System

Abstract

An object of a system according to an embodiment is to automatically correct an erroneous input at the time of keyboard input.SOLUTION: A system according to an embodiment includes a generation AI, an input error determination unit, and a correction unit. The generation AI analyzes input character strings before and after it. The erroneous input determination unit analyzes input character strings before and after the generated AI to determine an erroneous input. The correction unit corrects the incorrect input determined by the incorrect input determination unit to an appropriate character.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 techniques have not adequately corrected input errors automatically during keyboard input, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically correct erroneous inputs made on a keyboard. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation AI, an erroneous input determination unit, and a correction unit. The generation AI analyzes the preceding and following input character strings. The erroneous input determination unit analyzes the preceding and following input character strings and determines whether the input is erroneous. The correction unit corrects the erroneous input determined by the erroneous input determination unit to the correct character. [Effects of the Invention]

[0007] The system according to the embodiment can automatically correct erroneous inputs made at the time of keyboard input. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The input error correction system according to an embodiment of the present invention automatically corrects input errors when a user inputs a long string of characters. This system incorporates a generative AI to analyze the input string before and after the input, identify input errors, and correct them to the appropriate characters. This allows the input error correction system to smoothly input characters without the user feeling frustrated by input errors.

[0029] An input error correction system according to an embodiment includes a generation AI, an input error determination unit, and a correction unit. The generation AI analyzes surrounding input strings. For example, the generation AI analyzes the input string using a text generation AI (e.g., LLM). The generation AI can also analyze the input string using a multimodal generation AI. The generation AI can also analyze the surrounding input strings using context analysis technology. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI analyzes the context of the input string using context analysis technology and determines whether the input is incorrect. The input error determination unit determines whether the input is incorrect based on the surrounding input strings analyzed by the generation AI. For example, the input error determination unit detects spelling errors. The input error determination unit can also detect grammatical errors. The input error determination unit can also detect words that do not fit the context. For example, the input error determination unit detects spelling errors based on a dictionary. Grammatical errors are detected using grammatical analysis technology. Words that do not fit the context are detected using context analysis technology. The correction unit corrects the incorrect input determined by the incorrect input determination unit to the correct character. For example, the correction unit corrects to the correct character based on a dictionary. The correction unit can also correct to the correct character based on the context. The correction unit can also correct to the correct character based on the user's input pattern. For example, the correction unit corrects spelling mistakes based on a dictionary. Context-based correction is performed using context analysis technology. User input pattern-based correction is performed based on the user's input pattern learned by the generation AI. This allows the incorrect input correction system according to the embodiment to smoothly input characters without the user feeling frustrated by incorrect input. For example, if a user mistakenly inputs "konichiwa" (hello) while trying to input "hello," the generation AI detects the incorrect input "nichi" from the surrounding characters and corrects it to "ni" (nichi). Similarly, if a user mistakenly inputs "applr" while trying to input "apple," the generation AI determines that the "r" is an incorrect input and corrects it to "e."Also, if a user frequently mistypes "the" as "teh," the generation AI will learn this pattern and automatically correct "teh" to "the" the next time it is entered.

[0030] The generation AI can learn users' input patterns and identify frequently occurring incorrect input patterns to improve correction accuracy. For example, the generation AI can learn users' input patterns and identify frequently occurring incorrect input patterns. For example, the generation AI can learn the pattern in which users frequently erroneously input "the" as "teh" and automatically correct "teh" to "the" the next time they input text. The generation AI can also learn the pattern in which users frequently erroneously input "apple" as "applr" and automatically correct "applr" to "apple" the next time they input text. The generation AI can also learn the pattern in which users frequently erroneously input "hello" as "konichiwa" and automatically correct "konichiwa" to "konichiwa" the next time they input text. This allows the generation AI to learn users' input patterns and improve correction accuracy.

[0031] The generation AI can learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct typographical errors. The generation AI can learn the user's typing speed and rhythm and detect abnormal typing patterns. For example, the generation AI can correct typographical errors if it detects a rhythm that differs from the user's normal typing speed. The generation AI can also correct typographical errors if the user's typing speed changes suddenly. The generation AI can also correct typographical errors if the user presses specific keys repeatedly. For example, the generation AI can detect a rhythm that differs from the user's normal typing rhythm and correct typographical errors based on that rhythm. The generation AI can also correct typographical errors if the user presses specific keys repeatedly. This allows the generation AI to learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct typographical errors.

[0032] The generation AI can simultaneously analyze a user's voice input and text input and correct any input errors. For example, the generation AI simultaneously analyzes a user's voice input and text input. For example, the generation AI checks whether the voice input and text input match and corrects any input errors. The generation AI can also detect mismatches between voice input and text input and correct any input errors. The generation AI can also detect timing discrepancies between voice input and text input and correct any input errors. For example, if a user speaks "hello" and types "konichiwa," the generation AI detects a discrepancy between the voice input and text input and corrects it to "ni." Similarly, if a user speaks "apple" and types "applr," the generation AI detects a discrepancy between the voice input and text input and corrects it to "e." Similarly, if a user incorrectly types "the" as "teh," the generation AI detects a timing discrepancy between the voice input and text input and corrects it to "the." This allows the generation AI to simultaneously analyze a user's voice input and text input and correct any input errors.

[0033] The generation AI can track a user's hand movements with a camera and determine erroneous inputs based on visual information. The generation AI can, for example, track a user's hand movements with a camera and determine erroneous inputs based on visual information. For example, the generation AI can analyze hand movements and key press positions to detect erroneous inputs. The generation AI can also analyze hand movements and key press speed to detect erroneous inputs. The generation AI can also analyze hand movements and key press timing to detect erroneous inputs. For example, the generation AI can capture a user's hand movements with a camera and analyze the hand movements and key press positions using image analysis technology. The generation AI can also capture a user's hand movements with a camera and analyze the hand movements and key press speed using image analysis technology. The generation AI can also capture a user's hand movements with a camera and analyze the hand movements and key press timing using image analysis technology. This makes it possible to track a user's hand movements with a camera and determine erroneous inputs based on visual information.

[0034] Generative AI can perform context analysis to understand the meaning of the entire sentence and correct typos. Generative AI can, for example, perform context analysis to understand the meaning of the entire sentence and correct typos. For example, generative AI can analyze the context of a sentence and correct it to the appropriate word. Generative AI can also analyze the logical structure of a sentence and correct typos. Generative AI can also analyze the topic of a sentence and correct typos. For example, generative AI can analyze the context of a sentence and correct it to the appropriate word based on the context. Generative AI can also analyze the logical structure of a sentence and correct typos to maintain logical consistency. Generative AI can also analyze the topic of a sentence and correct it to a word related to the topic. This allows for context analysis, understanding the meaning of the entire sentence, and correcting typos.

[0035] The generative AI can translate user input in real time and correct input errors in different languages. The generative AI can, for example, translate user input in real time and correct input errors in different languages. For example, the generative AI can correct input errors when translating from English to Japanese. The generative AI can also correct input errors when translating from Japanese to Chinese. The generative AI can also correct input errors when translating from French to German. For example, the generative AI can correct spelling errors when translating from English to Japanese. The generative AI can also correct grammatical errors when translating from Japanese to Chinese. The generative AI can also correct out-of-context words when translating from French to German. This allows the generative AI to translate user input in real time and correct input errors in different languages.

[0036] The generation AI can automatically summarize the user's input and correct input errors in the summary. The generation AI can, for example, automatically summarize the user's input and correct input errors in the summary. For example, the generation AI can summarize a long sentence and correct input errors in the summary. The generation AI can also summarize multiple sentences and correct input errors in the summary. The generation AI can also summarize an entire paragraph and correct input errors in the summary. For example, the generation AI can summarize a long sentence and correct spelling errors in the summary. The generation AI can also summarize multiple sentences and correct grammatical errors in the summary. The generation AI can also summarize an entire paragraph and correct words that do not fit the context of the summary. This makes it possible to automatically summarize the user's input and correct input errors in the summary.

[0037] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0038] The typo correction system translates user input in real time and can correct typos in different languages. For example, it can correct typos when translating from English to Japanese. It can also correct typos when translating from Japanese to Chinese. It can also correct typos when translating from French to German. Specifically, it corrects spelling errors when translating from English to Japanese. It can also correct grammatical errors when translating from Japanese to Chinese. It can also correct out-of-context words when translating from French to German. This allows the system to translate user input in real time and correct typos in different languages.

[0039] The typo correction system can automatically summarize the user's input and correct typo errors in the summary. For example, it can summarize a long sentence and correct typo errors in the summary. It can also summarize multiple sentences and correct typo errors in the summary. It can also summarize an entire paragraph and correct typo errors in the summary. Specifically, it can summarize a long sentence and correct spelling errors in the summary. It can also summarize multiple sentences and correct grammatical errors in the summary. It can also summarize an entire paragraph and correct words that do not fit the context of the summary. In this way, it is possible to automatically summarize the user's input and correct typo errors in the summary.

[0040] The input error correction system tracks the user's hand movements with a camera and can identify input errors based on visual information. For example, it can detect input errors by analyzing hand movements and key press positions. It can also detect input errors by analyzing hand movements and key press speed. It can also detect input errors by analyzing hand movements and key press timing. Specifically, it captures the user's hand movements with a camera and analyzes the hand movements and key press positions using image analysis technology. It also captures the user's hand movements with a camera and analyzes the hand movements and key press speed using image analysis technology. It also captures the user's hand movements with a camera and analyzes the hand movements and key press timing using image analysis technology. In this way, it is possible to track the user's hand movements with a camera and identify input errors based on visual information.

[0041] The typo correction system can simultaneously analyze a user's voice input and text input and correct typos. For example, it can check whether the voice input matches the text input and correct typos. It can also detect mismatches between voice input and text input and correct typos. It can also detect timing discrepancies between voice input and text input and correct typos. Specifically, if a user speaks "hello" and types "konichiwa," the system detects a discrepancy between the voice input and text input and corrects it to "ni." If a user speaks "apple" and types "applr," the system detects a discrepancy between the voice input and text input and corrects it to "e." If a user mistypes "the" as "teh," the system detects a timing discrepancy between the voice input and text input and corrects it to "the." This allows the system to simultaneously analyze a user's voice input and text input and correct typos.

[0042] The input error correction system can learn a user's input patterns and identify frequently occurring input errors to improve correction accuracy. For example, the system can learn the user's frequent input error of "the" as "teh" and automatically correct "teh" to "the" from the next time onward. It can also learn the user's frequent input error of "apple" as "applr" and automatically correct "applr" to "apple" from the next time onward. It can also learn the user's frequent input error of "hello" as "konichiwa" and automatically correct "konichiwa" to "konichiwa" from the next time onward. This allows the system to learn a user's input patterns and improve correction accuracy.

[0043] The input error correction system uses generative AI to learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct input errors. For example, if it detects a rhythm that differs from the normal typing speed, it corrects input errors. It can also correct input errors if the user's typing speed changes suddenly. It can also correct input errors if the user presses specific keys repeatedly. Specifically, it detects a rhythm that differs from normal typing and corrects input errors based on that rhythm. It can also correct input errors if the user's typing speed changes suddenly. It can also correct input errors based on the continuous input of specific keys. This allows the system to learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct input errors.

[0044] The processing flow of the first embodiment will be briefly explained below.

[0045] Step 1: The generation AI analyzes the surrounding input string. For example, the generation AI analyzes the input string using a text generation AI (e.g., LLM). The generation AI can also analyze the input string using a multimodal generation AI. The generation AI uses context analysis technology to analyze the surrounding input string and determine whether it is an incorrect input. Step 2: The input error detection unit detects input errors based on the preceding and following input strings analyzed by the generation AI. For example, the input error detection unit detects spelling errors, grammatical errors, and out-of-context words. It detects spelling errors based on a dictionary, grammatical analysis technology detects grammatical errors, and contextual words using context analysis technology. Step 3: The correction unit corrects the incorrect input identified by the incorrect input determination unit to the correct characters. For example, the correction unit corrects spelling mistakes based on a dictionary, performs context-based correction using context analysis technology, and performs correction based on the user's input patterns learned by the generation AI.

[0046] (Example 2) The input error correction system according to an embodiment of the present invention automatically corrects input errors when a user inputs a long string of characters. This system incorporates a generative AI to analyze the input string before and after the input, identify input errors, and correct them to the appropriate characters. This allows the input error correction system to smoothly input characters without the user feeling frustrated by input errors.

[0047] An input error correction system according to an embodiment includes a generation AI, an input error determination unit, and a correction unit. The generation AI analyzes surrounding input strings. For example, the generation AI analyzes the input string using a text generation AI (e.g., LLM). The generation AI can also analyze the input string using a multimodal generation AI. The generation AI can also analyze the surrounding input strings using context analysis technology. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and audio. The generation AI analyzes the context of the input string using context analysis technology and determines whether the input is incorrect. The input error determination unit determines whether the input is incorrect based on the surrounding input strings analyzed by the generation AI. For example, the input error determination unit detects spelling errors. The input error determination unit can also detect grammatical errors. The input error determination unit can also detect words that do not fit the context. For example, the input error determination unit detects spelling errors based on a dictionary. Grammatical errors are detected using grammatical analysis technology. Words that do not fit the context are detected using context analysis technology. The correction unit corrects the incorrect input determined by the incorrect input determination unit to the correct character. For example, the correction unit corrects to the correct character based on a dictionary. The correction unit can also correct to the correct character based on the context. The correction unit can also correct to the correct character based on the user's input pattern. For example, the correction unit corrects spelling mistakes based on a dictionary. Context-based correction is performed using context analysis technology. User input pattern-based correction is performed based on the user's input pattern learned by the generation AI. This allows the incorrect input correction system according to the embodiment to smoothly input characters without the user feeling frustrated by incorrect input. For example, if a user mistakenly inputs "konichiwa" (hello) while trying to input "hello," the generation AI detects the incorrect input "nichi" from the surrounding characters and corrects it to "ni" (nichi). Similarly, if a user mistakenly inputs "applr" while trying to input "apple," the generation AI determines that the "r" is an incorrect input and corrects it to "e."Also, if a user frequently mistypes "the" as "teh," the generation AI will learn this pattern and automatically correct "teh" to "the" the next time it is entered.

[0048] The generation AI can learn users' input patterns and identify frequently occurring incorrect input patterns to improve correction accuracy. For example, the generation AI can learn users' input patterns and identify frequently occurring incorrect input patterns. For example, the generation AI can learn the pattern in which users frequently erroneously input "the" as "teh" and automatically correct "teh" to "the" the next time they input text. The generation AI can also learn the pattern in which users frequently erroneously input "apple" as "applr" and automatically correct "applr" to "apple" the next time they input text. The generation AI can also learn the pattern in which users frequently erroneously input "hello" as "konichiwa" and automatically correct "konichiwa" to "konichiwa" the next time they input text. This allows the generation AI to learn users' input patterns and improve correction accuracy.

[0049] The generation AI can learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct typographical errors. The generation AI can learn the user's typing speed and rhythm and detect abnormal typing patterns. For example, the generation AI can correct typographical errors if it detects a rhythm that differs from the user's normal typing speed. The generation AI can also correct typographical errors if the user's typing speed changes suddenly. The generation AI can also correct typographical errors if the user presses specific keys repeatedly. For example, the generation AI can detect a rhythm that differs from the user's normal typing rhythm and correct typographical errors based on that rhythm. The generation AI can also correct typographical errors if the user presses specific keys repeatedly. This allows the generation AI to learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct typographical errors.

[0050] The generation AI can use its emotion estimation function to analyze whether input errors tend to increase when the user is feeling stressed and make corrections to reduce stress. For example, the generation AI can use its emotion estimation function to analyze whether input errors tend to increase when the user is feeling stressed. For example, the generation AI can analyze the user's facial expressions and voice to detect their stress level. The generation AI can also analyze the user's heart rate and electrodermal activity to detect their stress level. The generation AI can also analyze changes in the user's input speed and rhythm to detect their stress level. For example, the generation AI can capture the user's facial expressions with a camera and detect their stress level using facial expression recognition technology. The generation AI can also record the user's voice and detect their stress level using voice analysis technology. The generation AI can also collect the user's heart rate and electrodermal activity with a sensor and detect their stress level using biometrics technology. The generation AI can also analyze changes in the user's input speed and rhythm to detect their stress level. This allows the generation AI to analyze whether input errors tend to increase when the user is feeling stressed and make corrections to reduce stress.

[0051] The generation AI can simultaneously analyze a user's voice input and text input and correct any input errors. For example, the generation AI simultaneously analyzes a user's voice input and text input. For example, the generation AI checks whether the voice input and text input match and corrects any input errors. The generation AI can also detect mismatches between voice input and text input and correct any input errors. The generation AI can also detect timing discrepancies between voice input and text input and correct any input errors. For example, if a user speaks "hello" and types "konichiwa," the generation AI detects a discrepancy between the voice input and text input and corrects it to "ni." Similarly, if a user speaks "apple" and types "applr," the generation AI detects a discrepancy between the voice input and text input and corrects it to "e." Similarly, if a user incorrectly types "the" as "teh," the generation AI detects a timing discrepancy between the voice input and text input and corrects it to "the." This allows the generation AI to simultaneously analyze a user's voice input and text input and correct any input errors.

[0052] The generation AI can track a user's hand movements with a camera and determine erroneous inputs based on visual information. The generation AI can, for example, track a user's hand movements with a camera and determine erroneous inputs based on visual information. For example, the generation AI can analyze hand movements and key press positions to detect erroneous inputs. The generation AI can also analyze hand movements and key press speed to detect erroneous inputs. The generation AI can also analyze hand movements and key press timing to detect erroneous inputs. For example, the generation AI can capture a user's hand movements with a camera and analyze the hand movements and key press positions using image analysis technology. The generation AI can also capture a user's hand movements with a camera and analyze the hand movements and key press speed using image analysis technology. The generation AI can also capture a user's hand movements with a camera and analyze the hand movements and key press timing using image analysis technology. This makes it possible to track a user's hand movements with a camera and determine erroneous inputs based on visual information.

[0053] The generation AI can use its emotion estimation function to provide feedback to promote a state of relaxation, taking advantage of the fact that input errors are fewer when the user is relaxed. For example, the generation AI can use its emotion estimation function to analyze the fact that input errors are fewer when the user is relaxed. For example, the generation AI can analyze the user's facial expressions and voice to detect a state of relaxation. The generation AI can also analyze the user's heart rate and electrodermal activity to detect a state of relaxation. The generation AI can also analyze changes in the user's input speed and rhythm to detect a state of relaxation. For example, the generation AI can capture the user's facial expressions with a camera and detect a state of relaxation using facial expression recognition technology. The generation AI can also record the user's voice and detect a state of relaxation using voice analysis technology. The generation AI can also collect the user's heart rate and electrodermal activity with a sensor and detect a state of relaxation using biometrics technology. The generation AI can also analyze changes in the user's input speed and rhythm to detect a state of relaxation. In this way, the generation AI can provide feedback to promote a state of relaxation, taking advantage of the fact that input errors are fewer when the user is relaxed.

[0054] Generative AI can perform context analysis to understand the meaning of the entire sentence and correct typos. Generative AI can, for example, perform context analysis to understand the meaning of the entire sentence and correct typos. For example, generative AI can analyze the context of a sentence and correct it to the appropriate word. Generative AI can also analyze the logical structure of a sentence and correct typos. Generative AI can also analyze the topic of a sentence and correct typos. For example, generative AI can analyze the context of a sentence and correct it to the appropriate word based on the context. Generative AI can also analyze the logical structure of a sentence and correct typos to maintain logical consistency. Generative AI can also analyze the topic of a sentence and correct it to a word related to the topic. This allows for context analysis, understanding the meaning of the entire sentence, and correcting typos.

[0055] The generation AI can use its emotion estimation function to analyze whether input errors tend to increase when the user is in a particular emotional state and make corrections according to that state. For example, the generation AI can use its emotion estimation function to analyze whether input errors tend to increase when the user is in a particular emotional state. For example, the generation AI can analyze the user's facial expressions and voice to detect a particular emotional state. The generation AI can also analyze the user's heart rate and electrodermal activity to detect a particular emotional state. The generation AI can also analyze changes in the user's typing speed and rhythm to detect a particular emotional state. For example, the generation AI can capture the user's facial expressions with a camera and detect a particular emotional state using facial expression recognition technology. The generation AI can also record the user's voice and detect a particular emotional state using voice analysis technology. The generation AI can also collect the user's heart rate and electrodermal activity with a sensor and detect a particular emotional state using biometrics technology. The generation AI can also analyze changes in the user's typing speed and rhythm to detect a particular emotional state. This allows the generation AI to analyze whether input errors tend to increase when the user is in a particular emotional state and make corrections according to that state.

[0056] The generative AI can translate user input in real time and correct input errors in different languages. The generative AI can, for example, translate user input in real time and correct input errors in different languages. For example, the generative AI can correct input errors when translating from English to Japanese. The generative AI can also correct input errors when translating from Japanese to Chinese. The generative AI can also correct input errors when translating from French to German. For example, the generative AI can correct spelling errors when translating from English to Japanese. The generative AI can also correct grammatical errors when translating from Japanese to Chinese. The generative AI can also correct out-of-context words when translating from French to German. This allows the generative AI to translate user input in real time and correct input errors in different languages.

[0057] The generation AI can automatically summarize the user's input and correct input errors in the summary. The generation AI can, for example, automatically summarize the user's input and correct input errors in the summary. For example, the generation AI can summarize a long sentence and correct input errors in the summary. The generation AI can also summarize multiple sentences and correct input errors in the summary. The generation AI can also summarize an entire paragraph and correct input errors in the summary. For example, the generation AI can summarize a long sentence and correct spelling errors in the summary. The generation AI can also summarize multiple sentences and correct grammatical errors in the summary. The generation AI can also summarize an entire paragraph and correct words that do not fit the context of the summary. This makes it possible to automatically summarize the user's input and correct input errors in the summary.

[0058] The generation AI can use its emotion estimation function to prioritize correction of words and phrases that evoke positive emotions in the user. For example, the generation AI can use its emotion estimation function to prioritize correction of words and phrases that evoke positive emotions in the user. For example, the generation AI can analyze the user's facial expressions and voice to detect positive emotions. The generation AI can also analyze the user's heart rate and electrodermal activity to detect positive emotions. The generation AI can also analyze changes in the user's typing speed and rhythm to detect positive emotions. For example, the generation AI can capture the user's facial expressions with a camera and detect positive emotions using facial expression recognition technology. The generation AI can also record the user's voice and detect positive emotions using voice analysis technology. The generation AI can also collect the user's heart rate and electrodermal activity with a sensor and detect positive emotions using biometrics technology. The generation AI can also analyze changes in the user's typing speed and rhythm to detect positive emotions. This allows the generation AI to prioritize correction of words and phrases that evoke positive emotions in the user.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The typo correction system translates user input in real time and can correct typos in different languages. For example, it can correct typos when translating from English to Japanese. It can also correct typos when translating from Japanese to Chinese. It can also correct typos when translating from French to German. Specifically, it corrects spelling errors when translating from English to Japanese. It can also correct grammatical errors when translating from Japanese to Chinese. It can also correct out-of-context words when translating from French to German. This allows the system to translate user input in real time and correct typos in different languages.

[0061] The typo correction system can automatically summarize the user's input and correct typo errors in the summary. For example, it can summarize a long sentence and correct typo errors in the summary. It can also summarize multiple sentences and correct typo errors in the summary. It can also summarize an entire paragraph and correct typo errors in the summary. Specifically, it can summarize a long sentence and correct spelling errors in the summary. It can also summarize multiple sentences and correct grammatical errors in the summary. It can also summarize an entire paragraph and correct words that do not fit the context of the summary. In this way, it is possible to automatically summarize the user's input and correct typo errors in the summary.

[0062] The input error correction system tracks the user's hand movements with a camera and can identify input errors based on visual information. For example, it can detect input errors by analyzing hand movements and key press positions. It can also detect input errors by analyzing hand movements and key press speed. It can also detect input errors by analyzing hand movements and key press timing. Specifically, it captures the user's hand movements with a camera and analyzes the hand movements and key press positions using image analysis technology. It also captures the user's hand movements with a camera and analyzes the hand movements and key press speed using image analysis technology. It also captures the user's hand movements with a camera and analyzes the hand movements and key press timing using image analysis technology. In this way, it is possible to track the user's hand movements with a camera and identify input errors based on visual information.

[0063] The typo correction system can simultaneously analyze a user's voice input and text input and correct typos. For example, it can check whether the voice input matches the text input and correct typos. It can also detect mismatches between voice input and text input and correct typos. It can also detect timing discrepancies between voice input and text input and correct typos. Specifically, if a user speaks "hello" and types "konichiwa," the system detects a discrepancy between the voice input and text input and corrects it to "ni." If a user speaks "apple" and types "applr," the system detects a discrepancy between the voice input and text input and corrects it to "e." If a user mistypes "the" as "teh," the system detects a timing discrepancy between the voice input and text input and corrects it to "the." This allows the system to simultaneously analyze a user's voice input and text input and correct typos.

[0064] The input error correction system can learn a user's input patterns and identify frequently occurring input errors to improve correction accuracy. For example, the system can learn the user's frequent input error of "the" as "teh" and automatically correct "teh" to "the" from the next time onward. It can also learn the user's frequent input error of "apple" as "applr" and automatically correct "applr" to "apple" from the next time onward. It can also learn the user's frequent input error of "hello" as "konichiwa" and automatically correct "konichiwa" to "konichiwa" from the next time onward. This allows the system to learn a user's input patterns and improve correction accuracy.

[0065] The input error correction system uses an emotion estimation function to analyze the tendency for input errors to increase when the user is feeling stressed and can make corrections to reduce stress. For example, the system can analyze the user's facial expressions and voice to detect the user's stress level. It can also analyze the user's heart rate and electrodermal activity to detect the user's stress level. It can also analyze changes in the user's input speed and rhythm to detect the user's stress level. Specifically, the system captures the user's facial expressions with a camera and detects the user's stress level using facial expression recognition technology. It can also record the user's voice and detect the user's stress level using voice analysis technology. It can also collect the user's heart rate and electrodermal activity with a sensor and detect the user's stress level using biometrics technology. It can also analyze changes in the user's input speed and rhythm to detect the user's stress level. This allows the system to analyze the tendency for input errors to increase when the user is feeling stressed and make corrections to reduce stress.

[0066] The input error correction system can use an emotion estimation function to provide feedback to promote a relaxed state, taking advantage of the fact that input errors are fewer when the user is relaxed. For example, the system can detect a state of relaxation by analyzing the user's facial expressions and voice. It can also detect a state of relaxation by analyzing the user's heart rate and electrodermal activity. It can also detect a state of relaxation by analyzing changes in the user's input speed and rhythm. Specifically, the system captures the user's facial expressions with a camera and detects a state of relaxation using facial expression recognition technology. It can also record the user's voice and detect a state of relaxation using voice analysis technology. It can also collect the user's heart rate and electrodermal activity with a sensor and detect a state of relaxation using biometrics technology. It can also analyze changes in the user's input speed and rhythm to detect a state of relaxation. This makes it possible to provide feedback to promote a state of relaxation, taking advantage of the fact that input errors are fewer when the user is relaxed.

[0067] The input error correction system uses an emotion estimation function to analyze the tendency for input errors to increase when a user is in a specific emotional state and can make corrections according to that state. For example, the system can analyze the user's facial expressions and voice to detect a specific emotional state. It can also analyze the user's heart rate and electrodermal activity to detect a specific emotional state. It can also analyze changes in the user's input speed and rhythm to detect a specific emotional state. Specifically, the system captures the user's facial expressions with a camera and detects a specific emotional state using facial expression recognition technology. It can also record the user's voice and detect a specific emotional state using voice analysis technology. It can also collect the user's heart rate and electrodermal activity with a sensor and detect a specific emotional state using biometric technology. It can also analyze changes in the user's input speed and rhythm to detect a specific emotional state. This allows the system to analyze the tendency for input errors to increase when a user is in a specific emotional state and make corrections according to that state.

[0068] The input error correction system can use an emotion estimation function to prioritize correction of words and phrases that the user associates with positive emotions. For example, the system can analyze the user's facial expressions and voice to detect positive emotions. It can also analyze the user's heart rate and electrodermal activity to detect positive emotions. It can also analyze changes in the user's typing speed and rhythm to detect positive emotions. Specifically, the system captures the user's facial expressions with a camera and detects positive emotions using facial expression recognition technology. It can also record the user's voice and detect positive emotions using voice analysis technology. It can also collect the user's heart rate and electrodermal activity with a sensor and detect positive emotions using biometrics technology. It can also analyze changes in the user's typing speed and rhythm to detect positive emotions. This allows the system to prioritize correction of words and phrases that the user associates with positive emotions.

[0069] The input error correction system uses generative AI to learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct input errors. For example, if it detects a rhythm that differs from the normal typing speed, it corrects input errors. It can also correct input errors if the user's typing speed changes suddenly. It can also correct input errors if the user presses specific keys repeatedly. Specifically, it detects a rhythm that differs from normal typing and corrects input errors based on that rhythm. It can also correct input errors if the user's typing speed changes suddenly. It can also correct input errors based on the continuous input of specific keys. This allows the system to learn the user's typing speed and rhythm, detect abnormal typing patterns, and correct input errors.

[0070] The processing flow of the second embodiment will be briefly explained below.

[0071] Step 1: The generation AI analyzes the surrounding input string. For example, the generation AI analyzes the input string using a text generation AI (e.g., LLM). The generation AI can also analyze the input string using a multimodal generation AI. The generation AI uses context analysis technology to analyze the surrounding input string and determine whether it is an incorrect input. Step 2: The input error detection unit detects input errors based on the preceding and following input strings analyzed by the generation AI. For example, the input error detection unit detects spelling errors, grammatical errors, and out-of-context words. It detects spelling errors based on a dictionary, grammatical analysis technology detects grammatical errors, and contextual words using context analysis technology. Step 3: The correction unit corrects the incorrect input identified by the incorrect input determination unit to the correct characters. For example, the correction unit corrects spelling mistakes based on a dictionary, performs context-based correction using context analysis technology, and performs correction based on the user's input patterns learned by the generation AI.

[0072] 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.

[0073] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0074] 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.

[0075] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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).

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0085] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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).

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0100] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0106] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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."

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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. [Explanation of symbols]

[0139] 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. Equipped with generative AI, The generation AI analyzes the surrounding input strings, an erroneous input determination unit that determines an erroneous input; a correction unit that corrects the incorrect input determined by the incorrect input determination unit to a correct character. A system characterized by:

2. The generated AI is Learns the user's typing speed and rhythm, detects abnormal typing patterns, and corrects input errors 2. The system of claim 1.

3. The generated AI is Simultaneously analyzes the user's voice input and text input, correcting input errors 2. The system of claim 1.

4. The generated AI is Analyzes the user's input history and identifies frequently occurring input errors to improve correction accuracy 2. The system of claim 1.

5. The generated AI is Analyzes the tendency for input errors to increase when users are stressed, and makes corrections to reduce stress.

2. The system of claim 1.

6. The generated AI is Performs context analysis to understand the meaning of the entire sentence and corrects input errors 2. The system of claim 1.

7. The generated AI is Translates user input in real time and corrects typos in different languages 2. The system of claim 1.

8. The generated AI is Prioritize corrections to words and phrases that users have positive sentiments about 2. The system of claim 1.

Images