system

Abstract

The system according to this embodiment aims to perform appropriate contextual correction in response to user input. [Solution] The system according to the embodiment comprises a reception unit, a correction unit, and a provision unit. The reception unit receives input from the user. The correction unit analyzes the input received by the reception unit and performs contextual correction. The provision unit provides the corrected result from the correction unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, context correction for input from a user is not sufficiently performed, and there is room for improvement.

[0005] The system according to the embodiment aims to perform appropriate context correction for input from a user.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, a correction unit, and a provision unit. The reception unit receives input from a user. The correction unit analyzes the input received by the reception unit and performs context correction. The provision unit provides the result corrected by the correction unit.

Effects of the Invention

[0007] The system according to this embodiment can perform appropriate contextual correction in response to user input. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The context correction system according to an embodiment of the present invention is a system that significantly improves communication efficiency by performing context correction using generative AI. In the context correction system, the user takes input, the generative AI analyzes the input, and performs context correction. The corrected result is provided to the user. This system can solve problems such as decreased time performance due to the time required to interpret emails and chats, loss of credibility due to misleading requests, and insufficient knowledge sharing due to reliance on individual expertise. In addition to general document proofreading by LLM, the generative AI is used to supplement context by acquiring background information through analysis of internal company data. Examples of reference information that are likely to be useful include approval documents, meeting minutes, and email and chat histories of relevant parties. This idea targets B2B companies ranging from small and medium-sized enterprises to large corporations, and aims to solve problems such as decreased time performance due to the time required to interpret emails and chats, loss of credibility due to misleading requests, and insufficient knowledge sharing due to reliance on individual expertise. The market size will include companies worldwide, and will vary depending on the supported languages. Amidst a mix of online and offline face-to-face interactions, and with the increasing use of text-based communication via email and chat, concerns about business stagnation and misinterpretation due to insufficient writing skills are growing. Against this backdrop, the idea of ​​contextual correction using generative AI aims to eliminate stress in business settings and create a faster-paced environment. This allows the contextual correction system to efficiently correct and deliver user input.

[0029] The context correction system according to this embodiment comprises a reception unit, a correction unit, and a provision unit. The reception unit receives input from the user. User input includes, but is not limited to, text input, voice input, and image input. The reception unit can, for example, receive text input using a keyboard or touchscreen. The reception unit can also receive voice input using a microphone. For example, it can convert voice to text using speech recognition technology. Furthermore, the reception unit can also receive image input using a camera or scanner. For example, it can analyze an image using image recognition technology and extract text information. The correction unit uses a generation AI to analyze the input received by the reception unit and perform context correction. Context correction is performed by, for example, grammatical correction, semantic analysis, and typographical error correction, but is not limited to these methods. For example, the generation AI can perform grammatical correction using a text generation AI (e.g., LLM). The correction unit can also perform semantic analysis using the generation AI. The correction unit can also perform typographical error correction using the generation AI. For example, the text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. The generation AI performs grammatical correction based on grammatical rules, understands the context through semantic analysis, and corrects typographical errors. The provisioning unit provides the user with the corrected results from the correction unit. The provisioning unit provides the corrected results in text format, for example. The provisioning unit can also provide the corrected results in report format. The provisioning unit can also provide the corrected results in a graphical display. For example, the provisioning unit displays the corrected results to the user through a web application or a mobile application. This allows the context correction system according to the embodiment to efficiently correct and provide user input. Some or all of the above-described processes in the correction unit may be performed using the generation AI, for example, or without the generation AI. For example, the correction unit can input user input to the generation AI and have the generation AI perform context correction. Some or all of the above-described processes in the provisioning unit may be performed using the generation AI, for example, or without the generation AI.For example, the supply unit can input the corrected results into the generation AI and have the generation AI execute the provision of the results.

[0030] The reception desk receives input from users. User input includes, but is not limited to, text input, voice input, and image input. For example, the reception desk accepts text input using a keyboard or touchscreen. Specifically, it receives text data entered by the user using a keyboard in real time and stores it in the system. Furthermore, the touchscreen allows users to intuitively input text. The reception desk can also accept voice input using a microphone. For example, it can convert speech to text using speech recognition technology. Speech recognition technology can analyze user speech with high accuracy and import it into the system as text data. This allows users to input by voice without using their hands, improving convenience. The reception desk can also accept image input using a camera or scanner. For example, it can analyze images using image recognition technology and extract text information. Image recognition technology can digitize handwritten notes and printed documents and import them into the system as text data. This allows information on paper to be efficiently digitized and processed within the system. The reception unit integrates these diverse input methods, enabling efficient reception of user input. Furthermore, the reception unit preprocesses the input data, removing noise and standardizing the format, allowing for smoother processing in the subsequent correction unit. As a result, the reception unit can efficiently receive diverse user inputs and improve the overall system performance.

[0031] The correction unit uses a generation AI to analyze the input received by the reception unit and perform contextual correction. Contextual correction is performed by methods such as grammatical correction, semantic analysis, and typographical error correction, but is not limited to these examples. For example, the generation AI can perform grammatical correction using a text generation AI (e.g., LLM). Specifically, the generation AI analyzes the input text, detects grammatical errors, and corrects them. For example, it performs corrections based on grammatical rules, such as subject-verb agreement and tense agreement. The correction unit can also perform semantic analysis using the generation AI. In semantic analysis, it understands the context of the input text and replaces it with words and phrases that have appropriate meaning. For example, by selecting synonyms or selecting words according to the context, it can correct the text to make it more natural and meaningful. The correction unit can also perform typographical error correction using the generation AI. For example, a text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. The generation AI performs grammatical correction based on grammatical rules, understands the context through semantic analysis, and corrects typographical errors. In typographical error correction, the system detects typos in the input text and replaces them with correct words. This allows the correction unit to correct user input with high accuracy, transforming it into natural and meaningful sentences. Furthermore, the correction unit can learn from the user's input history and past correction results, continuously improving its accuracy. This enables the correction unit to always provide highly accurate contextual correction based on the latest information, meeting the user's needs.

[0032] The service provider delivers the corrected results to the user. For example, the service provider can provide the corrected results in text format. Specifically, it can display the corrected text on the user's device for user review. The service provider can also provide the corrected results in report format. In addition to the corrected text, the report can include information such as correction details and a comparison before and after the correction. This allows the user to review the correction in detail and make corrections as needed. The service provider can also provide the corrected results graphically. For example, it can display the corrected text visually in an easy-to-understand format, allowing the user to intuitively comprehend it. The service provider can display the corrected results to the user through web or mobile applications. This allows the user to check the correction results anytime, anywhere. Furthermore, the service provider can collect user feedback to improve the accuracy and delivery method of the correction unit. For example, by providing evaluations and comments on the correction results, the system can learn from that feedback and improve the accuracy of future corrections. This allows the service provider to deliver high-quality correction results to users and improve user satisfaction. Furthermore, the service provider can integrate the correction results with other systems and applications. For example, automatically transferring the corrected text to other document creation or communication tools can improve user efficiency. This allows the service provider to offer users flexible and efficient correction results, thereby enhancing the overall value of the system.

[0033] The correction unit can perform contextual correction using a generative AI. For example, the correction unit can perform grammatical correction using a generative AI. For example, the generative AI performs grammatical correction based on grammatical rules. The correction unit can also perform semantic analysis using a generative AI. For example, the generative AI understands the context through semantic analysis. The correction unit can also correct typographical errors using a generative AI. For example, the generative AI detects typographical errors and corrects them to appropriate words. This improves the accuracy of contextual correction by using a generative AI. Some or all of the above-described processes in the correction unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the correction unit can input user input into a generative AI and have the generative AI perform contextual correction.

[0034] The correction unit can perform general document proofreading using LLM. For example, the correction unit can perform grammatical correction using LLM. For example, LLM performs grammatical correction based on grammatical rules. The correction unit can also perform semantic analysis using LLM. For example, LLM understands the context through semantic analysis. The correction unit can also correct typographical errors using LLM. For example, LLM detects typographical errors and corrects them to appropriate words. As a result, the accuracy of document proofreading is improved by using LLM. Some or all of the above processes in the correction unit may be performed using LLM, or not using LLM. For example, the correction unit can input user input into LLM and have LLM perform document proofreading.

[0035] The correction unit can analyze internal company data and obtain background information. For example, the correction unit can analyze internal company documents and obtain background information. For example, internal company documents include approval documents, meeting minutes, emails, and chat history. The correction unit can also analyze internal company databases and obtain background information. For example, internal company databases include project data, customer data, and business data. The correction unit can also analyze log data and obtain background information. For example, log data includes system logs, access logs, and operation logs. By analyzing internal company data, the accuracy of context correction is improved. Some or all of the above processing in the correction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction unit can input internal company data into a generation AI and have the generation AI perform the acquisition of background information.

[0036] The correction unit can supplement context based on reference information such as approval documents, meeting minutes, and email and chat histories of relevant parties. For example, the correction unit can refer to approval documents and supplement context. For example, approval documents contain information such as the items to be approved, the approvers, and the approval date. The correction unit can also refer to meeting minutes and supplement context. For example, meeting minutes contain information such as the agenda of the meeting, the participants, and the content of the discussions. The correction unit can also refer to email and chat histories of relevant parties and supplement context. For example, email and chat histories contain information such as the content of the exchange, the date and time, the sender, and the recipient. By supplementing context based on reference information, the accuracy of context correction is improved. Some or all of the above processing in the correction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction unit can input reference information into a generation AI and have the generation AI perform context supplementation.

[0037] The service provider can provide the corrected results to the user. For example, the service provider can provide the corrected results in text format. For example, the service provider can save the corrected results as a text file and provide it to the user. The service provider can also provide the corrected results in report format. For example, the service provider can save the corrected results as a PDF file and provide it to the user. The service provider can also provide the corrected results in a graphical display. For example, the service provider can display the corrected results as a graph or chart and provide it to the user. This improves user convenience by providing the corrected results to the user. Some or all of the above processing in the service provider may be performed using, for example, a generation AI, or without a generation AI. For example, the service provider can input the corrected results into a generation AI and have the generation AI perform the task of providing the results.

[0038] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk can prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. For instance, it can analyze the user's past input history and prioritize suggesting voice input to users who prefer it. The reception desk can also predict and suggest input methods to be used at specific times of day based on the user's past input history. For example, if the reception desk prefers text input in the morning, it will prioritize suggesting text input during that time. The reception desk can also suggest similar input methods based on content the user has entered in the past. For example, it can analyze content the user has entered in the past and suggest a similar input method when similar content is entered. In this way, the reception desk can provide the optimal reception method by analyzing past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the user's past input history into AI and have the AI ​​select the optimal reception method.

[0039] The reception unit can filter input based on the user's current projects and areas of interest. For example, the reception unit can prioritize receiving only input related to the project the user is currently working on. For example, the reception unit can refer to a project management tool and prioritize receiving input related to an ongoing project. The reception unit can also filter and prioritize relevant input based on the user's areas of interest. For example, the reception unit can refer to the user profile and prioritize receiving input related to the user's areas of interest. The reception unit can also filter and receive necessary input according to the user's project progress. For example, the reception unit can refer to the project progress and prioritize receiving input related to ongoing tasks. This allows for the priority of receiving highly relevant input by filtering based on the current project and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or not. For example, the reception unit can input the user's project data into an AI and have the AI ​​perform the filtering.

[0040] The reception unit can prioritize receiving inputs that are highly relevant based on the user's geographical location information. For example, if the user is in a specific region, the reception unit will prioritize receiving inputs related to that region. For example, the reception unit can refer to GPS data and prioritize receiving inputs related to the user's current location. The reception unit can also prioritize receiving relevant inputs based on the user's current location if the user is on the move. For example, the reception unit can refer to the IP address to detect that the user is on the move and prioritize receiving inputs related to the current location. The reception unit can also prioritize receiving inputs related to a specific location if the user is in that location. For example, the reception unit can refer to Wi-Fi data to detect that the user is in a specific location and prioritize receiving inputs related to that location. This improves user convenience by prioritizing the reception of highly relevant inputs based on geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception desk can input the user's geographical location information into the AI ​​and have the AI ​​select the most relevant inputs.

[0041] The reception unit can analyze the user's social media activity and accept relevant inputs when receiving input. For example, the reception unit can prioritize accepting inputs related to topics that the user frequently mentions on social media. For example, the reception unit can analyze the user's social media posts and prioritize accepting inputs related to frequently mentioned topics. The reception unit can also analyze the user's current interests from their social media activity and accept relevant inputs. For example, the reception unit can analyze the user's follower information and prioritize accepting inputs related to current interests. The reception unit can also prioritize accepting inputs related to accounts that the user follows on social media. For example, the reception unit can analyze the content of posts from accounts that the user follows and prioritize accepting relevant inputs. In this way, by analyzing social media activity, it is possible to prioritize the acceptance of relevant inputs. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's social media data into AI and have AI select relevant inputs.

[0042] The correction unit can adjust the level of detail of the correction based on the importance of the input during contextual correction. For example, the correction unit performs detailed contextual correction for high-importance inputs. For example, the correction unit performs detailed contextual correction for important business documents. The correction unit can also perform concise contextual correction for low-importance inputs. For example, the correction unit performs concise contextual correction for everyday messages. The correction unit can also adjust the level of detail of the contextual correction in stages according to importance. For example, the correction unit adjusts the level of detail of the contextual correction in three stages according to importance. This allows for efficient correction by adjusting the level of detail of the correction based on the importance of the input. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the importance of the input to the generative AI and have the generative AI perform the adjustment of the level of detail of the correction.

[0043] The correction unit can apply different correction algorithms depending on the input category during context correction. For example, the correction unit performs formal context correction on business-related inputs. For example, it performs formal context correction on business documents. The correction unit can also perform relaxed context correction on casual inputs. For example, it performs relaxed context correction on everyday messages. The correction unit can also perform context correction including technical terms on technical inputs. For example, it performs context correction including technical terms on technical documents. This allows for more appropriate correction by applying different correction algorithms depending on the input category. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the input category to the generative AI and have the generative AI select a correction algorithm.

[0044] The correction unit can determine the priority of corrections based on the submission date of the input when performing contextual corrections. For example, the correction unit will prioritize contextual corrections for inputs with high urgency. For example, the correction unit will prioritize contextual corrections for documents with approaching submission deadlines. The correction unit can also prioritize contextual corrections for inputs with approaching submission deadlines. For example, the correction unit will prioritize contextual corrections for documents with submission deadlines within one week. Furthermore, the correction unit can adjust the priority of contextual corrections in stages according to the submission date. For example, the correction unit can set a higher priority for submissions with approaching deadlines and a lower priority for submissions with distant deadlines. This allows for efficient corrections by determining the priority of corrections based on the submission date. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the submission date into a generative AI and have the generative AI determine the priority of corrections.

[0045] The correction unit can adjust the order of corrections based on the relevance of the inputs during contextual correction. For example, the correction unit prioritizes contextual correction for highly relevant inputs. For instance, it prioritizes contextual correction for documents related to relevant projects. The correction unit can also postpone contextual correction for less relevant inputs. For example, it postpones contextual correction for unrelated, everyday messages. Furthermore, the correction unit can adjust the order of contextual corrections in stages according to relevance. For instance, it can perform contextual corrections in order of relevance and postpone corrections in order of less relevance. This allows for efficient correction by adjusting the order of corrections based on relevance. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the relevance of the inputs into a generative AI and have the generative AI adjust the order of corrections.

[0046] The service provider can select the optimal display method by referring to the user's past operation history when providing results. For example, the service provider may prioritize providing display methods that the user has preferred to use in the past. For example, the service provider may analyze the user's past operation history and prioritize providing display methods that the user has preferred to use in the past. The service provider can also predict and provide the optimal display method based on the user's past operation history. For example, the service provider may analyze the user's past operation history, predict and provide the optimal display method. The service provider can also provide similar display methods based on display methods that the user has used in the past. For example, the service provider may analyze the user's past operation history and provide similar display methods. In this way, the optimal display method can be provided by referring to past operation history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider may input the user's past operation history into AI and have AI select the optimal display method.

[0047] The service provider can select the optimal display method when providing results, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. For example, the service provider can refer to the user's device information and provide a display method that matches the smartphone's screen size. The service provider can also provide a display method optimized for a larger screen if the user is using a tablet. For example, the service provider can refer to the user's device information and provide a display method optimized for the tablet's screen size. The service provider can also provide a concise and highly visible display method if the user is using a smartwatch. For example, the service provider can refer to the user's device information and provide a display method that matches the smartwatch's screen size. In this way, the service provider can provide the optimal display method by taking device information into consideration. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into AI and have AI select the optimal display method.

[0048] The service provider can select the optimal display method when providing results, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. For example, the service provider can refer to the user's device information and provide a display method that matches the smartphone's screen size. The service provider can also provide a display method optimized for a larger screen if the user is using a tablet. For example, the service provider can refer to the user's device information and provide a display method optimized for the tablet's screen size. The service provider can also provide a concise and highly visible display method if the user is using a smartwatch. For example, the service provider can refer to the user's device information and provide a display method that matches the smartwatch's screen size. In this way, the service provider can provide the optimal display method by taking device information into consideration. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into AI and have AI select the optimal display method.

[0049] The service provider can provide multilingual results according to the user's language settings when providing results. For example, the service provider can automatically set the language of the results based on the language settings of the user's device. For example, the service provider can refer to the language settings of the user's device and automatically set the language of the results. The service provider can also provide a language switching function if the user uses multiple languages. For example, the service provider can provide a language switching function if the user uses multiple languages. The service provider can also provide results in a specific language if the user selects a specific language. For example, the service provider can provide results in a specific language if the user selects a specific language. This improves user convenience by providing multilingual results according to language settings. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's language settings into AI and have AI perform the task of providing multilingual results.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The reception desk can analyze the user's past input history when receiving user input and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the user has frequently used in the past (such as voice or text). The reception desk can also predict and suggest input methods that the user will use at specific times of day based on their past input history. For example, if a user prefers text input in the morning, it will prioritize suggesting text input during that time. Furthermore, the reception desk can suggest similar input methods based on content the user has previously entered. In this way, by analyzing past input history, the system can provide the most optimal input method.

[0052] The service provider can select the optimal display method when providing results, taking into account the user's device information. For example, if the user is using a smartphone, it can provide a display method that matches the screen size. If the user is using a tablet, it can also provide a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible display method. In this way, the optimal display method can be provided by considering the device information.

[0053] The correction unit can adjust the level of detail of the correction based on the importance of the input during contextual correction. For example, it can perform detailed contextual correction for high-importance inputs, and simpler contextual correction for low-importance inputs. Furthermore, it can adjust the level of detail of the contextual correction in stages according to importance. This allows for efficient correction by adjusting the level of detail of the correction based on the importance of the input.

[0054] The reception system can prioritize inputs based on the user's geographical location when receiving input. For example, if a user is in a specific region, it can prioritize inputs related to that region. If a user is on the move, it can also prioritize inputs related to their current location. Furthermore, if a user is in a specific location, it can prioritize inputs related to that location. This improves user convenience by prioritizing highly relevant inputs based on geographical location.

[0055] The service provider can provide multilingual results according to the user's language settings. For example, it can automatically set the language of the results based on the language settings of the user's device. It can also provide a language switching function if the user uses multiple languages. Furthermore, if the user selects a specific language, the results can be provided in that language. This improves user convenience by providing multilingual results according to language settings.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The reception desk receives input from the user. User input includes text input, voice input, and image input. For example, text input is received using a keyboard or touchscreen, voice input is converted to text using speech recognition technology via a microphone, and image input is extracted as text information using image recognition technology via a camera or scanner. Step 2: The correction unit analyzes the input received by the reception unit using a generation AI and performs contextual correction. Contextual correction includes grammatical correction, semantic analysis, and typographical error correction. For example, grammatical correction is performed using a text generation AI (LLM), the context is understood through semantic analysis, and typographical errors are corrected. Step 3: The provider unit provides the user with the corrected results from the correction unit. The provider unit provides the corrected results in text format, report format, graphical display, etc. For example, it may be displayed to the user through a web application or mobile application.

[0058] (Example of form 2) The context correction system according to an embodiment of the present invention is a system that significantly improves communication efficiency by performing context correction using generative AI. In the context correction system, the user takes input, the generative AI analyzes the input, and performs context correction. The corrected result is provided to the user. This system can solve problems such as decreased time performance due to the time required to interpret emails and chats, loss of credibility due to misleading requests, and insufficient knowledge sharing due to reliance on individual expertise. In addition to general document proofreading by LLM, the generative AI is used to supplement context by acquiring background information through analysis of internal company data. Examples of reference information that are likely to be useful include approval documents, meeting minutes, and email and chat histories of relevant parties. This idea targets B2B companies ranging from small and medium-sized enterprises to large corporations, and aims to solve problems such as decreased time performance due to the time required to interpret emails and chats, loss of credibility due to misleading requests, and insufficient knowledge sharing due to reliance on individual expertise. The market size will include companies worldwide, and will vary depending on the supported languages. Amidst a mix of online and offline face-to-face interactions, and with the increasing use of text-based communication via email and chat, concerns about business stagnation and misinterpretation due to insufficient writing skills are growing. Against this backdrop, the idea of ​​contextual correction using generative AI aims to eliminate stress in business settings and create a faster-paced environment. This allows the contextual correction system to efficiently correct and deliver user input.

[0059] The context correction system according to this embodiment comprises a reception unit, a correction unit, and a provision unit. The reception unit receives input from the user. User input includes, but is not limited to, text input, voice input, and image input. The reception unit can, for example, receive text input using a keyboard or touchscreen. The reception unit can also receive voice input using a microphone. For example, it can convert voice to text using speech recognition technology. Furthermore, the reception unit can also receive image input using a camera or scanner. For example, it can analyze an image using image recognition technology and extract text information. The correction unit uses a generation AI to analyze the input received by the reception unit and perform context correction. Context correction is performed by, for example, grammatical correction, semantic analysis, and typographical error correction, but is not limited to these methods. For example, the generation AI can perform grammatical correction using a text generation AI (e.g., LLM). The correction unit can also perform semantic analysis using the generation AI. The correction unit can also perform typographical error correction using the generation AI. For example, the text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. The generation AI performs grammatical correction based on grammatical rules, understands the context through semantic analysis, and corrects typographical errors. The provisioning unit provides the user with the corrected results from the correction unit. The provisioning unit provides the corrected results in text format, for example. The provisioning unit can also provide the corrected results in report format. The provisioning unit can also provide the corrected results in a graphical display. For example, the provisioning unit displays the corrected results to the user through a web application or a mobile application. This allows the context correction system according to the embodiment to efficiently correct and provide user input. Some or all of the above-described processes in the correction unit may be performed using the generation AI, for example, or without the generation AI. For example, the correction unit can input user input to the generation AI and have the generation AI perform context correction. Some or all of the above-described processes in the provisioning unit may be performed using the generation AI, for example, or without the generation AI.For example, the supply unit can input the corrected results into the generation AI and have the generation AI execute the provision of the results.

[0060] The reception desk receives input from users. User input includes, but is not limited to, text input, voice input, and image input. For example, the reception desk accepts text input using a keyboard or touchscreen. Specifically, it receives text data entered by the user using a keyboard in real time and stores it in the system. Furthermore, the touchscreen allows users to intuitively input text. The reception desk can also accept voice input using a microphone. For example, it can convert speech to text using speech recognition technology. Speech recognition technology can analyze user speech with high accuracy and import it into the system as text data. This allows users to input by voice without using their hands, improving convenience. The reception desk can also accept image input using a camera or scanner. For example, it can analyze images using image recognition technology and extract text information. Image recognition technology can digitize handwritten notes and printed documents and import them into the system as text data. This allows information on paper to be efficiently digitized and processed within the system. The reception unit integrates these diverse input methods, enabling efficient reception of user input. Furthermore, the reception unit preprocesses the input data, removing noise and standardizing the format, allowing for smoother processing in the subsequent correction unit. As a result, the reception unit can efficiently receive diverse user inputs and improve the overall system performance.

[0061] The correction unit uses a generation AI to analyze the input received by the reception unit and perform contextual correction. Contextual correction is performed by methods such as grammatical correction, semantic analysis, and typographical error correction, but is not limited to these examples. For example, the generation AI can perform grammatical correction using a text generation AI (e.g., LLM). Specifically, the generation AI analyzes the input text, detects grammatical errors, and corrects them. For example, it performs corrections based on grammatical rules, such as subject-verb agreement and tense agreement. The correction unit can also perform semantic analysis using the generation AI. In semantic analysis, it understands the context of the input text and replaces it with words and phrases that have appropriate meaning. For example, by selecting synonyms or selecting words according to the context, it can correct the text to make it more natural and meaningful. The correction unit can also perform typographical error correction using the generation AI. For example, a text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. The generation AI performs grammatical correction based on grammatical rules, understands the context through semantic analysis, and corrects typographical errors. In typographical error correction, the system detects typos in the input text and replaces them with correct words. This allows the correction unit to correct user input with high accuracy, transforming it into natural and meaningful sentences. Furthermore, the correction unit can learn from the user's input history and past correction results, continuously improving its accuracy. This enables the correction unit to always provide highly accurate contextual correction based on the latest information, meeting the user's needs.

[0062] The service provider delivers the corrected results to the user. For example, the service provider can provide the corrected results in text format. Specifically, it can display the corrected text on the user's device for user review. The service provider can also provide the corrected results in report format. In addition to the corrected text, the report can include information such as correction details and a comparison before and after the correction. This allows the user to review the correction in detail and make corrections as needed. The service provider can also provide the corrected results graphically. For example, it can display the corrected text visually in an easy-to-understand format, allowing the user to intuitively comprehend it. The service provider can display the corrected results to the user through web or mobile applications. This allows the user to check the correction results anytime, anywhere. Furthermore, the service provider can collect user feedback to improve the accuracy and delivery method of the correction unit. For example, by providing evaluations and comments on the correction results, the system can learn from that feedback and improve the accuracy of future corrections. This allows the service provider to deliver high-quality correction results to users and improve user satisfaction. Furthermore, the service provider can integrate the correction results with other systems and applications. For example, automatically transferring the corrected text to other document creation or communication tools can improve user efficiency. This allows the service provider to offer users flexible and efficient correction results, thereby enhancing the overall value of the system.

[0063] The correction unit can perform contextual correction using a generative AI. For example, the correction unit can perform grammatical correction using a generative AI. For example, the generative AI performs grammatical correction based on grammatical rules. The correction unit can also perform semantic analysis using a generative AI. For example, the generative AI understands the context through semantic analysis. The correction unit can also correct typographical errors using a generative AI. For example, the generative AI detects typographical errors and corrects them to appropriate words. This improves the accuracy of contextual correction by using a generative AI. Some or all of the above-described processes in the correction unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the correction unit can input user input into a generative AI and have the generative AI perform contextual correction.

[0064] The correction unit can perform general document proofreading using LLM. For example, the correction unit can perform grammatical correction using LLM. For example, LLM performs grammatical correction based on grammatical rules. The correction unit can also perform semantic analysis using LLM. For example, LLM understands the context through semantic analysis. The correction unit can also correct typographical errors using LLM. For example, LLM detects typographical errors and corrects them to appropriate words. As a result, the accuracy of document proofreading is improved by using LLM. Some or all of the above processes in the correction unit may be performed using LLM, or not using LLM. For example, the correction unit can input user input into LLM and have LLM perform document proofreading.

[0065] The correction unit can analyze internal company data and obtain background information. For example, the correction unit can analyze internal company documents and obtain background information. For example, internal company documents include approval documents, meeting minutes, emails, and chat history. The correction unit can also analyze internal company databases and obtain background information. For example, internal company databases include project data, customer data, and business data. The correction unit can also analyze log data and obtain background information. For example, log data includes system logs, access logs, and operation logs. By analyzing internal company data, the accuracy of context correction is improved. Some or all of the above processing in the correction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction unit can input internal company data into a generation AI and have the generation AI perform the acquisition of background information.

[0066] The correction unit can supplement context based on reference information such as approval documents, meeting minutes, and email and chat histories of relevant parties. For example, the correction unit can refer to approval documents and supplement context. For example, approval documents contain information such as the items to be approved, the approvers, and the approval date. The correction unit can also refer to meeting minutes and supplement context. For example, meeting minutes contain information such as the agenda of the meeting, the participants, and the content of the discussions. The correction unit can also refer to email and chat histories of relevant parties and supplement context. For example, email and chat histories contain information such as the content of the exchange, the date and time, the sender, and the recipient. By supplementing context based on reference information, the accuracy of context correction is improved. Some or all of the above processing in the correction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction unit can input reference information into a generation AI and have the generation AI perform context supplementation.

[0067] The service provider can provide the corrected results to the user. For example, the service provider can provide the corrected results in text format. For example, the service provider can save the corrected results as a text file and provide it to the user. The service provider can also provide the corrected results in report format. For example, the service provider can save the corrected results as a PDF file and provide it to the user. The service provider can also provide the corrected results in a graphical display. For example, the service provider can display the corrected results as a graph or chart and provide it to the user. This improves user convenience by providing the corrected results to the user. Some or all of the above processing in the service provider may be performed using, for example, a generation AI, or without a generation AI. For example, the service provider can input the corrected results into a generation AI and have the generation AI perform the task of providing the results.

[0068] The reception system can estimate the user's emotions and adjust the timing of input acceptance based on those emotions. For example, if the user is stressed, the reception system can delay the input acceptance timing to allow them to input in a relaxed state. For example, the reception system can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on changes in facial expressions. The reception system can also speed up the input acceptance timing if the user is in a hurry to accept input quickly. For example, the reception system can record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of their voice to calculate an emotion score. The reception system can also adjust the input acceptance timing if the user is concentrating, allowing them to input while maintaining their concentration. For example, the reception system can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on fluctuations in heart rate. By adjusting the input acceptance timing according to the user's emotions, the system can reduce user stress. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using a generative AI, or not using a generative AI. For example, the reception unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0069] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk can prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. For instance, it can analyze the user's past input history and prioritize suggesting voice input to users who prefer it. The reception desk can also predict and suggest input methods to be used at specific times of day based on the user's past input history. For example, if the reception desk prefers text input in the morning, it will prioritize suggesting text input during that time. The reception desk can also suggest similar input methods based on content the user has entered in the past. For example, it can analyze content the user has entered in the past and suggest a similar input method when similar content is entered. In this way, the reception desk can provide the optimal reception method by analyzing past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the user's past input history into AI and have the AI ​​select the optimal reception method.

[0070] The reception unit can filter input based on the user's current projects and areas of interest. For example, the reception unit can prioritize receiving only input related to the project the user is currently working on. For example, the reception unit can refer to a project management tool and prioritize receiving input related to an ongoing project. The reception unit can also filter and prioritize relevant input based on the user's areas of interest. For example, the reception unit can refer to the user profile and prioritize receiving input related to the user's areas of interest. The reception unit can also filter and receive necessary input according to the user's project progress. For example, the reception unit can refer to the project progress and prioritize receiving input related to ongoing tasks. This allows for the priority of receiving highly relevant input by filtering based on the current project and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or not. For example, the reception unit can input the user's project data into an AI and have the AI ​​perform the filtering.

[0071] The reception system can estimate the user's emotions and determine the priority of inputs to be received based on the estimated emotions. For example, if the user is stressed, the reception system will postpone less important inputs and prioritize more important ones. For example, the reception system can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on changes in facial expressions and prioritize more important inputs. Also, if the user is relaxed, the reception system can accept all inputs equally. For example, the reception system can record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of the voice, calculate an emotion score, and accept all inputs equally. Furthermore, if the user is in a hurry, the reception system can prioritize receiving urgent inputs. For example, the reception system can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on fluctuations in heart rate and prioritize receiving urgent inputs. This allows important inputs to be processed preferentially by determining the priority of inputs according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using a generative AI, or not using a generative AI. For example, the reception unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0072] The reception unit can prioritize receiving inputs that are highly relevant based on the user's geographical location information. For example, if the user is in a specific region, the reception unit will prioritize receiving inputs related to that region. For example, the reception unit can refer to GPS data and prioritize receiving inputs related to the user's current location. The reception unit can also prioritize receiving relevant inputs based on the user's current location if the user is on the move. For example, the reception unit can refer to the IP address to detect that the user is on the move and prioritize receiving inputs related to the current location. The reception unit can also prioritize receiving inputs related to a specific location if the user is in that location. For example, the reception unit can refer to Wi-Fi data to detect that the user is in a specific location and prioritize receiving inputs related to that location. This improves user convenience by prioritizing the reception of highly relevant inputs based on geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception desk can input the user's geographical location information into the AI ​​and have the AI ​​select the most relevant inputs.

[0073] The reception unit can analyze the user's social media activity and accept relevant inputs when receiving input. For example, the reception unit can prioritize accepting inputs related to topics that the user frequently mentions on social media. For example, the reception unit can analyze the user's social media posts and prioritize accepting inputs related to frequently mentioned topics. The reception unit can also analyze the user's current interests from their social media activity and accept relevant inputs. For example, the reception unit can analyze the user's follower information and prioritize accepting inputs related to current interests. The reception unit can also prioritize accepting inputs related to accounts that the user follows on social media. For example, the reception unit can analyze the content of posts from accounts that the user follows and prioritize accepting relevant inputs. In this way, by analyzing social media activity, it is possible to prioritize the acceptance of relevant inputs. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's social media data into AI and have AI select relevant inputs.

[0074] The correction unit can estimate the user's emotions and adjust the expression of contextual correction based on the estimated user emotions. For example, if the user is stressed, the correction unit performs contextual correction using concise and clear expressions. For example, the correction unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions and performs contextual correction using concise and clear expressions. The correction unit can also perform contextual correction with detailed explanations if the user is relaxed. For example, the correction unit records the user's voice and estimates the emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice, calculates an emotion score, and performs contextual correction with detailed explanations. The correction unit can also perform concise contextual correction if the user is in a hurry. For example, the correction unit collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates the emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate and performs concise contextual correction. This allows for more appropriate correction by adjusting the expression of contextual correction according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the correction unit may be performed using a generative AI, or not using a generative AI. For example, the correction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0075] The correction unit can adjust the level of detail of the correction based on the importance of the input during contextual correction. For example, the correction unit performs detailed contextual correction for high-importance inputs. For example, the correction unit performs detailed contextual correction for important business documents. The correction unit can also perform concise contextual correction for low-importance inputs. For example, the correction unit performs concise contextual correction for everyday messages. The correction unit can also adjust the level of detail of the contextual correction in stages according to importance. For example, the correction unit adjusts the level of detail of the contextual correction in three stages according to importance. This allows for efficient correction by adjusting the level of detail of the correction based on the importance of the input. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the importance of the input to the generative AI and have the generative AI perform the adjustment of the level of detail of the correction.

[0076] The correction unit can apply different correction algorithms depending on the input category during context correction. For example, the correction unit performs formal context correction on business-related inputs. For example, it performs formal context correction on business documents. The correction unit can also perform relaxed context correction on casual inputs. For example, it performs relaxed context correction on everyday messages. The correction unit can also perform context correction including technical terms on technical inputs. For example, it performs context correction including technical terms on technical documents. This allows for more appropriate correction by applying different correction algorithms depending on the input category. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the input category to the generative AI and have the generative AI select a correction algorithm.

[0077] The correction unit can estimate the user's emotions and adjust the length of the correction based on the estimated emotions. For example, if the user is stressed, the correction unit will perform a short, concise correction. For example, the correction unit will capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it will calculate an emotion score based on changes in facial expressions and perform a short, concise correction. The correction unit can also perform a detailed correction if the user is relaxed. For example, the correction unit will record the user's voice and estimate their emotions using voice analysis technology. For example, it will analyze the tone and speed of the voice, calculate an emotion score, and perform a detailed correction. The correction unit can also adjust the length of the correction so that it can be quickly understood if the user is in a hurry. For example, the correction unit will collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it will calculate an emotion score based on fluctuations in heart rate and adjust the length of the correction so that it can be quickly understood. In this way, by adjusting the length of the correction according to the user's emotions, more appropriate corrections can be performed. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the correction unit may be performed using the generative AI, or not using the generative AI. For example, the correction unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0078] The correction unit can determine the priority of corrections based on the submission date of the input when performing contextual corrections. For example, the correction unit will prioritize contextual corrections for inputs with high urgency. For example, the correction unit will prioritize contextual corrections for documents with approaching submission deadlines. The correction unit can also prioritize contextual corrections for inputs with approaching submission deadlines. For example, the correction unit will prioritize contextual corrections for documents with submission deadlines within one week. Furthermore, the correction unit can adjust the priority of contextual corrections in stages according to the submission date. For example, the correction unit can set a higher priority for submissions with approaching deadlines and a lower priority for submissions with distant deadlines. This allows for efficient corrections by determining the priority of corrections based on the submission date. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the submission date into a generative AI and have the generative AI determine the priority of corrections.

[0079] The correction unit can adjust the order of corrections based on the relevance of the inputs during contextual correction. For example, the correction unit prioritizes contextual correction for highly relevant inputs. For instance, it prioritizes contextual correction for documents related to relevant projects. The correction unit can also postpone contextual correction for less relevant inputs. For example, it postpones contextual correction for unrelated, everyday messages. Furthermore, the correction unit can adjust the order of contextual corrections in stages according to relevance. For instance, it can perform contextual corrections in order of relevance and postpone corrections in order of less relevance. This allows for efficient correction by adjusting the order of corrections based on relevance. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the correction unit can input the relevance of the inputs into a generative AI and have the generative AI adjust the order of corrections.

[0080] The service provider can estimate the user's emotions and adjust the display method of the results based on the estimated emotions. For example, if the user is stressed, the service provider can provide a simple and easy-to-understand display method. For example, the service provider can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on changes in facial expressions and provide a simple and easy-to-understand display method. The service provider can also provide a display method that includes detailed information if the user is relaxed. For example, the service provider can record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of the voice, calculate an emotion score, and provide a display method that includes detailed information. The service provider can also provide a concise display method if the user is in a hurry. For example, the service provider can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on fluctuations in heart rate and provide a concise display method. By adjusting the display method according to the user's emotions, more appropriate results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the service provider may be performed using a generative AI, or not using a generative AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0081] The service provider can select the optimal display method by referring to the user's past operation history when providing results. For example, the service provider may prioritize providing display methods that the user has preferred to use in the past. For example, the service provider may analyze the user's past operation history and prioritize providing display methods that the user has preferred to use in the past. The service provider can also predict and provide the optimal display method based on the user's past operation history. For example, the service provider may analyze the user's past operation history, predict and provide the optimal display method. The service provider can also provide similar display methods based on display methods that the user has used in the past. For example, the service provider may analyze the user's past operation history and provide similar display methods. In this way, the optimal display method can be provided by referring to past operation history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider may input the user's past operation history into AI and have AI select the optimal display method.

[0082] The service provider can select the optimal display method when providing results, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. For example, the service provider can refer to the user's device information and provide a display method that matches the smartphone's screen size. The service provider can also provide a display method optimized for a larger screen if the user is using a tablet. For example, the service provider can refer to the user's device information and provide a display method optimized for the tablet's screen size. The service provider can also provide a concise and highly visible display method if the user is using a smartwatch. For example, the service provider can refer to the user's device information and provide a display method that matches the smartwatch's screen size. In this way, the service provider can provide the optimal display method by taking device information into consideration. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into AI and have AI select the optimal display method.

[0083] The service provider can estimate the user's emotions and prioritize the results to be provided based on those emotions. For example, if the user is stressed, the service provider will prioritize providing results of high importance. For instance, the service provider can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on changes in facial expressions and prioritize providing results of high importance. The service provider can also provide all results equally if the user is relaxed. For example, the service provider can record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of the voice, calculate an emotion score, and provide all results equally. The service provider can also prioritize providing results of high urgency if the user is in a hurry. For example, the service provider can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on fluctuations in heart rate and prioritize providing results of high urgency. This allows the service provider to prioritize important results by determining the priority of results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the service provider may be performed using a generative AI, or not using a generative AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0084] The service provider can select the optimal display method when providing results, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. For example, the service provider can refer to the user's device information and provide a display method that matches the smartphone's screen size. The service provider can also provide a display method optimized for a larger screen if the user is using a tablet. For example, the service provider can refer to the user's device information and provide a display method optimized for the tablet's screen size. The service provider can also provide a concise and highly visible display method if the user is using a smartwatch. For example, the service provider can refer to the user's device information and provide a display method that matches the smartwatch's screen size. In this way, the service provider can provide the optimal display method by taking device information into consideration. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into AI and have AI select the optimal display method.

[0085] The service provider can provide multilingual results according to the user's language settings when providing results. For example, the service provider can automatically set the language of the results based on the language settings of the user's device. For example, the service provider can refer to the language settings of the user's device and automatically set the language of the results. The service provider can also provide a language switching function if the user uses multiple languages. For example, the service provider can provide a language switching function if the user uses multiple languages. The service provider can also provide results in a specific language if the user selects a specific language. For example, the service provider can provide results in a specific language if the user selects a specific language. This improves user convenience by providing multilingual results according to language settings. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's language settings into AI and have AI perform the task of providing multilingual results.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The reception desk can analyze the user's past input history when receiving user input and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the user has frequently used in the past (such as voice or text). The reception desk can also predict and suggest input methods that the user will use at specific times of day based on their past input history. For example, if a user prefers text input in the morning, it will prioritize suggesting text input during that time. Furthermore, the reception desk can suggest similar input methods based on content the user has previously entered. In this way, by analyzing past input history, the system can provide the most optimal input method.

[0088] The correction unit can estimate the user's emotions and adjust the expression of contextual corrections based on the estimated emotions. For example, if the user is stressed, it can perform contextual corrections using concise and clear language. If the user is relaxed, it can also perform contextual corrections that include detailed explanations. Furthermore, if the user is in a hurry, it can perform contextual corrections that get straight to the point. In this way, by adjusting the expression of contextual corrections according to the user's emotions, more appropriate corrections can be made.

[0089] The service provider can select the optimal display method when providing results, taking into account the user's device information. For example, if the user is using a smartphone, it can provide a display method that matches the screen size. If the user is using a tablet, it can also provide a display method optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible display method. In this way, the optimal display method can be provided by considering the device information.

[0090] The reception system can estimate the user's emotions and prioritize the inputs it receives based on those emotions. For example, if the user is stressed, it can postpone less important inputs and prioritize more important ones. If the user is relaxed, it can accept all inputs equally. Furthermore, if the user is in a hurry, it can prioritize urgent inputs. In this way, by prioritizing inputs according to the user's emotions, important inputs can be processed with priority.

[0091] The correction unit can adjust the level of detail of the correction based on the importance of the input during contextual correction. For example, it can perform detailed contextual correction for high-importance inputs, and simpler contextual correction for low-importance inputs. Furthermore, it can adjust the level of detail of the contextual correction in stages according to importance. This allows for efficient correction by adjusting the level of detail of the correction based on the importance of the input.

[0092] The service provider can estimate the user's emotions and adjust how the results are displayed based on those emotions. For example, if the user is stressed, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the essentials can be provided. By adjusting the display method according to the user's emotions, more appropriate results can be provided.

[0093] The reception system can prioritize inputs based on the user's geographical location when receiving input. For example, if a user is in a specific region, it can prioritize inputs related to that region. If a user is on the move, it can also prioritize inputs related to their current location. Furthermore, if a user is in a specific location, it can prioritize inputs related to that location. This improves user convenience by prioritizing highly relevant inputs based on geographical location.

[0094] The correction unit can estimate the user's emotions and adjust the length of the correction based on the estimated emotions. For example, if the user is stressed, it will provide a short, concise correction. If the user is relaxed, it can provide a more detailed correction. Furthermore, if the user is in a hurry, the length of the correction can be adjusted to allow for quick understanding. By adjusting the length of the correction according to the user's emotions, more appropriate corrections can be provided.

[0095] The service provider can provide multilingual results according to the user's language settings. For example, it can automatically set the language of the results based on the language settings of the user's device. It can also provide a language switching function if the user uses multiple languages. Furthermore, if the user selects a specific language, the results can be provided in that language. This improves user convenience by providing multilingual results according to language settings.

[0096] The delivery unit can estimate the user's emotions and determine the priority of the results to be delivered based on those estimated emotions. For example, if the user is stressed, it can prioritize delivering results of high importance. If the user is relaxed, it can deliver all results equally. Furthermore, if the user is in a hurry, it can prioritize delivering results of high urgency. In this way, by prioritizing results according to the user's emotions, it is possible to deliver important results first.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The reception desk receives input from the user. User input includes text input, voice input, and image input. For example, text input is received using a keyboard or touchscreen, voice input is converted to text using speech recognition technology via a microphone, and image input is extracted as text information using image recognition technology via a camera or scanner. Step 2: The correction unit analyzes the input received by the reception unit using a generation AI and performs contextual correction. Contextual correction includes grammatical correction, semantic analysis, and typographical error correction. For example, grammatical correction is performed using a text generation AI (LLM), the context is understood through semantic analysis, and typographical errors are corrected. Step 3: The provider unit provides the user with the corrected results from the correction unit. The provider unit provides the corrected results in text format, report format, graphical display, etc. For example, it may be displayed to the user through a web application or mobile application.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0101] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0102] Each of the multiple elements described above, including the reception unit, correction unit, and provision unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit can receive input from the user using the reception device 38 of the smart device 14. The correction unit can perform contextual correction using generated AI by the specific processing unit 290 of the data processing unit 12. The provision unit can provide the corrected result to the user using the output device 40 of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0109] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0110] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0111] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0112] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0113] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements described above, including the reception unit, correction unit, and provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit can receive voice input from the user using the microphone 238 of the smart glasses 214. The correction unit can perform contextual correction using generated AI by the specific processing unit 290 of the data processing unit 12. The provision unit can provide the corrected result to the user using the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0119] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0120] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0122] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0125] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0126] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0127] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0128] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0129] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the reception unit, correction unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit can receive voice input from the user using the microphone 238 of the headset terminal 314. The correction unit can perform contextual correction using generated AI by the specific processing unit 290 of the data processing unit 12. The provision unit can provide the corrected results to the user using the display 343 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0143] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0144] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0145] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0146] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0148] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0150] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the reception unit, correction unit, and provision unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the reception unit can receive voice input from the user using the microphone 238 of the robot 414. The correction unit can perform contextual correction using generated AI by the specific processing unit 290 of the data processing unit 12. The provision unit can provide the corrected result to the user using the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0152] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0154] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0155] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0156] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0160] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0161] 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.

[0162] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0163] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0164] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0165] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0167] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0168] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0169] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0170] (Note 1) A reception area that receives input from users, A correction unit analyzes the input received by the aforementioned reception unit and performs contextual correction, The system includes a providing unit that provides the corrected result from the correction unit. A system characterized by the following features. (Note 2) The correction unit, Contextual correction is performed using generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 3) The correction unit, Perform general document proofreading using LLM. The system described in Appendix 1, characterized by the features described herein. (Note 4) The correction unit, Analyze internal company data to obtain background information. The system described in Appendix 1, characterized by the features described herein. (Note 5) The correction unit, Contextual information is supplemented based on reference materials such as approval documents, meeting minutes, and email and chat histories of those involved. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Provide the corrected results to the user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past input history to select the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving input, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and determines the priority of input to accept based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving input, the system prioritizes accepting inputs that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving input, the system analyzes the user's social media activity and accepts relevant input. The system described in Appendix 1, characterized by the features described herein. (Note 13) The correction unit, It estimates the user's emotions and adjusts the expression of contextual correction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The correction unit, During contextual correction, adjust the level of detail of the correction based on the importance of the input. The system described in Appendix 1, characterized by the features described herein. (Note 15) The correction unit, During contextual correction, different correction algorithms are applied depending on the input category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The correction unit, The system estimates the user's emotions and adjusts the length of the correction based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The correction unit, During contextual correction, the priority of corrections is determined based on when the input was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The correction unit, During contextual correction, the order of corrections is adjusted based on the relevance of the inputs. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing results, the system selects the optimal display method by referring to the user's past operation history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing results, the optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the results to provide based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing results, the optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing results, we will provide multilingual results according to the user's language settings. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that receives input from users, A correction unit analyzes the input received by the aforementioned reception unit and performs contextual correction, The system includes a providing unit that provides the corrected result from the correction unit. A system characterized by the following features.

2. The correction unit, Contextual correction is performed using generative AI. The system according to feature 1.

3. The correction unit, Perform general document proofreading using LLM. The system according to feature 1.

4. The correction unit, Analyze internal company data to obtain background information. The system according to feature 1.

5. The correction unit, Contextual information is supplemented based on reference materials such as approval documents, meeting minutes, and email and chat histories of those involved. The system according to feature 1.

6. The aforementioned supply unit is, Provide the corrected results to the user. The system according to feature 1.

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

8. The aforementioned reception unit is Analyze the user's past input history to select the optimal reception method. The system according to feature 1.

Images