system

Abstract

The system according to this embodiment aims to construct an individual's personality model based on data from daily life. [Solution] The system according to the embodiment comprises a data collection unit, a data preprocessing unit, and a model construction unit. The data collection unit collects data from daily life. The data preprocessing unit converts the data collected by the data collection unit into text. The model construction unit constructs an individual personality model based on the data converted into text by the data preprocessing unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the methods of self-analysis and self-understanding are limited and deep insights cannot be obtained.

[0005] The system according to the embodiment aims to construct an individual personality model based on daily life data.

Means for Solving the Problems

[0006] The system according to the embodiment includes a data collection unit, a data preprocessing unit, and a model construction unit. The data collection unit collects daily life data. The data preprocessing unit texts the data collected by the data collection unit. The model construction unit constructs an individual personality model based on the data texted by the data preprocessing unit. [Effects of the Invention]

[0007] The system according to this embodiment can construct an individual's personality model based on data from their daily life. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The personal AI personality model construction service according to an embodiment of the present invention is a system that constructs an AI model that reproduces an individual's personality based on data recorded by the individual in their daily life. This system films and records daily life over a long period of time, collecting data in various situations and emotional states. Next, the collected audio data is converted into text using high-precision speech recognition technology, and slurred speech and mispronunciations are corrected by a language model. In addition, situations are analyzed from video data and converted into text. Based on this text data, a generative AI (large-scale language model) is fine-tuned to construct an individual's personality model. For example, the personal AI personality model construction service uses a wearable camera and audio recording device to film and record daily life over a long period of time. This collects data in various situations and emotional states. Next, the collected audio data is converted into text using high-precision speech recognition technology, and slurred speech and mispronunciations are corrected by a language model. In addition, situations are analyzed from video data and converted into text. Based on this text data, a generative AI (large-scale language model) is fine-tuned to construct an individual's personality model. This means that the personal AI personality model building service can be used in a variety of ways, including deepening self-understanding, improving communication, supporting creative activities, and improving the accuracy of a personalized AI agent.

[0029] The personal AI personality model construction service according to this embodiment comprises a data collection unit, a data preprocessing unit, and a model construction unit. The data collection unit collects data from daily life. The data collection unit can, for example, collect data from daily life over a long period of time using a wearable device. The data collection unit can, for example, collect audio data from daily life using an audio recording device. The data collection unit can, for example, collect video data from daily life using a video recording device. The data preprocessing unit converts the data collected by the data collection unit into text. The data preprocessing unit can, for example, convert audio data into text using high-precision speech recognition technology. The data preprocessing unit can, for example, correct poor articulation or mispronunciation in audio data. The data preprocessing unit can, for example, analyze situations from video data and convert them into text. The model construction unit constructs an individual personality model based on the data converted into text by the data preprocessing unit. The model construction unit can, for example, fine-tune the generated AI based on the collected text data to construct an individual personality model. The model construction unit can, for example, perform periodic data addition and retraining. As a result, the personal AI personality model building service according to this embodiment can collect data from daily life, convert it into text, and build an individual personality model.

[0030] The data collection unit can utilize various devices to collect data from daily life. Specifically, wearable devices can be used to collect biometric data such as the user's activity level, heart rate, etc., over long periods. Wearable devices are worn on the user's arm or chest, allowing for natural data collection during daily life, minimizing the burden on the user. Furthermore, voice recording devices can be used to collect audio data such as conversations and monologues during daily life. Voice recording devices are attached to the user's clothing or accessories and can record ambient sounds in high quality, capturing the user's natural speech and emotional changes. Video recording devices can also be used to collect video data from daily life. Video recording devices are attached to the user's glasses or hats and can record video from the user's perspective, allowing for detailed recording of the user's actions and surrounding environment. By using these devices in combination, the data collection unit can comprehensively collect diverse aspects of the user's daily life. In addition, the data collection unit can use encryption technology to securely store the collected data and protect privacy. This allows for the collection of high-quality data while protecting the user's personal information.

[0031] The data preprocessing unit can utilize advanced technologies to convert data collected by the data collection unit into text. For example, when converting audio data into text, it can use highly accurate speech recognition technology. This technology analyzes the audio data and accurately transcribes the spoken content into text. Furthermore, it is equipped with a function to correct poor articulation and mispronunciation in the audio data, allowing for a more accurate reflection of the user's speech. It can also use technology to analyze situations from video data and transcribe them into text. By analyzing video data, it can understand the user's actions and surrounding environment and record them as text. For example, it can transcribe information such as where the user is, what they are doing, and who they are talking to. As a result, the data preprocessing unit can transcribe the collected data in detail and accurately and provide it to the model building unit. Furthermore, the data preprocessing unit can perform preprocessing such as noise reduction and data normalization to improve the quality of the collected data. This ensures data consistency and reliability, allowing the model building unit to construct a personality model using high-quality data.

[0032] The model building unit can utilize generative AI to build individual personality models based on data transcribed into text by the data preprocessing unit. The generative AI can analyze the collected text data and learn the user's speech patterns and behavioral characteristics. For example, it can build a personality model that reflects the user's personality, preferences, and values ​​based on the user's speech content and behavioral history. Furthermore, the model building unit can improve the accuracy of the personality model by regularly adding new data and retraining the generative AI. This allows it to maintain a more accurate personality model that reflects the user's latest behavior and speech content. In addition, the model building unit can collect user feedback and continuously improve the accuracy and reliability of the model. For example, it can adjust the model's output based on user feedback to provide a personality model that meets user expectations. This allows the model building unit to build and provide high-quality personality models that meet user needs. Furthermore, the model building unit can integrate the constructed personality model with other systems and services. For example, by integrating it into applications such as chatbots and virtual assistants, it can provide advanced dialogue and support utilizing the user's personality model. This allows the model building unit to provide a variety of services that enrich the user's life.

[0033] The data collection unit can collect data from daily life over a long period of time using wearable devices. For example, the data collection unit can collect video data from daily life using a wearable camera. For example, the data collection unit can collect audio data from daily life using a wearable microphone. For example, the data collection unit can collect behavioral data from daily life using a wearable sensor. This makes it possible to collect data from daily life over a long period of time by using wearable devices. Some or all of the above-described processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input video data acquired by a wearable camera into a generating AI and have the generating AI perform analysis of the video data.

[0034] The data preprocessing unit can convert audio data into text using high-precision speech recognition technology and correct for slurred speech and mispronunciation. For example, the data preprocessing unit can convert audio data into text using deep learning-based speech recognition technology. For example, the data preprocessing unit can convert audio data into text using HMM-based speech recognition technology. For example, the data preprocessing unit can analyze audio data using speech recognition technology to correct for slurred speech. For example, the data preprocessing unit can analyze audio data using speech recognition technology to correct for mispronunciation. This allows for high-precision text conversion of audio data and correction of slurred speech and mispronunciation. Some or all of the above-described processes in the data preprocessing unit may be performed using AI, or without AI. For example, the data preprocessing unit can input audio data into a generating AI and have the generating AI perform the text conversion of the audio data.

[0035] The data preprocessing unit can analyze situations from video data and convert them into text. For example, the data preprocessing unit can analyze video data to identify situations such as location, time, and actions. For example, the data preprocessing unit can analyze video data to generate text information related to a specific situation. For example, the data preprocessing unit can analyze video data and convert it into text based on the situation. This allows for the analysis and conversion of situations from video data into text. Some or all of the above-described processes in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input video data into a generating AI and have the generating AI perform situation analysis and text conversion.

[0036] The model building unit can construct an individual personality model by fine-tuning the generative AI based on the collected text data. For example, the model building unit can train the generative AI based on the collected text data and fine-tune it to match the individual's language patterns and thinking tendencies. For example, the model building unit can fine-tune the generative AI based on the collected text data and apply an algorithm to construct an individual personality model. This allows the model building unit to construct an individual personality model by fine-tuning the generative AI based on the collected text data. Some or all of the above-described processes in the model building unit may be performed using the generative AI, or without it. For example, the model building unit can input the collected text data into the generative AI and have the generative AI construct an individual personality model.

[0037] The model building unit can perform periodic data addition and retraining. For example, the model building unit can add new data every month and retrain the generative AI. For example, the model building unit can add new data every week and retrain the generative AI. For example, the model building unit can add new data every day and retrain the generative AI. This allows the accuracy of the model to be maintained by performing periodic data addition and retraining. Some or all of the above processes in the model building unit may be performed using the generative AI, or not using the generative AI. For example, the model building unit can input new data into the generative AI and have the generative AI perform retraining.

[0038] The data collection unit can analyze the user's past behavioral history and select the optimal data collection method. For example, the data collection unit can prioritize data collection at places the user has frequently visited in the past. For example, the data collection unit can analyze the user's behavioral patterns and concentrate data collection during specific time periods. For example, the data collection unit can focus on collecting data related to specific events or activities from the user's past behavioral history. This allows the optimal data collection method to be selected by analyzing the user's past behavioral history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's behavioral history data into a generating AI and have the generating AI select the optimal data collection method.

[0039] The data collection unit can filter data based on the user's current activities and areas of interest during data collection. For example, if the user is playing sports, the data collection unit can prioritize collecting data related to that activity. For example, if the user is reading, the data collection unit can collect data related to reading and filter out other data. For example, if the user is traveling, the data collection unit can collect data related to travel and filter out data related to daily life. This allows for the collection of highly relevant data by filtering data based on the user's current activities and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user activity data into a generating AI and have the generating AI perform the filtering.

[0040] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, if the user is in a specific location, the data collection unit can prioritize the collection of data related to that location. For example, if the user is traveling, the data collection unit can prioritize the collection of data based on the geographical location information of the travel destination. For example, if the user is at home, the data collection unit can prioritize the collection of data related to activities at home. In this way, by considering the user's geographical location information, highly relevant data can be prioritized. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and cause the generating AI to prioritize the collection of highly relevant data.

[0041] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can collect relevant data based on what a user shares on social media. For example, the data collection unit can analyze a user's social media activity patterns and collect data related to specific topics. For example, the data collection unit can collect relevant data based on the accounts a user follows on social media. In this way, relevant data can be collected by analyzing a user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0042] The data preprocessing unit can adjust the level of detail in the transcription of audio data based on the importance of the utterances. For example, the data preprocessing unit can transcribe important utterances in detail and less important utterances in detail. For example, the data preprocessing unit can transcribe particularly emphasized parts of a conversation in detail. For example, if the user uses a specific keyword, the data preprocessing unit can transcribe that part in detail. This allows important utterances to be transcribed in detail by adjusting the level of detail based on the importance of the utterances. Some or all of the above processing in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail in the transcription.

[0043] The data preprocessing unit can apply different analysis algorithms to video data depending on the category of the situation when transcribing it into text. For example, the data preprocessing unit can apply an algorithm to video data of a meeting that transcribes the content of the discussion in detail. For example, the data preprocessing unit can apply an algorithm to video data of a home that simplifies everyday conversations into text. For example, the data preprocessing unit can apply an algorithm to video data of an event that highlights the event's key features into text. By applying different analysis algorithms depending on the category of the situation, appropriate transcription becomes possible. Some or all of the above processing in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input video data into a generating AI and have the generating AI apply an analysis algorithm according to the category of the situation.

[0044] The data preprocessing unit can determine the priority of transcription based on the timing of utterances when transcribing audio data into text. For example, the data preprocessing unit can prioritize the transcription of parts of a conversation that are particularly emphasized. For example, if a user uses a specific keyword, the data preprocessing unit can prioritize the transcription of that part. For example, the data preprocessing unit can prioritize the transcription of important utterances in line with the flow of the conversation. This ensures that important utterances are prioritized for transcription by determining the priority of transcription based on the timing of utterances. Some or all of the above-described processes in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input audio data into a generating AI and have the generating AI determine the transcription priority.

[0045] The data preprocessing unit can adjust the order of text transcription based on the relevance of the situations when transcribing video data. For example, in video data of a meeting, the data preprocessing unit can adjust the order of text transcription according to the flow of the discussion. For example, in video data of a home, the data preprocessing unit can adjust the order of text transcription according to the flow of everyday conversation. For example, in video data of an event, the data preprocessing unit can prioritize the transcription of event highlights. This allows for appropriate transcription by adjusting the order of text transcription based on the relevance of the situations. Some or all of the above processing in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input video data into a generating AI and have the generating AI perform the adjustment of the text transcription order based on the relevance of the situations.

[0046] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0047] The data collection unit can monitor the user's activity level and determine the optimal timing for data collection. For example, if the user is exercising, it can prioritize collecting data related to that activity. This enables appropriate data collection according to the user's activity level. For example, if the user is resting, it can collect data related to their relaxation state. Also, if the user is working, it can prioritize collecting data related to their work. Furthermore, by monitoring the user's activity level in real time and dynamically adjusting the timing of data collection, the accuracy of data collection can be improved.

[0048] The data collection unit can analyze the user's ambient sounds and select the optimal data collection method. For example, if the user is in a quiet environment, the collection of audio data can be prioritized. This enables appropriate data collection according to the ambient sounds. For example, if the user is in a noisy environment, the collection of video data can be prioritized. Also, if the user is in a natural environment, ambient sounds can be collected to gather data that enhances relaxation. Furthermore, by analyzing the user's ambient sounds in real time and dynamically adjusting the data collection method, the accuracy of data collection can be improved.

[0049] The data collection unit can monitor the user's device usage and determine the optimal timing for data collection. For example, if the user is using a smartphone, it can prioritize collecting data related to that usage. This enables appropriate data collection according to device usage. For example, if the user is using a PC, it can collect data related to that usage. Also, if the user is using a tablet, it can prioritize collecting data related to that usage. Furthermore, by monitoring the user's device usage in real time and dynamically adjusting the timing of data collection, the accuracy of data collection can be improved.

[0050] The data collection unit can monitor the user's health data and select the optimal data collection method. For example, it can collect the user's sleep data and prioritize the collection of data related to sleep quality. This enables appropriate data collection according to the health data. For example, it can collect the user's dietary data and prioritize the collection of data related to the content of the diet. It can also collect the user's exercise data and prioritize the collection of data related to the effects of exercise. Furthermore, by monitoring the user's health data in real time and dynamically adjusting the data collection method, the accuracy of data collection can be improved.

[0051] The data collection unit can analyze users' hobbies and interests and select the optimal data collection method. For example, if a user is interested in music, it can prioritize collecting data related to that interest. This enables appropriate data collection tailored to hobbies and interests. For example, if a user is interested in sports, it can prioritize collecting data related to that interest. Also, if a user is interested in cooking, it can prioritize collecting data related to that interest. Furthermore, by analyzing users' hobbies and interests in real time and dynamically adjusting the data collection method, the accuracy of data collection can be improved.

[0052] The following briefly describes the processing flow for example form 1.

[0053] Step 1: The data collection unit collects data from daily life. For example, data from daily life can be collected over a long period using wearable devices. Audio data from daily life can also be collected using voice recording devices, and video data from daily life can be collected using video recording devices. Step 2: The data preprocessing unit converts the data collected by the data acquisition unit into text. For example, it can convert audio data into text using high-precision speech recognition technology, correcting poor articulation and mispronunciation in the audio data. It can also analyze situations from video data and convert them into text. Step 3: The model building unit constructs an individual personality model based on the data that has been transcribed into text by the data preprocessing unit. For example, the generated AI can be fine-tuned based on the collected text data to build an individual personality model, and periodic data additions and retraining can be performed.

[0054] (Example of form 2) The personal AI personality model construction service according to an embodiment of the present invention is a system that constructs an AI model that reproduces an individual's personality based on data recorded by the individual in their daily life. This system films and records daily life over a long period of time, collecting data in various situations and emotional states. Next, the collected audio data is converted into text using high-precision speech recognition technology, and slurred speech and mispronunciations are corrected by a language model. In addition, situations are analyzed from video data and converted into text. Based on this text data, a generative AI (large-scale language model) is fine-tuned to construct an individual's personality model. For example, the personal AI personality model construction service uses a wearable camera and audio recording device to film and record daily life over a long period of time. This collects data in various situations and emotional states. Next, the collected audio data is converted into text using high-precision speech recognition technology, and slurred speech and mispronunciations are corrected by a language model. In addition, situations are analyzed from video data and converted into text. Based on this text data, a generative AI (large-scale language model) is fine-tuned to construct an individual's personality model. This means that the personal AI personality model building service can be used in a variety of ways, including deepening self-understanding, improving communication, supporting creative activities, and improving the accuracy of a personalized AI agent.

[0055] The personal AI personality model construction service according to this embodiment comprises a data collection unit, a data preprocessing unit, and a model construction unit. The data collection unit collects data from daily life. The data collection unit can, for example, collect data from daily life over a long period of time using a wearable device. The data collection unit can, for example, collect audio data from daily life using an audio recording device. The data collection unit can, for example, collect video data from daily life using a video recording device. The data preprocessing unit converts the data collected by the data collection unit into text. The data preprocessing unit can, for example, convert audio data into text using high-precision speech recognition technology. The data preprocessing unit can, for example, correct poor articulation or mispronunciation in audio data. The data preprocessing unit can, for example, analyze situations from video data and convert them into text. The model construction unit constructs an individual personality model based on the data converted into text by the data preprocessing unit. The model construction unit can, for example, fine-tune the generated AI based on the collected text data to construct an individual personality model. The model construction unit can, for example, perform periodic data addition and retraining. As a result, the personal AI personality model building service according to this embodiment can collect data from daily life, convert it into text, and build an individual personality model.

[0056] The data collection unit can utilize various devices to collect data from daily life. Specifically, wearable devices can be used to collect biometric data such as the user's activity level, heart rate, etc., over long periods. Wearable devices are worn on the user's arm or chest, allowing for natural data collection during daily life, minimizing the burden on the user. Furthermore, voice recording devices can be used to collect audio data such as conversations and monologues during daily life. Voice recording devices are attached to the user's clothing or accessories and can record ambient sounds in high quality, capturing the user's natural speech and emotional changes. Video recording devices can also be used to collect video data from daily life. Video recording devices are attached to the user's glasses or hats and can record video from the user's perspective, allowing for detailed recording of the user's actions and surrounding environment. By using these devices in combination, the data collection unit can comprehensively collect diverse aspects of the user's daily life. In addition, the data collection unit can use encryption technology to securely store the collected data and protect privacy. This allows for the collection of high-quality data while protecting the user's personal information.

[0057] The data preprocessing unit can utilize advanced technologies to convert data collected by the data collection unit into text. For example, when converting audio data into text, it can use highly accurate speech recognition technology. This technology analyzes the audio data and accurately transcribes the spoken content into text. Furthermore, it is equipped with a function to correct poor articulation and mispronunciation in the audio data, allowing for a more accurate reflection of the user's speech. It can also use technology to analyze situations from video data and transcribe them into text. By analyzing video data, it can understand the user's actions and surrounding environment and record them as text. For example, it can transcribe information such as where the user is, what they are doing, and who they are talking to. As a result, the data preprocessing unit can transcribe the collected data in detail and accurately and provide it to the model building unit. Furthermore, the data preprocessing unit can perform preprocessing such as noise reduction and data normalization to improve the quality of the collected data. This ensures data consistency and reliability, allowing the model building unit to construct a personality model using high-quality data.

[0058] The model building unit can utilize generative AI to build individual personality models based on data transcribed into text by the data preprocessing unit. The generative AI can analyze the collected text data and learn the user's speech patterns and behavioral characteristics. For example, it can build a personality model that reflects the user's personality, preferences, and values ​​based on the user's speech content and behavioral history. Furthermore, the model building unit can improve the accuracy of the personality model by regularly adding new data and retraining the generative AI. This allows it to maintain a more accurate personality model that reflects the user's latest behavior and speech content. In addition, the model building unit can collect user feedback and continuously improve the accuracy and reliability of the model. For example, it can adjust the model's output based on user feedback to provide a personality model that meets user expectations. This allows the model building unit to build and provide high-quality personality models that meet user needs. Furthermore, the model building unit can integrate the constructed personality model with other systems and services. For example, by integrating it into applications such as chatbots and virtual assistants, it can provide advanced dialogue and support utilizing the user's personality model. This allows the model building unit to provide a variety of services that enrich the user's life.

[0059] The data collection unit can collect data from daily life over a long period of time using wearable devices. For example, the data collection unit can collect video data from daily life using a wearable camera. For example, the data collection unit can collect audio data from daily life using a wearable microphone. For example, the data collection unit can collect behavioral data from daily life using a wearable sensor. This makes it possible to collect data from daily life over a long period of time by using wearable devices. Some or all of the above-described processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input video data acquired by a wearable camera into a generating AI and have the generating AI perform analysis of the video data.

[0060] The data preprocessing unit can convert audio data into text using high-precision speech recognition technology and correct for slurred speech and mispronunciation. For example, the data preprocessing unit can convert audio data into text using deep learning-based speech recognition technology. For example, the data preprocessing unit can convert audio data into text using HMM-based speech recognition technology. For example, the data preprocessing unit can analyze audio data using speech recognition technology to correct for slurred speech. For example, the data preprocessing unit can analyze audio data using speech recognition technology to correct for mispronunciation. This allows for high-precision text conversion of audio data and correction of slurred speech and mispronunciation. Some or all of the above-described processes in the data preprocessing unit may be performed using AI, or without AI. For example, the data preprocessing unit can input audio data into a generating AI and have the generating AI perform the text conversion of the audio data.

[0061] The data preprocessing unit can analyze situations from video data and convert them into text. For example, the data preprocessing unit can analyze video data to identify situations such as location, time, and actions. For example, the data preprocessing unit can analyze video data to generate text information related to a specific situation. For example, the data preprocessing unit can analyze video data and convert it into text based on the situation. This allows for the analysis and conversion of situations from video data into text. Some or all of the above-described processes in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input video data into a generating AI and have the generating AI perform situation analysis and text conversion.

[0062] The model building unit can construct an individual personality model by fine-tuning the generative AI based on the collected text data. For example, the model building unit can train the generative AI based on the collected text data and fine-tune it to match the individual's language patterns and thinking tendencies. For example, the model building unit can fine-tune the generative AI based on the collected text data and apply an algorithm to construct an individual personality model. This allows the model building unit to construct an individual personality model by fine-tuning the generative AI based on the collected text data. Some or all of the above-described processes in the model building unit may be performed using the generative AI, or without it. For example, the model building unit can input the collected text data into the generative AI and have the generative AI construct an individual personality model.

[0063] The model building unit can perform periodic data addition and retraining. For example, the model building unit can add new data every month and retrain the generative AI. For example, the model building unit can add new data every week and retrain the generative AI. For example, the model building unit can add new data every day and retrain the generative AI. This allows the accuracy of the model to be maintained by performing periodic data addition and retraining. Some or all of the above processes in the model building unit may be performed using the generative AI, or not using the generative AI. For example, the model building unit can input new data into the generative AI and have the generative AI perform retraining.

[0064] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can reduce the frequency of data collection and collect data when the user is relaxed. For example, if the user is excited, the data collection unit can collect data at the peak of the emotion and record the changes in emotion in detail. For example, if the user is tired, the data collection unit can temporarily stop data collection and resume it after rest. This allows for the collection of more appropriate data by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0065] The data collection unit can analyze the user's past behavioral history and select the optimal data collection method. For example, the data collection unit can prioritize data collection at places the user has frequently visited in the past. For example, the data collection unit can analyze the user's behavioral patterns and concentrate data collection during specific time periods. For example, the data collection unit can focus on collecting data related to specific events or activities from the user's past behavioral history. This allows the optimal data collection method to be selected by analyzing the user's past behavioral history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's behavioral history data into a generating AI and have the generating AI select the optimal data collection method.

[0066] The data collection unit can filter data based on the user's current activities and areas of interest during data collection. For example, if the user is playing sports, the data collection unit can prioritize collecting data related to that activity. For example, if the user is reading, the data collection unit can collect data related to reading and filter out other data. For example, if the user is traveling, the data collection unit can collect data related to travel and filter out data related to daily life. This allows for the collection of highly relevant data by filtering data based on the user's current activities and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user activity data into a generating AI and have the generating AI perform the filtering.

[0067] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated user emotions. For example, if the user is sad, the data collection unit can prioritize collecting events and conversations related to that emotion. For example, if the user is happy, the data collection unit can prioritize collecting positive events and conversations related to that emotion. For example, if the user is angry, the data collection unit can prioritize collecting triggering events and conversations related to that emotion. In this way, important data can be collected preferentially by determining the priority of data to collect based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI determine the priority of data to collect.

[0068] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, if the user is in a specific location, the data collection unit can prioritize the collection of data related to that location. For example, if the user is traveling, the data collection unit can prioritize the collection of data based on the geographical location information of the travel destination. For example, if the user is at home, the data collection unit can prioritize the collection of data related to activities at home. In this way, by considering the user's geographical location information, highly relevant data can be prioritized. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the user's geographical location information into a generating AI and cause the generating AI to prioritize the collection of highly relevant data.

[0069] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can collect relevant data based on what a user shares on social media. For example, the data collection unit can analyze a user's social media activity patterns and collect data related to specific topics. For example, the data collection unit can collect relevant data based on the accounts a user follows on social media. In this way, relevant data can be collected by analyzing a user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0070] The data preprocessing unit can estimate the user's emotions and adjust the text formatting based on the estimated emotions. For example, if the user is sad, the data preprocessing unit can use expressions that reflect those emotions when creating the text. For example, if the user is happy, the data preprocessing unit can use positive expressions when creating the text. For example, if the user is angry, the data preprocessing unit can use expressions that reflect the intensity of those emotions when creating the text. This allows for emotionally reflective text by adjusting the text formatting based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the data preprocessing unit may be performed using AI or not. For example, the data preprocessing unit can input user emotion data into a generative AI and have the generative AI adjust the text formatting.

[0071] The data preprocessing unit can adjust the level of detail in the transcription of audio data based on the importance of the utterances. For example, the data preprocessing unit can transcribe important utterances in detail and less important utterances in detail. For example, the data preprocessing unit can transcribe particularly emphasized parts of a conversation in detail. For example, if the user uses a specific keyword, the data preprocessing unit can transcribe that part in detail. This allows important utterances to be transcribed in detail by adjusting the level of detail based on the importance of the utterances. Some or all of the above processing in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input audio data into a generating AI and have the generating AI perform the adjustment of the level of detail in the transcription.

[0072] The data preprocessing unit can apply different analysis algorithms to video data depending on the category of the situation when transcribing it into text. For example, the data preprocessing unit can apply an algorithm to video data of a meeting that transcribes the content of the discussion in detail. For example, the data preprocessing unit can apply an algorithm to video data of a home that simplifies everyday conversations into text. For example, the data preprocessing unit can apply an algorithm to video data of an event that highlights the event's key features into text. By applying different analysis algorithms depending on the category of the situation, appropriate transcription becomes possible. Some or all of the above processing in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input video data into a generating AI and have the generating AI apply an analysis algorithm according to the category of the situation.

[0073] The data preprocessing unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is in a hurry, the data preprocessing unit can produce a short, concise text. If the user is relaxed, the data preprocessing unit can produce a longer text with detailed explanations. If the user is excited, the data preprocessing unit can produce a longer text that reflects the intensity of the emotion. By adjusting the length of the text based on the user's emotions, appropriate text tailored to the emotion becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data preprocessing unit may be performed using AI or not. For example, the data preprocessing unit can input user emotion data into the generative AI and have the generative AI adjust the length of the text.

[0074] The data preprocessing unit can determine the priority of transcription based on the timing of utterances when transcribing audio data into text. For example, the data preprocessing unit can prioritize the transcription of parts of a conversation that are particularly emphasized. For example, if a user uses a specific keyword, the data preprocessing unit can prioritize the transcription of that part. For example, the data preprocessing unit can prioritize the transcription of important utterances in line with the flow of the conversation. This ensures that important utterances are prioritized for transcription by determining the priority of transcription based on the timing of utterances. Some or all of the above-described processes in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input audio data into a generating AI and have the generating AI determine the transcription priority.

[0075] The data preprocessing unit can adjust the order of text transcription based on the relevance of the situations when transcribing video data. For example, in video data of a meeting, the data preprocessing unit can adjust the order of text transcription according to the flow of the discussion. For example, in video data of a home, the data preprocessing unit can adjust the order of text transcription according to the flow of everyday conversation. For example, in video data of an event, the data preprocessing unit can prioritize the transcription of event highlights. This allows for appropriate transcription by adjusting the order of text transcription based on the relevance of the situations. Some or all of the above processing in the data preprocessing unit may be performed using AI, for example, or without AI. For example, the data preprocessing unit can input video data into a generating AI and have the generating AI perform the adjustment of the text transcription order based on the relevance of the situations.

[0076] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0077] The data collection unit can collect the user's physiological data and use it for emotion estimation. For example, it can collect physiological data such as heart rate and skin electrical activity to estimate the user's stress level and relaxation state. This allows for a more accurate understanding of the user's emotional state and enables adjustments to the timing and content of data collection. For instance, if the user is in a high-stress state, data collection can be temporarily stopped and resumed after they return to a relaxed state. Conversely, if the user is relaxed, data to maintain that state can be prioritized for collection. Furthermore, by analyzing the user's physiological data, changes in emotion can be tracked in real time, improving the accuracy of data collection.

[0078] The data collection unit can analyze users' social interactions and use this information for emotion estimation. For example, it can analyze what kind of conversations users are having with others and what facial expressions they are making to estimate their emotional state. This allows for a more accurate understanding of the user's emotional state and enables adjustments to the timing and content of data collection. For instance, if a user is having a pleasant conversation with a friend, the data can be prioritized to reflect the user's positive emotions. Conversely, if a user is experiencing stress, the data collection can be adjusted to identify the conversation or situation causing the stress. Furthermore, by analyzing users' social interactions, changes in emotions can be tracked in real time, improving the accuracy of data collection.

[0079] The data preprocessing unit can estimate the user's emotions and filter the data based on those estimates. For example, if the user is sad, data related to that emotion can be prioritized for text conversion and other data filtered. This allows for priority processing of important data based on the user's emotions. For instance, if the user is happy, positive events and conversations related to that emotion can be prioritized for text conversion. Similarly, if the user is angry, triggering events and conversations related to that emotion can be prioritized for text conversion. Furthermore, the accuracy of data preprocessing can be improved by estimating the user's emotions in real time and dynamically adjusting data filtering.

[0080] The data preprocessing unit can estimate the user's emotions and summarize the data based on those emotions. For example, if the user is in a hurry, it can generate a short, concise summary. This allows for the provision of an appropriate summary tailored to the user's emotions. For example, if the user is relaxed, it can generate a longer summary with more detailed explanations. If the user is excited, it can generate a summary that reflects the intensity of their emotions. Furthermore, by estimating the user's emotions in real time and dynamically adjusting the content of the summary, the accuracy of data preprocessing can be improved.

[0081] The data preprocessing unit can estimate the user's emotions and classify the data based on those emotions. For example, if a user is sad, data related to that emotion can be classified into a specific category. This allows for appropriate data classification based on the user's emotions. For example, if a user is happy, positive events and conversations related to that emotion can be classified into a specific category. Similarly, if a user is angry, triggering events and conversations related to that emotion can be classified into a specific category. Furthermore, by estimating the user's emotions in real time and dynamically adjusting the data classification, the accuracy of data preprocessing can be improved.

[0082] The data collection unit can monitor the user's activity level and determine the optimal timing for data collection. For example, if the user is exercising, it can prioritize collecting data related to that activity. This enables appropriate data collection according to the user's activity level. For example, if the user is resting, it can collect data related to their relaxation state. Also, if the user is working, it can prioritize collecting data related to their work. Furthermore, by monitoring the user's activity level in real time and dynamically adjusting the timing of data collection, the accuracy of data collection can be improved.

[0083] The data collection unit can analyze the user's ambient sounds and select the optimal data collection method. For example, if the user is in a quiet environment, the collection of audio data can be prioritized. This enables appropriate data collection according to the ambient sounds. For example, if the user is in a noisy environment, the collection of video data can be prioritized. Also, if the user is in a natural environment, ambient sounds can be collected to gather data that enhances relaxation. Furthermore, by analyzing the user's ambient sounds in real time and dynamically adjusting the data collection method, the accuracy of data collection can be improved.

[0084] The data collection unit can monitor the user's device usage and determine the optimal timing for data collection. For example, if the user is using a smartphone, it can prioritize collecting data related to that usage. This enables appropriate data collection according to device usage. For example, if the user is using a PC, it can collect data related to that usage. Also, if the user is using a tablet, it can prioritize collecting data related to that usage. Furthermore, by monitoring the user's device usage in real time and dynamically adjusting the timing of data collection, the accuracy of data collection can be improved.

[0085] The data collection unit can monitor the user's health data and select the optimal data collection method. For example, it can collect the user's sleep data and prioritize the collection of data related to sleep quality. This enables appropriate data collection according to the health data. For example, it can collect the user's dietary data and prioritize the collection of data related to the content of the diet. It can also collect the user's exercise data and prioritize the collection of data related to the effects of exercise. Furthermore, by monitoring the user's health data in real time and dynamically adjusting the data collection method, the accuracy of data collection can be improved.

[0086] The data collection unit can analyze users' hobbies and interests and select the optimal data collection method. For example, if a user is interested in music, it can prioritize collecting data related to that interest. This enables appropriate data collection tailored to hobbies and interests. For example, if a user is interested in sports, it can prioritize collecting data related to that interest. Also, if a user is interested in cooking, it can prioritize collecting data related to that interest. Furthermore, by analyzing users' hobbies and interests in real time and dynamically adjusting the data collection method, the accuracy of data collection can be improved.

[0087] The following briefly describes the processing flow for example form 2.

[0088] Step 1: The data collection unit collects data from daily life. For example, data from daily life can be collected over a long period using wearable devices. Audio data from daily life can also be collected using voice recording devices, and video data from daily life can be collected using video recording devices. Step 2: The data preprocessing unit converts the data collected by the data acquisition unit into text. For example, it can convert audio data into text using high-precision speech recognition technology, correcting poor articulation and mispronunciation in the audio data. It can also analyze situations from video data and convert them into text. Step 3: The model building unit constructs an individual personality model based on the data that has been transcribed into text by the data preprocessing unit. For example, the generated AI can be fine-tuned based on the collected text data to build an individual personality model, and periodic data additions and retraining can be performed.

[0089] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0090] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0091] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0092] Each of the multiple elements described above, including the data acquisition unit, data preprocessing unit, and model building unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the data acquisition unit collects video and audio data of daily life using the camera 42 and microphone 38B of the smart device 14. The data preprocessing unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, and transcribes the collected audio data into text using high-precision speech recognition technology, correcting slurred speech and mispronunciations. The model building unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, and constructs an individual personality model by fine-tuning the generated AI based on the transcribed data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0093] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0094] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0095] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0096] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0097] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0098] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0099] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0100] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0101] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0102] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0103] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0104] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0107] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] Each of the multiple elements described above, including the data acquisition unit, data preprocessing unit, and model building unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data acquisition unit collects video and audio data of daily life using the camera 42 and microphone 238 of the smart glasses 214. The data preprocessing unit is implemented in the specific processing unit 290 of the data processing unit 12, and transcribes the collected audio data into text using high-precision speech recognition technology, correcting slurred speech and mispronunciations. The model building unit is implemented in the specific processing unit 290 of the data processing unit 12, and constructs an individual personality model by fine-tuning the generated AI based on the transcribed data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0109] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0110] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0111] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0112] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0113] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0114] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0115] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0116] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0117] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0118] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0119] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0120] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0121] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0123] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements described above, including the data acquisition unit, data preprocessing unit, and model building unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data acquisition unit collects video and audio data of daily life using the camera 42 and microphone 238 of the headset terminal 314. The data preprocessing unit is implemented in the specific processing unit 290 of the data processing unit 12, and transcribes the collected audio data into text using high-precision speech recognition technology, correcting slurred speech and mispronunciations. The model building unit is implemented in the specific processing unit 290 of the data processing unit 12, and constructs an individual personality model by fine-tuning the generated AI based on the transcribed data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0125] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0126] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0127] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0128] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0129] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0131] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0132] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0133] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0136] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements described above, including the data acquisition unit, data preprocessing unit, and model building unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the data acquisition unit collects video and audio data of daily life using the camera 42 and microphone 238 of the robot 414. The data preprocessing unit is implemented in, for example, the specific processing unit 290 of the data processing unit 12, and transcribes the collected audio data into text using high-precision speech recognition technology, correcting slurred speech and mispronunciations. The model building unit is implemented in, for example, the specific processing unit 290 of the data processing unit 12, and constructs an individual personality model by fine-tuning the generated AI based on the transcribed data. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0142] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0143] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0144] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0145] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0146] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0147] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0148] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0149] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0150] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0151] 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.

[0152] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0153] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0154] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0155] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0156] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0157] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0158] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0159] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0160] (Note 1) The data collection unit collects data on daily life, A data preprocessing unit that converts the data collected by the data acquisition unit into text, The system includes a model construction unit that constructs an individual personality model based on the data that has been converted into text by the data preprocessing unit. A system characterized by the following features. (Note 2) The aforementioned data acquisition unit, Collecting data on daily life over a long period using wearable devices. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned data preprocessing unit The system converts audio data into text using highly accurate speech recognition technology, correcting for slurred speech and mispronunciations. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned data preprocessing unit Analyze the situation from video data and convert it into text. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned model building unit, Based on the collected text data, the generated AI is fine-tuned to construct an individual personality model. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned model building unit, Perform regular data additions and retraining. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned data acquisition unit, We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned data acquisition unit, Analyze the user's past behavior history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned data acquisition unit, When collecting data, filtering is performed based on the user's current activities and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned data acquisition unit, It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned data acquisition unit, When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned data acquisition unit, During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned data preprocessing unit It estimates the user's emotions and adjusts the textual expression based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned data preprocessing unit When transcribing audio data into text, adjust the level of detail in the transcription based on the importance of each utterance. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned data preprocessing unit When converting video data to text, different analysis algorithms are applied depending on the category of the situation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned data preprocessing unit It estimates the user's emotions and adjusts the length of the text based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned data preprocessing unit When converting audio data to text, the transcription priority is determined based on the timing of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned data preprocessing unit When converting video data to text, the order of text conversion is adjusted based on the relevance of the situations. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0161] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The data collection unit collects data on daily life, A data preprocessing unit that converts the data collected by the data acquisition unit into text, The system includes a model construction unit that constructs an individual personality model based on the data that has been converted into text by the aforementioned data preprocessing unit. A system characterized by the following features.

2. The aforementioned data acquisition unit is Collecting data on daily life over a long period using wearable devices. The system according to feature 1.

3. The aforementioned data preprocessing unit Audio data is converted into text using highly accurate speech recognition technology, and slurred speech and mispronunciations are corrected. The system according to feature 1.

4. The aforementioned data preprocessing unit Analyze the situation from video data and convert it into text. The system according to feature 1.

5. The aforementioned model building unit, Based on the collected text data, the generated AI is fine-tuned to construct an individual personality model. The system according to feature 1.

6. The aforementioned model building unit, Perform regular data additions and retraining. The system according to feature 1.

7. The aforementioned data acquisition unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

8. The aforementioned data acquisition unit is Analyze the user's past behavior history and select the optimal data collection method. The system according to feature 1.

Images