech data into a generative AI and have the generative AI perform emotion estimation.

[0082] The translation unit can provide consistent translations by referring to the user's past translation history during the translation process. For example, the translation unit can refer to translation expressions previously used by the user to provide consistent translations. The translation unit can also consistently use certain terms if the user has used them in the past. The translation unit can also refer to contexts in which the user has previously translated and provide consistent translations in similar contexts. This improves translation accuracy by providing consistent translations by referring to past translation history. Some or all of the above processes in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input past translation history data into a generating AI and have the generating AI perform consistent translations.

[0083] The translation unit can select appropriate expressions while considering the user's cultural background during translation. For example, if the user belongs to a specific cultural sphere, the translation unit will select expressions appropriate to that culture. If the user is speaking with someone from a different cultural sphere, the translation unit can also select appropriate expressions considering both cultures. If the user is speaking in an international setting, the translation unit can also select culturally neutral expressions. By selecting appropriate expressions while considering cultural background, the accuracy of the translation is improved. Some or all of the above processing in the translation unit may be performed using AI, for example, or not using AI. For example, the translation unit can input cultural background data into a generating AI and have the generating AI perform the selection of appropriate expressions.

[0084] The output unit can estimate the user's emotions and adjust the tone of the output voice based on the estimated user emotions. For example, if the user is tense, the output unit can use an emotion engine to output voice in a calm tone. If the user is relaxed, the output unit can also use an emotion engine to output voice in a natural tone. If the user is excited, the output unit can also use an emotion engine to output voice in a bright tone. By adjusting the tone of the output voice according to the user's emotions, a more appropriate voice is provided. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input user emotion data into a generative AI and have the generative AI adjust the tone of the output voice.

[0085] The output unit can optimize the audio quality according to the acoustic characteristics of the user's device when outputting. For example, if the user is using a smartphone, the output unit can optimize the audio quality according to the speaker characteristics of the device. If the user is using headphones, the output unit can also optimize the audio quality according to the acoustic characteristics of the headphones. If the user is using the device in a car, the output unit can also optimize the audio quality according to the acoustic characteristics of the car. This provides better audio by optimizing the audio quality according to the acoustic characteristics of the device. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the device's acoustic characteristic data into a generating AI and have the generating AI perform the optimization of the audio quality.

[0086] The output unit can adjust the frequency band of the audio based on the user's auditory characteristics during output. For example, if the user has difficulty hearing high frequencies, the output unit can adjust the frequency band of the audio to emphasize the high frequencies. If the user has difficulty hearing low frequencies, the output unit can also adjust the frequency band of the audio to emphasize the low frequencies. If the user is sensitive to a particular frequency band, the output unit can adjust that frequency band to provide a more comfortable audio experience. In this way, by adjusting the frequency band of the audio based on auditory characteristics, a more appropriate audio is provided. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's auditory characteristics data into a generating AI and have the generating AI perform the adjustment of the audio frequency band.

[0087] The output unit can estimate the user's emotions and adjust the speed of the output audio based on the estimated emotions. For example, if the user is in a hurry, the output unit can use the emotion engine to speed up the audio. If the user is relaxed, the output unit can also use the emotion engine to maintain a normal audio speed. If the user is tired, the output unit can also use the emotion engine to slow down the audio speed. This allows for more appropriate audio to be provided by adjusting the speed of the output audio according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input user emotion data into a generative AI and have the generative AI adjust the speed of the output audio.

[0088] The output unit can analyze the user's ambient noise and set the optimal volume when outputting. For example, if the user is in a noisy environment, the output unit can analyze the ambient noise and automatically increase the volume. If the user is in a quiet environment, the output unit can also analyze the ambient noise and automatically decrease the volume. If the user is moving, the output unit can analyze changes in ambient noise in real time and dynamically adjust the volume. This allows for more appropriate audio to be provided by analyzing ambient noise and setting the optimal volume. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input ambient noise data into a generating AI and have the generating AI set the optimal volume.

[0089] The output unit can apply a power-saving mode when outputting, taking into account the battery status of the user's device. For example, if the battery of the user's device is low, the output unit will apply a power-saving mode to optimize audio output. The output unit can also output audio in normal mode when the user's device is charging. The output unit can also monitor the battery status of the user's device in real time and apply a power-saving mode as needed. This allows for extending battery life by applying a power-saving mode while considering the device's battery status. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input battery status data to a generating AI and have the generating AI execute the application of a power-saving mode.

[0090] The information delivery unit can estimate the user's emotions and adjust the delivery method based on the estimated emotions. For example, if the user is tense, the information delivery unit can use an emotion engine to deliver information in a calm manner. If the user is relaxed, the information delivery unit can also use an emotion engine to deliver information in a natural manner. If the user is excited, the information delivery unit can also use an emotion engine to deliver information in a cheerful manner. This allows for more appropriate information delivery by adjusting the delivery method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or without AI. For example, the information delivery unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the delivery method.

[0091] The service provider can select the optimal delivery timing by referring to the user's past usage history at the time of delivery. For example, if the service provider has received information during a specific time period in the past, it will provide the information during that time period. If the service provider has received information under specific circumstances in the past, it can also provide the information under similar circumstances. The service provider can also analyze the user's past usage history and select the optimal delivery timing. By selecting the optimal delivery timing by referring to past usage history, information can be provided to the user at the most opportune time. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input past usage history data into a generating AI and have the generating AI select the optimal delivery timing.

[0092] The information delivery unit can customize the delivery method according to the user's current activity status at the time of delivery. For example, if the user is exercising, the information delivery unit can provide information via voice. If the user is working, the information delivery unit can also provide information via text. If the user is resting, the information delivery unit can also provide information via visuals. In this way, by customizing the delivery method according to the current activity status, information can be delivered in the most optimal way for the user. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or without AI. For example, the information delivery unit can input current activity status data into a generating AI and have the generating AI perform the customization of the delivery method.

[0093] The service provider can estimate the user's emotions and determine the priority of the content offered based on the estimated emotions. For example, if the user is in an urgent situation, the service provider can use the emotion engine to prioritize important information. If the user is relaxed, the service provider can also use the emotion engine to provide information with normal priority. If the user is agitated, the service provider can use the emotion engine to adjust the priority of information according to its importance. This allows for the priority of important information to be provided by determining the priority of the content offered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI determine the priority of the content offered.

[0094] The information delivery unit can select the optimal delivery method at the time of delivery, taking into account the user's device information. For example, if the user is using a smartphone, the information delivery unit can provide information according to the characteristics of the device. If the user is using a tablet, the information delivery unit can also provide information optimized for a larger screen. If the user is using a smartwatch, the information delivery unit can also provide concise and highly visible information. In this way, by selecting the optimal delivery method considering device information, information can be delivered in the most optimal way for the user. Some or all of the above processing in the information delivery unit may be performed using AI, for example, or without AI. For example, the information delivery unit can input device information data into a generating AI and have the generating AI select the optimal delivery method.

[0095] The data delivery unit can optimize the efficiency of data transfer by considering the user's network conditions at the time of delivery. For example, if the user is connected to a high-speed network, the data delivery unit can deliver high-quality data quickly. If the user is connected to a low-speed network, the data delivery unit can also compress the data and deliver it efficiently. The data delivery unit can also monitor the user's network conditions in real time and select the optimal data transfer method. This enables efficient information delivery by optimizing the efficiency of data transfer by considering the network conditions. Some or all of the above processing in the data delivery unit may be performed using AI, for example, or without AI. For example, the data delivery unit can input network condition data into a generating AI and have the generating AI perform the optimization of data transfer efficiency.

[0096] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is relaxed, the learning unit can use an emotion engine to select statements made in a relaxed state as training data. If the user is tense, the learning unit can also use an emotion engine to select statements made in a tense state as training data. If the user is excited, the learning unit can also use an emotion engine to select statements made in an excited state as training data. This improves the accuracy of learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0097] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal learning algorithm. The learning unit can also adjust the learning algorithm based on patterns obtained from past learning data. The learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. As a result, the accuracy of learning is improved by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0098] The learning unit can update the learning content by reflecting user feedback during the learning process. For example, the learning unit can collect user feedback and incorporate it into the learning content. The learning unit can also adjust the learning algorithm based on user feedback. The learning unit can also analyze user feedback and optimize the learning content. This improves the accuracy of learning by updating the learning content in accordance with user feedback. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user feedback data into a generating AI and have the generating AI perform the update of the learning content.

[0099] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is relaxed, the learning unit can use the emotion engine to maintain a normal learning frequency. If the user is stressed, the learning unit can also use the emotion engine to reduce the learning frequency. If the user is excited, the learning unit can also use the emotion engine to increase the learning frequency. This improves learning efficiency by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI adjust the learning frequency.

[0100] The learning unit can weight the training data based on user usage during training. For example, the learning unit can weight the training data based on features that the user frequently uses. The learning unit can also weight the training data based on data that the user uses in specific situations. The learning unit can also analyze user usage and perform optimal training data weighting. This improves the accuracy of training by weighting the training data based on usage. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input usage data into a generating AI and have the generating AI perform the training data weighting.

[0101] The learning unit can optimize the learning algorithm during learning by taking into account the user's device information. For example, if the user is using a smartphone, the learning unit optimizes the learning algorithm according to the device's characteristics. If the user is using a tablet, the learning unit can also apply a learning algorithm optimized for a larger screen. If the user is using a smartwatch, the learning unit can also adjust the learning algorithm according to the device's characteristics. This improves the accuracy of learning by optimizing the learning algorithm while considering device information. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input device information data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0102] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0103] The speech recognition unit can analyze background noise from the user's speech and optimize noise cancellation. For example, if the user is in a noisy environment, it can analyze the background noise in real time and apply noise cancellation to clearly recognize the speech. If the user is in a quiet environment, it can also analyze the background noise and adjust the intensity of noise cancellation to recognize natural speech. If the user is moving, it can detect changes in background noise in real time and dynamically adjust noise cancellation. This allows for clear recognition of speech by analyzing background noise and optimizing noise cancellation.

[0104] The speech recognition unit can adjust its recognition algorithm according to the user's speaking speed and rhythm. For example, if the user speaks quickly, it can detect the speaking speed in real time and speed up the recognition algorithm accordingly. If the user speaks slowly, it can analyze the rhythm of the speech and optimize the recognition algorithm for accurate recognition. If the user speaks with an irregular rhythm, it can learn the speech patterns and dynamically adjust the recognition algorithm. In this way, the recognition accuracy is improved by adjusting the recognition algorithm according to the speaking speed and rhythm.

[0105] The speech recognition unit can correct dialects and accents based on the user's geographical location information. For example, if the user is in a specific region, it corrects and recognizes the dialect and accent of that region based on the geographical location information. If the user moves to a different region, it can acquire new geographical location information and dynamically correct the dialect and accent. If the user is in an international environment, it can correct and recognize multiple dialects and accents based on the geographical location information. As a result, recognition accuracy is improved by correcting dialects and accents based on geographical location information.

[0106] The speech recognition unit can analyze the user's social media activity and prioritize the recognition of specific terms and phrases. For example, it can analyze and prioritize the recognition of terms and phrases that the user frequently uses on social media. If the user is talking about a specific topic, it can also prioritize the recognition of relevant terms and phrases based on their social media activity. If the user uses new terms or phrases, it can analyze their social media activity in real time and update the recognition algorithm. This improves recognition accuracy by analyzing social media activity and prioritizing the recognition of specific terms and phrases.

[0107] The speech recognition unit can estimate the user's emotions and determine the priority of speech recognition based on the estimated emotions. For example, if the user is in an urgent situation, the emotion engine can be used to estimate the user's emotions and prioritize the recognition of their speech. If the user is relaxed, the emotion engine can be used to recognize speech with the normal priority. If the user is agitated, the emotion engine can be used to determine the importance of their speech and adjust the priority accordingly. This allows important speech to be recognized preferentially by determining the priority of speech recognition according to the user's emotions.

[0108] The translation unit can estimate the user's emotions and adjust the translation's expression based on those emotions. For example, if the user is angry, the emotion engine can be used to select an expression that softens the emotion. If the user is sad, the emotion engine can be used to select a gentler expression. If the user is happy, the emotion engine can be used to select a cheerful expression. By adjusting the translation's expression according to the user's emotions, a more appropriate translation can be provided.

[0109] The translation department can select the most appropriate translation by considering the context of the statement. For example, if the user is speaking in a business meeting, it will select formal expressions considering the context. If the user is having a casual conversation, it can also select relaxed expressions considering the context. If the user is talking about a technical topic, it can also appropriately translate technical terms considering the context. This improves the accuracy of the translation by selecting the most appropriate translation based on the context of the statement.

[0110] The translation department can appropriately translate specialized terminology according to the user's field of expertise. For example, if the user is a medical expert, it can appropriately translate medical terminology. If the user is a legal expert, it can appropriately translate legal terminology. If the user is an engineering expert, it can appropriately translate technical terminology. This improves the accuracy of the translation by appropriately translating specialized terminology according to the user's field of expertise.

[0111] The output unit can estimate the user's emotions and adjust the tone of the output voice based on those emotions. For example, if the user is tense, the emotion engine can be used to output a calm tone of voice. If the user is relaxed, the emotion engine can be used to output a natural tone of voice. If the user is excited, the emotion engine can be used to output a bright tone of voice. By adjusting the tone of the output voice according to the user's emotions, a more appropriate voice can be provided.

[0112] The output unit can optimize audio quality according to the acoustic characteristics of the user's device during output. For example, if the user is using a smartphone, the audio quality can be optimized according to the device's speaker characteristics. If the user is using headphones, the audio quality can also be optimized according to the headphones' acoustic characteristics. If the user is using it in a car, the audio quality can also be optimized according to the car's acoustic characteristics. This optimizes audio quality according to the device's acoustic characteristics, resulting in better sound quality.

[0113] The following briefly describes the processing flow for example form 2.

[0114] Step 1: The speech recognition unit recognizes the user's speech. For example, the speech recognition unit collects the user's voice using a microphone and converts it into text data using speech recognition technology. The speech recognition unit can analyze the voice data using AI and accurately recognize the content of the speech. For example, the speech recognition unit removes background noise using noise cancellation technology to clearly recognize the content of the speech. The speech recognition unit can also adjust the recognition algorithm according to the speed and rhythm of the user's speech. For example, if the user speaks quickly, the speech recognition unit speeds up the recognition algorithm to accommodate this. Step 2: The translation unit translates the speech recognized by the speech recognition unit. The translation unit can use AI to translate text data into other languages. For example, the translation unit can translate what a user says in English into Japanese. The translation unit can also learn the user's language usage patterns to improve translation accuracy. For example, the translation unit can learn frequently used phrases and words from the user and incorporate them into future translations. Step 3: The output unit outputs the audio translated by the translation unit. The output unit can generate audio data using AI and provide it to the user. For example, the output unit can convert the translated text data into audio data using speech synthesis technology and output it through the speaker. The output unit can also optimize the audio quality according to the acoustic characteristics of the user's device. For example, the output unit can adjust the audio quality according to the speaker characteristics of a smartphone. Step 4: The delivery unit provides the user with the audio translated by the translation unit. The delivery unit can use AI to estimate the user's emotions and adjust the delivery method accordingly. For example, if the user is nervous, the delivery unit will deliver the information in a calm manner. The delivery unit can also refer to the user's past usage history to select the optimal delivery timing. For example, if the delivery unit has received information at a specific time in the past, it will deliver the information at that time.

[0115] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0116] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0117] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements described above, including the speech recognition unit, translation unit, output unit, providing unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the speech recognition unit collects the user's speech using the microphone 38B of the smart device 14 and converts the speech data into text data using the control unit 46A. The translation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and translates the text data recognized by the speech recognition unit into another language. The output unit outputs the translated speech using, for example, the speaker 40B of the smart device 14. The providing unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and estimates the user's emotions and provides information in an appropriate manner. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and learns the user's language usage patterns to improve translation accuracy. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0119] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0120] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0121] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0122] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0125] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0126] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0127] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0128] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0129] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0131] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0133] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the speech recognition unit, translation unit, output unit, providing unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the speech recognition unit collects the user's speech using the microphone 238 of the smart glasses 214 and converts the speech data into text data using the control unit 46A. The translation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and translates the text data recognized by the speech recognition unit into another language. The output unit outputs the translated speech using, for example, the speaker 240 of the smart glasses 214. The providing unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and estimates the user's emotions and provides information in an appropriate manner. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and learns the user's language usage patterns to improve translation accuracy. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0135] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0136] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0143] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the speech recognition unit, translation unit, output unit, providing unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the speech recognition unit collects the user's speech using the microphone 238 of the headset terminal 314 and converts the speech data into text data using the control unit 46A. The translation unit is implemented in the specific processing unit 290 of the data processing unit 12 and translates the text data recognized by the speech recognition unit into another language. The output unit outputs the translated speech using the speaker 240 of the headset terminal 314. The providing unit is implemented in the specific processing unit 290 of the data processing unit 12 and estimates the user's emotions and provides information in an appropriate manner. The learning unit is implemented in the specific processing unit 290 of the data processing unit 12 and learns the user's language usage patterns to improve translation accuracy. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0151] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0152] As shown in Figure 7, the 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.

[0153] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0154] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0155] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0157] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0158] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0159] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0160] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0161] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0162] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0163] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0164] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0165] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0166] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0167] Each of the multiple elements described above, including the speech recognition unit, translation unit, output unit, providing unit, and learning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the speech recognition unit collects user speech using the microphone 238 of the robot 414 and converts the speech data into text data using the control unit 46A. The translation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and translates the text data recognized by the speech recognition unit into another language. The output unit outputs the translated speech using, for example, the speaker 240 of the robot 414. The providing unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and estimates the user's emotions and provides information in an appropriate manner. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and learns the user's language usage patterns to improve translation accuracy. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0168] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0169] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0170] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0171] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0172] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0173] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0174] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0175] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0176] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0177] 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.

[0178] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0179] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0180] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0181] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0182] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0183] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0184] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0185] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0186] (Note 1) A speech recognition unit that recognizes the user's speech, A translation unit that translates the speech recognized by the speech recognition unit, An output unit that outputs the audio translated by the translation unit, The system comprises a providing unit that provides the user with the audio translated by the translation unit. A system characterized by the following features. (Note 2) It also includes a learning unit that learns the user's language usage patterns. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned speech recognition unit, Analyzes background noise from the user's speech and optimizes noise cancellation. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned speech recognition unit, During speech recognition, the recognition algorithm is adjusted according to the speed and rhythm of the user's speech. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned speech recognition unit, It estimates the user's emotions and determines the priority of speech recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned speech recognition unit, During speech recognition, dialect and accent correction is performed based on the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned speech recognition unit, During speech recognition, the system analyzes the user's social media activity and prioritizes the recognition of specific terms and phrases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned translation department, It estimates the user's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned translation department, When translating, the most appropriate translation is selected by considering the context of the statement. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned translation department, During translation, technical terms are translated appropriately according to the user's area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned translation department, It estimates the user's emotions and adjusts the tone of the translation based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned translation department, During translation, the system references the user's past translation history to provide consistent translations. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned translation department, When translating, select appropriate expressions while considering the user's cultural background. The system described in Appendix 1, characterized by the features described herein. (Note 15) The output unit is, It estimates the user's emotions and adjusts the tone of the output voice based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The output unit is, During output, the audio quality is optimized according to the acoustic characteristics of the user's device. The system described in Appendix 1, characterized by the features described herein. (Note 17) The output unit is, During output, the audio frequency range is adjusted based on the user's auditory characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 18) The output unit is, It estimates the user's emotions and adjusts the output audio speed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The output unit is, When outputting, the system analyzes the user's ambient noise and sets the optimal volume. The system described in Appendix 1, characterized by the features described herein. (Note 20) The output unit is, When outputting, a power-saving mode is applied considering the battery status of the user's device. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, It estimates the user's emotions and adjusts the delivery method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When providing the service, the optimal timing for delivery is selected by referring to the user's past usage history. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing the service, the delivery method will be customized according to the user's current activity status. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the content offered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing the service, the optimal delivery method will be selected, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the service, the efficiency of data transfer is optimized considering the user's network conditions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned learning unit, During the learning process, the learning content is updated to reflect user feedback. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the training data is weighted based on user usage. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned learning unit, During training, the learning algorithm is optimized by taking into account the user's device information. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0187] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A speech recognition unit that recognizes the user's speech, A translation unit that translates the speech recognized by the speech recognition unit, An output unit that outputs the audio translated by the translation unit, The system comprises a providing unit that provides the user with the audio translated by the translation unit. A system characterized by the following features.

2. It also includes a learning unit that learns the user's language usage patterns. The system according to feature 1.

3. The aforementioned speech recognition unit, It estimates the user's emotions and adjusts the accuracy of speech recognition based on the estimated emotions. The system according to feature 1.

4. The aforementioned speech recognition unit, Analyzes background noise from the user's speech and optimizes noise cancellation. The system according to feature 1.

5. The aforementioned speech recognition unit, During speech recognition, the recognition algorithm is adjusted according to the speed and rhythm of the user's speech. The system according to feature 1.

6. The aforementioned speech recognition unit, It estimates the user's emotions and determines the priority of speech recognition based on the estimated emotions. The system according to feature 1.

7. The aforementioned speech recognition unit, During speech recognition, dialect and accent correction is performed based on the user's geographical location information. The system according to feature 1.

8. The aforementioned speech recognition unit, During speech recognition, the system analyzes the user's social media activity and prioritizes the recognition of specific terms and phrases. The system according to feature 1.

9. The aforementioned translation department, It estimates the user's emotions and adjusts the translation's expression based on those estimated emotions. The system according to feature 1.

10. The aforementioned translation department, When translating, the most appropriate translation is selected by considering the context of the statement. The system according to feature 1.

Images