system

Abstract

The system according to this embodiment aims to correct errors in handwriting recognition using voice information and provide accurate character input. [Solution] The system according to the embodiment comprises a reception unit, an integration unit, and a correction unit. The reception unit receives user input. The integration unit integrates handwriting recognition and voice data based on the information received by the reception unit. The correction unit provides accurate character input based on the data integrated by the integration unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that means for correcting handwriting recognition errors are insufficient, and it is particularly difficult to use for elderly people or those with handwriting habits.

[0005] The system according to the embodiment aims to correct handwriting recognition errors with voice information and provide accurate character input.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, an integration unit, and a correction unit. The reception unit receives user input. The integration unit integrates handwriting recognition and voice data based on the information received by the reception unit. The correction unit provides accurate character input based on the data integrated by the integration unit. [Effects of the Invention]

[0007] The system according to this embodiment can correct errors in handwriting recognition using voice information and provide accurate character input. [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) An AI agent system according to an embodiment of the present invention is a system that, when a user is inputting text on a mobile phone or PAD device, works in conjunction with voice input to complete ambiguous handwriting. This AI agent system corrects errors in handwriting recognition with voice information, enabling accurate text input. It is a particularly user-friendly application for the elderly and people with distinctive handwriting habits. This brings the device closer to the experience of using paper and pen. For example, when a user inputs text on a mobile phone or PAD device, voice input is also used. For example, if a user intended to write "7" but it was converted to "1", the system can use voice input to complete it by saying, "I just said 7". This prevents ambiguous handwriting and misrecognition, enabling accurate text input. Next, the AI ​​agent integrates handwriting recognition and voice data. Specifically, it utilizes an LLM (Large-Scale Language Model) to integrate text-based voice recognition results with handwriting recognition results. For example, if the handwritten "1" and "7" are ambiguous, the system can use the user's voice to complete it by saying, "I just said 7". Furthermore, the AI ​​agent learns the user's handwriting habits. Through reinforcement learning, the AI ​​agent learns the user's habits and input patterns through daily use, gradually improving its accuracy. For example, for a user who frequently confuses "3" and "ru," the AI ​​agent learns this and predicts and corrects it if the same mistake occurs repeatedly. The AI ​​agent also improves the user interface. Adopting a human-centered design, it continuously improves the UI / UX based on user interaction data from the AI ​​agent. For example, it suggests more intuitive UI designs based on functions that users frequently use and parts that they focus on for extended periods. This AI agent has a large potential market in many countries facing aging societies, and can be applied not only to the senior market but also to users with a wide range of visual and motor function limitations. Currently, advances in speech recognition and AI technology are enabling real-time, highly accurate supplementation, and a great need is expected, especially in the aging Japanese market. The vision of this AI agent is to enable stress-free text input for the elderly and those with handwriting habits, supporting independent living. At the same time, it aims to create a society where everyone can easily and accurately disseminate information.This allows the AI ​​agent system to accurately correct user input.

[0029] The AI ​​agent system according to this embodiment comprises a reception unit, an integration unit, and a correction unit. The reception unit receives user input. User input includes, but is not limited to, handwritten character input and voice input. The reception unit can, for example, receive handwritten characters using a touchscreen. The reception unit can also receive voice input through a microphone. Furthermore, the reception unit can process the characters and voice input from the user in real time. For example, the reception unit detects handwritten characters with a high-precision touchscreen sensor and converts them into digital data. Voice input is obtained using a microphone with noise-canceling capabilities to capture clear audio. The integration unit integrates handwriting recognition and voice data based on the information received by the reception unit. The integration unit can, for example, utilize an LLM (Large-Scale Language Model) to integrate text-based voice recognition results and handwritten character recognition results. For example, if the handwritten "1" and "7" are ambiguous, the integration unit can complete the ambiguity by saying "You just said 7" from the user's voice. The integration unit can also learn the user's input patterns and gradually improve its accuracy. For example, the integration unit learns the user's habits and input patterns through reinforcement learning as they use the system daily. The correction unit provides accurate character input based on the data integrated by the integration unit. The correction unit can, for example, complete ambiguous handwriting from the user's voice. For example, if a user intended to write "7" but it was converted to "1", the correction unit can complete the input by saying "I just said 7" via voice input. The correction unit can also learn the user's habits and predict and correct frequent mistakes. For example, if a user frequently confuses "3" and "ru", the correction unit can learn and predict and correct this frequent mistake. As a result, the AI ​​agent system according to this embodiment can accurately correct the user's input.

[0030] The reception unit receives user input. User input includes, but is not limited to, handwritten text input and voice input. For example, the reception unit receives handwritten text using a touchscreen. Specifically, the touchscreen is equipped with a high-precision sensor that can accurately detect characters written by the user with their finger or stylus pen. This converts the handwritten text into digital data and inputs it into the system. The reception unit can also receive voice input via a microphone. A high-sensitivity microphone with noise-canceling capabilities is used for voice input to remove ambient noise and obtain clear audio. Furthermore, the reception unit can process the text and voice input entered by the user in real time. For example, handwritten text is instantly converted into digital data by the touchscreen sensor, and voice input is analyzed in real time as audio data is acquired through the microphone. This allows the user to input smoothly and the system to respond quickly. The reception unit plays the role of centrally managing this input data and sending it to the next processing step.

[0031] The integration unit integrates handwriting recognition and voice data based on information received by the reception unit. For example, the integration unit utilizes an LLM (Large-Scale Language Model) to integrate text-based voice recognition results with handwriting recognition results. Specifically, the LLM uses natural language processing techniques to convert voice data into text and compare it with the handwriting recognition results. For example, if a user writes "1" but the system recognizes it as "7," the system can obtain the correct recognition result by supplementing the information "I just said 7" from the voice input. Furthermore, the integration unit can learn the user's input patterns and gradually improve its accuracy. For example, through reinforcement learning, the integration unit learns the user's habits and input patterns through daily use. This allows the system to understand the user's specific input tendencies and provide more accurate recognition results. Additionally, the integration unit can more accurately understand the user's intent by integrating multiple input modes. For example, by combining both handwriting and voice input, it can supplement ambiguous inputs and generate accurate data. This allows the integration unit to accommodate diverse user input methods and provide accurate information.

[0032] The correction unit provides accurate character input based on data integrated by the integration unit. For example, the correction unit can complete ambiguous handwriting based on the user's voice. Specifically, the correction unit analyzes the data provided by the integration unit to accurately understand the user's intent. For example, if a user intended to write "7" but it was converted to "1", the correction unit can provide the correct character by completing the input with voice input such as "I just said 7". The correction unit can also learn the user's habits and predict and correct the same mistakes if they occur frequently. For example, if a user frequently confuses "3" and "ru", the correction unit will learn this and predict and correct it if it occurs frequently. This allows the correction unit to reduce user input errors and provide accurate data. Furthermore, the correction unit can collect user feedback and continuously improve the system's accuracy. For example, by providing feedback on the correction results, the system can learn from that information and improve the accuracy of corrections in the future. This allows the correction unit to accurately correct user input and improve the overall reliability and ease of use of the system.

[0033] The integration unit can integrate text-based speech recognition results and handwriting recognition results using an LLM (Large-Scale Language Model). For example, the integration unit uses an LLM to integrate speech recognition results and handwriting recognition results. For example, if the handwritten "1" and "7" are ambiguous, the integration unit can complete the ambiguity by saying "You just said 7" based on the user's voice. The integration unit can also use an LLM to learn the user's input patterns and gradually improve its accuracy. For example, through reinforcement learning, the integration unit learns the user's habits and input patterns through daily use. This improves the accuracy of integrating speech recognition results and handwriting recognition results by utilizing an LLM. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the integration unit can perform integration using a generative AI model that takes speech recognition results and handwriting recognition results as input and outputs an integrated result.

[0034] The correction unit can complete ambiguous handwriting from the user's voice. For example, if a user intended to write "7" but it was converted to "1", the correction unit can complete it by voice input saying, "I just said 7." The correction unit can also learn the user's habits and predict and correct the same mistakes if they occur frequently. For example, if a user frequently confuses "3" and "ru", the correction unit will learn this and predict and correct it if it occurs frequently. This makes it possible to complete ambiguous handwriting using the user's voice. Ambiguous handwriting includes, but is not limited to, the degree of ambiguity of the handwriting and the details of the completion algorithm. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the correction unit can input the user's voice data into a generative AI and have the generative AI complete the ambiguous handwriting.

[0035] The learning unit can learn the user's habits. For example, the learning unit learns the user's habits and input patterns through daily use, such as through reinforcement learning. For example, if a user frequently confuses "3" and "ru," the learning unit will learn this and predict and correct it if the same mistake occurs often. This improves input accuracy by learning the user's habits. Habits include, but are not limited to, specific writing patterns and input timing. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input user input data into a generative AI and have the generative AI perform habit learning.

[0036] The learning unit can improve accuracy by learning user habits and input patterns through reinforcement learning. For example, the learning unit uses reinforcement learning to learn the user's habits and input patterns through daily use. For example, if a user frequently confuses "3" and "ru", the learning unit will learn this and predict and correct it. In this way, the system's accuracy improves through learning via reinforcement learning. Reinforcement learning includes, but is not limited to, Q-learning and Deep Q-Network. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or without generative AI. For example, the learning unit can input user input data into a generative AI and have the generative AI perform reinforcement learning.

[0037] The Improvement Unit can improve the user interface. For example, the Improvement Unit adopts human-centered design and continuously improves the UI / UX based on user interaction data from an AI agent. For example, the Improvement Unit proposes a more intuitive UI design based on functions that users frequently use and parts that they focus on for extended periods. This improves usability by improving the user interface. User interface improvements include, but are not limited to, layout changes and improved operability. Some or all of the above processes in the Improvement Unit may be performed using, for example, generative AI, or not using generative AI. For example, the Improvement Unit can input user interaction data into a generative AI and have the generative AI perform UI / UX improvements.

[0038] The improvement unit can continuously improve the UI / UX based on user interaction data. For example, the improvement unit can propose more intuitive UI designs based on features that users frequently use or areas that receive long periods of focus. For example, the improvement unit can analyze user click data and scroll data to identify areas for UI / UX improvement. The improvement unit can also build a feedback loop for improving the UI / UX based on user interaction data. For example, the improvement unit can collect user operation history and improve the UI / UX based on that data. This improves the accuracy of the UI / UX by making improvements based on user interaction data. Interaction data includes, but is not limited to, click data and scroll data. Some or all of the above processes in the improvement unit may be performed using, for example, generative AI, or not using generative AI. For example, the improvement unit can input user interaction data into generative AI and have the generative AI perform UI / UX improvements.

[0039] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk may prioritize suggesting input methods that the user has frequently used in the past (e.g., voice, handwriting). For example, the reception desk may analyze the user's past input history and predict and suggest the input method to be used during a specific time period. The reception desk can also automatically display input candidates based on the user's past input. For example, the reception desk automatically displays input candidates based on the user's past input history. This allows the reception desk to select the optimal reception method by analyzing past input history. The optimal reception method includes, but is not limited to, the type of input and the user's past behavior patterns. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's past input history data into a generative AI and have the generative AI select the optimal reception method.

[0040] The reception unit can filter input based on the user's current situation and areas of interest. For example, the reception unit can prioritize displaying relevant input items according to the user's current situation. For example, the reception unit analyzes the user's current situation and prioritizes displaying relevant input items. The reception unit can also filter input items based on the user's areas of interest and display highly relevant items. For example, the reception unit analyzes the user's areas of interest and filters the input items. The reception unit can also adjust the order of input items based on the user's current situation and areas of interest. For example, the reception unit adjusts the order of input items based on the user's current situation and areas of interest. This allows for highly relevant input by filtering based on the user's situation and areas of interest. Filtering includes, but is not limited to, methods for identifying areas of interest and filtering algorithms. Some or all of the above processing in the reception unit may be performed using, for example, generative AI, or without generative AI. For example, the reception desk can input data on the user's current situation and areas of interest into the generating AI, and have the generating AI perform filtering.

[0041] The reception unit can prioritize accepting inputs that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific location, the reception unit will prioritize accepting inputs related to that location. For example, the reception unit will analyze the user's geographical location information and prioritize accepting inputs related to that location. The reception unit can also display relevant input items based on the user's geographical location information. For example, the reception unit will display relevant input items based on the user's current location. The reception unit can also adjust the order of input items based on the user's current location. For example, the reception unit will adjust the order of input items based on the user's current location. This makes it possible to receive highly relevant inputs by considering geographical location information. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's geographical location information data into a generative AI and have the generative AI prioritize accepting highly relevant inputs.

[0042] The reception unit can analyze the user's social media activity and accept relevant inputs when receiving input. For example, the reception unit can display relevant input items based on the user's social media activity. For example, the reception unit can analyze the user's social media activity and display relevant input items. The reception unit can also analyze the user's social media activity and adjust the order of input items. For example, the reception unit can analyze the user's social media activity and adjust the order of input items. The reception unit can also automatically display input suggestions based on the user's social media activity. For example, the reception unit can analyze the user's social media activity and automatically display input suggestions. This makes it possible to input relevant information by analyzing social media activity. Social media activity includes, but is not limited to, analysis of post content and follower analysis. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception unit can input the user's social media activity data into a generative AI and have the generative AI perform the acceptance of relevant inputs.

[0043] The integration unit can improve the accuracy of integration by considering the interrelationships of the input data during integration. For example, the integration unit can analyze the interrelationships of the input data and prioritize the integration of highly relevant data. The integration unit can also improve the accuracy of integration based on the interrelationships of the input data. For example, the integration unit can adjust the integration order by considering the interrelationships of the input data. This improves the accuracy of integration by considering the interrelationships of the input data. Interrelationships include, but are not limited to, correlation analysis and network analysis. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the interrelationship data of the input data into a generative AI and have the generative AI perform the integration accuracy improvement.

[0044] The integration unit can perform integration while considering the attribute information of the input data submitters. For example, the integration unit prioritizes integrating highly relevant data based on the attribute information of the input data submitters. For example, the integration unit analyzes the attribute information of the input data submitters and prioritizes integrating highly relevant data. The integration unit can also improve the accuracy of integration by considering the attribute information of the input data submitters. For example, the integration unit adjusts the integration order based on the attribute information of the input data submitters. This improves the accuracy of integration by considering the submitters' attribute information. Attribute information includes, but is not limited to, age, occupation, and interests. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the attribute information data of the input data submitters into a generative AI and have the generative AI perform the integration accuracy improvement.

[0045] The integration unit can perform integration while considering the geographical distribution of the input data. For example, the integration unit can prioritize the integration of highly relevant data based on the geographical distribution of the input data. For example, the integration unit can analyze the geographical distribution of the input data and prioritize the integration of highly relevant data. The integration unit can also improve the accuracy of integration by considering the geographical distribution of the input data. For example, the integration unit can adjust the order of integration based on the geographical distribution of the input data. This makes it possible to perform integration with higher relevance by considering the geographical distribution. Geographical distribution includes, but is not limited to, regional data distribution and geographical cluster analysis. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the geographical distribution data of the input data into a generative AI and have the generative AI perform the task of improving the accuracy of integration.

[0046] The integration unit can improve the accuracy of the integration by referring to relevant literature for the input data during the integration process. For example, the integration unit can improve the accuracy of the integration by referring to relevant literature for the input data. For example, the integration unit can improve the accuracy of the integration by analyzing the relevant literature for the input data. The integration unit can also adjust the order of integration based on the relevant literature for the input data. For example, the integration unit can adjust the order of integration by referring to relevant literature for the input data. This improves the accuracy of the integration by referring to relevant literature. Relevant literature includes, but is not limited to, the use of literature databases and the analysis of citation relationships. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the relevant literature data for the input data into a generative AI and have the generative AI perform the integration accuracy improvement.

[0047] The correction unit can adjust the level of detail of the correction based on the importance of the input data during the correction process. For example, the correction unit can perform detailed corrections based on the importance of the input data. For example, the correction unit can analyze the importance of the input data and perform detailed corrections. The correction unit can also adjust the order of corrections, taking into account the importance of the input data. For example, the correction unit can analyze the importance of the input data and adjust the order of corrections. The correction unit can also improve the accuracy of the corrections based on the importance of the input data. For example, the correction unit can analyze the importance of the input data and improve the accuracy of the corrections. This allows important data to be corrected preferentially by adjusting the level of detail of the correction based on the importance of the input data. Importance includes, but is not limited to, the degree of impact of the data and the method of evaluating priority. Some or all of the above-described processes in the correction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the correction unit can input the importance data of the input data into a generating AI and have the generating AI perform the adjustment of the level of detail of the corrections.

[0048] The correction unit can apply different correction algorithms depending on the category of the input data during correction. For example, the correction unit can apply the optimal correction algorithm depending on the category of the input data. For example, the correction unit can analyze the category of the input data and apply the optimal correction algorithm. The correction unit can also adjust the order of corrections considering the category of the input data. For example, the correction unit can analyze the category of the input data and adjust the order of corrections. The correction unit can also improve the accuracy of the correction based on the category of the input data. For example, the correction unit can analyze the category of the input data and improve the accuracy of the correction. This improves the accuracy of the correction by applying the optimal correction algorithm according to the category of the input data. Categories include, but are not limited to, data types and category-specific correction algorithms. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the category data of the input data into a generative AI and have the generative AI execute the application of the correction algorithm.

[0049] The correction unit can determine the priority of corrections based on the submission timing of the input data during the correction process. For example, the correction unit may prioritize important corrections based on the submission timing of the input data. For example, the correction unit may analyze the submission timing of the input data and prioritize important corrections. The correction unit may also adjust the order of corrections considering the submission timing of the input data. For example, the correction unit may analyze the submission timing of the input data and adjust the order of corrections. The correction unit may also improve the accuracy of corrections based on the submission timing of the input data. For example, the correction unit may analyze the submission timing of the input data and improve the accuracy of corrections. This allows important data to be corrected preferentially by determining the priority of corrections based on the submission timing of the input data. Submission timing includes, but is not limited to, the use of timestamps and methods for evaluating submission timing. Some or all of the above-described processes in the correction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the correction unit may input the input data submission timing data into a generating AI and have the generating AI perform the correction priority determination.

[0050] The correction unit can adjust the order of corrections based on the relationships between the input data during the correction process. For example, the correction unit may prioritize important corrections based on the relationships between the input data. For example, the correction unit may analyze the relationships between the input data and prioritize important corrections. The correction unit can also adjust the order of corrections considering the relationships between the input data. For example, the correction unit may analyze the relationships between the input data and adjust the order of corrections. The correction unit can also improve the accuracy of corrections based on the relationships between the input data. For example, the correction unit may analyze the relationships between the input data and improve the accuracy of corrections. This allows important data to be corrected preferentially by adjusting the order of corrections based on the relationships between the input data. Relationships include, but are not limited to, data correlation analysis and relationship evaluation criteria. Some or all of the above-described processes in the correction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the correction unit may input relationship data of the input data into a generative AI and have the generative AI perform the correction order adjustment.

[0051] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm by referring to past learning data. For example, the learning unit can select the optimal learning algorithm by analyzing past learning data. The learning unit can also adjust the parameters of the learning algorithm based on past learning data. For example, the learning unit can adjust the parameters of the learning algorithm by analyzing past learning data. The learning unit can also improve the accuracy of the learning algorithm by analyzing past learning data. For example, the learning unit improves the accuracy of the learning algorithm by analyzing past learning data. Thus, the accuracy of the learning algorithm is improved by referring to past learning data. Optimization of the learning algorithm includes, but is not limited to, the use of past data and the details of the optimization algorithm. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input past learning data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0052] The learning unit can weight the training data based on the submission timing of the input data during training. For example, the learning unit can weight important training data based on the submission timing of the input data. For example, the learning unit can analyze the submission timing of the input data and weight important training data. The learning unit can also adjust the weighting of the training data considering the submission timing of the input data. For example, the learning unit can analyze the submission timing of the input data and adjust the weighting of the training data. The learning unit can also improve the accuracy of the training data based on the submission timing of the input data. For example, the learning unit can analyze the submission timing of the input data and improve the accuracy of the training data. This allows for priority learning of important data by weighting the training data based on the submission timing of the input data. Weighting includes, but is not limited to, data importance and details of the weighting algorithm. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the input data submission timing data into a generative AI and have the generative AI perform the weighting of the training data.

[0053] The improvement unit can select the optimal display method by referring to the user's past operation history when displaying the interface. For example, the improvement unit can propose the optimal display method based on the user's past operation history. For example, the improvement unit can analyze the user's past operation history and propose the optimal display method. The improvement unit can also analyze the user's past operation history and improve the accuracy of the display method. For example, the improvement unit can analyze the user's past operation history and improve the accuracy of the display method. The improvement unit can also adjust the order of the display methods based on the user's past operation history. For example, the improvement unit can analyze the user's past operation history and adjust the order of the display methods. This allows the optimal display method to be selected by referring to the past operation history. Operation history includes, but is not limited to, click data and operation log analysis methods. Some or all of the above processing in the improvement unit may be performed using, for example, a generation AI, or without a generation AI. For example, the improvement unit can input the user's past operation history data into a generation AI and have the generation AI select the optimal display method.

[0054] The improvement unit can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, the improvement unit can provide a display method that matches the screen size. For example, the improvement unit can analyze the user's device information and provide a display method that matches the screen size. The improvement unit can also provide a display method optimized for a larger screen if the user is using a tablet. For example, the improvement unit can analyze the user's device information and provide a display method optimized for a larger screen. The improvement unit can also provide a concise and highly visible display method if the user is using a smartwatch. For example, the improvement unit can analyze the user's device information and provide a concise and highly visible display method. In this way, the optimal display method can be selected by taking device information into consideration. Device information includes, but is not limited to, the type of device and the method of analyzing usage. Some or all of the above processing in the improvement unit may be performed using, for example, a generation AI, or without a generation AI. For example, the improvement unit can input the user's device information data into a generation AI and have the generation AI select the optimal display method.

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

[0056] The reception desk can analyze the user's past input history when receiving user input and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the user has frequently used in the past (such as voice or handwriting). The reception desk can also predict and suggest input methods to be used during specific time periods based on the user's past input history. Furthermore, the reception desk can automatically display input candidates based on the user's past input history. This allows for the selection of the most suitable input method by analyzing past input history. The optimal input method may include, but is not limited to, the type of input and the user's past behavioral patterns.

[0057] The reception system can prioritize accepting inputs that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, it will prioritize accepting inputs related to that location. It analyzes the user's geographical location and prioritizes accepting inputs related to that location. It can also display relevant input items based on the user's geographical location. It displays relevant input items based on the user's current location. It can also adjust the order of input items based on the user's current location. It adjusts the order of input items based on the user's current location. This allows for more relevant input by considering geographical location.

[0058] The integration unit can improve the accuracy of integration by considering the interrelationships of the input data. For example, it can analyze the interrelationships of the input data and prioritize the integration of highly relevant data. It can also improve the accuracy of integration based on the interrelationships of the input data. It adjusts the integration order considering the interrelationships of the input data. This improves the accuracy of integration by considering the interrelationships of the input data. Interrelationships include, but are not limited to, correlation analysis and network analysis.

[0059] The correction unit can adjust the level of detail of the correction based on the importance of the input data. For example, it can perform detailed corrections based on the importance of the input data. It analyzes the importance of the input data and performs detailed corrections. It can also adjust the order of corrections, taking into account the importance of the input data. It analyzes the importance of the input data and adjusts the order of corrections. It can also improve the accuracy of the corrections based on the importance of the input data. It analyzes the importance of the input data and improves the accuracy of the corrections. As a result, by adjusting the level of detail of the corrections based on the importance of the input data, important data can be corrected preferentially.

[0060] The learning unit can optimize the learning algorithm by referring to past training data. For example, it can select the optimal learning algorithm by referring to past training data. It can also select the optimal learning algorithm by analyzing past training data. Furthermore, it can adjust the parameters of the learning algorithm based on past training data. It can also improve the accuracy of the learning algorithm by analyzing past training data. Thus, the accuracy of the learning algorithm is improved by referring to past training data.

[0061] The improvement unit can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, it can provide a display method that matches the screen size. It analyzes the user's device information and provides a display method that matches the screen size. Also, if the user is using a tablet, it can provide a display method optimized for a larger screen. It analyzes the user's device information and provides a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible display method. It analyzes the user's device information and provides a concise and highly visible display method. In this way, the optimal display method can be selected by taking device information into consideration.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The reception desk receives user input. User input includes handwritten text and voice input. The reception desk can receive handwritten text using a touchscreen and voice input via a microphone. Furthermore, the reception desk can process the text and voice input from the user in real time. For example, handwritten text is detected by a high-precision touchscreen sensor and converted into digital data. Voice input is captured clearly using a microphone with noise-canceling capabilities. Step 2: The integration unit integrates the handwriting recognition and voice data based on the information received by the reception unit. The integration unit utilizes an LLM (Large-Scale Language Model) to integrate the text-based voice recognition results with the handwriting recognition results. For example, if the handwritten "1" and "7" are ambiguous, it can complete the ambiguity by saying "You just said 7" based on the user's voice. The integration unit can also learn the user's input patterns and gradually improve its accuracy. Step 3: The correction unit provides accurate character input based on the data integrated by the integration unit. The correction unit complements ambiguous handwriting from the user's voice. For example, if the user intended to write "7" but it was converted to "1", the correction unit can correct it by saying "I just said 7" via voice input. The correction unit can also learn the user's habits and, if the same mistakes occur frequently, can learn, predict, and correct them.

[0064] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that, when a user is inputting text on a mobile phone or PAD device, works in conjunction with voice input to complete ambiguous handwriting. This AI agent system corrects errors in handwriting recognition with voice information, enabling accurate text input. It is a particularly user-friendly application for the elderly and people with distinctive handwriting habits. This brings the device closer to the experience of using paper and pen. For example, when a user inputs text on a mobile phone or PAD device, voice input is also used. For example, if a user intended to write "7" but it was converted to "1", the system can use voice input to complete it by saying, "I just said 7". This prevents ambiguous handwriting and misrecognition, enabling accurate text input. Next, the AI ​​agent integrates handwriting recognition and voice data. Specifically, it utilizes an LLM (Large-Scale Language Model) to integrate text-based voice recognition results with handwriting recognition results. For example, if the handwritten "1" and "7" are ambiguous, the system can use the user's voice to complete it by saying, "I just said 7". Furthermore, the AI ​​agent learns the user's handwriting habits. Through reinforcement learning, the AI ​​agent learns the user's habits and input patterns through daily use, gradually improving its accuracy. For example, for a user who frequently confuses "3" and "ru," the AI ​​agent learns this and predicts and corrects it if the same mistake occurs repeatedly. The AI ​​agent also improves the user interface. Adopting a human-centered design, it continuously improves the UI / UX based on user interaction data from the AI ​​agent. For example, it suggests more intuitive UI designs based on functions that users frequently use and parts that they focus on for extended periods. This AI agent has a large potential market in many countries facing aging societies, and can be applied not only to the senior market but also to users with a wide range of visual and motor function limitations. Currently, advances in speech recognition and AI technology are enabling real-time, highly accurate supplementation, and a great need is expected, especially in the aging Japanese market. The vision of this AI agent is to enable stress-free text input for the elderly and those with handwriting habits, supporting independent living. At the same time, it aims to create a society where everyone can easily and accurately disseminate information.This allows the AI ​​agent system to accurately correct user input.

[0065] The AI ​​agent system according to this embodiment comprises a reception unit, an integration unit, and a correction unit. The reception unit receives user input. User input includes, but is not limited to, handwritten character input and voice input. The reception unit can, for example, receive handwritten characters using a touchscreen. The reception unit can also receive voice input through a microphone. Furthermore, the reception unit can process the characters and voice input from the user in real time. For example, the reception unit detects handwritten characters with a high-precision touchscreen sensor and converts them into digital data. Voice input is obtained using a microphone with noise-canceling capabilities to capture clear audio. The integration unit integrates handwriting recognition and voice data based on the information received by the reception unit. The integration unit can, for example, utilize an LLM (Large-Scale Language Model) to integrate text-based voice recognition results and handwritten character recognition results. For example, if the handwritten "1" and "7" are ambiguous, the integration unit can complete the ambiguity by saying "You just said 7" from the user's voice. The integration unit can also learn the user's input patterns and gradually improve its accuracy. For example, the integration unit learns the user's habits and input patterns through reinforcement learning as they use the system daily. The correction unit provides accurate character input based on the data integrated by the integration unit. The correction unit can, for example, complete ambiguous handwriting from the user's voice. For example, if a user intended to write "7" but it was converted to "1", the correction unit can complete the input by saying "I just said 7" via voice input. The correction unit can also learn the user's habits and predict and correct frequent mistakes. For example, if a user frequently confuses "3" and "ru", the correction unit can learn and predict and correct this frequent mistake. As a result, the AI ​​agent system according to this embodiment can accurately correct the user's input.

[0066] The reception unit receives user input. User input includes, but is not limited to, handwritten text input and voice input. For example, the reception unit receives handwritten text using a touchscreen. Specifically, the touchscreen is equipped with a high-precision sensor that can accurately detect characters written by the user with their finger or stylus pen. This converts the handwritten text into digital data and inputs it into the system. The reception unit can also receive voice input via a microphone. A high-sensitivity microphone with noise-canceling capabilities is used for voice input to remove ambient noise and obtain clear audio. Furthermore, the reception unit can process the text and voice input entered by the user in real time. For example, handwritten text is instantly converted into digital data by the touchscreen sensor, and voice input is analyzed in real time as audio data is acquired through the microphone. This allows the user to input smoothly and the system to respond quickly. The reception unit plays the role of centrally managing this input data and sending it to the next processing step.

[0067] The integration unit integrates handwriting recognition and voice data based on information received by the reception unit. For example, the integration unit utilizes an LLM (Large-Scale Language Model) to integrate text-based voice recognition results with handwriting recognition results. Specifically, the LLM uses natural language processing techniques to convert voice data into text and compare it with the handwriting recognition results. For example, if a user writes "1" but the system recognizes it as "7," the system can obtain the correct recognition result by supplementing the information "I just said 7" from the voice input. Furthermore, the integration unit can learn the user's input patterns and gradually improve its accuracy. For example, through reinforcement learning, the integration unit learns the user's habits and input patterns through daily use. This allows the system to understand the user's specific input tendencies and provide more accurate recognition results. Additionally, the integration unit can more accurately understand the user's intent by integrating multiple input modes. For example, by combining both handwriting and voice input, it can supplement ambiguous inputs and generate accurate data. This allows the integration unit to accommodate diverse user input methods and provide accurate information.

[0068] The correction unit provides accurate character input based on data integrated by the integration unit. For example, the correction unit can complete ambiguous handwriting based on the user's voice. Specifically, the correction unit analyzes the data provided by the integration unit to accurately understand the user's intent. For example, if a user intended to write "7" but it was converted to "1", the correction unit can provide the correct character by completing the input with voice input such as "I just said 7". The correction unit can also learn the user's habits and predict and correct the same mistakes if they occur frequently. For example, if a user frequently confuses "3" and "ru", the correction unit will learn this and predict and correct it if it occurs frequently. This allows the correction unit to reduce user input errors and provide accurate data. Furthermore, the correction unit can collect user feedback and continuously improve the system's accuracy. For example, by providing feedback on the correction results, the system can learn from that information and improve the accuracy of corrections in the future. This allows the correction unit to accurately correct user input and improve the overall reliability and ease of use of the system.

[0069] The integration unit can integrate text-based speech recognition results and handwriting recognition results using an LLM (Large-Scale Language Model). For example, the integration unit uses an LLM to integrate speech recognition results and handwriting recognition results. For example, if the handwritten "1" and "7" are ambiguous, the integration unit can complete the ambiguity by saying "You just said 7" based on the user's voice. The integration unit can also use an LLM to learn the user's input patterns and gradually improve its accuracy. For example, through reinforcement learning, the integration unit learns the user's habits and input patterns through daily use. This improves the accuracy of integrating speech recognition results and handwriting recognition results by utilizing an LLM. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the integration unit can perform integration using a generative AI model that takes speech recognition results and handwriting recognition results as input and outputs an integrated result.

[0070] The correction unit can complete ambiguous handwriting from the user's voice. For example, if a user intended to write "7" but it was converted to "1", the correction unit can complete it by voice input saying, "I just said 7." The correction unit can also learn the user's habits and predict and correct the same mistakes if they occur frequently. For example, if a user frequently confuses "3" and "ru", the correction unit will learn this and predict and correct it if it occurs frequently. This makes it possible to complete ambiguous handwriting using the user's voice. Ambiguous handwriting includes, but is not limited to, the degree of ambiguity of the handwriting and the details of the completion algorithm. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the correction unit can input the user's voice data into a generative AI and have the generative AI complete the ambiguous handwriting.

[0071] The learning unit can learn the user's habits. For example, the learning unit learns the user's habits and input patterns through daily use, such as through reinforcement learning. For example, if a user frequently confuses "3" and "ru," the learning unit will learn this and predict and correct it if the same mistake occurs often. This improves input accuracy by learning the user's habits. Habits include, but are not limited to, specific writing patterns and input timing. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input user input data into a generative AI and have the generative AI perform habit learning.

[0072] The learning unit can improve accuracy by learning user habits and input patterns through reinforcement learning. For example, the learning unit uses reinforcement learning to learn the user's habits and input patterns through daily use. For example, if a user frequently confuses "3" and "ru", the learning unit will learn this and predict and correct it. In this way, the system's accuracy improves through learning via reinforcement learning. Reinforcement learning includes, but is not limited to, Q-learning and Deep Q-Network. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or without generative AI. For example, the learning unit can input user input data into a generative AI and have the generative AI perform reinforcement learning.

[0073] The Improvement Unit can improve the user interface. For example, the Improvement Unit adopts human-centered design and continuously improves the UI / UX based on user interaction data from an AI agent. For example, the Improvement Unit proposes a more intuitive UI design based on functions that users frequently use and parts that they focus on for extended periods. This improves usability by improving the user interface. User interface improvements include, but are not limited to, layout changes and improved operability. Some or all of the above processes in the Improvement Unit may be performed using, for example, generative AI, or not using generative AI. For example, the Improvement Unit can input user interaction data into a generative AI and have the generative AI perform UI / UX improvements.

[0074] The improvement unit can continuously improve the UI / UX based on user interaction data. For example, the improvement unit can propose more intuitive UI designs based on features that users frequently use or areas that receive long periods of focus. For example, the improvement unit can analyze user click data and scroll data to identify areas for UI / UX improvement. The improvement unit can also build a feedback loop for improving the UI / UX based on user interaction data. For example, the improvement unit can collect user operation history and improve the UI / UX based on that data. This improves the accuracy of the UI / UX by making improvements based on user interaction data. Interaction data includes, but is not limited to, click data and scroll data. Some or all of the above processes in the improvement unit may be performed using, for example, generative AI, or not using generative AI. For example, the improvement unit can input user interaction data into generative AI and have the generative AI perform UI / UX improvements.

[0075] The reception unit can estimate the user's emotions and adjust the timing of input acceptance based on the estimated emotions. For example, if the user is anxious, the reception unit can delay the input acceptance timing to allow the user to enter information calmly. For example, the reception unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The reception unit can also speed up the input acceptance timing if the user is relaxed to facilitate smooth input. For example, the reception unit can record the user's voice and estimate their emotions using voice analysis technology. The reception unit can also adjust the input acceptance timing if the user is tired to allow them to enter information without strain. For example, the reception unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. By adjusting the input acceptance timing according to the user's emotions, more appropriate input becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes at the reception desk may be performed using, for example, a generative AI, or without using a generative AI. For example, the reception desk can input image data of the user captured by a camera into a generative AI and have the generative AI perform an estimation of the user's emotions.

[0076] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk may prioritize suggesting input methods that the user has frequently used in the past (e.g., voice, handwriting). For example, the reception desk may analyze the user's past input history and predict and suggest the input method to be used during a specific time period. The reception desk can also automatically display input candidates based on the user's past input. For example, the reception desk automatically displays input candidates based on the user's past input history. This allows the reception desk to select the optimal reception method by analyzing past input history. The optimal reception method includes, but is not limited to, the type of input and the user's past behavior patterns. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's past input history data into a generative AI and have the generative AI select the optimal reception method.

[0077] The reception unit can filter input based on the user's current situation and areas of interest. For example, the reception unit can prioritize displaying relevant input items according to the user's current situation. For example, the reception unit analyzes the user's current situation and prioritizes displaying relevant input items. The reception unit can also filter input items based on the user's areas of interest and display highly relevant items. For example, the reception unit analyzes the user's areas of interest and filters the input items. The reception unit can also adjust the order of input items based on the user's current situation and areas of interest. For example, the reception unit adjusts the order of input items based on the user's current situation and areas of interest. This allows for highly relevant input by filtering based on the user's situation and areas of interest. Filtering includes, but is not limited to, methods for identifying areas of interest and filtering algorithms. Some or all of the above processing in the reception unit may be performed using, for example, generative AI, or without generative AI. For example, the reception desk can input data on the user's current situation and areas of interest into the generating AI, and have the generating AI perform filtering.

[0078] The reception unit can estimate the user's emotions and determine the priority of inputs to be received based on the estimated emotions. For example, if the user is anxious, the reception unit will prioritize receiving important inputs. For example, the reception unit may capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the reception unit can also accept all inputs equally. For example, the reception unit may record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is tired, the reception unit can also prioritize receiving simple inputs. For example, the reception unit may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to prioritize inputs according to the user's emotions, thereby prioritizing the acceptance of important inputs. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes at the reception desk may be performed using, for example, a generative AI, or without using a generative AI. For example, the reception desk can input image data of the user captured by a camera into a generative AI and have the generative AI perform an estimation of the user's emotions.

[0079] The reception unit can prioritize accepting inputs that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific location, the reception unit will prioritize accepting inputs related to that location. For example, the reception unit will analyze the user's geographical location information and prioritize accepting inputs related to that location. The reception unit can also display relevant input items based on the user's geographical location information. For example, the reception unit will display relevant input items based on the user's current location. The reception unit can also adjust the order of input items based on the user's current location. For example, the reception unit will adjust the order of input items based on the user's current location. This makes it possible to receive highly relevant inputs by considering geographical location information. Geographical location information includes, but is not limited to, GPS data and location services. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's geographical location information data into a generative AI and have the generative AI prioritize accepting highly relevant inputs.

[0080] The reception unit can analyze the user's social media activity and accept relevant inputs when receiving input. For example, the reception unit can display relevant input items based on the user's social media activity. For example, the reception unit can analyze the user's social media activity and display relevant input items. The reception unit can also analyze the user's social media activity and adjust the order of input items. For example, the reception unit can analyze the user's social media activity and adjust the order of input items. The reception unit can also automatically display input suggestions based on the user's social media activity. For example, the reception unit can analyze the user's social media activity and automatically display input suggestions. This makes it possible to input relevant information by analyzing social media activity. Social media activity includes, but is not limited to, analysis of post content and follower analysis. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception unit can input the user's social media activity data into a generative AI and have the generative AI perform the acceptance of relevant inputs.

[0081] The integration unit can estimate the user's emotions and adjust the integration criteria based on the estimated emotions. For example, if the user is anxious, the integration unit can apply simple integration criteria. For instance, it might capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The integration unit can also apply more detailed integration criteria if the user is relaxed. For example, it might record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is tired, the integration unit can adjust the integration criteria to facilitate integration. For example, it might collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for more appropriate integration by adjusting the integration criteria according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the integration unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the integration unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0082] The integration unit can improve the accuracy of integration by considering the interrelationships of the input data during integration. For example, the integration unit can analyze the interrelationships of the input data and prioritize the integration of highly relevant data. The integration unit can also improve the accuracy of integration based on the interrelationships of the input data. For example, the integration unit can adjust the integration order by considering the interrelationships of the input data. This improves the accuracy of integration by considering the interrelationships of the input data. Interrelationships include, but are not limited to, correlation analysis and network analysis. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the interrelationship data of the input data into a generative AI and have the generative AI perform the integration accuracy improvement.

[0083] The integration unit can perform integration while considering the attribute information of the input data submitters. For example, the integration unit prioritizes integrating highly relevant data based on the attribute information of the input data submitters. For example, the integration unit analyzes the attribute information of the input data submitters and prioritizes integrating highly relevant data. The integration unit can also improve the accuracy of integration by considering the attribute information of the input data submitters. For example, the integration unit adjusts the integration order based on the attribute information of the input data submitters. This improves the accuracy of integration by considering the submitters' attribute information. Attribute information includes, but is not limited to, age, occupation, and interests. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the attribute information data of the input data submitters into a generative AI and have the generative AI perform the integration accuracy improvement.

[0084] The integration unit can estimate the user's emotions and adjust the order in which the integration results are displayed based on the estimated emotions. For example, if the user is anxious, the integration unit will prioritize displaying important integration results. For example, the integration unit may capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The integration unit can also display all integration results equally if the user is relaxed. For example, the integration unit may record the user's voice and estimate their emotions using voice analysis technology. The integration unit can also prioritize displaying simpler integration results if the user is tired. For example, the integration unit may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to prioritize the display of important results by adjusting the display order according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the integration unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the integration unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0085] The integration unit can perform integration while considering the geographical distribution of the input data. For example, the integration unit can prioritize the integration of highly relevant data based on the geographical distribution of the input data. For example, the integration unit can analyze the geographical distribution of the input data and prioritize the integration of highly relevant data. The integration unit can also improve the accuracy of integration by considering the geographical distribution of the input data. For example, the integration unit can adjust the order of integration based on the geographical distribution of the input data. This makes it possible to perform integration with higher relevance by considering the geographical distribution. Geographical distribution includes, but is not limited to, regional data distribution and geographical cluster analysis. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the geographical distribution data of the input data into a generative AI and have the generative AI perform the task of improving the accuracy of integration.

[0086] The integration unit can improve the accuracy of the integration by referring to relevant literature for the input data during the integration process. For example, the integration unit can improve the accuracy of the integration by referring to relevant literature for the input data. For example, the integration unit can improve the accuracy of the integration by analyzing the relevant literature for the input data. The integration unit can also adjust the order of integration based on the relevant literature for the input data. For example, the integration unit can adjust the order of integration by referring to relevant literature for the input data. This improves the accuracy of the integration by referring to relevant literature. Relevant literature includes, but is not limited to, the use of literature databases and the analysis of citation relationships. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the relevant literature data for the input data into a generative AI and have the generative AI perform the integration accuracy improvement.

[0087] The correction unit can estimate the user's emotions and adjust the correction method based on the estimated emotions. For example, if the user is anxious, the correction unit can apply a simple correction method. For example, the correction unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The correction unit can also apply a more detailed correction method if the user is relaxed. For example, the correction unit can record the user's voice and estimate the emotion using voice analysis technology. The correction unit can also adjust the correction method if the user is tired to ensure that the correction is performed without strain. For example, the correction unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. This allows for more appropriate correction by adjusting the correction method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the correction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the correction unit can input user image data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0088] The correction unit can adjust the level of detail of the correction based on the importance of the input data during the correction process. For example, the correction unit can perform detailed corrections based on the importance of the input data. For example, the correction unit can analyze the importance of the input data and perform detailed corrections. The correction unit can also adjust the order of corrections, taking into account the importance of the input data. For example, the correction unit can analyze the importance of the input data and adjust the order of corrections. The correction unit can also improve the accuracy of the corrections based on the importance of the input data. For example, the correction unit can analyze the importance of the input data and improve the accuracy of the corrections. This allows important data to be corrected preferentially by adjusting the level of detail of the correction based on the importance of the input data. Importance includes, but is not limited to, the degree of impact of the data and the method of evaluating priority. Some or all of the above-described processes in the correction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the correction unit can input the importance data of the input data into a generating AI and have the generating AI perform the adjustment of the level of detail of the corrections.

[0089] The correction unit can apply different correction algorithms depending on the category of the input data during correction. For example, the correction unit can apply the optimal correction algorithm depending on the category of the input data. For example, the correction unit can analyze the category of the input data and apply the optimal correction algorithm. The correction unit can also adjust the order of corrections considering the category of the input data. For example, the correction unit can analyze the category of the input data and adjust the order of corrections. The correction unit can also improve the accuracy of the correction based on the category of the input data. For example, the correction unit can analyze the category of the input data and improve the accuracy of the correction. This improves the accuracy of the correction by applying the optimal correction algorithm according to the category of the input data. Categories include, but are not limited to, data types and category-specific correction algorithms. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the category data of the input data into a generative AI and have the generative AI execute the application of the correction algorithm.

[0090] The correction unit can estimate the user's emotions and determine the priority of corrections based on the estimated emotions. For example, if the user is anxious, the correction unit will prioritize important corrections. For example, the correction unit may capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. The correction unit can also perform all corrections equally if the user is relaxed. For example, the correction unit may record the user's voice and estimate the emotion using voice analysis technology. The correction unit can also prioritize simpler corrections if the user is tired. For example, the correction unit may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. This allows the correction unit to prioritize important corrections according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the correction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the correction unit can input user image data captured by a camera into a generating AI and have the generating AI perform the estimation of the user's emotions.

[0091] The correction unit can determine the priority of corrections based on the submission timing of the input data during the correction process. For example, the correction unit may prioritize important corrections based on the submission timing of the input data. For example, the correction unit may analyze the submission timing of the input data and prioritize important corrections. The correction unit may also adjust the order of corrections considering the submission timing of the input data. For example, the correction unit may analyze the submission timing of the input data and adjust the order of corrections. The correction unit may also improve the accuracy of corrections based on the submission timing of the input data. For example, the correction unit may analyze the submission timing of the input data and improve the accuracy of corrections. This allows important data to be corrected preferentially by determining the priority of corrections based on the submission timing of the input data. Submission timing includes, but is not limited to, the use of timestamps and methods for evaluating submission timing. Some or all of the above-described processes in the correction unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the correction unit may input the input data submission timing data into a generating AI and have the generating AI perform the correction priority determination.

[0092] The correction unit can adjust the order of corrections based on the relationships between the input data during the correction process. For example, the correction unit may prioritize important corrections based on the relationships between the input data. For example, the correction unit may analyze the relationships between the input data and prioritize important corrections. The correction unit can also adjust the order of corrections considering the relationships between the input data. For example, the correction unit may analyze the relationships between the input data and adjust the order of corrections. The correction unit can also improve the accuracy of corrections based on the relationships between the input data. For example, the correction unit may analyze the relationships between the input data and improve the accuracy of corrections. This allows important data to be corrected preferentially by adjusting the order of corrections based on the relationships between the input data. Relationships include, but are not limited to, data correlation analysis and relationship evaluation criteria. Some or all of the above-described processes in the correction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the correction unit may input relationship data of the input data into a generative AI and have the generative AI perform the correction order adjustment.

[0093] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is anxious, the learning unit will prioritize selecting simple training data. For instance, the learning unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The learning unit can also select detailed training data if the user is relaxed. For example, the learning unit can record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is tired, the learning unit can adjust the selection of training data to allow for stress-free learning. For example, the learning unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for more appropriate learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0094] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm by referring to past learning data. For example, the learning unit can select the optimal learning algorithm by analyzing past learning data. The learning unit can also adjust the parameters of the learning algorithm based on past learning data. For example, the learning unit can adjust the parameters of the learning algorithm by analyzing past learning data. The learning unit can also improve the accuracy of the learning algorithm by analyzing past learning data. For example, the learning unit improves the accuracy of the learning algorithm by analyzing past learning data. Thus, the accuracy of the learning algorithm is improved by referring to past learning data. Optimization of the learning algorithm includes, but is not limited to, the use of past data and the details of the optimization algorithm. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input past learning data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0095] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is anxious, the learning unit can reduce the learning frequency to allow for more manageable learning. For example, the learning unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The learning unit can also increase the learning frequency when the user is relaxed to enable more efficient learning. For example, the learning unit can record the user's voice and estimate their emotions using voice analysis technology. The learning unit can also adjust the learning frequency when the user is tired to allow for more manageable learning. For example, the learning unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for more appropriate learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0096] The learning unit can weight the training data based on the submission timing of the input data during training. For example, the learning unit can weight important training data based on the submission timing of the input data. For example, the learning unit can analyze the submission timing of the input data and weight important training data. The learning unit can also adjust the weighting of the training data considering the submission timing of the input data. For example, the learning unit can analyze the submission timing of the input data and adjust the weighting of the training data. The learning unit can also improve the accuracy of the training data based on the submission timing of the input data. For example, the learning unit can analyze the submission timing of the input data and improve the accuracy of the training data. This allows for priority learning of important data by weighting the training data based on the submission timing of the input data. Weighting includes, but is not limited to, data importance and details of the weighting algorithm. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the input data submission timing data into a generative AI and have the generative AI perform the weighting of the training data.

[0097] The improvement unit can estimate the user's emotions and adjust the interface display method based on the estimated user emotions. For example, if the user is tense, the improvement unit can provide an interface with calming colors to reduce visual stress. For example, the improvement unit can capture the user's facial expression with a camera and estimate the emotion using an emotion estimation algorithm. Also, if the user is having fun, the improvement unit can provide an interface with bright colors to make the input process more enjoyable. For example, the improvement unit can record the user's voice and estimate the emotion using voice analysis technology. Also, if the user is tired, the improvement unit can provide a simple and highly visible interface to make the input process easier. For example, the improvement unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate the emotion using an emotion estimation algorithm. This allows for a more appropriate display by adjusting the interface display method according to 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-described processes in the improvement unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the improvement unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0098] The improvement unit can select the optimal display method by referring to the user's past operation history when displaying the interface. For example, the improvement unit can propose the optimal display method based on the user's past operation history. For example, the improvement unit can analyze the user's past operation history and propose the optimal display method. The improvement unit can also analyze the user's past operation history and improve the accuracy of the display method. For example, the improvement unit can analyze the user's past operation history and improve the accuracy of the display method. The improvement unit can also adjust the order of the display methods based on the user's past operation history. For example, the improvement unit can analyze the user's past operation history and adjust the order of the display methods. This allows the optimal display method to be selected by referring to the past operation history. Operation history includes, but is not limited to, click data and operation log analysis methods. Some or all of the above processing in the improvement unit may be performed using, for example, a generation AI, or without a generation AI. For example, the improvement unit can input the user's past operation history data into a generation AI and have the generation AI select the optimal display method.

[0099] The improvement unit can estimate the user's emotions and adjust the interface's operating procedures based on the estimated emotions. For example, if the user is tense, the improvement unit can provide simple operating procedures to reduce the burden of operation. For example, the improvement unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Also, if the user is enjoying themselves, the improvement unit can provide detailed operating procedures to enhance the enjoyment of operation. For example, the improvement unit can record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is tired, the improvement unit can simplify the operating procedures to reduce the burden of operation. For example, the improvement unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows for more appropriate operation by adjusting the operating procedures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the improvement unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the improvement unit can input user image data captured by a camera into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0100] The improvement unit can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, the improvement unit can provide a display method that matches the screen size. For example, the improvement unit can analyze the user's device information and provide a display method that matches the screen size. The improvement unit can also provide a display method optimized for a larger screen if the user is using a tablet. For example, the improvement unit can analyze the user's device information and provide a display method optimized for a larger screen. The improvement unit can also provide a concise and highly visible display method if the user is using a smartwatch. For example, the improvement unit can analyze the user's device information and provide a concise and highly visible display method. In this way, the optimal display method can be selected by taking device information into consideration. Device information includes, but is not limited to, the type of device and the method of analyzing usage. Some or all of the above processing in the improvement unit may be performed using, for example, a generation AI, or without a generation AI. For example, the improvement unit can input the user's device information data into a generation AI and have the generation AI select the optimal display method.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The reception desk can analyze the user's past input history when receiving user input and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the user has frequently used in the past (such as voice or handwriting). The reception desk can also predict and suggest input methods to be used during specific time periods based on the user's past input history. Furthermore, the reception desk can automatically display input candidates based on the user's past input history. This allows for the selection of the most suitable input method by analyzing past input history. The optimal input method may include, but is not limited to, the type of input and the user's past behavioral patterns.

[0103] The integration unit can estimate the user's emotions and adjust the integration criteria based on the estimated emotions. For example, if the user is anxious, a simple integration criterion is applied. The user's facial expressions are captured by a camera, and emotions are estimated using an emotion estimation algorithm. If the user is relaxed, a more detailed integration criterion can also be applied. The user's voice is recorded, and emotions are estimated using voice analysis technology. Furthermore, if the user is tired, the integration criteria can be adjusted to allow for smoother integration. The user's biometric data (heart rate and skin electrical activity) is collected by sensors, and emotions are estimated using an emotion estimation algorithm. This allows for more appropriate integration by adjusting the integration criteria according to the user's emotions.

[0104] The correction unit can estimate the user's emotions and adjust the correction method based on the estimated emotions. For example, if the user is anxious, a simple correction method can be applied. The user's facial expressions are captured by a camera, and emotions are estimated using an emotion estimation algorithm. If the user is relaxed, a more detailed correction method can also be applied. The user's voice is recorded, and emotions are estimated using voice analysis technology. If the user is tired, the correction method can be adjusted to allow for a more comfortable correction. The user's biometric data (heart rate and skin electrical activity) is collected by sensors, and emotions are estimated using an emotion estimation algorithm. This allows for more appropriate correction by adjusting the correction method according to the user's emotions.

[0105] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is anxious, it will prioritize selecting simple training data. It captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. If the user is relaxed, it can also select more detailed training data. It records the user's voice and estimates their emotions using voice analysis technology. Furthermore, if the user is tired, it can adjust the selection of training data to allow for more manageable learning. It collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. This allows for more appropriate learning by selecting training data according to the user's emotions.

[0106] The improvement unit can estimate the user's emotions and adjust the interface display method based on the estimated emotions. For example, if the user is tense, it can provide an interface with calming colors to reduce visual stress. The user's facial expressions are captured by a camera, and emotions are estimated using an emotion estimation algorithm. Also, if the user is enjoying themselves, a brightly colored interface can be provided to make the input process more enjoyable. The user's voice is recorded, and emotions are estimated using voice analysis technology. Furthermore, if the user is tired, a simple and highly visible interface can be provided to facilitate the input process. The user's biometric data (heart rate and skin electrical activity) is collected by sensors, and emotions are estimated using an emotion estimation algorithm. This allows for a more appropriate display by adjusting the interface display method according to the user's emotions.

[0107] The reception system can prioritize accepting inputs that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, it will prioritize accepting inputs related to that location. It analyzes the user's geographical location and prioritizes accepting inputs related to that location. It can also display relevant input items based on the user's geographical location. It displays relevant input items based on the user's current location. It can also adjust the order of input items based on the user's current location. It adjusts the order of input items based on the user's current location. This allows for more relevant input by considering geographical location.

[0108] The integration unit can improve the accuracy of integration by considering the interrelationships of the input data. For example, it can analyze the interrelationships of the input data and prioritize the integration of highly relevant data. It can also improve the accuracy of integration based on the interrelationships of the input data. It adjusts the integration order considering the interrelationships of the input data. This improves the accuracy of integration by considering the interrelationships of the input data. Interrelationships include, but are not limited to, correlation analysis and network analysis.

[0109] The correction unit can adjust the level of detail of the correction based on the importance of the input data. For example, it can perform detailed corrections based on the importance of the input data. It analyzes the importance of the input data and performs detailed corrections. It can also adjust the order of corrections, taking into account the importance of the input data. It analyzes the importance of the input data and adjusts the order of corrections. It can also improve the accuracy of the corrections based on the importance of the input data. It analyzes the importance of the input data and improves the accuracy of the corrections. As a result, by adjusting the level of detail of the corrections based on the importance of the input data, important data can be corrected preferentially.

[0110] The learning unit can optimize the learning algorithm by referring to past training data. For example, it can select the optimal learning algorithm by referring to past training data. It can also select the optimal learning algorithm by analyzing past training data. Furthermore, it can adjust the parameters of the learning algorithm based on past training data. It can also improve the accuracy of the learning algorithm by analyzing past training data. Thus, the accuracy of the learning algorithm is improved by referring to past training data.

[0111] The improvement unit can select the optimal display method when displaying the interface, taking into account the user's device information. For example, if the user is using a smartphone, it can provide a display method that matches the screen size. It analyzes the user's device information and provides a display method that matches the screen size. Also, if the user is using a tablet, it can provide a display method optimized for a larger screen. It analyzes the user's device information and provides a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible display method. It analyzes the user's device information and provides a concise and highly visible display method. In this way, the optimal display method can be selected by taking device information into consideration.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The reception desk receives user input. User input includes handwritten text and voice input. The reception desk can receive handwritten text using a touchscreen and voice input via a microphone. Furthermore, the reception desk can process the text and voice input from the user in real time. For example, handwritten text is detected by a high-precision touchscreen sensor and converted into digital data. Voice input is captured clearly using a microphone with noise-canceling capabilities. Step 2: The integration unit integrates the handwriting recognition and voice data based on the information received by the reception unit. The integration unit utilizes an LLM (Large-Scale Language Model) to integrate the text-based voice recognition results with the handwriting recognition results. For example, if the handwritten "1" and "7" are ambiguous, it can complete the ambiguity by saying "You just said 7" based on the user's voice. The integration unit can also learn the user's input patterns and gradually improve its accuracy. Step 3: The correction unit provides accurate character input based on the data integrated by the integration unit. The correction unit complements ambiguous handwriting from the user's voice. For example, if the user intended to write "7" but it was converted to "1", the correction unit can correct it by saying "I just said 7" via voice input. The correction unit can also learn the user's habits and, if the same mistakes occur frequently, can learn, predict, and correct them.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] Each of the multiple elements described above, including the reception unit, integration unit, correction unit, learning unit, and improvement unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives the user's handwritten characters or voice input using the touchscreen or microphone 38B of the smart device 14. The integration unit integrates the handwritten character recognition results and voice recognition results using the specific processing unit 290 of the data processing unit 12. The correction unit supplements ambiguous handwriting with voice information using the specific processing unit 290 of the data processing unit 12. The learning unit learns the user's habits and input patterns using the specific processing unit 290 of the data processing unit 12. The improvement unit continuously improves the user interface using the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Each of the multiple elements described above, including the reception unit, integration unit, correction unit, learning unit, and improvement unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives the user's handwritten characters or voice input using the touchscreen or microphone 238 of the smart glasses 214. The integration unit integrates the handwritten character recognition results and voice recognition results using the identification processing unit 290 of the data processing unit 12. The correction unit uses the identification processing unit 290 of the data processing unit 12 to supplement ambiguous handwriting with voice information. The learning unit uses the identification processing unit 290 of the data processing unit 12 to learn the user's habits and input patterns. The improvement unit uses the control unit 46A of the smart glasses 214 to continuously improve the user interface. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] Each of the multiple elements described above, including the reception unit, integration unit, correction unit, learning unit, and improvement unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives the user's handwritten characters or voice input using the touchscreen or microphone 238 of the headset terminal 314. The integration unit integrates the handwritten character recognition results and voice recognition results using the specific processing unit 290 of the data processing unit 12. The correction unit supplements ambiguous handwriting with voice information using the specific processing unit 290 of the data processing unit 12. The learning unit learns the user's habits and input patterns using the specific processing unit 290 of the data processing unit 12. The improvement unit continuously improves the user interface using the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the reception unit, integration unit, correction unit, learning unit, and improvement unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives the user's handwritten characters or voice input using the robot 414's touchscreen or microphone 238. The integration unit integrates the handwritten character recognition results and voice recognition results using the specific processing unit 290 of the data processing unit 12. The correction unit uses the specific processing unit 290 of the data processing unit 12 to supplement ambiguous handwriting with voice information. The learning unit uses the specific processing unit 290 of the data processing unit 12 to learn the user's habits and input patterns. The improvement unit uses the control unit 46A of the robot 414 to continuously improve the user interface. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] (Note 1) A reception area that receives user input, An integration unit that integrates handwriting recognition and voice data based on the information received by the aforementioned reception unit, The system includes a correction unit that provides accurate character input based on the data integrated by the integration unit. A system characterized by the following features. (Note 2) The aforementioned integration unit is LLM is used to integrate text-based speech recognition results and handwriting recognition results. The system described in Appendix 1, characterized by the features described herein. (Note 3) The correction unit, Completing ambiguous handwriting from the user's voice. The system described in Appendix 1, characterized by the features described herein. (Note 4) It has a learning unit that learns the user's habits. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, Through reinforcement learning, the system learns the user's habits and input patterns to improve accuracy. The system described in Appendix 4, characterized by the features described herein. (Note 6) It includes an improvement section to enhance the user interface. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned improvement unit is, Continuously improve UI / UX based on user interaction data. The system described in Appendix 6, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is Analyze the user's past input history to select the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving input, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is It estimates the user's emotions and determines the priority of input to accept based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving input, the system prioritizes accepting inputs that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When receiving input, the system analyzes the user's social media activity and accepts relevant input. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned integration unit is It estimates user sentiment and adjusts integration criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned integration unit is During integration, the interrelationships between input data are taken into consideration to improve the accuracy of the integration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned integration unit is During the integration process, the attribute information of the data submitters will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned integration unit is It estimates the user's sentiment and adjusts the order in which the integration results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned integration unit is During integration, the geographical distribution of the input data is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned integration unit is During integration, we improve the accuracy of the integration by referring to relevant literature for the input data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The correction unit, The system estimates the user's emotions and adjusts the correction method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The correction unit, During correction, the level of detail of the correction is adjusted based on the importance of the input data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The correction unit, During correction, different correction algorithms are applied depending on the category of the input data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The correction unit, The system estimates the user's emotions and determines the priority of corrections based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The correction unit, During the correction process, the priority of corrections is determined based on when the input data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The correction unit, During correction, the order of corrections is adjusted based on the relevance of the input data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, During training, the training data is weighted based on when the input data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned improvement unit is, It estimates the user's emotions and adjusts the interface display based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned improvement unit is, When displaying the interface, the system selects the optimal display method by referring to the user's past operation history. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned improvement unit is, It estimates the user's emotions and adjusts the interface operation procedures based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned improvement unit is, When displaying the interface, the optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that receives user input, An integration unit that integrates handwriting recognition and voice data based on the information received by the aforementioned reception unit, The system includes a correction unit that provides accurate character input based on the data integrated by the integration unit. A system characterized by the following features.

2. The aforementioned integration unit is LLM is used to integrate text-based speech recognition results and handwriting recognition results. The system according to feature 1.

3. The correction unit, Completing ambiguous handwriting from the user's voice. The system according to feature 1.

4. It has a learning unit that learns the user's habits. The system according to feature 1.

5. The aforementioned learning unit, Through reinforcement learning, the system learns the user's habits and input patterns to improve accuracy. The system according to feature 4.

6. It includes an improvement section to enhance the user interface. The system according to feature 1.

7. The aforementioned improvement unit is, Continuously improve UI / UX based on user interaction data. The system described in claim 6.

8. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of input acceptance based on the estimated emotions. The system according to feature 1.

Images