System

Abstract

To provide a system that reduces time and labor required for creating replies to received emails.SOLUTION: A system according to the embodiment comprises an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the contents of received emails. The generation unit generates a reply text based on the contents analyzed by the analysis unit. The presentation unit presents the reply text generated by the generation unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have the drawback that creating a reply to an incoming email takes a lot of time and effort.

[0005] The system according to the embodiment aims to reduce the time and effort required to write a reply to an incoming email. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the content of the received email. The generation unit generates a reply message based on the content analyzed by the analysis unit. The presentation unit presents the reply message generated by the generation unit to a user. Effect of the Invention

[0007] The system according to the embodiment can reduce the time and effort required to write a reply to an incoming email. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The email reply support system according to the embodiment of the present invention is a system that automatically creates an email reply using a generation AI. In this system, a user inputs an email received by the user into the system, and the generation AI analyzes the contents of the received email and generates an appropriate reply. The generated reply is presented to the user by push notification. The user can check the generated reply and send it as is or modify it as necessary. Once the modification is complete, the user sends the reply. For example, if a user receives an email saying "Please adjust the meeting schedule," the generation AI generates a reply saying "We propose the following candidate dates for the meeting schedule." The user can send this reply as is or add candidate dates and then send it. This system allows users to significantly reduce the time it takes to reply to emails. In addition, since the generation AI generates appropriate reply sentences, users can easily create high-quality reply sentences. As a result, the email reply support system can significantly reduce the time and effort required to reply to emails.

[0029] The email reply support system according to the embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the contents of the received email. The analysis unit analyzes the contents of the received email using, for example, natural language processing technology. The analysis unit can also extract important information of the received email using keyword extraction technology. The analysis unit can also analyze the emotional nuances of the received email using emotion analysis technology. The generation unit generates a reply text based on the contents analyzed by the analysis unit. The generation unit generates a reply text using, for example, template-based generation technology. The generation unit can also generate a reply text according to the contents of the received email using a machine learning model. The generation unit can also generate a reply text by referring to past email history or a specific template. The presentation unit presents the reply text generated by the generation unit to the user. The presentation unit presents the reply text through, for example, a user interface. The presentation unit can also notify the user of the reply text using push notification. The presentation unit can also present the generated reply text by push notification. As a result, the email reply support system of the embodiment can significantly reduce the time and effort required to reply to an email by analyzing the contents of the received email, generating an appropriate reply message, and presenting it to the user.

[0030] The analysis unit analyzes the contents of the received email. The analysis unit analyzes the contents of the received email, for example, using natural language processing technology. Specifically, the analysis unit uses natural language processing technology to analyze the grammatical structure of the email body and identify grammatical elements such as the subject, predicate, and object. Furthermore, the analysis unit can also extract important information from the received email using keyword extraction technology. For example, specific keywords and phrases are extracted from the email body and their importance is evaluated. This allows the subject and important points of the email to be quickly grasped. The analysis unit can also analyze the emotional nuances of the received email using emotion analysis technology. The emotion analysis technology evaluates the emotional tone of words and phrases in the email body and classifies them into emotion categories such as positive, negative, and neutral. This allows the emotional state of the email sender to be understood and basic information for generating an appropriate reply text to be provided. The analysis unit combines these technologies to analyze the contents of the received email from various angles and provides detailed information for generating a reply text. Furthermore, the analysis unit can utilize past email data as learning data to improve the analysis accuracy. For example, the analysis unit can learn specific patterns and trends based on the results of analyzing past emails and reflect them in the analysis of new emails. This allows the analysis unit to analyze the contents of received emails with high accuracy and provide basic information for generating appropriate reply messages.

[0031] The generation unit generates a reply message based on the contents analyzed by the analysis unit. The generation unit generates a reply message using, for example, a template-based generation technology. Specifically, based on a reply template prepared in advance, an appropriate template according to the analysis result is selected, and a reply message is generated by embedding necessary information. This allows the reply message to be created quickly and efficiently. Furthermore, the generation unit can also generate a reply message according to the contents of the received email using a machine learning model. The machine learning model has the ability to learn a large amount of email data and generate a reply message that is optimal for the contents of the received email. For example, a generation model using a neural network can be used to generate a natural reply message that takes into account the context and emotions of the received email. The generation unit can also generate a reply message by referring to past email history and specific templates. By referring to past email history, past replies in similar situations can be used as a reference to generate a more appropriate reply message. Furthermore, by referring to a specific template, a standard reply message according to a specific task or situation can be quickly generated. The generation unit combines these technologies to generate a reply message that is optimal for the contents of the received email, thereby significantly streamlining the user's email reply work.

[0032] The presentation unit presents the reply text generated by the generation unit to the user. The presentation unit presents the reply text through, for example, a user interface. Specifically, the reply text is displayed in the email client or dedicated application used by the user, so that the user can confirm and edit it. This allows the user to easily confirm the generated reply text and make corrections as necessary. Furthermore, the presentation unit can also notify the user of the reply text using a push notification. For example, a push notification is sent to a smartphone or tablet to immediately notify the user of the generated reply text. This allows the user to quickly confirm the reply text and perform the reply work. The presentation unit can also present the generated reply text by a push notification. For example, when a reply text to an important email is generated, the user can be immediately notified by using a push notification to prompt a quick response. The presentation unit combines these means to effectively present the generated reply text to the user and greatly improve the efficiency of email reply work. Furthermore, the presentation unit can collect user feedback and provide feedback to the generation unit and analysis unit, thereby continuously improving the accuracy and efficiency of the entire system. For example, by analyzing the corrections made by the user to the generated reply text and using them as learning data for the generation unit, it is possible to generate more natural and appropriate reply texts. This allows the presentation unit to present reply texts to the user quickly and effectively, greatly improving the efficiency of email reply work.

[0033] The generation unit can generate a reply by referring to a past email history or a specific template. The generation unit adjusts the tone and style of the reply based on the content of emails sent in the past, for example. The generation unit can also generate a reply in accordance with a format by referring to a specific template. The generation unit can also extract frequently used phrases and expressions from the past email history and reflect them in the reply. As a result, the accuracy of the reply is improved by referring to the past email history and the specific template. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the past email history and a specific template into the generation AI and cause the generation AI to generate a reply.

[0034] The presentation unit can present the generated reply text by push notification. The presentation unit, for example, presents the generated reply text to the user by push notification. The presentation unit adjusts the timing and format of the notification so that the user can quickly check the reply text. The presentation unit presents the generated reply text by push notification so that the user can quickly check the reply text. As a result, by presenting the generated reply text by push notification, the user can quickly check the reply text. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the generated reply text to a generation AI and cause the generation AI to generate a push notification.

[0035] The email reply support system includes a correction unit for allowing a user to correct a reply text. The correction unit provides a function for the user to correct a generated reply text. The correction unit provides, for example, a manual correction function, allowing the user to freely correct the reply text. The correction unit can also provide a suggestion-based correction function, suggesting corrections to the user. The correction unit provides, for example, a grammar correction function, correcting grammatical errors in the reply text. The correction unit can also provide an expression improvement function, correcting the expression of the reply text to a more appropriate one. This allows the user to correct the reply text to send a more appropriate reply text. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input the generated reply text to a generation AI and cause the generation AI to execute the suggested corrections.

[0036] The analysis unit can improve the accuracy of the analysis by referring to the past email history of the sender of the received email. The analysis unit can adjust the tone and style of the reply text based on the contents of emails sent by the sender in the past, for example. The analysis unit can also extract specific keywords and phrases from the sender's past email history and reflect them in the analysis. The analysis unit can also analyze the reply patterns of the sender's past emails and generate optimal reply text. This improves the accuracy of the analysis by referring to the sender's past email history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the sender's past email history to the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0037] The analysis unit can apply different analysis algorithms depending on the contents of the received email. For example, in the case of a business email, the analysis unit applies a formal analysis algorithm to generate an appropriate reply. In the case of a private email, the analysis unit can also apply a casual analysis algorithm to generate a friendly reply. In the case of an urgent email, the analysis unit can also apply an analysis algorithm that requires a quick response to generate a reply immediately. In this way, a more appropriate reply can be generated by applying an appropriate analysis algorithm depending on the contents of the received email. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the contents of the received email to the generation AI and cause the generation AI to apply different analysis algorithms.

[0038] The analysis unit can perform analysis based on the geographical location information of the sender when analyzing the received email. For example, when the sender is in a different time zone, the analysis unit performs analysis taking into account an appropriate reply time. The analysis unit can also perform analysis taking into account regional expressions and culture based on the geographical location of the sender. The analysis unit can also reflect related geographical information in the analysis based on the location information of the sender. This makes it possible to generate a more appropriate reply text by taking into account the geographical location information of the sender. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the geographical location information of the sender to the generation AI and cause the generation AI to perform improvement of the accuracy of the analysis.

[0039] The analysis unit can analyze the sender's social media activity and obtain related information when analyzing the received email. The analysis unit can, for example, analyze the sender's social media posts and obtain information related to the content of the email. The analysis unit can also adjust the tone and style of the reply based on the sender's social media activity. The analysis unit can also generate an appropriate reply by reflecting the sender's social media interests in the analysis. In this way, a more appropriate reply can be generated by analyzing the sender's social media activity. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input the sender's social media activity to the generation AI and cause the generation AI to obtain related information.

[0040] When generating a reply text, the generation unit can improve the accuracy of generation by referring to past email history and a specific template. The generation unit adjusts the tone and style of the reply text based on the content of emails sent in the past, for example. The generation unit can also generate a reply text that conforms to a format by referring to a specific template. The generation unit can also extract frequently used phrases and expressions from the past email history and reflect them in the reply text. As a result, the accuracy of the reply text is improved by referring to the past email history and a specific template. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the past email history and a specific template into the generation AI and cause the generation AI to generate a reply text.

[0041] The generation unit can apply different generation algorithms depending on the category of the received email when generating a reply message. For example, in the case of a business email, the generation unit applies a formal generation algorithm to generate an appropriate reply message. In the case of a private email, the generation unit can also apply a casual generation algorithm to generate a friendly reply message. In the case of an urgent email, the generation unit can also apply a generation algorithm that requires a quick response to generate a reply message immediately. In this way, a more appropriate reply message can be generated by applying an appropriate generation algorithm depending on the category of the received email. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of the received email to the generation AI and cause the generation AI to apply different generation algorithms.

[0042] The generation unit can determine the priority of the reply text based on the time of sending the received email when generating the reply text. For example, if the received email is urgent, the generation unit quickly generates a reply text and presents it preferentially. If the received email is sent outside of normal business hours, the generation unit can also generate a reply text during the next business hours. If the received email is related to a specific event, the generation unit can also generate a reply text before the event. This allows for a prompt response to important emails by determining the priority of the reply text based on the time of sending the received email. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the time of sending the received email to the generation AI and cause the generation AI to determine the priority of the reply text.

[0043] The generation unit can adjust the order of the reply texts based on the relevance of the received emails when generating the reply texts. For example, when the received emails are related to an important project, the generation unit generates the reply texts with priority. When the received emails are related to daily work, the generation unit can also generate the reply texts in the normal order. When the received emails are private, the generation unit can also generate the reply texts later. In this way, by adjusting the order of the reply texts based on the relevance of the received emails, it is possible to deal with important emails with priority. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the relevance of the received emails to the generation AI and cause the generation AI to adjust the order of the reply texts.

[0044] The presentation unit can select the optimal presentation method by referring to the user's past operation history at the time of presentation. For example, the presentation unit preferentially provides a presentation method that the user has used in the past. The presentation unit can also select the most efficient presentation method from the user's past operation history. The presentation unit can also analyze the user's past operation history and present a reply message at an optimal timing. In this way, the optimal presentation method can be selected by referring to the user's past operation history. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input the user's past operation history to the generation AI and cause the generation AI to select the optimal presentation method.

[0045] The presentation unit can adjust the level of detail of the presentation based on the importance of the reply message when presenting the reply message. For example, in the case of an important reply message, the presentation unit provides a presentation method including a detailed explanation. In the case of a normal reply message, the presentation unit can also provide a concise presentation method. In the case of an urgent reply message, the presentation unit can also provide a presentation method that allows for quick confirmation. In this way, by adjusting the level of detail of the presentation based on the importance of the reply message, it is possible to present an important reply message in detail. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the importance of the reply message to the generation AI and cause the generation AI to adjust the level of detail of the presentation.

[0046] The presentation unit can select the optimal display method in consideration of the device information of the user at the time of presentation. For example, when the user is using a smartphone, the presentation unit provides a display method that matches the screen size. When the user is using a tablet, the presentation unit can also provide a display method optimized for a large screen. When the user is using a smartwatch, the presentation unit can also provide a display method that is simple and highly visible. This allows the optimal display method to be selected by considering the device information of the user. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the device information of the user to the generation AI and cause the generation AI to select the optimal display method.

[0047] The presentation unit can present the reply message at the optimal timing by referring to the user's schedule information at the time of presentation. The presentation unit presents the reply message at the optimal timing, for example, based on the user's schedule. The presentation unit can also present the reply message before an important appointment based on the user's schedule information. The presentation unit can also push the reply message at the optimal timing based on the user's schedule information. This makes it possible to present the reply message at the optimal timing by referring to the user's schedule information. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the user's schedule information to the generation AI and cause the generation AI to execute presentation at the optimal timing.

[0048] The correction unit can suggest an optimal correction method by referring to the past correction history at the time of correction. The correction unit suggests an optimal correction method based on, for example, the correction content made in the past. The correction unit can also identify a frequently corrected part from the past correction history and present a correction proposal in advance. The correction unit can also analyze past correction patterns and suggest an efficient correction method. In this way, the optimal correction method can be suggested by referring to the past correction history. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input the past correction history to the generation AI and cause the generation AI to execute a suggestion of an optimal correction method.

[0049] The correction unit can apply different correction algorithms depending on the contents of the received email when correcting. For example, in the case of a business email, the correction unit applies a formal correction algorithm and presents an appropriate correction suggestion. In the case of a private email, the correction unit can also apply a casual correction algorithm and present a friendly correction suggestion. In the case of an urgent email, the correction unit can also apply a correction algorithm that requires a quick response and present a correction suggestion immediately. This allows more appropriate correction to be made by applying an appropriate correction algorithm depending on the contents of the received email. Part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI or may be performed without using AI. For example, the correction unit can input the contents of the received email to the generation AI and cause the generation AI to apply different correction algorithms.

[0050] The correction unit can propose an optimal correction method by taking into account the geographical location information of the user at the time of correction. For example, when the user is in a different time zone, the correction unit proposes a correction proposal by taking into account an appropriate correction time. The correction unit can also propose a correction proposal that takes into account regional expressions and culture based on the geographical location of the user. The correction unit can also reflect related geographical information in the correction based on the user's location information. In this way, the optimal correction method can be proposed by taking into account the user's geographical location information. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI or may be performed without using AI. For example, the correction unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a proposal of an optimal correction method.

[0051] The correction unit can analyze the user's social media activity and suggest a means of correction at the time of correction. For example, the correction unit analyzes the user's social media posts and suggests a correction related to the content of the email. The correction unit can also suggest a correction suggestion for adjusting the tone or style of the reply based on the user's social media activity. The correction unit can also reflect the user's interests on social media in the correction and suggest an appropriate correction suggestion. In this way, a more appropriate means of correction can be suggested by analyzing the user's social media activity. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI or may be performed without using AI. For example, the correction unit can input the user's social media activity to the generation AI and cause the generation AI to execute a suggestion of a means of correction.

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

[0053] When analyzing the contents of a received email, the analysis unit can adjust the analysis method based on the occupation or position of the email sender. For example, if the sender is a superior, a more formal analysis can be performed to generate a reply message that includes appropriate honorific language. If the sender is a colleague, a more casual analysis can be performed to generate a friendly reply message. If the sender is a customer, a polite and detailed analysis can be performed to generate a reply message that increases customer satisfaction. In this way, by adjusting the analysis method according to the sender's occupation or position, a more appropriate reply message can be generated.

[0054] When generating a reply, the generator can adjust the tone and content of the reply taking into account the user's past reply speed. For example, if the user has replied quickly in the past, the generator can generate a concise and quick reply. If the user has replied slowly in the past, the generator can also generate a detailed and polite reply. If the user tends to reply at a particular time of day, the generator can also generate a reply that matches that time of day. This allows the generator to generate a more appropriate reply by adjusting the reply based on the user's past reply speed.

[0055] When presenting the generated reply message, the presentation unit can adjust the presentation method taking into account the user's current activity status. For example, when the user is in a meeting, the reply message is presented using a quiet notification method. When the user is on the move, a simple and highly visible notification method can be used. When the user is doing desk work, a notification method including a detailed explanation can be used. In this way, the presentation method can be adjusted according to the user's current activity status, so that the reply message can be presented in a more appropriate manner.

[0056] When the user corrects a reply message, the correction unit can display the correction history in real time and visualize the correction process. For example, each time the user makes a correction, the correction content is displayed as a history. The user can make the current correction while referring to the past correction content. The correction unit can also suggest the optimal correction method based on the correction history. This allows the user to make corrections more efficiently by visualizing the correction process.

[0057] When analyzing the contents of a received email, the analysis unit can adjust the analysis method by taking into account the cultural background of the email sender. For example, if the sender is from a different cultural sphere, a reply message is generated using expressions and tones appropriate for that culture. If the sender has a specific religious background, a reply message can be generated that includes content that takes that religion into consideration. If the sender uses a dialect from a specific region, a reply message that corresponds to that dialect can be generated. In this way, a more appropriate reply message can be generated by adjusting the analysis method according to the sender's cultural background.

[0058] When analyzing the contents of a received email, the analysis unit can adjust the analysis method by taking into account the past behavioral patterns of the email sender. For example, if the sender has requested a quick reply in the past, a reply message can be generated quickly. If the sender has requested a detailed explanation in the past, a detailed analysis can be performed to generate a polite reply message. If the sender has preferred replies in a specific format in the past, a reply message that matches that format can be generated. In this way, a more appropriate reply message can be generated by adjusting the analysis method based on the sender's past behavioral patterns.

[0059] When analyzing the content of an incoming email, the analysis unit can analyze the social media activity of the email sender to obtain related information. For example, it can analyze the sender's social media posts to obtain information related to the content of the email. It can also adjust the tone and style of the reply based on the sender's social media activity. It can also generate an appropriate reply by reflecting the sender's social media interests in the analysis. This makes it possible to generate a more appropriate reply by analyzing the sender's social media activity.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The analysis unit analyzes the contents of the received email. The analysis unit can analyze the contents of the received email using natural language processing technology and extract important information using keyword extraction technology. It can also analyze the emotional nuances of the received email using sentiment analysis technology. Step 2: The generator generates a reply based on the content analyzed by the analyzer. The generator can generate a reply using template-based generation techniques or machine learning models, and can also refer to past email history or specific templates. Step 3: The presentation unit presents the reply text generated by the generation unit to the user. The presentation unit presents the reply text through a user interface, and can also notify the user of the reply text by using a push notification.

[0062] (Example 2) The email reply support system according to the embodiment of the present invention is a system that automatically creates an email reply using a generation AI. In this system, a user inputs an email received by the user into the system, and the generation AI analyzes the contents of the received email and generates an appropriate reply. The generated reply is presented to the user by push notification. The user can check the generated reply and send it as is or modify it as necessary. Once the modification is complete, the user sends the reply. For example, if a user receives an email saying "Please adjust the meeting schedule," the generation AI generates a reply saying "We propose the following candidate dates for the meeting schedule." The user can send this reply as is or add candidate dates and then send it. This system allows users to significantly reduce the time it takes to reply to emails. In addition, since the generation AI generates appropriate reply sentences, users can easily create high-quality reply sentences. As a result, the email reply support system can significantly reduce the time and effort required to reply to emails.

[0063] The email reply support system according to the embodiment includes an analysis unit, a generation unit, and a presentation unit. The analysis unit analyzes the contents of the received email. The analysis unit analyzes the contents of the received email using, for example, natural language processing technology. The analysis unit can also extract important information of the received email using keyword extraction technology. The analysis unit can also analyze the emotional nuances of the received email using emotion analysis technology. The generation unit generates a reply text based on the contents analyzed by the analysis unit. The generation unit generates a reply text using, for example, template-based generation technology. The generation unit can also generate a reply text according to the contents of the received email using a machine learning model. The generation unit can also generate a reply text by referring to past email history or a specific template. The presentation unit presents the reply text generated by the generation unit to the user. The presentation unit presents the reply text through, for example, a user interface. The presentation unit can also notify the user of the reply text using push notification. The presentation unit can also present the generated reply text by push notification. As a result, the email reply support system of the embodiment can significantly reduce the time and effort required to reply to an email by analyzing the contents of the received email, generating an appropriate reply message, and presenting it to the user.

[0064] The analysis unit analyzes the contents of the received email. The analysis unit analyzes the contents of the received email, for example, using natural language processing technology. Specifically, the analysis unit uses natural language processing technology to analyze the grammatical structure of the email body and identify grammatical elements such as the subject, predicate, and object. Furthermore, the analysis unit can also extract important information from the received email using keyword extraction technology. For example, specific keywords and phrases are extracted from the email body and their importance is evaluated. This allows the subject and important points of the email to be quickly grasped. The analysis unit can also analyze the emotional nuances of the received email using emotion analysis technology. The emotion analysis technology evaluates the emotional tone of words and phrases in the email body and classifies them into emotion categories such as positive, negative, and neutral. This allows the emotional state of the email sender to be understood and basic information for generating an appropriate reply text to be provided. The analysis unit combines these technologies to analyze the contents of the received email from various angles and provides detailed information for generating a reply text. Furthermore, the analysis unit can utilize past email data as learning data to improve the analysis accuracy. For example, the analysis unit can learn specific patterns and trends based on the results of analyzing past emails and reflect them in the analysis of new emails. This allows the analysis unit to analyze the contents of received emails with high accuracy and provide basic information for generating appropriate reply messages.

[0065] The generation unit generates a reply message based on the contents analyzed by the analysis unit. The generation unit generates a reply message using, for example, a template-based generation technology. Specifically, based on a reply template prepared in advance, an appropriate template according to the analysis result is selected, and a reply message is generated by embedding necessary information. This allows the reply message to be created quickly and efficiently. Furthermore, the generation unit can also generate a reply message according to the contents of the received email using a machine learning model. The machine learning model has the ability to learn a large amount of email data and generate a reply message that is optimal for the contents of the received email. For example, a generation model using a neural network can be used to generate a natural reply message that takes into account the context and emotions of the received email. The generation unit can also generate a reply message by referring to past email history and specific templates. By referring to past email history, past replies in similar situations can be used as a reference to generate a more appropriate reply message. Furthermore, by referring to a specific template, a standard reply message according to a specific task or situation can be quickly generated. The generation unit combines these technologies to generate a reply message that is optimal for the contents of the received email, thereby significantly streamlining the user's email reply work.

[0066] The presentation unit presents the reply text generated by the generation unit to the user. The presentation unit presents the reply text through, for example, a user interface. Specifically, the reply text is displayed in the email client or dedicated application used by the user, so that the user can confirm and edit it. This allows the user to easily confirm the generated reply text and make corrections as necessary. Furthermore, the presentation unit can also notify the user of the reply text using a push notification. For example, a push notification is sent to a smartphone or tablet to immediately notify the user of the generated reply text. This allows the user to quickly confirm the reply text and perform the reply work. The presentation unit can also present the generated reply text by a push notification. For example, when a reply text to an important email is generated, the user can be immediately notified by using a push notification to prompt a quick response. The presentation unit combines these means to effectively present the generated reply text to the user and greatly improve the efficiency of email reply work. Furthermore, the presentation unit can collect user feedback and provide feedback to the generation unit and analysis unit, thereby continuously improving the accuracy and efficiency of the entire system. For example, by analyzing the corrections made by the user to the generated reply text and using them as learning data for the generation unit, it is possible to generate more natural and appropriate reply texts. This allows the presentation unit to present reply texts to the user quickly and effectively, greatly improving the efficiency of email reply work.

[0067] The generation unit can generate a reply by referring to a past email history or a specific template. The generation unit adjusts the tone and style of the reply based on the content of emails sent in the past, for example. The generation unit can also generate a reply in accordance with a format by referring to a specific template. The generation unit can also extract frequently used phrases and expressions from the past email history and reflect them in the reply. As a result, the accuracy of the reply is improved by referring to the past email history and the specific template. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the past email history and a specific template into the generation AI and cause the generation AI to generate a reply.

[0068] The presentation unit can present the generated reply text by push notification. The presentation unit, for example, presents the generated reply text to the user by push notification. The presentation unit adjusts the timing and format of the notification so that the user can quickly check the reply text. The presentation unit presents the generated reply text by push notification so that the user can quickly check the reply text. As a result, by presenting the generated reply text by push notification, the user can quickly check the reply text. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the generated reply text to a generation AI and cause the generation AI to generate a push notification.

[0069] The email reply support system includes a correction unit for allowing a user to correct a reply text. The correction unit provides a function for the user to correct a generated reply text. The correction unit provides, for example, a manual correction function, allowing the user to freely correct the reply text. The correction unit can also provide a suggestion-based correction function, suggesting corrections to the user. The correction unit provides, for example, a grammar correction function, correcting grammatical errors in the reply text. The correction unit can also provide an expression improvement function, correcting the expression of the reply text to a more appropriate one. This allows the user to correct the reply text to send a more appropriate reply text. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input the generated reply text to a generation AI and cause the generation AI to execute the suggested corrections.

[0070] The analysis unit can estimate the user's emotion and adjust the analysis method of the received email based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the analysis method based on the estimated emotion. When the user is stressed, the analysis unit performs analysis quickly and generates a concise reply. When the user is relaxed, the analysis unit can also perform detailed analysis and generate a polite reply. When the user is in a hurry, the analysis unit can also perform analysis focusing on important points and generate a reply in a short time. This makes it possible to generate a more appropriate reply by adjusting the analysis method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0071] The analysis unit can improve the accuracy of the analysis by referring to the past email history of the sender of the received email. The analysis unit can adjust the tone and style of the reply text based on the contents of emails sent by the sender in the past, for example. The analysis unit can also extract specific keywords and phrases from the sender's past email history and reflect them in the analysis. The analysis unit can also analyze the reply patterns of the sender's past emails and generate optimal reply text. This improves the accuracy of the analysis by referring to the sender's past email history. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the sender's past email history to the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0072] The analysis unit can apply different analysis algorithms depending on the contents of the received email. For example, in the case of a business email, the analysis unit applies a formal analysis algorithm to generate an appropriate reply. In the case of a private email, the analysis unit can also apply a casual analysis algorithm to generate a friendly reply. In the case of an urgent email, the analysis unit can also apply an analysis algorithm that requires a quick response to generate a reply immediately. In this way, a more appropriate reply can be generated by applying an appropriate analysis algorithm depending on the contents of the received email. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the contents of the received email to the generation AI and cause the generation AI to apply different analysis algorithms.

[0073] The analysis unit can estimate the user's emotion and determine the priority of the analysis results based on the estimated user's emotion. For example, when the user is feeling stressed, the analysis unit prioritizes the analysis of important emails. When the user is relaxed, the analysis unit can also analyze all emails equally. When the user is in a hurry, the analysis unit can also prioritize the analysis of emails with high urgency. In this way, by determining the priority of the analysis results according to the user's emotion, important emails can be analyzed preferentially. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0074] The analysis unit can perform analysis based on the geographical location information of the sender when analyzing the received email. For example, when the sender is in a different time zone, the analysis unit performs analysis taking into account an appropriate reply time. The analysis unit can also perform analysis taking into account regional expressions and culture based on the geographical location of the sender. The analysis unit can also reflect related geographical information in the analysis based on the location information of the sender. This makes it possible to generate a more appropriate reply text by taking into account the geographical location information of the sender. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the geographical location information of the sender to the generation AI and cause the generation AI to perform improvement of the accuracy of the analysis.

[0075] The analysis unit can analyze the sender's social media activity and obtain related information when analyzing the received email. The analysis unit can, for example, analyze the sender's social media posts and obtain information related to the content of the email. The analysis unit can also adjust the tone and style of the reply based on the sender's social media activity. The analysis unit can also generate an appropriate reply by reflecting the sender's social media interests in the analysis. In this way, a more appropriate reply can be generated by analyzing the sender's social media activity. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using AI or can be performed without using AI. For example, the analysis unit can input the sender's social media activity to the generation AI and cause the generation AI to obtain related information.

[0076] The generation unit can estimate the user's emotion and adjust the expression method of the reply sentence based on the estimated user's emotion. For example, when the user is relaxed, the generation unit generates a polite and detailed reply sentence. When the user is in a hurry, the generation unit can also generate a concise and to the point reply sentence. When the user is stressed, the generation unit can also generate a reply sentence in a gentle tone. This allows a more appropriate reply sentence to be generated by adjusting the expression method of the reply sentence according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method.

[0077] When generating a reply text, the generation unit can improve the accuracy of generation by referring to past email history and a specific template. The generation unit adjusts the tone and style of the reply text based on the content of emails sent in the past, for example. The generation unit can also generate a reply text that conforms to a format by referring to a specific template. The generation unit can also extract frequently used phrases and expressions from the past email history and reflect them in the reply text. As a result, the accuracy of the reply text is improved by referring to the past email history and a specific template. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the past email history and a specific template into the generation AI and cause the generation AI to generate a reply text.

[0078] The generation unit can apply different generation algorithms depending on the category of the received email when generating a reply message. For example, in the case of a business email, the generation unit applies a formal generation algorithm to generate an appropriate reply message. In the case of a private email, the generation unit can also apply a casual generation algorithm to generate a friendly reply message. In the case of an urgent email, the generation unit can also apply a generation algorithm that requires a quick response to generate a reply message immediately. In this way, a more appropriate reply message can be generated by applying an appropriate generation algorithm depending on the category of the received email. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of the received email to the generation AI and cause the generation AI to apply different generation algorithms.

[0079] The generation unit can estimate the user's emotion and adjust the length of the reply based on the estimated user's emotion. For example, when the user is relaxed, the generation unit generates a longer reply including a detailed explanation. When the user is in a hurry, the generation unit can also generate a short reply that is to the point. When the user is stressed, the generation unit can also generate a reply with a concise and gentle tone. This allows a more appropriate reply to be generated by adjusting the length of the reply according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the reply.

[0080] The generation unit can determine the priority of the reply text based on the time of sending the received email when generating the reply text. For example, if the received email is urgent, the generation unit quickly generates a reply text and presents it preferentially. If the received email is sent outside of normal business hours, the generation unit can also generate a reply text during the next business hours. If the received email is related to a specific event, the generation unit can also generate a reply text before the event. This allows for a prompt response to important emails by determining the priority of the reply text based on the time of sending the received email. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the time of sending the received email to the generation AI and cause the generation AI to determine the priority of the reply text.

[0081] The generation unit can adjust the order of the reply texts based on the relevance of the received emails when generating the reply texts. For example, when the received emails are related to an important project, the generation unit generates the reply texts with priority. When the received emails are related to daily work, the generation unit can also generate the reply texts in the normal order. When the received emails are private, the generation unit can also generate the reply texts later. In this way, by adjusting the order of the reply texts based on the relevance of the received emails, it is possible to deal with important emails with priority. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the relevance of the received emails to the generation AI and cause the generation AI to adjust the order of the reply texts.

[0082] The presentation unit can estimate the user's emotion and adjust the presentation method of the reply sentence based on the estimated emotion of the user. For example, when the user is relaxed, the presentation unit provides a presentation method including a detailed explanation. When the user is in a hurry, the presentation unit can also provide a concise presentation method that focuses on the main points. When the user is stressed, the presentation unit can also present the reply sentence in a gentle tone. This allows the reply sentence to be presented in a more appropriate manner by adjusting the presentation method of the reply sentence according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the presentation method.

[0083] The presentation unit can select the optimal presentation method by referring to the user's past operation history at the time of presentation. For example, the presentation unit preferentially provides a presentation method that the user has used in the past. The presentation unit can also select the most efficient presentation method from the user's past operation history. The presentation unit can also analyze the user's past operation history and present a reply message at an optimal timing. In this way, the optimal presentation method can be selected by referring to the user's past operation history. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input the user's past operation history to the generation AI and cause the generation AI to select the optimal presentation method.

[0084] The presentation unit can adjust the level of detail of the presentation based on the importance of the reply message when presenting the reply message. For example, in the case of an important reply message, the presentation unit provides a presentation method including a detailed explanation. In the case of a normal reply message, the presentation unit can also provide a concise presentation method. In the case of an urgent reply message, the presentation unit can also provide a presentation method that allows for quick confirmation. In this way, by adjusting the level of detail of the presentation based on the importance of the reply message, it is possible to present an important reply message in detail. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the importance of the reply message to the generation AI and cause the generation AI to adjust the level of detail of the presentation.

[0085] The presentation unit can estimate the user's emotion and adjust the display order of the reply sentences based on the estimated user's emotion. For example, when the user is relaxed, the presentation unit provides a display order including a detailed explanation. When the user is in a hurry, the presentation unit can also provide a display order that is concise and to the point. When the user is stressed, the presentation unit can also display the reply sentences in a gentle tone. This allows important reply sentences to be preferentially displayed by adjusting the display order of the reply sentences according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order.

[0086] The presentation unit can select the optimal display method in consideration of the device information of the user at the time of presentation. For example, when the user is using a smartphone, the presentation unit provides a display method that matches the screen size. When the user is using a tablet, the presentation unit can also provide a display method optimized for a large screen. When the user is using a smartwatch, the presentation unit can also provide a display method that is simple and highly visible. This allows the optimal display method to be selected by considering the device information of the user. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the device information of the user to the generation AI and cause the generation AI to select the optimal display method.

[0087] The presentation unit can present the reply message at the optimal timing by referring to the user's schedule information at the time of presentation. The presentation unit presents the reply message at the optimal timing, for example, based on the user's schedule. The presentation unit can also present the reply message before an important appointment based on the user's schedule information. The presentation unit can also push the reply message at the optimal timing based on the user's schedule information. This makes it possible to present the reply message at the optimal timing by referring to the user's schedule information. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input the user's schedule information to the generation AI and cause the generation AI to execute presentation at the optimal timing.

[0088] The correction unit can estimate the user's emotion and provide correction advice based on the estimated user's emotion. For example, when the user is relaxed, the correction unit provides detailed correction advice. When the user is in a hurry, the correction unit can also provide concise and to the point correction advice. When the user is stressed, the correction unit can also provide correction advice in a gentle tone. This allows more appropriate correction by providing correction advice according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can input the user's emotion data to the generation AI and cause the generation AI to execute the correction advice.

[0089] The correction unit can suggest an optimal correction method by referring to the past correction history at the time of correction. The correction unit suggests an optimal correction method based on, for example, the correction content made in the past. The correction unit can also identify a frequently corrected part from the past correction history and present a correction proposal in advance. The correction unit can also analyze past correction patterns and suggest an efficient correction method. In this way, the optimal correction method can be suggested by referring to the past correction history. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI, or may be performed without using AI. For example, the correction unit can input the past correction history to the generation AI and cause the generation AI to execute a suggestion of an optimal correction method.

[0090] The correction unit can apply different correction algorithms depending on the contents of the received email when correcting. For example, in the case of a business email, the correction unit applies a formal correction algorithm and presents an appropriate correction suggestion. In the case of a private email, the correction unit can also apply a casual correction algorithm and present a friendly correction suggestion. In the case of an urgent email, the correction unit can also apply a correction algorithm that requires a quick response and present a correction suggestion immediately. This allows more appropriate correction to be made by applying an appropriate correction algorithm depending on the contents of the received email. Part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI or may be performed without using AI. For example, the correction unit can input the contents of the received email to the generation AI and cause the generation AI to apply different correction algorithms.

[0091] The correction unit can estimate the user's emotion and determine the priority of corrections based on the estimated user's emotion. For example, when the user is stressed, the correction unit prioritizes important corrections. When the user is relaxed, the correction unit can also perform all corrections equally. When the user is in a hurry, the correction unit can also prioritize corrections with high urgency. In this way, important corrections can be prioritized by determining the priority of corrections according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the correction unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the correction unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of corrections.

[0092] The correction unit can propose an optimal correction method by taking into account the geographical location information of the user at the time of correction. For example, when the user is in a different time zone, the correction unit proposes a correction proposal by taking into account an appropriate correction time. The correction unit can also propose a correction proposal that takes into account regional expressions and culture based on the geographical location of the user. The correction unit can also reflect related geographical information in the correction based on the user's location information. In this way, the optimal correction method can be proposed by taking into account the user's geographical location information. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI or may be performed without using AI. For example, the correction unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a proposal of an optimal correction method.

[0093] The correction unit can analyze the user's social media activity and suggest a means of correction at the time of correction. For example, the correction unit analyzes the user's social media posts and suggests a correction related to the content of the email. The correction unit can also suggest a correction suggestion for adjusting the tone or style of the reply based on the user's social media activity. The correction unit can also reflect the user's interests on social media in the correction and suggest an appropriate correction suggestion. In this way, a more appropriate means of correction can be suggested by analyzing the user's social media activity. A part or all of the above-mentioned processing in the correction unit may be performed, for example, using AI or may be performed without using AI. For example, the correction unit can input the user's social media activity to the generation AI and cause the generation AI to execute a suggestion of a means of correction.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] When analyzing the contents of a received email, the analysis unit can adjust the analysis method based on the occupation or position of the email sender. For example, if the sender is a superior, a more formal analysis can be performed to generate a reply message that includes appropriate honorific language. If the sender is a colleague, a more casual analysis can be performed to generate a friendly reply message. If the sender is a customer, a polite and detailed analysis can be performed to generate a reply message that increases customer satisfaction. In this way, by adjusting the analysis method according to the sender's occupation or position, a more appropriate reply message can be generated.

[0096] When generating a reply, the generator can adjust the tone and content of the reply taking into account the user's past reply speed. For example, if the user has replied quickly in the past, the generator can generate a concise and quick reply. If the user has replied slowly in the past, the generator can also generate a detailed and polite reply. If the user tends to reply at a particular time of day, the generator can also generate a reply that matches that time of day. This allows the generator to generate a more appropriate reply by adjusting the reply based on the user's past reply speed.

[0097] When presenting the generated reply message, the presentation unit can adjust the presentation method taking into account the user's current activity status. For example, when the user is in a meeting, the reply message is presented using a quiet notification method. When the user is on the move, a simple and highly visible notification method can be used. When the user is doing desk work, a notification method including a detailed explanation can be used. In this way, the presentation method can be adjusted according to the user's current activity status, so that the reply message can be presented in a more appropriate manner.

[0098] When the user corrects a reply message, the correction unit can display the correction history in real time and visualize the correction process. For example, each time the user makes a correction, the correction content is displayed as a history. The user can make the current correction while referring to the past correction content. The correction unit can also suggest the optimal correction method based on the correction history. This allows the user to make corrections more efficiently by visualizing the correction process.

[0099] The analysis unit can estimate the user's emotions and evaluate the importance of received emails based on the estimated user's emotions. For example, if the user is feeling stressed, important emails are analyzed first and a reply message is generated quickly. If the user is relaxed, all emails can be analyzed equally. If the user is in a hurry, emails with high urgency can be analyzed first. In this way, the importance of received emails can be evaluated according to the user's emotions, allowing a more appropriate reply message to be generated.

[0100] When analyzing the contents of a received email, the analysis unit can adjust the analysis method by taking into account the cultural background of the email sender. For example, if the sender is from a different cultural sphere, a reply message is generated using expressions and tones appropriate for that culture. If the sender has a specific religious background, a reply message can be generated that includes content that takes that religion into consideration. If the sender uses a dialect from a specific region, a reply message that corresponds to that dialect can be generated. In this way, a more appropriate reply message can be generated by adjusting the analysis method according to the sender's cultural background.

[0101] When analyzing the contents of a received email, the analysis unit can adjust the analysis method by taking into account the past behavioral patterns of the email sender. For example, if the sender has requested a quick reply in the past, a reply message can be generated quickly. If the sender has requested a detailed explanation in the past, a detailed analysis can be performed to generate a polite reply message. If the sender has preferred replies in a specific format in the past, a reply message that matches that format can be generated. In this way, a more appropriate reply message can be generated by adjusting the analysis method based on the sender's past behavioral patterns.

[0102] The analysis unit can estimate the user's emotions and determine the priority of received emails based on the estimated user's emotions. For example, if the user is feeling stressed, important emails are analyzed with priority and a reply text is generated quickly. If the user is relaxed, all emails can be analyzed equally. If the user is in a hurry, emails with high urgency can be analyzed with priority. In this way, important emails can be analyzed with priority by determining the priority of received emails according to the user's emotions.

[0103] When analyzing the content of an incoming email, the analysis unit can analyze the social media activity of the email sender to obtain related information. For example, it can analyze the sender's social media posts to obtain information related to the content of the email. It can also adjust the tone and style of the reply based on the sender's social media activity. It can also generate an appropriate reply by reflecting the sender's social media interests in the analysis. This makes it possible to generate a more appropriate reply by analyzing the sender's social media activity.

[0104] The generation unit can estimate the user's emotions and adjust the way in which a reply is expressed based on the estimated user's emotions. For example, if the user is relaxed, a polite and detailed reply can be generated. If the user is in a hurry, a concise reply that gets to the point can also be generated. If the user is stressed, a reply in a gentle tone can also be generated. In this way, a more appropriate reply can be generated by adjusting the way in which a reply is expressed depending on the user's emotions.

[0105] The process flow of the second embodiment will be briefly described below.

[0106] Step 1: The analysis unit analyzes the contents of the received email. The analysis unit can analyze the contents of the received email using natural language processing technology and extract important information using keyword extraction technology. It can also analyze the emotional nuances of the received email using sentiment analysis technology. Step 2: The generator generates a reply based on the content analyzed by the analyzer. The generator can generate a reply using template-based generation techniques or machine learning models, and can also refer to past email history or specific templates. Step 3: The presentation unit presents the reply text generated by the generation unit to the user. The presentation unit presents the reply text through a user interface, and can also notify the user of the reply text by using a push notification.

[0107] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0109] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0110] Each of the elements including the above-mentioned analysis unit, generation unit, presentation unit, and correction unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes the contents of the received mail. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a reply sentence based on the analyzed contents. The presentation unit is realized, for example, by the control unit 46A of the smart device 14 and presents the generated reply sentence to the user. The correction unit is realized, for example, by the control unit 46A of the smart device 14 and provides a function for the user to correct the generated reply sentence. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0118] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0121] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0123] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements including the above-mentioned analysis unit, generation unit, presentation unit, and correction unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes the contents of the received email. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a reply sentence based on the analyzed contents. The presentation unit is realized, for example, by the control unit 46A of the smart glasses 214 and presents the generated reply sentence to the user. The correction unit is realized, for example, by the control unit 46A of the smart glasses 214 and provides a function for the user to correct the generated reply sentence. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0129] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0134] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0137] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0141] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements including the above-mentioned analysis unit, generation unit, presentation unit, and correction unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes the contents of the received mail. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a reply text based on the analyzed contents. The presentation unit is realized, for example, by the control unit 46A of the headset type terminal 314 and presents the generated reply text to the user. The correction unit is realized, for example, by the control unit 46A of the headset type terminal 314 and provides a function for the user to correct the generated reply text. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0150] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0151] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0152] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0154] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0158] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0159] Each of the multiple elements including the above-mentioned analysis unit, generation unit, presentation unit, and correction unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes the contents of the received mail. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a reply sentence based on the analyzed contents. The presentation unit is realized, for example, by the control unit 46A of the robot 414 and presents the generated reply sentence to the user. The correction unit is realized, for example, by the control unit 46A of the robot 414 and provides a function for the user to correct the generated reply sentence. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0160] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0161] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0163] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0164] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0165] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0168] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0169] In addition, 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 upon request from the data processing device 12.

[0170] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0171] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0172] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0173] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0174] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0175] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0176] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0177] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0178] (Appendix 1) An analysis unit that analyzes the contents of received emails; A generation unit that generates a reply message based on the content analyzed by the analysis unit; a presentation unit that presents the reply message generated by the generation unit to a user; Equipped A system characterized by: (Appendix 2) The generation unit is Generate replies by referencing past email history or specific templates 2. The system of claim 1, (Appendix 3) The presentation unit is Present the generated reply via push notification 2. The system of claim 1, (Appendix 4) A correction section is provided for users to correct their reply. 2. The system of claim 1, (Appendix 5) The analysis unit is Infer user sentiment and adjust how incoming emails are parsed based on the inferred user sentiment 2. The system of claim 1, (Appendix 6) The analysis unit is Improve the accuracy of analysis by referring to the past email history of the sender of the received email 2. The system of claim 1, (Appendix 7) The analysis unit is Apply different analysis algorithms depending on the content of the received email 2. The system of claim 1, (Appendix 8) The analysis unit is Infer user emotions and prioritize analysis results based on the estimated user emotions. 2. The system of claim 1, (Appendix 9) The analysis unit is When parsing incoming emails, perform analysis based on the sender's geographic location 2. The system of claim 1, (Appendix 10) The analysis unit is When parsing incoming emails, analyze the sender's social media activity and obtain relevant information 2. The system of claim 1, (Appendix 11) The generation unit is Infer the user's emotions and adjust the way the reply is expressed based on the estimated user's emotions 2. The system of claim 1, (Appendix 12) The generation unit is When generating replies, improve accuracy by referencing past email history and specific templates. 2. The system of claim 1, (Appendix 13) The generation unit is When generating replies, different generation algorithms are applied depending on the category of the incoming email. 2. The system of claim 1, (Appendix 14) The generation unit is Infer the user's emotions and adjust the length of the reply based on the estimated user emotions. 2. The system of claim 1, (Appendix 15) The generation unit is When generating replies, prioritize replies based on when the incoming mail was sent 2. The system of claim 1, (Appendix 16) The generation unit is When generating replies, adjust the order of replies based on the relevance of the incoming email 2. The system of claim 1, (Appendix 17) The presentation unit is Infer the user's emotions and adjust the way the reply is presented based on the estimated user's emotions 2. The system of claim 1, (Appendix 18) The presentation unit is When presenting information, the system selects the optimal presentation method by referring to the user's past operation history. 2. The system of claim 1, (Appendix 19) The presentation unit is When suggesting, adjust the detail of the suggestion based on the importance of the reply 2. The system of claim 1, (Appendix 20) The presentation unit is Inferring a user's emotions and adjusting the display order of replies based on the estimated user's emotions 2. The system of claim 1, (Appendix 21) The presentation unit is When presenting, the optimal display method is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 22) The presentation unit is When presenting, refer to the user's schedule information and present at the optimal timing 2. The system of claim 1, (Appendix 23) The correction unit is Inferring user sentiment and providing remediation advice based on the inferred user sentiment 2. The system of claim 1, (Appendix 24) The correction unit is When making corrections, the system will suggest the best way to correct the problem by referring to the past correction history. 2. The system of claim 1, (Appendix 25) The correction unit is During editing, different editing algorithms are applied depending on the content of the incoming email 2. The system of claim 1, (Appendix 26) The correction unit is Inferring user sentiment and prioritizing modifications based on the estimated user sentiment 2. The system of claim 1, (Appendix 27) The correction unit is When making corrections, the system considers the user's geographic location to suggest the best way to correct the problem. 2. The system of claim 1, (Appendix 28) The correction unit is When revising, it analyzes the user's social media activity to suggest revising measures. 2. The system of claim 1, [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis unit that analyzes the contents of received emails; A generation unit that generates a reply message based on the content analyzed by the analysis unit; a presentation unit that presents the reply message generated by the generation unit to a user; Equipped A system characterized by:

2. The generation unit is Generate replies by referencing past email history or specific templates 2. The system of claim 1 .

3. The presentation unit is Present the generated reply via push notification 2. The system of claim 1 .

4. A correction section is provided for users to correct their reply.

2. The system of claim 1 .

5. The analysis unit is Infer user sentiment and adjust how incoming emails are parsed based on the inferred user sentiment 2. The system of claim 1 .

6. The analysis unit is Improve the accuracy of analysis by referring to the past email history of the sender of the received email 2. The system of claim 1 .

7. The analysis unit is Apply different analysis algorithms depending on the content of the received email 2. The system of claim 1 .

8. The analysis unit is Infer user emotions and prioritize analysis results based on the estimated user emotions.

2. The system of claim 1 .

9. The analysis unit is When parsing incoming emails, perform analysis based on the sender's geographic location 2. The system of claim 1 .

10. The analysis unit is When parsing incoming emails, analyze the sender's social media activity and obtain relevant information 2. The system of claim 1 .

Images