system

Abstract

The system according to the embodiment aims to realize voice recognition that supports a variety of dialects, enabling elderly people to operate IT devices by voice. [Solution] A system according to an embodiment includes a collection unit, a learning unit, a recognition unit, and an operation unit. The collection unit collects voice data. The learning unit learns the voice data collected by the collection unit. The recognition unit recognizes voice based on the results of learning by the learning unit. The operation unit performs an operation based on the voice recognized by the recognition unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to create a voice recognition system that could handle a variety of dialects, and there was a problem that elderly people in particular found it inconvenient when operating IT devices.

[0005] The system according to the embodiment aims to realize voice recognition that supports a variety of dialects, enabling elderly people to operate IT devices by voice. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a learning unit, a recognition unit, and an operation unit. The collection unit collects voice data. The learning unit learns the voice data collected by the collection unit. The recognition unit recognizes voice based on the results of learning by the learning unit. The operation unit performs an operation based on the voice recognized by the recognition unit. [Effects of the Invention]

[0007] The system according to the embodiment realizes voice recognition that supports a variety of dialects, enabling elderly people to operate IT devices by voice. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The voice recognition system according to an embodiment of the present invention allows elderly people to operate IT devices entirely through voice recognition alone. The voice recognition system aims to support all Japanese dialects, initially training the system on the Tsugaru dialect to facilitate practical use of voice recognition. For example, the voice recognition system collects voice data in the Tsugaru dialect, and a generation AI learns from that voice data. The voice recognition system then uses the trained generation AI to practically recognize Tsugaru dialect. For example, when an elderly person speaks to an IT device in Tsugaru dialect, the generation AI recognizes the voice and performs appropriate operations. Furthermore, after practical use of Tsugaru dialect voice recognition, the voice recognition system will expand its support to other dialects. For example, to support dialects in other regions, such as Kansai dialect and Hakata dialect, voice data will be collected using a similar method and the generation AI will be trained. This will enable voice recognition that supports dialects across Japan, allowing elderly people to operate IT devices in their native dialect, regardless of where they live. This significantly reduces the hurdles for elderly people to operate IT devices themselves. For example, voice recognition systems can be easily operated by elderly people who have limited vision or hand movements. Furthermore, dialect support allows users to use the system in their natural language, making it stress-free. This will improve the quality of life for the elderly and promote the widespread use of IT devices in a super-aging society.

[0029] A speech recognition system according to an embodiment includes a collection unit, a learning unit, a recognition unit, and an operation unit. The collection unit collects speech data. The speech data includes, for example, an audio file format, a sampling rate, a bit rate, and the like, but is not limited to these examples. The collection unit collects a variety of speech data, for example, including the characteristic pronunciation and vocabulary of Tsugaru dialect. The collection unit can also collect speech data of other regional dialects, such as Kansai dialect and Hakata dialect. For example, the collection unit collects speech data from various situations, such as everyday conversations and conversations in specific situations. The learning unit uses a generation AI to learn the speech data collected by the collection unit. The learning is performed based on, for example, a machine learning algorithm used and the type of training data, but is not limited to these examples. For example, the learning unit uses the generation AI to learn everyday conversations and conversations in specific situations. The learning unit can also learn speech data of other regional dialects using the generation AI. The recognition unit recognizes speech based on the results of learning by the learning unit. Recognition is performed based on, for example, a speech recognition algorithm, recognition accuracy, and tolerance for misrecognition, but is not limited to, such examples. For example, the recognition unit recognizes speech spoken by an elderly person to an IT device in Tsugaru dialect. The recognition unit can also recognize speech spoken by users of a specific age group to an IT device. The operation unit performs an operation based on the speech recognized by the recognition unit. The operation is performed based on, for example, the device to be operated, the type of operation, and the accuracy of the operation, but is not limited to such examples. For example, the operation unit operates the IT device based on the recognized speech. As a result, the speech recognition system according to the embodiment can perform a consistent process from collecting speech data to learning, recognition, and operation. For example, the speech recognition system allows elderly people to complete operations using only their voice. Furthermore, to support dialects in other regions, the speech recognition system can collect speech data using a similar method and train the generation AI. As a result, the speech recognition system can recognize speech that supports dialects across the country.

[0030] The collection unit can collect multiple pieces of speech data including characteristic pronunciation and vocabulary of the Tsugaru dialect. The characteristic pronunciation and vocabulary of the Tsugaru dialect include, for example, specific words and phrases, pronunciation features, etc., but are not limited to these examples. For example, to collect Tsugaru dialect speech data, the collection unit collects everyday conversations and conversations in specific situations. The collection unit can also collect speech data from local residents to collect Tsugaru dialect speech data. For example, the collection unit collects speech data at local events and gatherings. The collection unit can also collect speech data from the Internet to collect Tsugaru dialect speech data. For example, the collection unit collects video and audio files including Tsugaru dialect speech data. By collecting Tsugaru dialect speech data, dialect-specific speech recognition becomes possible.

[0031] The learning unit can train the generation AI on everyday conversations and conversations in specific situations. Examples of everyday conversations and specific situations include, but are not limited to, situations such as shopping, hospitals, and schools. For example, the learning unit trains the generation AI on voice data of everyday conversations. The learning unit can also train the generation AI on voice data in specific situations. For example, the learning unit trains the generation AI on conversations in hospitals and conversations in schools. The learning unit can also preprocess the voice data so that the generation AI can train on voice data of everyday conversations and specific situations. For example, the learning unit removes noise from the voice data and inputs clear voice data into the generation AI. This improves the accuracy of voice recognition by learning voice data from a variety of situations.

[0032] The recognition unit can recognize speech spoken to IT devices in Tsugaru dialect by users of a specific age group. Examples of specific age groups include, but are not limited to, elderly people, children, and young people. The recognition unit can also recognize speech spoken to IT devices in Tsugaru dialect by elderly people. The recognition unit can also recognize speech spoken to IT devices by children. For example, the recognition unit can learn the characteristics of children's voices to improve recognition accuracy. The recognition unit can also recognize speech spoken to IT devices by young people. For example, the recognition unit can learn slang and unique expressions used by young people to improve recognition accuracy. As a result, by recognizing speech spoken in Tsugaru dialect, elderly people can operate IT devices in their usual dialect.

[0033] The operation unit can operate IT devices based on the recognized voice. Examples of IT devices include, but are not limited to, smartphones, tablets, and personal computers. For example, the operation unit can operate a smartphone based on the recognized voice. The operation unit can also operate a tablet based on the recognized voice. For example, the operation unit can launch an application based on a voice command. The operation unit can also operate a personal computer based on the recognized voice. For example, the operation unit can open a file based on a voice command. In this way, by operating IT devices based on the recognized voice, elderly people can complete operations using only voice.

[0034] The collection unit can collect speech data of Kansai dialect, Hakata dialect, and dialects of other regions. Kansai dialect, Hakata dialect, and dialects of other regions include, for example, specific words, phrases, pronunciation features, etc., but are not limited to these examples. The collection unit, for example, collects speech data of Kansai dialect. The collection unit can also collect speech data of Hakata dialect. For example, the collection unit collects speech data from local residents. The collection unit can also collect speech data of dialects of other regions. For example, the collection unit collects speech data of Tohoku dialect and Kyushu dialect. In this way, by collecting speech data of dialects of other regions, speech recognition compatible with dialects across the country becomes possible.

[0035] The learning unit can use the generation AI to learn speech data in dialects of other regions. Dialects of other regions include, but are not limited to, Tohoku dialect and Kyushu dialect. For example, the learning unit uses the generation AI to learn speech data in Tohoku dialect. The learning unit can also use the generation AI to learn speech data in Kyushu dialect. For example, the learning unit uses the generation AI to learn speech data collected from local residents. The learning unit can also preprocess the speech data so that the generation AI can learn speech data in dialects of other regions. For example, the learning unit removes noise from the speech data and inputs clear speech data into the generation AI. In this way, by learning speech data in dialects of other regions, speech recognition compatible with dialects across the country becomes possible.

[0036] When collecting voice data, the collection unit can analyze the user's past speech history and select an appropriate collection method. For example, the collection unit prioritizes collection of phrases the user has frequently used in the past. The collection unit can also analyze the user's speech patterns and collect data at the most natural timing. For example, the collection unit adjusts the collection method taking into account the characteristics of the dialect the user has used in the past. This allows the optimal collection method to be selected by analyzing the past speech history. Some or all of the above-described processing in the collection unit can be performed using, for example, AI. For example, the collection unit can input the user's past speech data into a generation AI and have the generation AI select the optimal collection method. Furthermore, the collection unit can accumulate the user's speech history and analyze long-term speech patterns. For example, the collection unit can analyze the user's speech data chronologically to identify patterns of change in speech. The collection unit can also provide individual collection methods based on the user's speech history. For example, the collection unit can suggest the optimal collection device and timing depending on the user's speech characteristics. This allows the collection unit to grasp the user's past speech history in detail and optimize the collection method.

[0037] When collecting voice data, the collection unit can filter the voice data based on the user's current living situation and areas of interest. For example, the collection unit prioritizes collecting voice data of the user speaking at home. The collection unit can also collect voice data related to topics of interest to the user. For example, the collection unit collects voice data at optimal times in accordance with the user's daily rhythm. This allows for filtering based on the user's living situation and areas of interest, thereby collecting more relevant voice data. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's living situation data into the generation AI and cause the generation AI to select the optimal collection timing. Furthermore, the collection unit can analyze the user's areas of interest in real time and filter the collected data. For example, the collection unit can analyze the user's social media activity and search history to prioritize collecting voice data related to the areas of interest. The collection unit can also determine the priority of collected data based on the user's living situation. For example, the collection unit can suggest the optimal collection device and timing based on the user's occupation and home environment. This allows the collection unit to gain a detailed understanding of the user's current living situation and areas of interest, and optimize the collected data.

[0038] When collecting voice data, the collection unit can select an appropriate collection means depending on the user's input method. For example, when the user uses voice input, the collection unit prioritizes collecting voice data. Furthermore, when the user uses text input, the collection unit can convert text data into voice data and collect it. For example, when the user uses image input, the collection unit generates and collects related voice data from the image. This allows for efficient collection of voice data by selecting the optimal collection means depending on the user's input method. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's input data into a generation AI and cause the generation AI to select the optimal collection means. Furthermore, the collection unit can analyze the user's input method in real time and select the collection means. For example, the collection unit can analyze the user's input history and suggest the optimal collection means. The collection unit can also automatically adjust the settings of the collection device depending on the user's input method. For example, the collection unit adjusts the microphone sensitivity for voice input and optimizes the keyboard settings for text input. This allows the collection unit to grasp the user's input method in detail and optimize the collection means.

[0039] When collecting voice data, the collection unit can prioritize collection of highly relevant data based on the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collection of voice data related to the dialect of that area. Furthermore, when the user is traveling, the collection unit can also collect voice data related to the dialect of the place the user is visiting. For example, when the user is at home, the collection unit prioritizes collection of voice data of the dialect used at home. This allows highly relevant voice data to be collected preferentially by taking the user's geographical location information into consideration. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's geographical location data into the generation AI and cause the generation AI to select optimal collected data. Furthermore, the collection unit can analyze the user's geographical location information in real time and determine the priority of the collected data. For example, the collection unit prioritizes collection of highly relevant voice data based on the user's current location. Furthermore, the collection unit can automatically adjust the settings of the collection device based on the user's geographical location information. For example, if the collection unit is in a particular region, the collection unit will use a collection device that corresponds to the dialect of that region, which allows the collection unit to have a detailed understanding of the user's geographic location information and optimize the data collection.

[0040] The collection unit can analyze the user's social media activity and collect related data when collecting voice data. For example, the collection unit can analyze the language and dialect used by the user on social media and collect related voice data. The collection unit can also collect voice data on topics that the user is likely to be interested in based on the content of the user's social media posts. For example, the collection unit can collect related voice data based on the activity of the user's friends on social media. In this way, related voice data can be collected by analyzing the user's social media activity. Some or all of the above-mentioned processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's social media data into a generation AI and cause the generation AI to select related voice data. Furthermore, the collection unit can analyze the user's social media activity in real time and determine the priority of the collected data. For example, the collection unit can prioritize collecting highly relevant voice data based on the user's latest posts. The collection unit can also automatically adjust the settings of the collection device based on the user's social media activity. For example, the collection unit can adjust the sensitivity of the collection device to prioritize collecting voice data related to a specific topic. This allows the collection unit to gain a detailed understanding of users' social media activities and optimize the data collection.

[0041] When collecting voice data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit adjusts the collection method based on feedback provided by the user in the past. The collection unit can also collect voice data by reflecting the user's preferred collection timing and method. For example, the collection unit analyzes the user's past feedback and selects the optimal collection method. This allows the optimal collection method to be customized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's feedback data into a generation AI and cause the generation AI to customize the collection method. Furthermore, the collection unit can analyze the user's feedback in real time and adjust the collection method. For example, the collection unit adjusts the settings of the collection device based on the user's latest feedback. The collection unit can also prioritize the collection data based on the user's past feedback. For example, the collection unit prioritizes the use of collection methods that the user highly rated. This allows the collection unit to gain a detailed understanding of the user's past feedback and optimize the collection method.

[0042] The learning unit can adjust the level of detail of the learning based on the importance of the audio data during learning. For example, the learning unit can learn audio data with high importance in detail to improve accuracy. The learning unit can also simplify audio data with low importance and focus on efficiency during learning. For example, the learning unit optimally allocates learning resources according to the importance of the audio data. This enables efficient learning by adjusting the level of detail of the learning based on the importance of the audio data. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the importance of the audio data to the generation AI and cause the generation AI to adjust the level of detail of the learning. Furthermore, the learning unit can analyze the importance of the audio data in real time and adjust the level of detail of the learning. For example, the learning unit can evaluate the importance of the audio data in real time and optimally allocate learning resources. The learning unit can also determine the priority of the learning data based on the importance of the audio data. For example, the learning unit prioritizes learning of audio data with high importance. This allows the learning unit to grasp the importance of the audio data in detail and optimize the level of detail of the learning.

[0043] During learning, the learning unit can apply different learning algorithms depending on the category of the audio data. For example, the learning unit applies a natural language processing algorithm to audio data of everyday conversation. The learning unit can also apply a situation-specific algorithm to audio data in a specific situation. For example, the learning unit applies a dialect-specific algorithm to audio data in a dialect. This improves the accuracy of learning by applying different learning algorithms depending on the category of the audio data. Some or all of the above-described processing in the learning unit can be performed using, for example, AI. For example, the learning unit can input the category of the audio data to the generation AI and cause the generation AI to select the optimal learning algorithm. Furthermore, the learning unit can analyze the category of the audio data in real time and adjust the application of the learning algorithm. For example, the learning unit can evaluate the category of the audio data in real time and apply the optimal learning algorithm. The learning unit can also determine the priority of the training data based on the category of the audio data. For example, the learning unit can prioritize learning audio data of a specific category. This allows the learning unit to grasp the categories of the voice data in detail and optimize the learning algorithm.

[0044] The learning unit can improve the accuracy of learning by referring to the user's past learning results during learning. The learning unit can improve the accuracy of learning, for example, based on audio data used by the user in the past. The learning unit can also analyze the user's past learning results and select an optimal learning method. For example, the learning unit can optimally allocate learning resources by referring to the user's past learning history. This improves the accuracy of learning by referring to the user's past learning results. Some or all of the above-described processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning unit can input the user's past learning data into a generation AI and cause the generation AI to improve the accuracy of learning. Furthermore, the learning unit can analyze the user's past learning results in real time and adjust the learning method. For example, the learning unit can evaluate the user's learning history in real time and suggest an optimal learning method. The learning unit can also prioritize learning data based on the user's past learning results. For example, the learning unit can prioritize learning methods that the user highly evaluates. This allows the learning unit to grasp the user's past learning results in detail and optimize the accuracy of learning.

[0045] During learning, the learning unit can determine learning priorities based on the time when the voice data was collected. For example, the learning unit prioritizes learning the most recent voice data to improve accuracy. The learning unit can also prioritize the most recent data, leaving older voice data for later. For example, the learning unit optimally allocates learning resources according to the time when the voice data was collected. This enables learning that prioritizes the most recent data by determining learning priorities based on the time when the voice data was collected. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the time when the voice data was collected into the generation AI and cause the generation AI to determine the learning priorities. Furthermore, the learning unit can analyze the time when the voice data was collected in real time and adjust the learning priorities. For example, the learning unit evaluates the time when the voice data was collected in real time and prioritizes learning the most recent data. The learning unit can also determine the priority of learning data based on the time when the voice data was collected. For example, the learning unit prioritizes learning the most recent voice data. This allows the learning unit to have a detailed understanding of the time when the voice data was collected and optimize the learning priorities.

[0046] During learning, the learning unit can adjust the learning order based on the relevance of the voice data. For example, the learning unit prioritizes learning of highly relevant voice data to improve accuracy. The learning unit can also prioritize efficiency by leaving less relevant voice data for later. For example, the learning unit optimally allocates learning resources according to the relevance of the voice data. As a result, efficient learning is possible by adjusting the learning order based on the relevance of the voice data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the relevance of the voice data to a generation AI and cause the generation AI to adjust the learning order. Furthermore, the learning unit can analyze the relevance of the voice data in real time and adjust the learning order. For example, the learning unit evaluates the relevance of the voice data in real time and optimally allocates learning resources. The learning unit can also determine the priority of learning data based on the relevance of the voice data. For example, the learning unit prioritizes learning of highly relevant voice data. As a result, the learning unit can grasp the relevance of the voice data in detail and optimize the learning order.

[0047] During learning, the learning unit can adjust the use of technical terms in learning according to the user's level of expertise. For example, if the user has technical expertise, the learning unit may use a lot of technical terms in learning. Furthermore, if the user does not have technical expertise, the learning unit may avoid technical terms in learning. For example, the learning unit may select an optimal learning method according to the user's level of expertise. By adjusting the use of technical terms according to the user's level of expertise, optimal learning is possible. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit may input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms. Furthermore, the learning unit may analyze the user's level of expertise in real time and adjust the learning method. For example, the learning unit may evaluate the user's level of expertise in real time and suggest an optimal learning method. The learning unit may also prioritize learning data based on the user's level of expertise. For example, the learning unit may provide advanced learning data to users with specialized knowledge. This allows the learning unit to get a detailed understanding of the user's level of expertise and optimize the use of specialized terminology for learning.

[0048] The recognition unit can improve recognition accuracy by taking into account the interrelationships of voice data during recognition. The recognition unit can improve recognition accuracy by, for example, taking into account the context of the voice data. The recognition unit can also analyze the context of the voice data to reduce misrecognition. For example, the recognition unit selects an optimal recognition method based on the interrelationships of voice data. As a result, recognition accuracy is improved by taking the interrelationships of voice data into consideration. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input context information of the voice data to the generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the interrelationships of voice data in real time to improve recognition accuracy. For example, the recognition unit can evaluate the context of the voice data in real time to reduce misrecognition. The recognition unit can also determine the priority of recognition data based on the interrelationships of voice data. For example, the recognition unit prioritizes recognition of highly related voice data. As a result, the recognition unit can grasp the interrelationships of voice data in detail and optimize recognition accuracy.

[0049] The recognition unit can perform recognition by taking into account attribute information of the person submitting the voice data. The recognition unit can improve recognition accuracy by taking into account, for example, the submitter's age and gender. The recognition unit can also reduce recognition errors by taking into account the submitter's region and dialect. For example, the recognition unit selects the optimal recognition method based on the submitter's attribute information. As a result, recognition accuracy is improved by taking the submitter's attribute information into account. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input the submitter's attribute information into a generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the submitter's attribute information in real time to improve recognition accuracy. For example, the recognition unit can evaluate the submitter's attribute information in real time to reduce recognition errors. The recognition unit can also determine the priority of recognition data based on the submitter's attribute information. For example, the recognition unit can preferentially recognize voice data of submitters with specific attributes. As a result, the recognition unit can grasp the submitter's attribute information in detail and optimize recognition accuracy.

[0050] The recognition unit can weight recognition based on the frequency of voice data submission during recognition. For example, the recognition unit prioritizes recognition of frequently submitted voice data to improve accuracy. The recognition unit can also prioritize efficiency by leaving less frequently submitted voice data for later. For example, the recognition unit optimally allocates recognition resources according to the frequency of voice data submission. As a result, weighting based on the frequency of voice data submission enables efficient recognition. Some or all of the above-described processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the frequency of voice data submission to a generation AI and cause the generation AI to perform recognition weighting. Furthermore, the recognition unit can analyze the frequency of voice data submission in real time and adjust the recognition weighting. For example, the recognition unit can evaluate the frequency of voice data submission in real time and optimally allocate recognition resources. The recognition unit can also determine the priority of recognition data based on the frequency of voice data submission. For example, the recognition unit prioritizes recognition of frequently submitted voice data. This allows the recognition unit to grasp the frequency of voice data submission in detail and optimize the weighting of recognition.

[0051] The recognition unit can perform recognition by taking into account the geographical distribution of the voice data. For example, the recognition unit can prioritize recognition of voice data from a specific region to improve accuracy. The recognition unit can also reduce misrecognitions based on voice data with high geographical relevance. For example, the recognition unit selects an optimal recognition method based on the geographical distribution of the voice data. This improves recognition accuracy by taking the geographical distribution of the voice data into consideration. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input the geographical distribution of the voice data into a generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the geographical distribution of the voice data in real time to improve recognition accuracy. For example, the recognition unit can evaluate the geographical distribution of the voice data in real time to reduce misrecognitions. The recognition unit can also determine the priority of recognition data based on the geographical distribution of the voice data. For example, the recognition unit can prioritize recognition of voice data from a specific region. This allows the recognition unit to grasp the geographical distribution of the voice data in detail and optimize recognition accuracy.

[0052] The recognition unit can improve recognition accuracy by referring to related literature for the speech data during recognition. For example, the recognition unit improves recognition accuracy of the speech data based on related literature. The recognition unit can also reduce misrecognition by comparing the context of the speech data with the related literature. For example, the recognition unit can refer to related literature to select an optimal recognition method. By referring to the related literature, recognition accuracy is improved. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input related literature into a generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze related literature in real time to improve recognition accuracy. For example, the recognition unit can evaluate related literature in real time to reduce misrecognition. The recognition unit can also determine the priority of recognition data based on the related literature. For example, the recognition unit can preferentially refer to highly relevant literature. This allows the recognition unit to gain a detailed understanding of related literature and optimize recognition accuracy.

[0053] The recognition unit can perform recognition taking into account the market value of the voice data. For example, the recognition unit can prioritize recognition of voice data with high market value to improve accuracy. The recognition unit can also prioritize efficiency by leaving voice data with low market value for later. For example, the recognition unit optimally allocates recognition resources according to the market value of the voice data. This allows important data to be recognized preferentially by taking the market value of the voice data into consideration. Some or all of the above-described processing in the recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the recognition unit can input the market value of the voice data into the generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the market value of the voice data in real time to improve recognition accuracy. For example, the recognition unit can evaluate the market value of the voice data in real time to reduce recognition errors. The recognition unit can also determine the priority of recognition data based on the market value of the voice data. For example, the recognition unit prioritizes recognition of voice data with high market value. This allows the recognition unit to grasp the market value of the voice data in detail and optimize recognition accuracy.

[0054] During operation, the operation unit can analyze the user's past operation history and select the optimal operation method. For example, the operation unit can prioritize and provide operation methods that the user has used frequently in the past. The operation unit can also analyze the user's operation patterns and provide the most natural operation method. For example, the operation unit can provide the optimal operation procedure based on operation methods used by the user in the past. This allows the optimal operation method to be selected by analyzing the past operation history. Some or all of the above-described processing in the operation unit can be performed using, for example, AI, or can be performed without AI. For example, the operation unit can input the user's operation history data to a generation AI and cause the generation AI to select the optimal operation method. Furthermore, the operation unit can analyze the user's operation history in real time and adjust the operation method. For example, the operation unit can evaluate the user's operation pattern in real time and propose the optimal operation procedure. The operation unit can also determine the priority of operation data based on the user's operation history. For example, the operation unit can prioritize and use operation methods that the user has highly rated. This allows the operation unit to grasp the user's operation history in detail and optimize the operation method.

[0055] The operation unit can customize the operation means based on the user's current living situation during operation. For example, when the user operates the device at home, the operation unit provides an operation method that is optimal for the home. Furthermore, when the user operates the device while on the go, the operation unit can also provide an operation method that is optimal for the home. For example, the operation unit provides an operation method that is optimal for the home, according to the user's lifestyle. This allows for more appropriate operation by customizing the operation means based on the user's living situation. Some or all of the above-described processing in the operation unit may be performed using, for example, AI, or may be performed without AI. For example, the operation unit can input the user's living situation data into a generation AI and cause the generation AI to select an optimal operation means. Furthermore, the operation unit can analyze the user's living situation in real time and adjust the operation means. For example, the operation unit can evaluate the user's lifestyle in real time and suggest an optimal operation means. Furthermore, the operation unit can prioritize operation data based on the user's living situation. For example, the operation unit can prioritize operation methods that the user uses at home. This allows the operation unit to grasp the user's living situation in detail and optimize the operation means.

[0056] The operation unit can improve the operation method by reflecting user feedback during operation. The operation unit can improve the operation method based on, for example, feedback provided by the user. The operation unit can also analyze the user's feedback and provide an optimal operation procedure. For example, the operation unit can customize the operation method by referring to the user's past feedback. This allows the operation method to be improved by reflecting the user's feedback. Some or all of the above-mentioned processing in the operation unit can be performed using, for example, AI, or can be performed without using AI. For example, the operation unit can input user feedback data into a generation AI and cause the generation AI to improve the operation method. Furthermore, the operation unit can analyze user feedback in real time and adjust the operation method. For example, the operation unit can evaluate user feedback in real time and propose an optimal operation procedure. The operation unit can also determine the priority of operation data based on user feedback. For example, the operation unit can preferentially use operation methods that the user highly evaluates. This allows the operation unit to understand user feedback in detail and optimize the operation method.

[0057] The operation unit can select the optimal operation method by taking into account the user's geographical location information during operation. For example, when the user is in a specific area, the operation unit provides the optimal operation method for that area. Furthermore, when the user is traveling, the operation unit can also provide the optimal operation method for the destination. For example, when the user is at home, the operation unit provides the optimal operation method for the home. This allows the optimal operation method to be selected by taking the user's geographical location information into consideration. Some or all of the above-described processing in the operation unit may be performed using, for example, AI, or may be performed without AI. For example, the operation unit can input the user's geographical location data into a generation AI and cause the generation AI to select the optimal operation method. Furthermore, the operation unit can analyze the user's geographical location information in real time and adjust the operation method. For example, the operation unit can evaluate the user's current location in real time and suggest the optimal operation procedure. The operation unit can also prioritize operation data based on the user's geographical location information. For example, the operation unit can prioritize the operation method used by the user in a specific area. This allows the operation unit to obtain a detailed understanding of the user's geographical location information and optimize the operation method.

[0058] During operation, the operation unit can analyze the user's social media activity and suggest an operation method. For example, the operation unit analyzes the language and dialect used by the user on social media and provides an optimal operation method. The operation unit can also suggest an operation method that is likely to be of interest to the user based on the content posted by the user on social media. For example, the operation unit provides an optimal operation method by referring to the activity of the user's friends on social media. In this way, the optimal operation method can be suggested by analyzing the user's social media activity. Some or all of the above-mentioned processing in the operation unit may be performed using, for example, AI, or may be performed without using AI. For example, the operation unit can input the user's social media data into a generation AI and cause the generation AI to suggest an optimal operation method. Furthermore, the operation unit can analyze the user's social media activity in real time and suggest an operation method. For example, the operation unit evaluates the user's social media activity in real time and suggests an optimal operation procedure. The operation unit can also determine the priority of operation data based on the user's social media activity. For example, the operation unit prioritizes the language and dialect used by the user on social media. This allows the operation unit to grasp the user's social media activities in detail and optimize the operation means.

[0059] The operation unit can customize the operation method by reflecting the user's past feedback during operation. The operation unit customizes the operation method based on, for example, feedback provided by the user. The operation unit can also analyze the user's feedback and provide an optimal operation procedure. For example, the operation unit improves the operation method by referring to the user's past feedback. In this way, the operation method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the operation unit may be performed using, for example, AI, or may be performed without AI. For example, the operation unit can input the user's feedback data into a generation AI and cause the generation AI to customize the operation method. Furthermore, the operation unit can analyze the user's feedback in real time and adjust the operation method. For example, the operation unit evaluates the user's feedback in real time and proposes an optimal operation procedure. The operation unit can also determine the priority of operation data based on the user's feedback. For example, the operation unit prioritizes the use of operation methods that the user highly evaluates. In this way, the operation unit can grasp the user's feedback in detail and optimize the operation method.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The voice recognition system may further include a health management unit that monitors the user's health condition. The health management unit may, for example, measure the user's heart rate and blood pressure and issue a warning if an abnormality is detected. The health management unit may also collect the user's health data and support long-term health management. For example, the health management unit may analyze the user's health data and identify changes in the user's health condition. This allows the voice recognition system to monitor the user's health condition and take appropriate measures.

[0062] The voice recognition system can further include a rhythm adjustment unit that learns the user's daily rhythm and collects voice data at optimal timing. For example, if the user is active in the morning, the rhythm adjustment unit may preferentially collect voice data in the morning. Alternatively, if the user is relaxed in the evening, the rhythm adjustment unit may collect voice data in the evening. This allows the voice recognition system to collect voice data in accordance with the user's daily rhythm and obtain more natural data.

[0063] The voice recognition system may further include an interest learning unit that learns the user's hobbies and interests and prioritizes collecting related voice data. For example, if the user is interested in music, the interest learning unit may collect music-related voice data. Alternatively, if the user is interested in sports, the interest learning unit may collect sports-related voice data. This allows the voice recognition system to collect voice data based on the user's hobbies and interests and obtain more relevant data.

[0064] The speech recognition system may further include a history analysis unit that analyzes the user's past operation history and suggests the optimal operation method. For example, the history analysis unit may preferentially suggest operation methods that the user has used frequently in the past. The history analysis unit may also analyze the user's operation patterns and suggest the most natural operation method. This allows the speech recognition system to suggest the optimal operation method based on the user's past operation history and support the user's operation.

[0065] The voice recognition system can further include a location information unit that selects the optimal operation method by taking into account the user's geographical location information. For example, if the user is in a specific area, the location information unit can provide the optimal operation method for that area. Also, if the user is traveling, the location information unit can provide the optimal operation method for the destination. This allows the voice recognition system to select the optimal operation method by taking into account the user's geographical location information and support the user's operation.

[0066] The speech recognition system may further include a social analysis unit that analyzes the user's social media activity and suggests the optimal operation method. The social analysis unit may, for example, analyze the language or dialect used by the user on social media and suggest the optimal operation method. The social analysis unit may also suggest operation methods that the user may be interested in based on the content of the user's social media posts. This allows the speech recognition system to analyze the user's social media activity and suggest the optimal operation method.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The collection unit collects audio data. The audio data includes, but is not limited to, audio file formats, sampling rates, bit rates, etc. The collection unit collects a variety of audio data, including, for example, the characteristic pronunciation and vocabulary of Tsugaru dialect. The collection unit can also collect audio data of dialects of other regions, such as Kansai dialect and Hakata dialect. For example, the collection unit collects audio data from various situations, such as everyday conversations and conversations in specific situations. Step 2: The learning unit uses the generation AI to learn the voice data collected by the collection unit. The learning is performed based on, for example, the machine learning algorithm used and the type of training data, but is not limited to these examples. For example, the learning unit uses the generation AI to learn everyday conversations and conversations in specific situations. The learning unit can also use the generation AI to learn voice data in dialects of other regions. Step 3: The recognition unit recognizes the speech based on the results of learning by the learning unit. Recognition is performed based on, for example, a speech recognition algorithm, recognition accuracy, and tolerance for misrecognition, but is not limited to these examples. For example, the recognition unit recognizes speech spoken by an elderly person to an IT device in Tsugaru dialect. The recognition unit can also recognize speech spoken by users of a specific age group to an IT device. Step 4: The operation unit performs an operation based on the voice recognized by the recognition unit. The operation is performed based on, for example, the device to be operated, the type of operation, and the accuracy of the operation, but is not limited to these examples. For example, the operation unit operates an IT device based on the recognized voice.

[0069] (Example 2) The voice recognition system according to an embodiment of the present invention allows elderly people to operate IT devices entirely through voice recognition alone. The voice recognition system aims to support all Japanese dialects, initially training the system on the Tsugaru dialect to facilitate practical use of voice recognition. For example, the voice recognition system collects voice data in the Tsugaru dialect, and a generation AI learns from that voice data. The voice recognition system then uses the trained generation AI to practically recognize Tsugaru dialect. For example, when an elderly person speaks to an IT device in Tsugaru dialect, the generation AI recognizes the voice and performs appropriate operations. Furthermore, after practical use of Tsugaru dialect voice recognition, the voice recognition system will expand its support to other dialects. For example, to support dialects in other regions, such as Kansai dialect and Hakata dialect, voice data will be collected using a similar method and the generation AI will be trained. This will enable voice recognition that supports dialects across Japan, allowing elderly people to operate IT devices in their native dialect, regardless of where they live. This significantly reduces the hurdles for elderly people to operate IT devices themselves. For example, voice recognition systems can be easily operated by elderly people who have limited vision or hand movements. Furthermore, dialect support allows users to use the system in their natural language, making it stress-free. This will improve the quality of life for the elderly and promote the widespread use of IT devices in a super-aging society.

[0070] A speech recognition system according to an embodiment includes a collection unit, a learning unit, a recognition unit, and an operation unit. The collection unit collects speech data. The speech data includes, for example, an audio file format, a sampling rate, a bit rate, and the like, but is not limited to these examples. The collection unit collects a variety of speech data, for example, including the characteristic pronunciation and vocabulary of Tsugaru dialect. The collection unit can also collect speech data of other regional dialects, such as Kansai dialect and Hakata dialect. For example, the collection unit collects speech data from various situations, such as everyday conversations and conversations in specific situations. The learning unit uses a generation AI to learn the speech data collected by the collection unit. The learning is performed based on, for example, a machine learning algorithm used and the type of training data, but is not limited to these examples. For example, the learning unit uses the generation AI to learn everyday conversations and conversations in specific situations. The learning unit can also learn speech data of other regional dialects using the generation AI. The recognition unit recognizes speech based on the results of learning by the learning unit. Recognition is performed based on, for example, a speech recognition algorithm, recognition accuracy, and tolerance for misrecognition, but is not limited to, such examples. For example, the recognition unit recognizes speech spoken by an elderly person to an IT device in Tsugaru dialect. The recognition unit can also recognize speech spoken by users of a specific age group to an IT device. The operation unit performs an operation based on the speech recognized by the recognition unit. The operation is performed based on, for example, the device to be operated, the type of operation, and the accuracy of the operation, but is not limited to such examples. For example, the operation unit operates the IT device based on the recognized speech. As a result, the speech recognition system according to the embodiment can perform a consistent process from collecting speech data to learning, recognition, and operation. For example, the speech recognition system allows elderly people to complete operations using only their voice. Furthermore, to support dialects in other regions, the speech recognition system can collect speech data using a similar method and train the generation AI. As a result, the speech recognition system can recognize speech that supports dialects across the country.

[0071] The collection unit can collect multiple pieces of speech data including characteristic pronunciation and vocabulary of the Tsugaru dialect. The characteristic pronunciation and vocabulary of the Tsugaru dialect include, for example, specific words and phrases, pronunciation features, etc., but are not limited to these examples. For example, to collect Tsugaru dialect speech data, the collection unit collects everyday conversations and conversations in specific situations. The collection unit can also collect speech data from local residents to collect Tsugaru dialect speech data. For example, the collection unit collects speech data at local events and gatherings. The collection unit can also collect speech data from the Internet to collect Tsugaru dialect speech data. For example, the collection unit collects video and audio files including Tsugaru dialect speech data. By collecting Tsugaru dialect speech data, dialect-specific speech recognition becomes possible.

[0072] The learning unit can train the generation AI on everyday conversations and conversations in specific situations. Examples of everyday conversations and specific situations include, but are not limited to, situations such as shopping, hospitals, and schools. For example, the learning unit trains the generation AI on voice data of everyday conversations. The learning unit can also train the generation AI on voice data in specific situations. For example, the learning unit trains the generation AI on conversations in hospitals and conversations in schools. The learning unit can also preprocess the voice data so that the generation AI can train on voice data of everyday conversations and specific situations. For example, the learning unit removes noise from the voice data and inputs clear voice data into the generation AI. This improves the accuracy of voice recognition by learning voice data from a variety of situations.

[0073] The recognition unit can recognize speech spoken to IT devices in Tsugaru dialect by users of a specific age group. Examples of specific age groups include, but are not limited to, elderly people, children, and young people. The recognition unit can also recognize speech spoken to IT devices in Tsugaru dialect by elderly people. The recognition unit can also recognize speech spoken to IT devices by children. For example, the recognition unit can learn the characteristics of children's voices to improve recognition accuracy. The recognition unit can also recognize speech spoken to IT devices by young people. For example, the recognition unit can learn slang and unique expressions used by young people to improve recognition accuracy. As a result, by recognizing speech spoken in Tsugaru dialect, elderly people can operate IT devices in their usual dialect.

[0074] The operation unit can operate IT devices based on the recognized voice. Examples of IT devices include, but are not limited to, smartphones, tablets, and personal computers. For example, the operation unit can operate a smartphone based on the recognized voice. The operation unit can also operate a tablet based on the recognized voice. For example, the operation unit can launch an application based on a voice command. The operation unit can also operate a personal computer based on the recognized voice. For example, the operation unit can open a file based on a voice command. In this way, by operating IT devices based on the recognized voice, elderly people can complete operations using only voice.

[0075] The collection unit can collect speech data of Kansai dialect, Hakata dialect, and dialects of other regions. Kansai dialect, Hakata dialect, and dialects of other regions include, for example, specific words, phrases, pronunciation features, etc., but are not limited to these examples. The collection unit, for example, collects speech data of Kansai dialect. The collection unit can also collect speech data of Hakata dialect. For example, the collection unit collects speech data from local residents. The collection unit can also collect speech data of dialects of other regions. For example, the collection unit collects speech data of Tohoku dialect and Kyushu dialect. In this way, by collecting speech data of dialects of other regions, speech recognition compatible with dialects across the country becomes possible.

[0076] The learning unit can use the generation AI to learn speech data in dialects of other regions. Dialects of other regions include, but are not limited to, Tohoku dialect and Kyushu dialect. For example, the learning unit uses the generation AI to learn speech data in Tohoku dialect. The learning unit can also use the generation AI to learn speech data in Kyushu dialect. For example, the learning unit uses the generation AI to learn speech data collected from local residents. The learning unit can also preprocess the speech data so that the generation AI can learn speech data in dialects of other regions. For example, the learning unit removes noise from the speech data and inputs clear speech data into the generation AI. In this way, by learning speech data in dialects of other regions, speech recognition compatible with dialects across the country becomes possible.

[0077] The collection unit can estimate the user's emotions and adjust the timing of collecting voice data based on the estimated user emotions. For example, when the user is relaxed, the collection unit collects voice data during natural conversation. Furthermore, when the user is stressed, the collection unit can delay the collection timing and collect voice data in a relaxed state. For example, when the user is excited, the collection unit waits until the user's emotions have calmed down before collecting. This allows for adjusting the collection timing according to the user's emotions and collecting more natural voice data. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions. Furthermore, the collection unit can analyze the user's emotion data in real time and immediately grasp changes in emotions. For example, the collection unit can monitor the user's facial expressions in real time and immediately detect changes in emotions. The collection unit can also accumulate the user's emotional data and analyze long-term emotional trends. For example, the collection unit can analyze the user's emotional data over time to identify patterns of emotional change. This allows the user's emotions to be understood in detail and the timing of collection to be adjusted.

[0078] When collecting voice data, the collection unit can analyze the user's past speech history and select an appropriate collection method. For example, the collection unit prioritizes collection of phrases the user has frequently used in the past. The collection unit can also analyze the user's speech patterns and collect data at the most natural timing. For example, the collection unit adjusts the collection method taking into account the characteristics of the dialect the user has used in the past. This allows the optimal collection method to be selected by analyzing the past speech history. Some or all of the above-described processing in the collection unit can be performed using, for example, AI. For example, the collection unit can input the user's past speech data into a generation AI and have the generation AI select the optimal collection method. Furthermore, the collection unit can accumulate the user's speech history and analyze long-term speech patterns. For example, the collection unit can analyze the user's speech data chronologically to identify patterns of change in speech. The collection unit can also provide individual collection methods based on the user's speech history. For example, the collection unit can suggest the optimal collection device and timing depending on the user's speech characteristics. This allows the collection unit to grasp the user's past speech history in detail and optimize the collection method.

[0079] When collecting voice data, the collection unit can filter the voice data based on the user's current living situation and areas of interest. For example, the collection unit prioritizes collecting voice data of the user speaking at home. The collection unit can also collect voice data related to topics of interest to the user. For example, the collection unit collects voice data at optimal times in accordance with the user's daily rhythm. This allows for filtering based on the user's living situation and areas of interest, thereby collecting more relevant voice data. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's living situation data into the generation AI and cause the generation AI to select the optimal collection timing. Furthermore, the collection unit can analyze the user's areas of interest in real time and filter the collected data. For example, the collection unit can analyze the user's social media activity and search history to prioritize collecting voice data related to the areas of interest. The collection unit can also determine the priority of collected data based on the user's living situation. For example, the collection unit can suggest the optimal collection device and timing based on the user's occupation and home environment. This allows the collection unit to gain a detailed understanding of the user's current living situation and areas of interest, and optimize the collected data.

[0080] When collecting voice data, the collection unit can select an appropriate collection means depending on the user's input method. For example, when the user uses voice input, the collection unit prioritizes collecting voice data. Furthermore, when the user uses text input, the collection unit can convert text data into voice data and collect it. For example, when the user uses image input, the collection unit generates and collects related voice data from the image. This allows for efficient collection of voice data by selecting the optimal collection means depending on the user's input method. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's input data into a generation AI and cause the generation AI to select the optimal collection means. Furthermore, the collection unit can analyze the user's input method in real time and select the collection means. For example, the collection unit can analyze the user's input history and suggest the optimal collection means. The collection unit can also automatically adjust the settings of the collection device depending on the user's input method. For example, the collection unit adjusts the microphone sensitivity for voice input and optimizes the keyboard settings for text input. This allows the collection unit to grasp the user's input method in detail and optimize the collection means.

[0081] The collection unit can estimate the user's emotions and determine the priority of the voice data to be collected based on the estimated user's emotions. For example, when the user is relaxed, the collection unit prioritizes collecting voice data of everyday conversations. Furthermore, when the user is stressed, the collection unit can also prioritize collecting voice data related to stress reduction. For example, when the user is excited, the collection unit prioritizes collecting voice data related to excited states. Thus, by prioritizing the voice data according to the user's emotions, more important data can be collected preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions. Furthermore, the collection unit can analyze the user's emotion data in real time and immediately grasp changes in emotions. For example, the collection unit may monitor the user's facial expressions in real time and immediately detect changes in emotions. The collection unit may also accumulate the user's emotional data and analyze long-term emotional trends. For example, the collection unit may analyze the user's emotional data over time to identify patterns of emotional change. This allows for a detailed understanding of the user's emotions and the prioritization of collected data.

[0082] When collecting voice data, the collection unit can prioritize collection of highly relevant data based on the user's geographical location information. For example, when the user is in a specific area, the collection unit prioritizes collection of voice data related to the dialect of that area. Furthermore, when the user is traveling, the collection unit can also collect voice data related to the dialect of the place the user is visiting. For example, when the user is at home, the collection unit prioritizes collection of voice data of the dialect used at home. This allows highly relevant voice data to be collected preferentially by taking the user's geographical location information into consideration. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's geographical location data into the generation AI and cause the generation AI to select optimal collected data. Furthermore, the collection unit can analyze the user's geographical location information in real time and determine the priority of the collected data. For example, the collection unit prioritizes collection of highly relevant voice data based on the user's current location. Furthermore, the collection unit can automatically adjust the settings of the collection device based on the user's geographical location information. For example, if the collection unit is in a particular region, the collection unit will use a collection device that corresponds to the dialect of that region, which allows the collection unit to have a detailed understanding of the user's geographic location information and optimize the data collection.

[0083] The collection unit can analyze the user's social media activity and collect related data when collecting voice data. For example, the collection unit can analyze the language and dialect used by the user on social media and collect related voice data. The collection unit can also collect voice data on topics that the user is likely to be interested in based on the content of the user's social media posts. For example, the collection unit can collect related voice data based on the activity of the user's friends on social media. In this way, related voice data can be collected by analyzing the user's social media activity. Some or all of the above-mentioned processing by the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's social media data into a generation AI and cause the generation AI to select related voice data. Furthermore, the collection unit can analyze the user's social media activity in real time and determine the priority of the collected data. For example, the collection unit can prioritize collecting highly relevant voice data based on the user's latest posts. The collection unit can also automatically adjust the settings of the collection device based on the user's social media activity. For example, the collection unit can adjust the sensitivity of the collection device to prioritize collecting voice data related to a specific topic. This allows the collection unit to gain a detailed understanding of users' social media activities and optimize the data collection.

[0084] When collecting voice data, the collection unit can customize the collection method by reflecting the user's past feedback. For example, the collection unit adjusts the collection method based on feedback provided by the user in the past. The collection unit can also collect voice data by reflecting the user's preferred collection timing and method. For example, the collection unit analyzes the user's past feedback and selects the optimal collection method. This allows the optimal collection method to be customized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's feedback data into a generation AI and cause the generation AI to customize the collection method. Furthermore, the collection unit can analyze the user's feedback in real time and adjust the collection method. For example, the collection unit adjusts the settings of the collection device based on the user's latest feedback. The collection unit can also prioritize the collection data based on the user's past feedback. For example, the collection unit prioritizes the use of collection methods that the user highly rated. This allows the collection unit to gain a detailed understanding of the user's past feedback and optimize the collection method.

[0085] 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 prioritizes learning voice data in a relaxed state. Furthermore, if the user is stressed, the learning unit can prioritize learning voice data related to stress reduction. For example, if the user is excited, the learning unit prioritizes learning voice data related to an excited state. This improves the accuracy of learning by selecting training data according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions. Furthermore, the learning unit can analyze the user's emotion data in real time and select training data. For example, the learning unit monitors the user's facial expressions in real time and immediately detects changes in emotions. The learning unit can also accumulate user emotional data and analyze long-term emotional trends. For example, the learning unit can analyze the user's emotional data over time and identify patterns of emotional change. This allows the learning unit to gain a detailed understanding of the user's emotions and optimize the selection of learning data.

[0086] The learning unit can adjust the level of detail of the learning based on the importance of the audio data during learning. For example, the learning unit can learn audio data with high importance in detail to improve accuracy. The learning unit can also simplify audio data with low importance and focus on efficiency during learning. For example, the learning unit optimally allocates learning resources according to the importance of the audio data. This enables efficient learning by adjusting the level of detail of the learning based on the importance of the audio data. Some or all of the above-described processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the importance of the audio data to the generation AI and cause the generation AI to adjust the level of detail of the learning. Furthermore, the learning unit can analyze the importance of the audio data in real time and adjust the level of detail of the learning. For example, the learning unit can evaluate the importance of the audio data in real time and optimally allocate learning resources. The learning unit can also determine the priority of the learning data based on the importance of the audio data. For example, the learning unit prioritizes learning of audio data with high importance. This allows the learning unit to grasp the importance of the audio data in detail and optimize the level of detail of the learning.

[0087] During learning, the learning unit can apply different learning algorithms depending on the category of the audio data. For example, the learning unit applies a natural language processing algorithm to audio data of everyday conversation. The learning unit can also apply a situation-specific algorithm to audio data in a specific situation. For example, the learning unit applies a dialect-specific algorithm to audio data in a dialect. This improves the accuracy of learning by applying different learning algorithms depending on the category of the audio data. Some or all of the above-described processing in the learning unit can be performed using, for example, AI. For example, the learning unit can input the category of the audio data to the generation AI and cause the generation AI to select the optimal learning algorithm. Furthermore, the learning unit can analyze the category of the audio data in real time and adjust the application of the learning algorithm. For example, the learning unit can evaluate the category of the audio data in real time and apply the optimal learning algorithm. The learning unit can also determine the priority of the training data based on the category of the audio data. For example, the learning unit can prioritize learning audio data of a specific category. This allows the learning unit to grasp the categories of the voice data in detail and optimize the learning algorithm.

[0088] The learning unit can improve the accuracy of learning by referring to the user's past learning results during learning. The learning unit can improve the accuracy of learning, for example, based on audio data used by the user in the past. The learning unit can also analyze the user's past learning results and select an optimal learning method. For example, the learning unit can optimally allocate learning resources by referring to the user's past learning history. This improves the accuracy of learning by referring to the user's past learning results. Some or all of the above-described processing in the learning unit can be performed using, for example, AI, or without AI. For example, the learning unit can input the user's past learning data into a generation AI and cause the generation AI to improve the accuracy of learning. Furthermore, the learning unit can analyze the user's past learning results in real time and adjust the learning method. For example, the learning unit can evaluate the user's learning history in real time and suggest an optimal learning method. The learning unit can also prioritize learning data based on the user's past learning results. For example, the learning unit can prioritize learning methods that the user highly evaluates. This allows the learning unit to grasp the user's past learning results in detail and optimize the accuracy of learning.

[0089] The learning unit can estimate the user's emotions and adjust the length of the learning based on the estimated user emotions. For example, if the user is relaxed, the learning unit can set a longer learning session. Furthermore, if the user is feeling stressed, the learning unit can also set a shorter learning session. For example, if the user is excited, the learning unit can temporarily suspend learning until the user calms down. This allows for efficient learning by adjusting the length of the learning session according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without an AI. For example, the learning unit can input the user's facial expression data into the generative AI and cause the generative AI to estimate the user's emotions. Furthermore, the learning unit can analyze the user's emotional data in real time and adjust the length of the learning session. For example, the learning unit can monitor the user's facial expressions in real time and instantly detect changes in emotion. The learning unit can also accumulate user emotional data and analyze long-term emotional trends. For example, the learning unit can analyze the user emotional data over time to identify patterns of emotional change. This allows the learning unit to gain a detailed understanding of the user's emotions and optimize the length of learning.

[0090] During learning, the learning unit can determine learning priorities based on the time when the voice data was collected. For example, the learning unit prioritizes learning the most recent voice data to improve accuracy. The learning unit can also prioritize the most recent data, leaving older voice data for later. For example, the learning unit optimally allocates learning resources according to the time when the voice data was collected. This enables learning that prioritizes the most recent data by determining learning priorities based on the time when the voice data was collected. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the time when the voice data was collected into the generation AI and cause the generation AI to determine the learning priorities. Furthermore, the learning unit can analyze the time when the voice data was collected in real time and adjust the learning priorities. For example, the learning unit evaluates the time when the voice data was collected in real time and prioritizes learning the most recent data. The learning unit can also determine the priority of learning data based on the time when the voice data was collected. For example, the learning unit prioritizes learning the most recent voice data. This allows the learning unit to have a detailed understanding of the time when the voice data was collected and optimize the learning priorities.

[0091] During learning, the learning unit can adjust the learning order based on the relevance of the voice data. For example, the learning unit prioritizes learning of highly relevant voice data to improve accuracy. The learning unit can also prioritize efficiency by leaving less relevant voice data for later. For example, the learning unit optimally allocates learning resources according to the relevance of the voice data. As a result, efficient learning is possible by adjusting the learning order based on the relevance of the voice data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the relevance of the voice data to a generation AI and cause the generation AI to adjust the learning order. Furthermore, the learning unit can analyze the relevance of the voice data in real time and adjust the learning order. For example, the learning unit evaluates the relevance of the voice data in real time and optimally allocates learning resources. The learning unit can also determine the priority of learning data based on the relevance of the voice data. For example, the learning unit prioritizes learning of highly relevant voice data. As a result, the learning unit can grasp the relevance of the voice data in detail and optimize the learning order.

[0092] During learning, the learning unit can adjust the use of technical terms in learning according to the user's level of expertise. For example, if the user has technical expertise, the learning unit may use a lot of technical terms in learning. Furthermore, if the user does not have technical expertise, the learning unit may avoid technical terms in learning. For example, the learning unit may select an optimal learning method according to the user's level of expertise. By adjusting the use of technical terms according to the user's level of expertise, optimal learning is possible. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit may input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms. Furthermore, the learning unit may analyze the user's level of expertise in real time and adjust the learning method. For example, the learning unit may evaluate the user's level of expertise in real time and suggest an optimal learning method. The learning unit may also prioritize learning data based on the user's level of expertise. For example, the learning unit may provide advanced learning data to users with specialized knowledge. This allows the learning unit to get a detailed understanding of the user's level of expertise and optimize the use of specialized terminology for learning.

[0093] The recognition unit can estimate the user's emotions and adjust the recognition criteria based on the estimated user emotions. For example, when the user is relaxed, the recognition unit applies normal recognition criteria. Furthermore, when the user is stressed, the recognition unit can also relax the recognition criteria to reduce false recognition. For example, when the user is excited, the recognition unit temporarily suspends recognition until the user calms down. This adjusts the recognition criteria according to the user's emotions, thereby reducing false recognition. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recognition unit can be performed using, for example, an AI, or without an AI. For example, the recognition unit can input the user's facial expression data into the generation AI and have the generation AI estimate the user's emotions. Furthermore, the recognition unit can analyze the user's emotion data in real time and adjust the recognition criteria. For example, the recognition unit monitors the user's facial expressions in real time and immediately detects changes in emotions. The recognition unit can also accumulate user emotional data and analyze long-term emotional trends. For example, the recognition unit can analyze the user's emotional data over time and identify patterns of emotional changes. This allows the recognition unit to grasp the user's emotions in detail and optimize recognition criteria.

[0094] The recognition unit can improve recognition accuracy by taking into account the interrelationships of voice data during recognition. The recognition unit can improve recognition accuracy by, for example, taking into account the context of the voice data. The recognition unit can also analyze the context of the voice data to reduce misrecognition. For example, the recognition unit selects an optimal recognition method based on the interrelationships of voice data. As a result, recognition accuracy is improved by taking the interrelationships of voice data into consideration. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input context information of the voice data to the generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the interrelationships of voice data in real time to improve recognition accuracy. For example, the recognition unit can evaluate the context of the voice data in real time to reduce misrecognition. The recognition unit can also determine the priority of recognition data based on the interrelationships of voice data. For example, the recognition unit prioritizes recognition of highly related voice data. As a result, the recognition unit can grasp the interrelationships of voice data in detail and optimize recognition accuracy.

[0095] The recognition unit can perform recognition by taking into account attribute information of the person submitting the voice data. The recognition unit can improve recognition accuracy by taking into account, for example, the submitter's age and gender. The recognition unit can also reduce recognition errors by taking into account the submitter's region and dialect. For example, the recognition unit selects the optimal recognition method based on the submitter's attribute information. As a result, recognition accuracy is improved by taking the submitter's attribute information into account. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input the submitter's attribute information into a generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the submitter's attribute information in real time to improve recognition accuracy. For example, the recognition unit can evaluate the submitter's attribute information in real time to reduce recognition errors. The recognition unit can also determine the priority of recognition data based on the submitter's attribute information. For example, the recognition unit can preferentially recognize voice data of submitters with specific attributes. As a result, the recognition unit can grasp the submitter's attribute information in detail and optimize recognition accuracy.

[0096] The recognition unit can weight recognition based on the frequency of voice data submission during recognition. For example, the recognition unit prioritizes recognition of frequently submitted voice data to improve accuracy. The recognition unit can also prioritize efficiency by leaving less frequently submitted voice data for later. For example, the recognition unit optimally allocates recognition resources according to the frequency of voice data submission. As a result, weighting based on the frequency of voice data submission enables efficient recognition. Some or all of the above-described processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the frequency of voice data submission to a generation AI and cause the generation AI to perform recognition weighting. Furthermore, the recognition unit can analyze the frequency of voice data submission in real time and adjust the recognition weighting. For example, the recognition unit can evaluate the frequency of voice data submission in real time and optimally allocate recognition resources. The recognition unit can also determine the priority of recognition data based on the frequency of voice data submission. For example, the recognition unit prioritizes recognition of frequently submitted voice data. This allows the recognition unit to grasp the frequency of voice data submission in detail and optimize the weighting of recognition.

[0097] The recognition unit can estimate the user's emotion and adjust the display order of the recognition results based on the estimated user emotion. For example, when the user is relaxed, the recognition unit displays the recognition results in a normal order. Furthermore, when the user is stressed, the recognition unit can prioritize displaying important recognition results. For example, when the user is excited, the recognition unit temporarily suspends display of the recognition results until the user calms down. This allows important information to be prioritized by adjusting the display order of the recognition results according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recognition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recognition unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotion. Furthermore, the recognition unit can analyze the user's emotion data in real time and adjust the display order of the recognition results. For example, the recognition unit monitors the user's facial expressions in real time and immediately detects changes in emotions. The recognition unit can also accumulate user emotion data and analyze long-term emotional trends. For example, the recognition unit analyzes the user emotion data over time to identify patterns of emotional changes. This allows the recognition unit to grasp the user's emotions in detail and optimize the display order of the recognition results.

[0098] The recognition unit can perform recognition by taking into account the geographical distribution of the voice data. For example, the recognition unit can prioritize recognition of voice data from a specific region to improve accuracy. The recognition unit can also reduce misrecognitions based on voice data with high geographical relevance. For example, the recognition unit selects an optimal recognition method based on the geographical distribution of the voice data. This improves recognition accuracy by taking the geographical distribution of the voice data into consideration. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input the geographical distribution of the voice data into a generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the geographical distribution of the voice data in real time to improve recognition accuracy. For example, the recognition unit can evaluate the geographical distribution of the voice data in real time to reduce misrecognitions. The recognition unit can also determine the priority of recognition data based on the geographical distribution of the voice data. For example, the recognition unit can prioritize recognition of voice data from a specific region. This allows the recognition unit to grasp the geographical distribution of the voice data in detail and optimize recognition accuracy.

[0099] The recognition unit can improve recognition accuracy by referring to related literature for the speech data during recognition. For example, the recognition unit improves recognition accuracy of the speech data based on related literature. The recognition unit can also reduce misrecognition by comparing the context of the speech data with the related literature. For example, the recognition unit can refer to related literature to select an optimal recognition method. By referring to the related literature, recognition accuracy is improved. Some or all of the above-described processing in the recognition unit can be performed using, for example, AI, or without AI. For example, the recognition unit can input related literature into a generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze related literature in real time to improve recognition accuracy. For example, the recognition unit can evaluate related literature in real time to reduce misrecognition. The recognition unit can also determine the priority of recognition data based on the related literature. For example, the recognition unit can preferentially refer to highly relevant literature. This allows the recognition unit to gain a detailed understanding of related literature and optimize recognition accuracy.

[0100] The recognition unit can perform recognition taking into account the market value of the voice data. For example, the recognition unit can prioritize recognition of voice data with high market value to improve accuracy. The recognition unit can also prioritize efficiency by leaving voice data with low market value for later. For example, the recognition unit optimally allocates recognition resources according to the market value of the voice data. This allows important data to be recognized preferentially by taking the market value of the voice data into consideration. Some or all of the above-described processing in the recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the recognition unit can input the market value of the voice data into the generation AI and cause the generation AI to improve recognition accuracy. Furthermore, the recognition unit can analyze the market value of the voice data in real time to improve recognition accuracy. For example, the recognition unit can evaluate the market value of the voice data in real time to reduce recognition errors. The recognition unit can also determine the priority of recognition data based on the market value of the voice data. For example, the recognition unit prioritizes recognition of voice data with high market value. This allows the recognition unit to grasp the market value of the voice data in detail and optimize recognition accuracy.

[0101] The operation unit can estimate the user's emotions and adjust the operation method based on the estimated user emotions. For example, when the user is relaxed, the operation unit provides a normal operation method. Furthermore, when the user is stressed, the operation unit can provide a simplified operation procedure. For example, when the user is excited, the operation unit temporarily suspends operation until the user calms down. This allows for more appropriate operation by adjusting the operation method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the operation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the operation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions. Furthermore, the operation unit can analyze the user's emotion data in real time and adjust the operation method. For example, the operation unit can monitor the user's facial expressions in real time and instantly detect changes in emotions. The operation unit can also accumulate user emotional data and analyze long-term emotional trends. For example, the operation unit can analyze the user's emotional data over time and identify patterns of emotional change. This allows the operation unit to grasp the user's emotions in detail and optimize the operation method.

[0102] During operation, the operation unit can analyze the user's past operation history and select the optimal operation method. For example, the operation unit can prioritize and provide operation methods that the user has used frequently in the past. The operation unit can also analyze the user's operation patterns and provide the most natural operation method. For example, the operation unit can provide the optimal operation procedure based on operation methods used by the user in the past. This allows the optimal operation method to be selected by analyzing the past operation history. Some or all of the above-described processing in the operation unit can be performed using, for example, AI, or can be performed without AI. For example, the operation unit can input the user's operation history data to a generation AI and cause the generation AI to select the optimal operation method. Furthermore, the operation unit can analyze the user's operation history in real time and adjust the operation method. For example, the operation unit can evaluate the user's operation pattern in real time and propose the optimal operation procedure. The operation unit can also determine the priority of operation data based on the user's operation history. For example, the operation unit can prioritize and use operation methods that the user has highly rated. This allows the operation unit to grasp the user's operation history in detail and optimize the operation method.

[0103] The operation unit can customize the operation means based on the user's current living situation during operation. For example, when the user operates the device at home, the operation unit provides an operation method that is optimal for the home. Furthermore, when the user operates the device while on the go, the operation unit can also provide an operation method that is optimal for the home. For example, the operation unit provides an operation method that is optimal for the home, according to the user's lifestyle. This allows for more appropriate operation by customizing the operation means based on the user's living situation. Some or all of the above-described processing in the operation unit may be performed using, for example, AI, or may be performed without AI. For example, the operation unit can input the user's living situation data into a generation AI and cause the generation AI to select an optimal operation means. Furthermore, the operation unit can analyze the user's living situation in real time and adjust the operation means. For example, the operation unit can evaluate the user's lifestyle in real time and suggest an optimal operation means. Furthermore, the operation unit can prioritize operation data based on the user's living situation. For example, the operation unit can prioritize operation methods that the user uses at home. This allows the operation unit to grasp the user's living situation in detail and optimize the operation means.

[0104] The operation unit can improve the operation method by reflecting user feedback during operation. The operation unit can improve the operation method based on, for example, feedback provided by the user. The operation unit can also analyze the user's feedback and provide an optimal operation procedure. For example, the operation unit can customize the operation method by referring to the user's past feedback. This allows the operation method to be improved by reflecting the user's feedback. Some or all of the above-mentioned processing in the operation unit can be performed using, for example, AI, or can be performed without using AI. For example, the operation unit can input user feedback data into a generation AI and cause the generation AI to improve the operation method. Furthermore, the operation unit can analyze user feedback in real time and adjust the operation method. For example, the operation unit can evaluate user feedback in real time and propose an optimal operation procedure. The operation unit can also determine the priority of operation data based on user feedback. For example, the operation unit can preferentially use operation methods that the user highly evaluates. This allows the operation unit to understand user feedback in detail and optimize the operation method.

[0105] The operation unit can estimate the user's emotions and determine the priority of operations based on the estimated user emotions. For example, when the user is relaxed, the operation unit performs operations with normal priority. Furthermore, when the user is stressed, the operation unit can prioritize important operations. For example, when the user is excited, the operation unit temporarily suspends operations until the user calms down. This allows important operations to be prioritized by determining the priority of operations according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the operation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the operation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the user's emotions. Furthermore, the operation unit can analyze the user's emotion data in real time and determine the priority of operations. For example, the operation unit can monitor the user's facial expressions in real time and instantly detect changes in emotions. The operation unit can also accumulate user emotional data and analyze long-term emotional trends. For example, the operation unit can analyze the user's emotional data over time and identify patterns of emotional change. This allows the operation unit to grasp the user's emotions in detail and optimize the priority of operations.

[0106] The operation unit can select the optimal operation method by taking into account the user's geographical location information during operation. For example, when the user is in a specific area, the operation unit provides the optimal operation method for that area. Furthermore, when the user is traveling, the operation unit can also provide the optimal operation method for the destination. For example, when the user is at home, the operation unit provides the optimal operation method for the home. This allows the optimal operation method to be selected by taking the user's geographical location information into consideration. Some or all of the above-described processing in the operation unit may be performed using, for example, AI, or may be performed without AI. For example, the operation unit can input the user's geographical location data into a generation AI and cause the generation AI to select the optimal operation method. Furthermore, the operation unit can analyze the user's geographical location information in real time and adjust the operation method. For example, the operation unit can evaluate the user's current location in real time and suggest the optimal operation procedure. The operation unit can also prioritize operation data based on the user's geographical location information. For example, the operation unit can prioritize the operation method used by the user in a specific area. This allows the operation unit to obtain a detailed understanding of the user's geographical location information and optimize the operation method.

[0107] During operation, the operation unit can analyze the user's social media activity and suggest an operation method. For example, the operation unit analyzes the language and dialect used by the user on social media and provides an optimal operation method. The operation unit can also suggest an operation method that is likely to be of interest to the user based on the content posted by the user on social media. For example, the operation unit provides an optimal operation method by referring to the activity of the user's friends on social media. In this way, the optimal operation method can be suggested by analyzing the user's social media activity. Some or all of the above-mentioned processing in the operation unit may be performed using, for example, AI, or may be performed without using AI. For example, the operation unit can input the user's social media data into a generation AI and cause the generation AI to suggest an optimal operation method. Furthermore, the operation unit can analyze the user's social media activity in real time and suggest an operation method. For example, the operation unit evaluates the user's social media activity in real time and suggests an optimal operation procedure. The operation unit can also determine the priority of operation data based on the user's social media activity. For example, the operation unit prioritizes the language and dialect used by the user on social media. This allows the operation unit to grasp the user's social media activities in detail and optimize the operation means.

[0108] The operation unit can customize the operation method by reflecting the user's past feedback during operation. The operation unit customizes the operation method based on, for example, feedback provided by the user. The operation unit can also analyze the user's feedback and provide an optimal operation procedure. For example, the operation unit improves the operation method by referring to the user's past feedback. In this way, the operation method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the operation unit may be performed using, for example, AI, or may be performed without AI. For example, the operation unit can input the user's feedback data into a generation AI and cause the generation AI to customize the operation method. Furthermore, the operation unit can analyze the user's feedback in real time and adjust the operation method. For example, the operation unit evaluates the user's feedback in real time and proposes an optimal operation procedure. The operation unit can also determine the priority of operation data based on the user's feedback. For example, the operation unit prioritizes the use of operation methods that the user highly evaluates. In this way, the operation unit can grasp the user's feedback in detail and optimize the operation method. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, learning unit, recognition unit, and operation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects voice data using the camera 42 and microphone 38B of the smart device 14 and transmits the collected data to the data processing device 12 by the control unit 46A. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and causes the generation AI to learn the collected voice data. The recognition unit is realized by the specific processing unit 290 of the data processing device 12 and recognizes voice using the learned generation AI. The operation unit is realized by the control unit 46A of the smart device 14 and operates IT equipment based on the recognized voice. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, learning unit, recognition unit, and operation unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects voice data using the camera 42 and microphone 238 of the smart glasses 214 and transmits the collected data to the data processing device 12 by the control unit 46A. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and causes the generation AI to learn the collected voice data. The recognition unit is realized by the specific processing unit 290 of the data processing device 12 and recognizes voice using the learned generation AI. The operation unit is realized by the control unit 46A of the smart glasses 214 and operates IT equipment based on the recognized voice. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, learning unit, recognition unit, and operation unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects voice data using the camera 42 and microphone 238 of the headset type terminal 314, and transmits the collected data to the data processing device 12 by the control unit 46A. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and causes the generation AI to learn the collected voice data. The recognition unit is realized by the specific processing unit 290 of the data processing device 12, and recognizes voice using the learned generation AI. The operation unit is realized by the control unit 46A of the headset type terminal 314, and operates IT equipment based on the recognized voice. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, learning unit, recognition unit, and operation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects voice data using the camera 42 and microphone 238 of the robot 414, and transmits the collected data to the data processing device 12 by the control unit 46A. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and causes the generation AI to learn the collected voice data. The recognition unit is realized by the specific processing unit 290 of the data processing device 12, and recognizes voice using the learned generation AI. The operation unit is realized by the control unit 46A of the robot 414, and operates IT equipment based on the recognized voice.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The voice recognition system may further include a health management unit that monitors the user's health condition. The health management unit may, for example, measure the user's heart rate and blood pressure and issue a warning if an abnormality is detected. The health management unit may also collect the user's health data and support long-term health management. For example, the health management unit may analyze the user's health data and identify changes in the user's health condition. This allows the voice recognition system to monitor the user's health condition and take appropriate measures.

[0111] The voice recognition system may further include an emotion adjustment unit that estimates the user's emotion and adjusts the accuracy of voice recognition based on the estimated emotion. For example, if the user is feeling stressed, the emotion adjustment unit may widen the tolerance range of voice recognition to reduce erroneous recognition. The emotion adjustment unit may also maintain normal recognition accuracy when the user is relaxed. This allows the voice recognition system to adjust recognition accuracy according to the user's emotion and provide a more comfortable operation.

[0112] The voice recognition system can further include a rhythm adjustment unit that learns the user's daily rhythm and collects voice data at optimal timing. For example, if the user is active in the morning, the rhythm adjustment unit may preferentially collect voice data in the morning. Alternatively, if the user is relaxed in the evening, the rhythm adjustment unit may collect voice data in the evening. This allows the voice recognition system to collect voice data in accordance with the user's daily rhythm and obtain more natural data.

[0113] The voice recognition system may further include an interest learning unit that learns the user's hobbies and interests and prioritizes collecting related voice data. For example, if the user is interested in music, the interest learning unit may collect music-related voice data. Alternatively, if the user is interested in sports, the interest learning unit may collect sports-related voice data. This allows the voice recognition system to collect voice data based on the user's hobbies and interests and obtain more relevant data.

[0114] The voice recognition system may further include an emotion timing unit that estimates the user's emotion and adjusts the timing of voice data collection based on the estimated emotion. For example, when the user is relaxed, the emotion timing unit collects voice data during natural conversation. Furthermore, when the user is feeling stressed, the emotion timing unit may delay the collection timing to collect voice data in a relaxed state. This allows the voice recognition system to adjust the collection timing according to the user's emotion and collect more natural voice data.

[0115] The speech recognition system may further include a history analysis unit that analyzes the user's past operation history and suggests the optimal operation method. For example, the history analysis unit may preferentially suggest operation methods that the user has used frequently in the past. The history analysis unit may also analyze the user's operation patterns and suggest the most natural operation method. This allows the speech recognition system to suggest the optimal operation method based on the user's past operation history and support the user's operation.

[0116] The voice recognition system may further include an emotion prioritization unit that estimates the user's emotion and determines the priority of operations based on the estimated emotion. For example, when the user is relaxed, the emotion prioritization unit performs operations with normal priority. Also, when the user is feeling stressed, the emotion prioritization unit may prioritize important operations. In this way, the voice recognition system determines the priority of operations according to the user's emotion, and can prioritize important operations.

[0117] The voice recognition system can further include a location information unit that selects the optimal operation method by taking into account the user's geographical location information. For example, if the user is in a specific area, the location information unit can provide the optimal operation method for that area. Also, if the user is traveling, the location information unit can provide the optimal operation method for the destination. This allows the voice recognition system to select the optimal operation method by taking into account the user's geographical location information and support the user's operation.

[0118] The voice recognition system can further include an emotion manipulation unit that estimates the user's emotion and adjusts the operation method based on the estimated emotion. For example, the emotion manipulation unit provides a normal operation method when the user is relaxed. The emotion manipulation unit can also provide a simplified operation procedure when the user is feeling stressed. This allows the voice recognition system to adjust the operation method according to the user's emotion and provide a more appropriate operation.

[0119] The speech recognition system may further include a social analysis unit that analyzes the user's social media activity and suggests the optimal operation method. The social analysis unit may, for example, analyze the language or dialect used by the user on social media and suggest the optimal operation method. The social analysis unit may also suggest operation methods that the user may be interested in based on the content of the user's social media posts. This allows the speech recognition system to analyze the user's social media activity and suggest the optimal operation method.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The collection unit collects audio data. The audio data includes, but is not limited to, audio file formats, sampling rates, bit rates, etc. The collection unit collects a variety of audio data, including, for example, the characteristic pronunciation and vocabulary of Tsugaru dialect. The collection unit can also collect audio data of dialects of other regions, such as Kansai dialect and Hakata dialect. For example, the collection unit collects audio data from various situations, such as everyday conversations and conversations in specific situations. Step 2: The learning unit uses the generation AI to learn the voice data collected by the collection unit. The learning is performed based on, for example, the machine learning algorithm used and the type of training data, but is not limited to these examples. For example, the learning unit uses the generation AI to learn everyday conversations and conversations in specific situations. The learning unit can also use the generation AI to learn voice data in dialects of other regions. Step 3: The recognition unit recognizes the speech based on the results of learning by the learning unit. Recognition is performed based on, for example, a speech recognition algorithm, recognition accuracy, and tolerance for misrecognition, but is not limited to these examples. For example, the recognition unit recognizes speech spoken by an elderly person to an IT device in Tsugaru dialect. The recognition unit can also recognize speech spoken by users of a specific age group to an IT device. Step 4: The operation unit performs an operation based on the voice recognized by the recognition unit. The operation is performed based on, for example, the device to be operated, the type of operation, and the accuracy of the operation, but is not limited to these examples. For example, the operation unit operates an IT device based on the recognized voice.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0128] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0144] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0160] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0166] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0167] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0168] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0169] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0170] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0172] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0173] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0177] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0178] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0179] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0183] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0184] 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.

[0185] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0186] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0187] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0188] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0190] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0191] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0192] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0193] [Explanation of symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects voice data; a learning unit that learns the voice data collected by the collection unit; a recognition unit that recognizes speech based on the results of learning by the learning unit; an operation unit that performs an operation based on the voice recognized by the recognition unit; A system characterized by:

2. The collecting unit Collect multiple audio data sets that include the distinctive pronunciation and vocabulary of Tsugaru dialect 2. The system of claim 1.

3. The learning unit Learn everyday conversations and conversations in specific situations using generative AI 2. The system of claim 1.

4. The recognition unit Recognizing speech spoken in Tsugaru dialect by users of a specific age group to IT devices 2. The system of claim 1.

5. The operation unit includes: Control IT devices based on recognized voice 2. The system of claim 1.

6. The collecting unit Collect speech data for Kansai dialect, Hakata dialect, and other regional dialects 2. The system of claim 1.

7. The learning unit Learning speech data from dialects of other regions using generative AI 2. The system of claim 1.

8. The collecting unit The user's emotions are estimated, and the timing of collecting voice data is adjusted based on the estimated user's emotions.

2. The system of claim 1.

Images