System

Abstract

A system according to an embodiment aims to provide a more comfortable writing experience.SOLUTION: A system according to an embodiment includes an analysis unit, a prediction unit, and a feedback unit. The analysis unit analyzes the input content of the user. The prediction unit performs prediction based on the content analyzed by the analysis unit. When the user selects the prediction candidate presented by the prediction unit, the feedback unit receives the selection.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have the problem that dictionary-based input systems can only predict words or short sentences, resulting in low efficiency in writing sentences.

[0005] The system according to the embodiment aims to provide a more comfortable writing experience. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a prediction unit, and a feedback unit. The analysis unit analyzes the content of a user's input. The prediction unit makes a prediction based on the content analyzed by the analysis unit. When the user selects a prediction candidate presented by the prediction unit, the feedback unit receives the selection. [Effects of the Invention]

[0007] The system according to the embodiment can provide a more comfortable writing experience. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A Japanese input system according to an embodiment of the present invention utilizes a generative AI to analyze user input, make appropriate predictions, and receive feedback. When a user begins inputting Japanese text, this Japanese input system analyzes the input in real time, and the generative AI predicts appropriate words, phrases, or even entire sentences based on the analysis results. For example, if a user inputs "today," the system presents candidates such as "The weather is nice today, isn't it?" and "What are you going to do today?". Furthermore, the system can take the user's input history and context into account to make more appropriate predictions. For example, if a user has previously input "The weather is nice today, isn't it?", the system will prioritize presenting that phrase. Furthermore, if a user frequently uses specific technical terms, the system can provide predictions that include those terms. This system not only significantly improves the efficiency of writing, but also helps users write more natural and fluent sentences. This is particularly useful in situations that require accurate and polite writing, such as writing business emails or reports. The system can also learn from user feedback and improve its prediction accuracy. For example, if a user selects a suggested candidate, that selection is fed back to the system and reflected in future predictions. In this way, the Japanese input system and the integrated system that assists with writing using generative AI provide users with a comfortable and efficient writing experience. This allows the Japanese input system to analyze the user's input, make appropriate predictions, and receive feedback, providing a comfortable writing experience. This is particularly useful in situations that require accurate and polite writing, such as writing business emails or reports. The system also learns from user feedback and can improve its prediction accuracy. This allows users to write more natural and fluent sentences.

[0029] A Japanese input system according to an embodiment includes an analysis unit, a prediction unit, and a feedback unit. The analysis unit analyzes a user's input content. The analysis unit analyzes the user's input content using, for example, text analysis technology. The analysis unit can also analyze the user's input content using data mining technology. The analysis unit can also analyze the user's input content using a generation AI. For example, the analysis unit inputs the user's input content to the generation AI and outputs an analysis result. The prediction unit makes a prediction based on the content analyzed by the analysis unit. The prediction unit makes a prediction using, for example, a statistical model. The prediction unit can also make a prediction using a machine learning algorithm. The prediction unit can also make a prediction using the generation AI. For example, the prediction unit inputs the analysis result to the generation AI and outputs a prediction result. When a user selects a prediction candidate presented by the prediction unit, the feedback unit receives the selection. The feedback unit receives the user's selection by, for example, clicking or tapping. The feedback unit can also receive the user's selection by voice input. The feedback unit can also receive the user's selection by the generation AI. For example, the feedback unit inputs the user's selection to the generation AI and outputs the feedback result. As a result, the Japanese input system according to the embodiment can provide a comfortable writing experience by analyzing the user's input content, making appropriate predictions, and receiving feedback.

[0030] The analysis unit can perform analysis based on the user's input history and context. For example, the analysis unit stores the user's past input data and performs analysis based on that data. For example, the analysis unit stores data previously input by the user in a database and performs analysis based on that data. The analysis unit can also perform analysis taking the user's input history into consideration. For example, the analysis unit prioritizes analysis of phrases and words previously input by the user. Furthermore, the analysis unit can perform analysis taking the user's context into consideration. For example, the analysis unit analyzes the context before and after a sentence input by the user and performs analysis based on that context. This enables more appropriate analysis by taking the user's input history and context into consideration. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's input history and context into the generation AI and have the generation AI execute the analysis results.

[0031] The prediction unit can make predictions based on the user's input history and context. For example, the prediction unit stores the user's past input data and makes predictions based on that data. For example, the prediction unit stores data previously input by the user in a database and makes predictions based on that data. The prediction unit can also make predictions taking the user's input history into account. For example, the prediction unit prioritizes predicting phrases and words previously input by the user. Furthermore, the prediction unit can make predictions taking the user's context into account. For example, the prediction unit analyzes the context before and after a sentence input by the user and makes predictions based on that context. This enables more appropriate predictions by taking the user's input history and context into account. Some or all of the above-mentioned processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the user's input history and context into the generation AI and have the generation AI execute the prediction results.

[0032] The feedback unit can receive a user's selection and feed the selection back to the system. The feedback unit can receive the user's selection by, for example, clicking or tapping. For example, if the user selects a presented prediction candidate by clicking or tapping, the feedback unit receives the selection. The feedback unit can also receive the user's selection by voice input. For example, if the user selects a prediction candidate by voice, the feedback unit receives the selection. The feedback unit can also receive the user's selection using a generation AI. For example, the feedback unit can input the user's selection to the generation AI and have the generation AI execute the feedback result. This improves the prediction accuracy of the system by feeding back the user's selection. Some or all of the above-described processing in the feedback unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's selection to the generation AI and have the generation AI execute the feedback result.

[0033] The feedback unit can learn the feedback and improve prediction accuracy. For example, when a user selects a presented prediction candidate, the feedback unit learns the selection. For example, the feedback unit stores the prediction candidate selected by the user in a database and performs learning based on the data. The feedback unit can also learn the feedback using a machine learning algorithm. For example, the feedback unit can learn the user's selection data using a machine learning algorithm to improve prediction accuracy. Furthermore, the feedback unit can also learn the feedback using a generation AI. For example, the feedback unit can input the user's selection data to the generation AI and have the generation AI execute the learning results. As a result, the prediction accuracy of the system is improved by learning the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the feedback unit can input the user's selection data to the generation AI and have the generation AI execute the learning results.

[0034] The analysis unit can analyze the user's past input history and select an analysis algorithm. For example, the analysis unit stores the user's past input data and selects an analysis algorithm based on that data. For example, the analysis unit stores data previously entered by the user in a database and selects an analysis algorithm based on that data. The analysis unit can also select an analysis algorithm taking the user's past input history into consideration. For example, the analysis unit prioritizes analyzing phrases and words previously entered by the user. Furthermore, the analysis unit can extract specific patterns from the user's past input history and select an analysis algorithm based on those patterns. For example, the analysis unit selects a more appropriate analysis algorithm by taking into consideration the context of the user's past input. In this way, the optimal analysis algorithm can be selected by analyzing the user's past input history. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's past input history into a generation AI and have the generation AI select an analysis algorithm.

[0035] The analysis unit can perform filtering based on the user's current project or areas of interest. For example, the analysis unit prioritizes analyzing words and phrases related to the project the user is currently working on. For example, the analysis unit filters and analyzes information related to the project the user is currently working on. The analysis unit can also filter and analyze related information based on the user's areas of interest. For example, if the user is interested in a particular topic, the analysis unit prioritizes analyzing information related to that topic. This enables more relevant analysis by filtering based on the user's current project or areas of interest. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's current project or areas of interest into the generation AI and have the generation AI perform the filtering.

[0036] The analysis unit can select the optimal analysis means depending on the user's input method. For example, if the user uses voice input, the analysis unit performs analysis using voice recognition technology. For example, the analysis unit converts the content input by voice into text data using voice recognition technology and performs analysis based on the text data. Furthermore, if the user uses text input, the analysis unit can also perform analysis using text analysis technology. For example, the analysis unit analyzes text data input by the user using a keyboard. Furthermore, if the user uses image input, the analysis unit can also perform analysis using image recognition technology. For example, the analysis unit analyzes the content input by the user using image recognition technology and performs analysis based on the analysis results. This enables more appropriate analysis by selecting the optimal analysis means depending on the user's input method. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the user's input method into the generation AI and have the generation AI select the optimal analysis means.

[0037] The analysis unit can prioritize analysis of highly relevant information based on the user's geographical location information. For example, when the user is in a specific region, the analysis unit prioritizes analysis of information related to that region. For example, when the user is in a specific city, the analysis unit prioritizes analysis of information related to that city. Furthermore, when the user is traveling, the analysis unit can also prioritize analysis of information related to the travel destination. For example, the analysis unit prioritizes analysis of information related to the travel destination based on content input by the user at the travel destination. This allows for prioritized analysis of highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the user's geographical location information to the generation AI and cause the generation AI to analyze highly relevant information.

[0038] The analysis unit can analyze the user's social media activities and analyze related information. The analysis unit performs analysis based on, for example, information shared by the user on social media. For example, the analysis unit analyzes content posted by the user on social media and analyzes information related to that content. The analysis unit can also analyze related information by referring to the activities of the user's friends on social media. For example, the analysis unit performs analysis based on information shared by the user's friends on social media. In this way, related information can be analyzed by analyzing the user's social media activities. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the user's social media activities into the generation AI and cause the generation AI to analyze the related information.

[0039] The analysis unit can customize the analysis method by reflecting the user's past feedback. The analysis unit, for example, adjusts the analysis method based on feedback provided by the user in the past. For example, the analysis unit stores feedback previously selected by the user in a database and adjusts the analysis method based on that data. The analysis unit can also preferentially use a specific analysis method based on the user's past feedback. For example, the analysis unit selects a specific analysis algorithm based on the user's past feedback. The analysis unit can also customize the analysis algorithm by reflecting the user's feedback. For example, the analysis unit adjusts parameters of the analysis algorithm based on the user's feedback. In this way, the analysis method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the user's past feedback into the generation AI and have the generation AI customize the analysis method.

[0040] The prediction unit can adjust the level of detail of the prediction based on the importance of the input content. The prediction unit, for example, evaluates the importance of the input content and adjusts the level of detail of the prediction based on the evaluation. For example, the prediction unit presents a detailed prediction if the content is important. The prediction unit can also present a concise prediction if the content is general. Furthermore, if a user inputs a specific important keyword, the prediction unit can present a detailed prediction related to the keyword. For example, the prediction unit evaluates the frequency of appearance of the keyword input by the user and the importance of the context, and adjusts the level of detail of the prediction based on the evaluation. This enables more accurate predictions by adjusting the level of detail of the prediction based on the importance of the input content. Some or all of the above-mentioned processing in the prediction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the prediction unit can input the importance of the input content to the generation AI and have the generation AI adjust the level of detail of the prediction.

[0041] The prediction unit can apply different prediction algorithms depending on the category of the input content. For example, the prediction unit classifies the category of the input content and applies different prediction algorithms depending on the category. For example, the prediction unit applies a formal prediction algorithm to a business document. The prediction unit can also apply a casual prediction algorithm to a casual message. Furthermore, the prediction unit can apply a prediction algorithm including technical terms to a technical document. For example, the prediction unit selects an appropriate prediction algorithm based on the category of the input content and applies the selected algorithm. This enables more accurate prediction by applying different prediction algorithms depending on the category of the input content. Some or all of the above-described processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the category of the input content to the generation AI and have the generation AI select and apply a prediction algorithm.

[0042] The prediction unit can improve prediction accuracy by referring to the user's past prediction results. The prediction unit, for example, improves the accuracy of the next prediction based on prediction results selected by the user in the past. For example, the prediction unit stores prediction results selected by the user in a database and improves prediction accuracy based on that data. The prediction unit can also extract specific patterns from the user's past prediction results and make predictions based on those patterns. For example, the prediction unit prioritizes predicting phrases used by the user in the past. This improves prediction accuracy by referring to the user's past prediction results. Some or all of the above-described processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the user's past prediction results into the generation AI and cause the generation AI to improve prediction accuracy.

[0043] The prediction unit can determine the priority of predictions based on the submission time of the input content. The prediction unit, for example, evaluates the submission time of the input content and determines the priority of predictions based on the evaluation. For example, the prediction unit prioritizes important predictions when the deadline is approaching. The prediction unit can also present general predictions when the submission time is far away. Furthermore, if a user sets a specific submission time, the prediction unit can determine the priority of predictions based on that time. For example, the prediction unit determines the priority of predictions based on the submission deadline set by the user. This enables more accurate predictions by determining the priority of predictions based on the submission time of the input content. Some or all of the above-mentioned processing in the prediction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the prediction unit can input the submission time of the input content to the generation AI and have the generation AI determine the priority of predictions.

[0044] The prediction unit can adjust the order of predictions based on the relevance of the input content. The prediction unit, for example, evaluates the relevance of the input content and adjusts the order of predictions based on the evaluation. For example, the prediction unit prioritizes presenting predictions related to important keywords. The prediction unit can also postpone predictions related to general keywords. Furthermore, if a user sets a specific relevance, the prediction unit can adjust the order of predictions based on the relevance. For example, the prediction unit adjusts the order of predictions based on the relevance criteria set by the user. This enables more appropriate predictions by adjusting the order of predictions based on the relevance of the input content. Some or all of the above-described processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the relevance of the input content to the generation AI and have the generation AI adjust the order of predictions.

[0045] The prediction unit can adjust the use of technical terms in the prediction according to the user's level of expertise. The prediction unit, for example, evaluates the user's level of expertise and adjusts the use of technical terms in the prediction based on the evaluation. For example, if the user is an expert, the prediction unit presents a prediction that uses a lot of technical terms. Also, if the user is a beginner, the prediction unit can present a prediction that uses simple language. Furthermore, the prediction unit can estimate the user's level of expertise from the user's past input history and present a prediction accordingly. For example, the prediction unit evaluates the user's level of expertise based on the user's past input content and adjusts the use of technical terms in the prediction based on the evaluation. This enables more appropriate predictions by adjusting the use of technical terms in the prediction according to the user's level of expertise. Some or all of the above-described processing in the prediction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the prediction unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms in the prediction.

[0046] The feedback unit can select the optimal feedback method by analyzing the user's past selection history. The feedback unit, for example, selects the optimal method based on feedback methods previously selected by the user. For example, the feedback unit stores feedback methods previously selected by the user in a database and selects the optimal method based on that data. The feedback unit can also extract a specific pattern from the user's past selection history and provide feedback based on that pattern. For example, the feedback unit prioritizes providing feedback methods previously used by the user. This allows the optimal feedback method to be selected by analyzing the user's past selection history. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's past selection history into the generation AI and have the generation AI select the optimal feedback method.

[0047] The feedback unit can customize the feedback means based on the user's current situation. For example, when the user is busy, the feedback unit provides concise feedback. For example, when the user is busy, the feedback unit provides short and to-the-point feedback. The feedback unit can also provide detailed feedback when the user is relaxed. For example, when the user is relaxed, the feedback unit provides feedback including detailed explanations and advice. Furthermore, when the user is in a specific situation, the feedback unit can provide feedback appropriate to the situation. For example, when the user is working on a specific project, the feedback unit provides feedback related to the project. This enables more appropriate feedback by customizing the feedback means based on the user's current situation. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's current situation to the generation AI and cause the generation AI to customize the feedback means.

[0048] The feedback unit can improve the feedback method by reflecting the user's feedback. The feedback unit, for example, adjusts the feedback method based on the feedback provided by the user. For example, the feedback unit stores the feedback provided by the user in a database and adjusts the feedback method based on the data. The feedback unit can also extract specific improvements from the user's feedback and provide feedback based on the improvements. For example, the feedback unit improves the feedback method based on problems pointed out by the user. Furthermore, the feedback unit can learn feedback using a generation AI and improve the feedback method. For example, the feedback unit can input the user's feedback data into the generation AI and have the generation AI execute the learning results. In this way, the feedback method can be improved by reflecting the user's feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the feedback unit can input the user's feedback data into the generation AI and have the generation AI execute improvements to the feedback method.

[0049] The feedback unit can select the optimal feedback method by taking into account the user's geographical location information. For example, if the user is in a specific area, the feedback unit feeds back information related to that area. For example, if the user is in a specific city, the feedback unit feeds back information related to that city. Furthermore, if the user is traveling, the feedback unit can also feed back information related to the travel destination. For example, the feedback unit provides information the user needs at the travel destination. In this way, the optimal feedback method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's geographical location information into the generation AI and cause the generation AI to select the optimal feedback method.

[0050] The feedback unit can analyze the user's social media activity and suggest a means of feedback. The feedback unit, for example, provides feedback based on information shared by the user on social media. For example, the feedback unit analyzes content posted by the user on social media and provides feedback on information related to that content. The feedback unit can also provide feedback on related information by referring to the activities of the user's friends on social media. For example, the feedback unit provides feedback based on information shared by the user's friends on social media. In this way, by analyzing the user's social media activity, a means of feedback can be suggested. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's social media activity into the generation AI and cause the generation AI to suggest a means of feedback.

[0051] The feedback unit can customize the feedback method by reflecting the user's past feedback. The feedback unit, for example, adjusts the feedback method based on feedback provided by the user in the past. For example, the feedback unit stores feedback provided by the user in a database and adjusts the feedback method based on the data. The feedback unit can also extract specific improvements from the user's past feedback and provide feedback based on the improvements. For example, the feedback unit improves the feedback method based on problems pointed out by the user. Furthermore, the feedback unit can learn feedback using a generation AI and customize the feedback method. For example, the feedback unit can input the user's feedback data into the generation AI and have the generation AI execute the learning results. In this way, the feedback method can be customized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the feedback unit can input the user's past feedback into the generation AI and have the generation AI execute the customization of the feedback method.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The analysis unit can take the user's current activity status into consideration when analyzing the user's input content. For example, if the user is at work, the analysis unit can prioritize analyzing business-related words and phrases. If the user is on vacation, the analysis unit can prioritize analyzing travel- and leisure-related words and phrases. Furthermore, if the user is participating in a specific event, the analysis unit can prioritize analyzing information related to that event. This allows for more appropriate analysis by performing analysis based on the user's current activity status.

[0054] When receiving a user's selection, the feedback unit can estimate the reason for the user's selection. For example, the feedback unit can analyze the reason why the user selected a particular predicted candidate and provide feedback based on that reason. It can also estimate the reason for a predicted candidate that the user did not select and reflect that in the next prediction. Furthermore, it can analyze the user's selection pattern and provide feedback based on that pattern. This allows for more appropriate feedback by taking into account the reason for the user's selection.

[0055] The feedback unit can take the frequency of the user's selection into consideration when receiving the user's selection. For example, the feedback unit can preferentially present predicted candidates that the user frequently selects. Also, the feedback unit can avoid presenting predicted candidates that the user rarely selects. Furthermore, the feedback unit can adjust the presentation order of the predicted candidates based on the frequency of the user's selection. This allows for more appropriate feedback by taking the frequency of the user's selection into consideration.

[0056] The analysis unit can take into account the user's past input patterns when analyzing the user's input content. For example, it analyzes the patterns of content the user has input in the past and performs analysis based on those patterns. It can also adjust the analysis method based on the user's input pattern. Furthermore, it can also adjust the analysis method taking into account fluctuations in the user's input pattern. This allows for more appropriate analysis by taking into account the user's past input patterns.

[0057] The prediction unit can take the user's current activity status into consideration when predicting the user's input content. For example, if the user is at work, business-related predictions can be presented with priority. If the user is on vacation, travel- and leisure-related predictions can be presented with priority. Furthermore, if the user is participating in a specific event, predictions related to that event can be presented with priority. This allows for more accurate predictions by making predictions based on the user's current activity status.

[0058] When receiving a user's selection, the feedback unit can estimate the reason for the user's selection. For example, the feedback unit can analyze the reason why the user selected a particular predicted candidate and provide feedback based on that reason. It can also estimate the reason for a predicted candidate that the user did not select and reflect that in the next prediction. Furthermore, it can analyze the user's selection pattern and provide feedback based on that pattern. This allows for more appropriate feedback by taking into account the reason for the user's selection.

[0059] The feedback unit can take the frequency of the user's selection into consideration when receiving the user's selection. For example, the feedback unit can preferentially present predicted candidates that the user frequently selects. Also, the feedback unit can avoid presenting predicted candidates that the user rarely selects. Furthermore, the feedback unit can adjust the presentation order of the predicted candidates based on the frequency of the user's selection. This allows for more appropriate feedback by taking the frequency of the user's selection into consideration.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The analysis unit analyzes the user's input. The analysis unit can analyze the user's input using text analysis technology, data mining technology, or generation AI. For example, the user's input is input to the generation AI, which then outputs the analysis results. Step 2: The prediction unit makes a prediction based on the content analyzed by the analysis unit. The prediction unit can make a prediction using a statistical model, a machine learning algorithm, or a generation AI. For example, the analysis results are input to the generation AI, which then outputs a prediction result. Step 3: When the user selects a prediction candidate presented by the prediction unit, the feedback unit receives the selection. The feedback unit can receive the user's selection by clicking or tapping, voice input, or using the generation AI. For example, the feedback unit inputs the user's selection into the generation AI and outputs a feedback result.

[0062] (Example 2) A Japanese input system according to an embodiment of the present invention utilizes a generative AI to analyze user input, make appropriate predictions, and receive feedback. When a user begins inputting Japanese text, this Japanese input system analyzes the input in real time, and the generative AI predicts appropriate words, phrases, or even entire sentences based on the analysis results. For example, if a user inputs "today," the system presents candidates such as "The weather is nice today, isn't it?" and "What are you going to do today?". Furthermore, the system can take the user's input history and context into account to make more appropriate predictions. For example, if a user has previously input "The weather is nice today, isn't it?", the system will prioritize presenting that phrase. Furthermore, if a user frequently uses specific technical terms, the system can provide predictions that include those terms. This system not only significantly improves the efficiency of writing, but also helps users write more natural and fluent sentences. This is particularly useful in situations that require accurate and polite writing, such as writing business emails or reports. The system can also learn from user feedback and improve its prediction accuracy. For example, if a user selects a suggested candidate, that selection is fed back to the system and reflected in future predictions. In this way, the Japanese input system and the integrated system that assists with writing using generative AI provide users with a comfortable and efficient writing experience. This allows the Japanese input system to analyze the user's input, make appropriate predictions, and receive feedback, providing a comfortable writing experience. This is particularly useful in situations that require accurate and polite writing, such as writing business emails or reports. The system also learns from user feedback and can improve its prediction accuracy. This allows users to write more natural and fluent sentences.

[0063] A Japanese input system according to an embodiment includes an analysis unit, a prediction unit, and a feedback unit. The analysis unit analyzes a user's input content. The analysis unit analyzes the user's input content using, for example, text analysis technology. The analysis unit can also analyze the user's input content using data mining technology. The analysis unit can also analyze the user's input content using a generation AI. For example, the analysis unit inputs the user's input content to the generation AI and outputs an analysis result. The prediction unit makes a prediction based on the content analyzed by the analysis unit. The prediction unit makes a prediction using, for example, a statistical model. The prediction unit can also make a prediction using a machine learning algorithm. The prediction unit can also make a prediction using the generation AI. For example, the prediction unit inputs the analysis result to the generation AI and outputs a prediction result. When a user selects a prediction candidate presented by the prediction unit, the feedback unit receives the selection. The feedback unit receives the user's selection by, for example, clicking or tapping. The feedback unit can also receive the user's selection by voice input. The feedback unit can also receive the user's selection by the generation AI. For example, the feedback unit inputs the user's selection to the generation AI and outputs the feedback result. As a result, the Japanese input system according to the embodiment can provide a comfortable writing experience by analyzing the user's input content, making appropriate predictions, and receiving feedback.

[0064] The analysis unit can perform analysis based on the user's input history and context. For example, the analysis unit stores the user's past input data and performs analysis based on that data. For example, the analysis unit stores data previously input by the user in a database and performs analysis based on that data. The analysis unit can also perform analysis taking the user's input history into consideration. For example, the analysis unit prioritizes analysis of phrases and words previously input by the user. Furthermore, the analysis unit can perform analysis taking the user's context into consideration. For example, the analysis unit analyzes the context before and after a sentence input by the user and performs analysis based on that context. This enables more appropriate analysis by taking the user's input history and context into consideration. Some or all of the above-mentioned processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's input history and context into the generation AI and have the generation AI execute the analysis results.

[0065] The prediction unit can make predictions based on the user's input history and context. For example, the prediction unit stores the user's past input data and makes predictions based on that data. For example, the prediction unit stores data previously input by the user in a database and makes predictions based on that data. The prediction unit can also make predictions taking the user's input history into account. For example, the prediction unit prioritizes predicting phrases and words previously input by the user. Furthermore, the prediction unit can make predictions taking the user's context into account. For example, the prediction unit analyzes the context before and after a sentence input by the user and makes predictions based on that context. This enables more appropriate predictions by taking the user's input history and context into account. Some or all of the above-mentioned processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the user's input history and context into the generation AI and have the generation AI execute the prediction results.

[0066] The feedback unit can receive a user's selection and feed the selection back to the system. The feedback unit can receive the user's selection by, for example, clicking or tapping. For example, if the user selects a presented prediction candidate by clicking or tapping, the feedback unit receives the selection. The feedback unit can also receive the user's selection by voice input. For example, if the user selects a prediction candidate by voice, the feedback unit receives the selection. The feedback unit can also receive the user's selection using a generation AI. For example, the feedback unit can input the user's selection to the generation AI and have the generation AI execute the feedback result. This improves the prediction accuracy of the system by feeding back the user's selection. Some or all of the above-described processing in the feedback unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's selection to the generation AI and have the generation AI execute the feedback result.

[0067] The feedback unit can learn the feedback and improve prediction accuracy. For example, when a user selects a presented prediction candidate, the feedback unit learns the selection. For example, the feedback unit stores the prediction candidate selected by the user in a database and performs learning based on the data. The feedback unit can also learn the feedback using a machine learning algorithm. For example, the feedback unit can learn the user's selection data using a machine learning algorithm to improve prediction accuracy. Furthermore, the feedback unit can also learn the feedback using a generation AI. For example, the feedback unit can input the user's selection data to the generation AI and have the generation AI execute the learning results. As a result, the prediction accuracy of the system is improved by learning the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the feedback unit can input the user's selection data to the generation AI and have the generation AI execute the learning results.

[0068] The analysis unit can estimate the user's emotion and adjust the analysis method based on the estimated user's emotion. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expression. The analysis unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the analysis unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations. This allows the user's emotion to be estimated and the analysis method to be adjusted based on the estimated user's emotion, enabling more appropriate analysis. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input user emotion data into the generation AI and have the generation AI adjust the analysis method.

[0069] The analysis unit can analyze the user's past input history and select an analysis algorithm. For example, the analysis unit stores the user's past input data and selects an analysis algorithm based on that data. For example, the analysis unit stores data previously entered by the user in a database and selects an analysis algorithm based on that data. The analysis unit can also select an analysis algorithm taking the user's past input history into consideration. For example, the analysis unit prioritizes analyzing phrases and words previously entered by the user. Furthermore, the analysis unit can extract specific patterns from the user's past input history and select an analysis algorithm based on those patterns. For example, the analysis unit selects a more appropriate analysis algorithm by taking into consideration the context of the user's past input. In this way, the optimal analysis algorithm can be selected by analyzing the user's past input history. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's past input history into a generation AI and have the generation AI select an analysis algorithm.

[0070] The analysis unit can perform filtering based on the user's current project or areas of interest. For example, the analysis unit prioritizes analyzing words and phrases related to the project the user is currently working on. For example, the analysis unit filters and analyzes information related to the project the user is currently working on. The analysis unit can also filter and analyze related information based on the user's areas of interest. For example, if the user is interested in a particular topic, the analysis unit prioritizes analyzing information related to that topic. This enables more relevant analysis by filtering based on the user's current project or areas of interest. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input the user's current project or areas of interest into the generation AI and have the generation AI perform the filtering.

[0071] The analysis unit can select the optimal analysis means depending on the user's input method. For example, if the user uses voice input, the analysis unit performs analysis using voice recognition technology. For example, the analysis unit converts the content input by voice into text data using voice recognition technology and performs analysis based on the text data. Furthermore, if the user uses text input, the analysis unit can also perform analysis using text analysis technology. For example, the analysis unit analyzes text data input by the user using a keyboard. Furthermore, if the user uses image input, the analysis unit can also perform analysis using image recognition technology. For example, the analysis unit analyzes the content input by the user using image recognition technology and performs analysis based on the analysis results. This enables more appropriate analysis by selecting the optimal analysis means depending on the user's input method. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the user's input method into the generation AI and have the generation AI select the optimal analysis means.

[0072] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user emotions. For example, the analysis unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expression. The analysis unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the analysis unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations. This allows the user's emotions to be estimated and the analysis priority to be determined based on the estimated user emotions, enabling more appropriate analysis. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input user emotion data into the generation AI and have the generation AI determine the priority of analysis.

[0073] The analysis unit can prioritize analysis of highly relevant information based on the user's geographical location information. For example, when the user is in a specific region, the analysis unit prioritizes analysis of information related to that region. For example, when the user is in a specific city, the analysis unit prioritizes analysis of information related to that city. Furthermore, when the user is traveling, the analysis unit can also prioritize analysis of information related to the travel destination. For example, the analysis unit prioritizes analysis of information related to the travel destination based on content input by the user at the travel destination. This allows for prioritized analysis of highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the user's geographical location information to the generation AI and cause the generation AI to analyze highly relevant information.

[0074] The analysis unit can analyze the user's social media activities and analyze related information. The analysis unit performs analysis based on, for example, information shared by the user on social media. For example, the analysis unit analyzes content posted by the user on social media and analyzes information related to that content. The analysis unit can also analyze related information by referring to the activities of the user's friends on social media. For example, the analysis unit performs analysis based on information shared by the user's friends on social media. In this way, related information can be analyzed by analyzing the user's social media activities. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the user's social media activities into the generation AI and cause the generation AI to analyze the related information.

[0075] The analysis unit can customize the analysis method by reflecting the user's past feedback. The analysis unit, for example, adjusts the analysis method based on feedback provided by the user in the past. For example, the analysis unit stores feedback previously selected by the user in a database and adjusts the analysis method based on that data. The analysis unit can also preferentially use a specific analysis method based on the user's past feedback. For example, the analysis unit selects a specific analysis algorithm based on the user's past feedback. The analysis unit can also customize the analysis algorithm by reflecting the user's feedback. For example, the analysis unit adjusts parameters of the analysis algorithm based on the user's feedback. In this way, the analysis method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the analysis unit may be performed using, or without, a generation AI. For example, the analysis unit can input the user's past feedback into the generation AI and have the generation AI customize the analysis method.

[0076] The prediction unit can estimate the user's emotion and adjust the expression method of the prediction based on the estimated user's emotion. For example, the prediction unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the prediction unit calculates an emotion score based on changes in facial expression. The prediction unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the prediction unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the prediction unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the prediction unit calculates an emotion score based on heart rate fluctuations. This allows the user's emotion to be estimated and the expression method of the prediction to be adjusted based on the estimated user's emotion, enabling more accurate prediction. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the prediction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the prediction unit may input user emotion data into the generation AI and cause the generation AI to adjust the way the prediction is expressed.

[0077] The prediction unit can adjust the level of detail of the prediction based on the importance of the input content. The prediction unit, for example, evaluates the importance of the input content and adjusts the level of detail of the prediction based on the evaluation. For example, the prediction unit presents a detailed prediction if the content is important. The prediction unit can also present a concise prediction if the content is general. Furthermore, if a user inputs a specific important keyword, the prediction unit can present a detailed prediction related to the keyword. For example, the prediction unit evaluates the frequency of appearance of the keyword input by the user and the importance of the context, and adjusts the level of detail of the prediction based on the evaluation. This enables more accurate predictions by adjusting the level of detail of the prediction based on the importance of the input content. Some or all of the above-mentioned processing in the prediction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the prediction unit can input the importance of the input content to the generation AI and have the generation AI adjust the level of detail of the prediction.

[0078] The prediction unit can apply different prediction algorithms depending on the category of the input content. For example, the prediction unit classifies the category of the input content and applies different prediction algorithms depending on the category. For example, the prediction unit applies a formal prediction algorithm to a business document. The prediction unit can also apply a casual prediction algorithm to a casual message. Furthermore, the prediction unit can apply a prediction algorithm including technical terms to a technical document. For example, the prediction unit selects an appropriate prediction algorithm based on the category of the input content and applies the selected algorithm. This enables more accurate prediction by applying different prediction algorithms depending on the category of the input content. Some or all of the above-described processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the category of the input content to the generation AI and have the generation AI select and apply a prediction algorithm.

[0079] The prediction unit can improve prediction accuracy by referring to the user's past prediction results. The prediction unit, for example, improves the accuracy of the next prediction based on prediction results selected by the user in the past. For example, the prediction unit stores prediction results selected by the user in a database and improves prediction accuracy based on that data. The prediction unit can also extract specific patterns from the user's past prediction results and make predictions based on those patterns. For example, the prediction unit prioritizes predicting phrases used by the user in the past. This improves prediction accuracy by referring to the user's past prediction results. Some or all of the above-described processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the user's past prediction results into the generation AI and cause the generation AI to improve prediction accuracy.

[0080] The prediction unit can estimate the user's emotion and adjust the length of the prediction based on the estimated user emotion. For example, the prediction unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the prediction unit calculates an emotion score based on changes in facial expression. The prediction unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the prediction unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the prediction unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the prediction unit calculates an emotion score based on heart rate fluctuations. This allows the user's emotion to be estimated and the length of the prediction to be adjusted based on the estimated user emotion, enabling more accurate prediction. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the prediction unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the prediction unit may input user emotion data to the generation AI and cause the generation AI to adjust the length of the prediction.

[0081] The prediction unit can determine the priority of predictions based on the submission time of the input content. The prediction unit, for example, evaluates the submission time of the input content and determines the priority of predictions based on the evaluation. For example, the prediction unit prioritizes important predictions when the deadline is approaching. The prediction unit can also present general predictions when the submission time is far away. Furthermore, if a user sets a specific submission time, the prediction unit can determine the priority of predictions based on that time. For example, the prediction unit determines the priority of predictions based on the submission deadline set by the user. This enables more accurate predictions by determining the priority of predictions based on the submission time of the input content. Some or all of the above-mentioned processing in the prediction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the prediction unit can input the submission time of the input content to the generation AI and have the generation AI determine the priority of predictions.

[0082] The prediction unit can adjust the order of predictions based on the relevance of the input content. The prediction unit, for example, evaluates the relevance of the input content and adjusts the order of predictions based on the evaluation. For example, the prediction unit prioritizes presenting predictions related to important keywords. The prediction unit can also postpone predictions related to general keywords. Furthermore, if a user sets a specific relevance, the prediction unit can adjust the order of predictions based on the relevance. For example, the prediction unit adjusts the order of predictions based on the relevance criteria set by the user. This enables more appropriate predictions by adjusting the order of predictions based on the relevance of the input content. Some or all of the above-described processing in the prediction unit may be performed using, or without, a generation AI. For example, the prediction unit can input the relevance of the input content to the generation AI and have the generation AI adjust the order of predictions.

[0083] The prediction unit can adjust the use of technical terms in the prediction according to the user's level of expertise. The prediction unit, for example, evaluates the user's level of expertise and adjusts the use of technical terms in the prediction based on the evaluation. For example, if the user is an expert, the prediction unit presents a prediction that uses a lot of technical terms. Also, if the user is a beginner, the prediction unit can present a prediction that uses simple language. Furthermore, the prediction unit can estimate the user's level of expertise from the user's past input history and present a prediction accordingly. For example, the prediction unit evaluates the user's level of expertise based on the user's past input content and adjusts the use of technical terms in the prediction based on the evaluation. This enables more appropriate predictions by adjusting the use of technical terms in the prediction according to the user's level of expertise. Some or all of the above-described processing in the prediction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the prediction unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms in the prediction.

[0084] The feedback unit can estimate the user's emotion and adjust the feedback method based on the estimated user's emotion. For example, the feedback unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expression. The feedback unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the feedback unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the feedback unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on heart rate fluctuations. This allows the user's emotion to be estimated and the feedback method to be adjusted based on the estimated user's emotion, enabling more appropriate feedback. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the feedback unit may input user emotion data into the generation AI and cause the generation AI to adjust the feedback method.

[0085] The feedback unit can select the optimal feedback method by analyzing the user's past selection history. The feedback unit, for example, selects the optimal method based on feedback methods previously selected by the user. For example, the feedback unit stores feedback methods previously selected by the user in a database and selects the optimal method based on that data. The feedback unit can also extract a specific pattern from the user's past selection history and provide feedback based on that pattern. For example, the feedback unit prioritizes providing feedback methods previously used by the user. This allows the optimal feedback method to be selected by analyzing the user's past selection history. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's past selection history into the generation AI and have the generation AI select the optimal feedback method.

[0086] The feedback unit can customize the feedback means based on the user's current situation. For example, when the user is busy, the feedback unit provides concise feedback. For example, when the user is busy, the feedback unit provides short and to-the-point feedback. The feedback unit can also provide detailed feedback when the user is relaxed. For example, when the user is relaxed, the feedback unit provides feedback including detailed explanations and advice. Furthermore, when the user is in a specific situation, the feedback unit can provide feedback appropriate to the situation. For example, when the user is working on a specific project, the feedback unit provides feedback related to the project. This enables more appropriate feedback by customizing the feedback means based on the user's current situation. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's current situation to the generation AI and cause the generation AI to customize the feedback means.

[0087] The feedback unit can improve the feedback method by reflecting the user's feedback. The feedback unit, for example, adjusts the feedback method based on the feedback provided by the user. For example, the feedback unit stores the feedback provided by the user in a database and adjusts the feedback method based on the data. The feedback unit can also extract specific improvements from the user's feedback and provide feedback based on the improvements. For example, the feedback unit improves the feedback method based on problems pointed out by the user. Furthermore, the feedback unit can learn feedback using a generation AI and improve the feedback method. For example, the feedback unit can input the user's feedback data into the generation AI and have the generation AI execute the learning results. In this way, the feedback method can be improved by reflecting the user's feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the feedback unit can input the user's feedback data into the generation AI and have the generation AI execute improvements to the feedback method.

[0088] The feedback unit can estimate the user's emotions and determine the priority of feedback based on the estimated user emotions. For example, the feedback unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the feedback unit calculates an emotion score based on changes in facial expression. The feedback unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the feedback unit analyzes the tone and speed of the voice and calculates the emotion score. Furthermore, the feedback unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the feedback unit calculates the emotion score based on heart rate fluctuations. This enables more appropriate feedback by estimating the user's emotions and determining the priority of feedback based on the estimated user emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the feedback unit may input user emotion data into the generation AI and have the generation AI determine the priority of feedback.

[0089] The feedback unit can select the optimal feedback method by taking into account the user's geographical location information. For example, if the user is in a specific area, the feedback unit feeds back information related to that area. For example, if the user is in a specific city, the feedback unit feeds back information related to that city. Furthermore, if the user is traveling, the feedback unit can also feed back information related to the travel destination. For example, the feedback unit provides information the user needs at the travel destination. In this way, the optimal feedback method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's geographical location information into the generation AI and cause the generation AI to select the optimal feedback method.

[0090] The feedback unit can analyze the user's social media activity and suggest a means of feedback. The feedback unit, for example, provides feedback based on information shared by the user on social media. For example, the feedback unit analyzes content posted by the user on social media and provides feedback on information related to that content. The feedback unit can also provide feedback on related information by referring to the activities of the user's friends on social media. For example, the feedback unit provides feedback based on information shared by the user's friends on social media. In this way, by analyzing the user's social media activity, a means of feedback can be suggested. Some or all of the above-described processing in the feedback unit may be performed using, or without, a generation AI. For example, the feedback unit can input the user's social media activity into the generation AI and cause the generation AI to suggest a means of feedback.

[0091] The feedback unit can customize the feedback method by reflecting the user's past feedback. The feedback unit, for example, adjusts the feedback method based on feedback provided by the user in the past. For example, the feedback unit stores feedback provided by the user in a database and adjusts the feedback method based on the data. The feedback unit can also extract specific improvements from the user's past feedback and provide feedback based on the improvements. For example, the feedback unit improves the feedback method based on problems pointed out by the user. Furthermore, the feedback unit can learn feedback using a generation AI and customize the feedback method. For example, the feedback unit can input the user's feedback data into the generation AI and have the generation AI execute the learning results. In this way, the feedback method can be customized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the feedback unit can input the user's past feedback into the generation AI and have the generation AI execute the customization of the feedback method. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, prediction unit, and feedback unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 or the processor 28 of the data processing device 12 and analyzes the user's input. The prediction unit is realized, for example, by the processor 46 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and makes a prediction based on the analysis result. The feedback unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and receives the user's selection. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, prediction unit, and feedback unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 or the processor 28 of the data processing device 12, and analyzes the user's input. The prediction unit is realized, for example, by the processor 46 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and makes a prediction based on the analysis result. The feedback unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and receives the user's selection. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, prediction unit, and feedback unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 or the processor 28 of the data processing device 12, and analyzes the user's input. The prediction unit is realized, for example, by the processor 46 of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and makes a prediction based on the analysis result. The feedback unit is realized, for example, by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and receives the user's selection. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, prediction unit, and feedback unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 or the processor 28 of the data processing device 12, and analyzes the user's input. The prediction unit is realized, for example, by the processor 46 of the robot 414 or the specific processing unit 290 of the data processing device 12, and makes a prediction based on the analysis result. The feedback unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and receives the user's selection.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The analysis unit can take the user's current activity status into consideration when analyzing the user's input content. For example, if the user is at work, the analysis unit can prioritize analyzing business-related words and phrases. If the user is on vacation, the analysis unit can prioritize analyzing travel- and leisure-related words and phrases. Furthermore, if the user is participating in a specific event, the analysis unit can prioritize analyzing information related to that event. This allows for more appropriate analysis by performing analysis based on the user's current activity status.

[0094] The analysis unit can take into account the user's past emotional data when analyzing the user's input content. For example, if the user has expressed positive emotions toward content previously entered, the analysis unit can prioritize information related to that content. Also, if the user has expressed negative emotions toward content previously entered, the analysis unit can avoid that content. Furthermore, the analysis method can be adjusted taking into account fluctuations in the user's emotions. This allows for more appropriate analysis by taking into account the user's past emotional data.

[0095] The prediction unit can take the user's current mood into account when predicting the user's input content. For example, if the user is relaxed, a casual prediction can be presented. If the user is nervous, a formal prediction can be presented. Furthermore, the prediction unit can adjust the tone and style of the prediction depending on the user's mood. This allows for more appropriate predictions by making predictions based on the user's current mood.

[0096] When receiving a user's selection, the feedback unit can estimate the reason for the user's selection. For example, the feedback unit can analyze the reason why the user selected a particular predicted candidate and provide feedback based on that reason. It can also estimate the reason for a predicted candidate that the user did not select and reflect that in the next prediction. Furthermore, it can analyze the user's selection pattern and provide feedback based on that pattern. This allows for more appropriate feedback by taking into account the reason for the user's selection.

[0097] The feedback unit can take the frequency of the user's selection into consideration when receiving the user's selection. For example, the feedback unit can preferentially present predicted candidates that the user frequently selects. Also, the feedback unit can avoid presenting predicted candidates that the user rarely selects. Furthermore, the feedback unit can adjust the presentation order of the predicted candidates based on the frequency of the user's selection. This allows for more appropriate feedback by taking the frequency of the user's selection into consideration.

[0098] The analysis unit can take into account the user's past input patterns when analyzing the user's input content. For example, it analyzes the patterns of content the user has input in the past and performs analysis based on those patterns. It can also adjust the analysis method based on the user's input pattern. Furthermore, it can also adjust the analysis method taking into account fluctuations in the user's input pattern. This allows for more appropriate analysis by taking into account the user's past input patterns.

[0099] The prediction unit can take the user's current activity status into consideration when predicting the user's input content. For example, if the user is at work, business-related predictions can be presented with priority. If the user is on vacation, travel- and leisure-related predictions can be presented with priority. Furthermore, if the user is participating in a specific event, predictions related to that event can be presented with priority. This allows for more accurate predictions by making predictions based on the user's current activity status.

[0100] The prediction unit can take into account the user's past emotional data when predicting the user's input content. For example, if the user has expressed positive emotions toward content previously input, predictions related to that content can be presented preferentially. Also, if the user has expressed negative emotions toward content previously input, predictions can be made to avoid that content. Furthermore, the prediction method can be adjusted taking into account fluctuations in the user's emotions. In this way, by taking into account the user's past emotional data, more appropriate predictions can be made.

[0101] When receiving a user's selection, the feedback unit can estimate the reason for the user's selection. For example, the feedback unit can analyze the reason why the user selected a particular predicted candidate and provide feedback based on that reason. It can also estimate the reason for a predicted candidate that the user did not select and reflect that in the next prediction. Furthermore, it can analyze the user's selection pattern and provide feedback based on that pattern. This allows for more appropriate feedback by taking into account the reason for the user's selection.

[0102] The feedback unit can take the frequency of the user's selection into consideration when receiving the user's selection. For example, the feedback unit can preferentially present predicted candidates that the user frequently selects. Also, the feedback unit can avoid presenting predicted candidates that the user rarely selects. Furthermore, the feedback unit can adjust the presentation order of the predicted candidates based on the frequency of the user's selection. This allows for more appropriate feedback by taking the frequency of the user's selection into consideration.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The analysis unit analyzes the user's input. The analysis unit can analyze the user's input using text analysis technology, data mining technology, or generation AI. For example, the user's input is input to the generation AI, which then outputs the analysis results. Step 2: The prediction unit makes a prediction based on the content analyzed by the analysis unit. The prediction unit can make a prediction using a statistical model, a machine learning algorithm, or a generation AI. For example, the analysis results are input to the generation AI, which then outputs a prediction result. Step 3: When the user selects a prediction candidate presented by the prediction unit, the feedback unit receives the selection. The feedback unit can receive the user's selection by clicking or tapping, voice input, or using the generation AI. For example, the feedback unit inputs the user's selection into the generation AI and outputs a feedback result.

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0112] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

[0115] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0116] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0119] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0120] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

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

[0128] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0132] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0136] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0137] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0149] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0152] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

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

[0154] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0156] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0158] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0159] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0160] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0161] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0162] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0163] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0164] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0165] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0166] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0167] 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.

[0168] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0169] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0170] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0171] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0172] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0173] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0174] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0175] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0176] [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the content of a user's input; a prediction unit that makes a prediction based on the content analyzed by the analysis unit; a feedback unit that receives a user's selection of a predicted candidate presented by the prediction unit. A system characterized by:

2. The analysis unit Analyze based on user input history and context 2. The system of claim 1.

3. The prediction unit Make predictions based on user input history and context 2. The system of claim 1.

4. The feedback unit Accept the user's selection and feed that selection back into the system 2. The system of claim 1.

5. The feedback unit Learn from feedback and improve prediction accuracy 2. The system of claim 1.

6. The analysis unit Estimate the user's emotions and adjust the analysis method based on the estimated user emotions.

2. The system of claim 1.

7. The analysis unit Analyze the user's past input history and select an analysis algorithm 2. The system of claim 1.

8. The analysis unit Filter based on your current projects and interests 2. The system of claim 1.

Images