System

Abstract

To reproduce the content of mails or short messages by voice, convert verbal replies into a literary style, and automatically transmit the converted replies.SOLUTION: A system according to an embodiment comprises a message reception unit, a colloquial style conversion unit, a reproduction unit, a reply reception unit, a literary style conversion unit, and a transmission unit. The message reception unit receives a mail message or a short message. The colloquial style conversion unit converts the message received by the message reception unit from a literary style to a colloquial style. The reproduction unit reproduces by voice a message in a colloquial style having been converted by the colloquial style conversion unit. The reply reception unit receives a user's reply to the message reproduced by the reproduction unit. The literary style conversion unit converts the reply received by the reply reception unit into the colloquial style. The transmission unit automatically transmits a reply in a literary style having been converted by the literary style conversion unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the process of playing back the contents of emails and short messages aloud, converting verbal responses into written language, and automatically sending them is not sufficiently automated, and there is room for improvement.

[0005] The system according to the embodiment aims to play back the contents of emails and short messages aloud, convert verbal responses into written language, and automatically send them. [Means for solving the problem]

[0006] The system according to the embodiment includes a message receiving unit, a colloquial language conversion unit, a playback unit, a response receiving unit, a literary language conversion unit, and a sending unit. The message receiving unit receives an email message or a short message. The colloquial language conversion unit converts the message received by the message receiving unit from literary language to colloquial language. The playback unit plays back the colloquial language message converted by the colloquial language conversion unit by voice. The response receiving unit receives a user's response to the message played back by the playback unit. The literary language conversion unit converts the response received by the response receiving unit into literary language. The sending unit automatically sends the response converted by the literary language conversion unit into literary language. [Effects of the Invention]

[0007] The system according to the embodiment can play back the contents of emails and short messages aloud and convert verbal responses into written language before automatically sending them. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A message conversion system according to an embodiment of the present invention translates emails and short messages into colloquial language and plays the translated colloquial message through a speaker. The message conversion system accepts emails or short messages, converts the accepted message from written language to colloquial language, and plays the translated colloquial message aloud. When a user verbally responds to the message, the system converts the response into written language and automatically transmits it. For example, a user inputs a message received on a smartphone or computer into the system. This message is accepted by a message acceptance unit. The accepted message is then converted from written language to colloquial language. The colloquial language conversion unit analyzes the written message and converts it into a more natural colloquial language. For example, a written expression such as "Thank you for your help" is converted into a colloquial language such as "Hello." The translated colloquial message is then played aloud by a playback unit. The playback unit has a function for emphasizing specific keywords and a function for adjusting the tone and speed of the audio based on user settings. For example, important keywords can be emphasized during playback to ensure that the user does not miss important information. When a user verbally responds to a message played back as audio, the response is accepted by the response acceptance unit. The response acceptance unit converts the user's speech into text, which is then converted into written language by the literary style conversion unit. For example, a verbal response such as "Yes, I understand" is converted into written language such as "I understand." Finally, the converted response is automatically transmitted by the transmission unit. The transmission unit has a function to prompt the user for confirmation before transmission. For example, the user can review the content of the message and revise it as necessary. This system facilitates the exchange of emails and short messages, improving user convenience. For example, it enables quick and accurate communication in business situations. It also has the function of accepting multiple messages at once and the function of determining the importance of messages and processing them preferentially, enabling efficient message management. As a result, the message conversion system can translate emails and short messages into colloquial language, play them back aloud, and automatically transmit the verbal response converted into written language.

[0029] A message conversion system according to an embodiment includes a message receiving unit, a colloquial language conversion unit, a playback unit, a response receiving unit, a written language conversion unit, and a transmission unit. The message receiving unit receives an email message or a short message. Examples of the email message or short message include, but are not limited to, a text message or a message with an image. The message receiving unit inputs a message received by a user on a smartphone or a personal computer into the system. The message is received by the message receiving unit. The colloquial language conversion unit converts the received message from written language to colloquial language. The colloquial language conversion unit, for example, analyzes a written message and converts it to a more natural colloquial language. For example, the colloquial language conversion unit converts a written expression such as "Thank you for your help" to a more natural colloquial expression such as "Hello." The colloquial language conversion unit uses a generation AI to analyze the written message and convert it to a more natural colloquial language. The generation AI converts the written message to a colloquial language using a text generation AI (e.g., LLM). The playback unit plays back the colloquial message converted by the colloquial language conversion unit as audio. The playback unit has, for example, a function to highlight specific keywords and a function to adjust the tone and speed of the audio based on information set by the user. For example, by highlighting important keywords during playback, the user does not miss important information. The playback unit uses a generation AI to play back a colloquial message aloud. The generation AI uses a voice generation AI to play back a colloquial message aloud. The answer receiving unit receives a user's answer to the message played back by the playback unit. For example, the answer receiving unit converts the user's voice into text, and then converts it into a written style using a literary style conversion unit. The literary style conversion unit converts the answer received by the answer receiving unit into a written style. For example, the literary style conversion unit converts a verbal answer such as "Yes, I understand" into a written style such as "I understand." The literary style conversion unit converts the verbal answer into a written style using the generation AI. The generation AI converts the verbal answer into a written style using a text generation AI (e.g., LLM). The sending unit automatically sends the answer in formal language converted by the formal language conversion unit. The sending unit has, for example, a function of prompting the user for confirmation before sending.For example, the user can check the content of the transmission and correct it as necessary. The transmission unit uses a generation AI to automatically transmit a response in formal language. The generation AI automatically transmits a response in formal language using a text generation AI (e.g., LLM). As a result, the message conversion system according to the embodiment can translate emails and short messages into colloquial language, play them aloud, and convert verbal responses into formal language and automatically transmit them.

[0030] The message reception unit receives email messages or short messages. Examples of email messages or short messages include, but are not limited to, text messages and messages with images. The message reception unit inputs messages received by users on their smartphones or personal computers into the system. These messages are then received by the message reception unit. The message reception unit analyzes the received messages and identifies their type and content. For example, in the case of text messages, the message content is analyzed and important keywords and phrases are extracted. In the case of messages with images, the image content is analyzed using image recognition technology and relevant text information is extracted. Furthermore, the message reception unit records metadata, such as the sender and date and time of the received message, for use in subsequent processing. The message reception unit uses AI to classify the content of the message and prepare for appropriate processing. For example, the message reception unit uses natural language processing technology to analyze the intent of the message and select the appropriate conversion process. The message reception unit also has a function to filter specific messages based on user settings. For example, it can automatically filter out spam messages and unnecessary notifications, and process only important messages. This allows the message receiving unit to efficiently and accurately receive messages and provide information necessary for subsequent processing.

[0031] The colloquial language conversion unit converts the received message from formal language to colloquial language. For example, the colloquial language conversion unit analyzes a formal message and converts it to a natural colloquial language. For example, it converts a formal expression such as "Thank you for your help" to a colloquial expression such as "Hello." The colloquial language conversion unit uses a generation AI to analyze the formal message and convert it to a natural colloquial language. The generation AI converts the formal message to a colloquial language using a text generation AI (e.g., LLM). Specifically, the generation AI receives a formal message as input and converts it to a colloquial language by applying grammar and vocabulary conversion rules. For example, it replaces honorifics and polite language contained in the formal message with appropriate colloquial expressions. The generation AI can also add appropriate conjunctions and phrases to understand the context and maintain a natural conversational flow. Furthermore, the generation AI can learn user preferences and past message history and perform personalized conversions. For example, it converts to a colloquial language that reflects the expressions and style preferred by a specific user. This allows the colloquial language conversion unit to convert a written message into a natural, easily understandable colloquial language, thereby providing a message that is easy for the user to use.

[0032] The playback unit plays back the colloquial message converted by the colloquial conversion unit. The playback unit has functions, for example, to highlight specific keywords and to adjust the tone and speed of the speech based on user settings. For example, by emphasizing important keywords during playback, the user can ensure that they do not miss important information. The playback unit uses a generation AI to play back the colloquial message. The generation AI uses a speech generation AI to play back the colloquial message. Specifically, the generation AI generates natural pronunciation and intonation when converting text to speech. For example, the speech generation AI understands the context of the text and adds appropriate emotion and emphasis to generate more natural, easy-to-listen speech. The playback unit also has a function to adjust the tone and speed of the speech according to the user's preferences. For example, if a user prefers fast playback, the playback speed can be adjusted to quickly convey the message. The playback unit also has a function to highlight specific keywords and phrases. For example, by highlighting important information or action items, the user can ensure that they do not miss important points. This allows the playback unit to provide users with an easy-to-understand and effective speech message.

[0033] The answer acceptance unit accepts the user's answer to the message played by the playback unit. For example, the answer acceptance unit converts the user's voice into text, and then the literary style conversion unit converts it into literary style. The answer acceptance unit converts the user's voice into text using voice recognition technology. Specifically, a voice recognition AI analyzes the user's speech in real time and converts it into text data. For example, if the user utters "Yes, I understand," the voice recognition AI acquires this as text data. Furthermore, the answer acceptance unit analyzes the content of the user's speech and prepares to convert it into an appropriate literary style. For example, it analyzes the intention and emotion of the speech content and selects an appropriate literary style expression. As a result, the answer acceptance unit can accurately convert the user's voice answer into text and use it for subsequent processing.

[0034] The literary style conversion unit converts the response received by the response receiving unit into a literary style. For example, the literary style conversion unit converts a verbal response such as "Yes, I understand" into a literary style such as "I understand." The literary style conversion unit converts the verbal response into a literary style using a generation AI. The generation AI converts the verbal response into a literary style using a text generation AI (e.g., LLM). Specifically, the generation AI receives the verbal response as input and converts it into a literary style by applying grammar and vocabulary conversion rules. For example, it converts the colloquial expression "I understand" into the literary style "I understand." The generation AI also understands the context and generates more formal literary expressions by adding appropriate honorifics and polite language. Furthermore, the generation AI can learn user preferences and past message history and perform personalized conversions. For example, it converts into a literary style that reflects the expressions and style preferred by a specific user. As a result, the literary style conversion unit converts the verbal response into a natural and appropriate literary style, thereby providing a message that is easy for the user to use.

[0035] The sending unit automatically sends the response in formal language converted by the formal language conversion unit. The sending unit has, for example, a function to prompt the user for confirmation before sending. For example, the user can check the content of the message and correct it if necessary. The sending unit automatically sends the response in formal language using a generation AI. The generation AI automatically sends the response in formal language using a text generation AI (for example, LLM). Specifically, the generation AI receives the response in formal language as input and selects an appropriate recipient and sending method. For example, it automatically extracts an email address or phone number and sends it in an appropriate format. The sending unit also has a function to prompt the user for confirmation before sending. For example, the user can check the content of the message and correct it if necessary. Furthermore, the sending unit has a function to record the sending history and make it available for later reference. This allows the sending unit to accurately and quickly send responses in formal language and provide a message sending function that is easy for users to use.

[0036] The playback unit may have a function for emphasizing specific keywords, thereby preventing the user from missing important information. The playback unit may adjust the tone and volume of the audio to emphasize specific keywords. For example, the playback unit may raise the tone and volume of the audio to emphasize important keywords. The playback unit may also adjust the speed of the audio to emphasize specific keywords. For example, the playback unit may slow down the speed of the audio to emphasize important keywords. This allows the playback unit to play back audio with emphasis on specific keywords, preventing the user from missing important information. Some or all of the above-described processing in the playback unit may be performed using, or without, AI. For example, the playback unit may input audio data to a generation AI to emphasize specific keywords, and have the generation AI adjust the tone and volume of the audio.

[0037] The playback unit may have a function to adjust the tone and speed of the voice based on information set by the user. This enables easier-to-listen voice playback. The playback unit may change the pitch of the voice or emotional expression to adjust the tone of the voice. For example, the playback unit may increase or decrease the pitch of the voice based on information set by the user. The playback unit may also change the playback speed of the voice to adjust the speed of the voice. For example, the playback unit may increase or decrease the playback speed of the voice based on information set by the user. This enables easier-to-listen voice playback by adjusting the tone and speed of the voice based on the information set by the user. Some or all of the above-described processing in the playback unit may be performed using, or without, AI. For example, the playback unit may input voice data to a generation AI and have the generation AI adjust the tone and speed of the voice.

[0038] The transmission unit can have a function to prompt the user for confirmation before transmission. This can prevent erroneous transmission. The transmission unit can use methods such as a pop-up notification or audio confirmation to prompt the user for confirmation. For example, the transmission unit can display a pop-up notification before transmission to prompt the user to confirm the content of the transmission. The transmission unit can also perform audio confirmation before transmission to prompt the user to confirm the content of the transmission. This can prevent erroneous transmission by prompting the user for confirmation before transmission. Some or all of the above-mentioned processing in the transmission unit can be performed using, for example, AI, or can be performed without using AI. For example, the transmission unit can have the generation AI perform a pop-up notification or audio confirmation to prompt the user to confirm the content before transmission.

[0039] The message reception unit can have a function of accepting multiple messages in a batch. This enables efficient message management. The message reception unit can set the number and type of messages to be accepted simultaneously. For example, the message reception unit can set the number of messages to be accepted simultaneously and accept multiple messages in a batch. The message reception unit can also set the type of messages to be accepted simultaneously and accept messages of a specific type in a batch. This enables efficient message management by the message reception unit accepting multiple messages in a batch. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the message reception unit can have the generation AI set the number and type of messages in order to accept multiple messages in a batch.

[0040] The system includes a determination unit that determines the importance of each of the plurality of messages, and the colloquial language conversion unit can convert the plurality of messages from a written style to a colloquial style in descending order of importance determined by the determination unit. The determination unit, for example, determines the importance of the plurality of messages. The importance is determined, for example, based on urgency or the importance of the content, but is not limited to such examples. The determination unit determines the importance of the messages based on urgency, for example. For example, the determination unit prioritizes determining messages with a high urgency as being of high importance. The determination unit can also determine the importance of the messages based on the importance of the content. For example, the determination unit prioritizes determining messages with a high importance as being of high importance. The colloquial language conversion unit converts the plurality of messages from a written style to a colloquial style in descending order of importance determined by the determination unit. For example, the colloquial language conversion unit prioritizes converting messages with a high importance from a written style to a colloquial style. As a result, the colloquial language conversion unit can quickly process important messages by preferentially converting messages with a high importance to a colloquial style. Some or all of the above-described processes in the determination unit and the colloquial language conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit may have the generation AI evaluate the urgency or importance of the content to determine the importance of the message. Furthermore, the colloquial language conversion unit may have the generation AI perform a conversion process to preferentially convert messages with high importance from written language to colloquial language.

[0041] The playback unit can play back messages in the voice of a specific character selected by the user. This enables more familiar voice playback. The playback unit can use a voice customized by the user or the voice of a famous character to select the voice of the specific character. For example, the playback unit can play back messages using a voice customized by the user. The playback unit can also play back messages using the voice of a famous character. This enables more familiar voice playback by playing back messages in the voice of a specific character selected by the user. Some or all of the above-described processing in the playback unit may be performed using, for example, AI or without AI. For example, the playback unit can input the voice of a specific character into a generation AI and cause the generation AI to generate voice data.

[0042] The literary style conversion unit can use appropriate abbreviations depending on the length of the message. This allows conversion to a more concise literary style. The literary style conversion unit can set criteria for using abbreviations depending on the length of the message. For example, the literary style conversion unit can use abbreviations when the length of the message is equal to or greater than a certain level. The literary style conversion unit can also use abbreviations depending on the content of the message. For example, the literary style conversion unit can convert to a more concise literary style by omitting less important parts. This allows the literary style conversion unit to convert to a more concise literary style by using appropriate abbreviations depending on the length of the message. Some or all of the above-mentioned processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can cause the generation AI to set criteria for abbreviations in order to use abbreviations depending on the length of the message.

[0043] The colloquial language conversion unit can convert the message into a dialect corresponding to the user's geographical location. This allows for conversion to a more natural colloquial style. The colloquial language conversion unit can acquire the user's geographical location and convert the message into a dialect corresponding to that location. For example, the colloquial language conversion unit can acquire the user's geographical location from GPS data or an IP address and convert the message into a dialect corresponding to that location. The colloquial language conversion unit can also convert the message into a dialect using a regional dialect list and conversion rules. For example, the colloquial language conversion unit can refer to a regional dialect list and convert the message into the regional dialect. This allows the colloquial language conversion unit to convert the message into a dialect corresponding to the user's geographical location, allowing for conversion to a more natural colloquial style. Some or all of the above-described processing in the colloquial language conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial language conversion unit can input the user's geographical location into a generation AI and have the generation AI perform dialect conversion.

[0044] The message reception unit can analyze the user's past message reception history and select the optimal reception method. This allows the optimal reception method to be selected. The message reception unit can acquire and analyze the past message reception history. For example, the message reception unit can analyze time periods during which the user frequently received messages in the past and prioritize receiving messages during those time periods. The message reception unit can also prioritize receiving message formats (email, short messages, etc.) that the user has previously preferred. Furthermore, the message reception unit can prioritize receiving messages from specific senders based on the user's past message reception history. This allows the message reception unit to select the optimal reception method by analyzing the user's past message reception history. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without AI. For example, the message reception unit can input the user's past message reception history into a generation AI and have the generation AI select the optimal reception method.

[0045] When receiving messages, the message reception unit can filter messages based on the user's current project or area of ​​interest. This allows highly relevant messages to be preferentially received. The message reception unit can acquire the user's current project or area of ​​interest and filter messages based on that information. For example, the message reception unit can preferentially receive messages related to a project the user is currently working on. The message reception unit can also filter and receive highly relevant messages based on the user's area of ​​interest. Furthermore, the message reception unit can preferentially receive important messages based on keywords set by the user. This allows the message reception unit to preferentially receive highly relevant messages by filtering based on the user's current project or area of ​​interest. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the message reception unit can input the user's current project or area of ​​interest into a generation AI and have the generation AI perform filtering.

[0046] When receiving messages, the message reception unit can prioritize receiving highly relevant messages by taking into account the user's geographical location information. This enables more appropriate message management. The message reception unit can acquire the user's geographical location information and filter messages based on that information. For example, if the user is in a specific area, the message reception unit can prioritize receiving messages related to that area. Furthermore, if the user is traveling, the message reception unit can prioritize receiving messages related to the travel destination. Furthermore, if the user is at home, the message reception unit can prioritize receiving messages related to the home. This enables more appropriate message management by the message reception unit prioritizing receiving highly relevant messages by taking into account the user's geographical location information. Some or all of the above-described processing in the message reception unit may be performed using AI, for example, or may be performed without using AI. For example, the message reception unit can input the user's geographical location information to a generation AI and cause the generation AI to filter highly relevant messages.

[0047] When receiving a message, the message reception unit can analyze the user's social media activity and receive related messages. This allows for preferential reception of related messages. The message reception unit can acquire the user's social media activity and filter messages based on that information. For example, the message reception unit can preferentially receive messages related to topics that the user frequently mentions on social media. The message reception unit can also preferentially receive messages from accounts the user follows. Furthermore, the message reception unit can preferentially receive messages related to groups or communities in which the user participates. This allows the message reception unit to preferentially receive related messages by analyzing the user's social media activity. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the message reception unit can input the user's social media activity into a generation AI and have the generation AI filter out related messages.

[0048] During colloquial conversion, the colloquial conversion unit can adjust the level of detail of the conversion based on the importance of the message. This allows conversion to a colloquial style with an appropriate level of detail. The colloquial conversion unit can determine the importance of the message and adjust the level of detail of the conversion based on the importance. For example, the colloquial conversion unit can convert a message of high importance into a colloquial style that includes detailed explanations. The colloquial conversion unit can also convert a message of low importance into a concise colloquial style. Furthermore, the colloquial conversion unit can convert into a colloquial style with an appropriate level of detail depending on the importance. This allows conversion to a colloquial style with an appropriate level of detail by adjusting the level of detail of the conversion based on the importance of the message. Some or all of the above-described processing in the colloquial conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial conversion unit can input the importance of the message to a generation AI and cause the generation AI to adjust the level of detail of the conversion.

[0049] When converting a message into a colloquial style, the colloquial style conversion unit can apply different conversion algorithms depending on the category of the message. This allows for conversion into a more appropriate colloquial style. The colloquial style conversion unit can determine the category of the message and apply different conversion algorithms depending on the category. For example, the colloquial style conversion unit can convert a business-related message into a formal colloquial style. The colloquial style conversion unit can also convert a private message into a casual colloquial style. Furthermore, the colloquial style conversion unit can convert an urgent message into a colloquial style that can be quickly understood. This allows for conversion into a more appropriate colloquial style by applying different conversion algorithms depending on the category of the message. Some or all of the above-described processing in the colloquial style conversion unit may be performed using, or without, AI. For example, the colloquial style conversion unit can input the message category into a generation AI and cause the generation AI to apply different conversion algorithms.

[0050] When converting a message into a colloquial style, the colloquial style conversion unit can determine the priority of conversion based on the time the message was submitted. This allows conversion to a colloquial style in an appropriate order. The colloquial style conversion unit can obtain the time the message was submitted and determine the priority of conversion based on that information. For example, the colloquial style conversion unit can preferentially convert recently submitted messages into a colloquial style. The colloquial style conversion unit can also convert older submitted messages into a colloquial style later. Furthermore, the colloquial style conversion unit can convert messages into a colloquial style in an appropriate priority depending on the time of submission. This allows conversion to a colloquial style in an appropriate order by determining the priority of conversion based on the time the message was submitted. Some or all of the above-described processing in the colloquial style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial style conversion unit can input the time the message was submitted to a generation AI and have the generation AI determine the priority of conversion.

[0051] During colloquial conversion, the colloquial conversion unit can adjust the order of conversion based on the relevance of the messages. This allows highly relevant messages to be preferentially converted to colloquial form. The colloquial conversion unit can determine the relevance of the messages and adjust the order of conversion based on the relevance. For example, the colloquial conversion unit can preferentially convert messages related to the user's current project into colloquial form. The colloquial conversion unit can also preferentially convert messages related to the user's areas of interest into colloquial form. Furthermore, the colloquial conversion unit can preferentially convert important messages into colloquial form based on keywords set by the user. This allows the colloquial conversion unit to preferentially convert highly relevant messages into colloquial form by adjusting the order of conversion based on the relevance of the messages. Some or all of the above-described processing in the colloquial conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial conversion unit can input the relevance of the messages to a generation AI and have the generation AI adjust the order of conversion.

[0052] During playback, the playback unit can adjust the playback speed based on the importance of the message. This allows the message to be played at an appropriate speed. The playback unit can determine the importance of the message and adjust the playback speed based on the importance. For example, the playback unit can play messages of high importance slowly to facilitate understanding. The playback unit can also play messages of low importance faster to improve efficiency. Furthermore, the playback unit can play messages at an appropriate speed depending on the importance. This allows the playback unit to play messages at an appropriate speed by adjusting the playback speed based on the importance of the message. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the importance of the message to the generation AI and have the generation AI adjust the playback speed.

[0053] During playback, the playback unit can apply different playback algorithms depending on the message category. This allows the message to be played back in a more appropriate tone. The playback unit can determine the message category and apply different playback algorithms depending on the category. For example, the playback unit can play back business-related messages in a formal tone. The playback unit can also play back private messages in a casual tone. Furthermore, the playback unit can play back emergency messages in a tone that is quickly understandable. This allows the playback unit to play back messages in a more appropriate tone by applying different playback algorithms depending on the message category. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the message category to a generation AI and cause the generation AI to apply different playback algorithms.

[0054] During playback, the playback unit can determine the playback priority based on the submission time of the message. This allows messages to be played back in an appropriate order. The playback unit can obtain the submission time of the message and determine the playback priority based on that information. For example, the playback unit can prioritize playback of recently submitted messages. The playback unit can also postpone playback of messages that were submitted earlier. Furthermore, the playback unit can play back messages with an appropriate priority based on the submission time. This allows messages to be played back in an appropriate order by determining the playback priority based on the submission time of the message. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the submission time of the message to the generation AI and have the generation AI determine the playback priority.

[0055] During playback, the playback unit can adjust the playback order based on the relevance of the messages. This allows highly relevant messages to be prioritized for playback. The playback unit can determine the relevance of the messages and adjust the playback order based on the relevance. For example, the playback unit can prioritize playback of messages related to the user's current project. The playback unit can also prioritize playback of messages related to the user's areas of interest. Furthermore, the playback unit can prioritize playback of important messages based on keywords set by the user. This allows the playback unit to prioritize playback of highly relevant messages by adjusting the playback order based on the relevance of the messages. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the relevance of the messages to a generation AI and have the generation AI adjust the playback order.

[0056] When accepting an answer, the answer accepting unit can analyze the user's past answer history and select the optimal answer accepting method. The answer accepting unit can acquire and analyze the past answer history. For example, the answer accepting unit can preferentially accept answer methods (voice, text, etc.) that the user has frequently used in the past. The answer accepting unit can also predict and suggest an answer method to be used in a specific time period based on the user's past answer history. Furthermore, the answer accepting unit can preferentially accept answer formats that the user has preferred in the past. In this way, the answer accepting unit can select the optimal answer accepting method by analyzing the user's past answer history. Some or all of the above-described processing in the answer accepting unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer accepting unit can input the user's past answer history into a generation AI and have the generation AI select the optimal answer accepting method.

[0057] When receiving answers, the answer receiving unit can filter answers based on the user's current project or area of ​​interest. This allows highly relevant answers to be preferentially received. The answer receiving unit can acquire the user's current project or area of ​​interest and filter answers based on that information. For example, the answer receiving unit can preferentially receive answers related to a project the user is currently working on. The answer receiving unit can also filter and receive highly relevant answers based on the user's area of ​​interest. Furthermore, the answer receiving unit can preferentially receive important answers based on keywords set by the user. This allows the answer receiving unit to preferentially receive highly relevant answers by filtering based on the user's current project or area of ​​interest. Some or all of the above-described processing in the answer receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer receiving unit can input the user's current project or area of ​​interest to a generation AI and have the generation AI perform filtering.

[0058] When accepting answers, the answer acceptance unit can prioritize accepting highly relevant answers by taking into account the user's geographical location information. This enables more appropriate answer management. The answer acceptance unit can acquire the user's geographical location information and filter answers based on that information. For example, if the user is in a specific area, the answer acceptance unit can prioritize accepting answers related to that area. Furthermore, if the user is traveling, the answer acceptance unit can prioritize accepting answers related to the travel destination. Furthermore, if the user is at home, the answer acceptance unit can prioritize accepting answers related to the home. This enables more appropriate answer management by preferentially accepting highly relevant answers by taking into account the user's geographical location information. Some or all of the above-described processing in the answer acceptance unit may be performed using AI, for example, or may be performed without using AI. For example, the answer acceptance unit can input the user's geographical location information to the generation AI and cause the generation AI to filter highly relevant answers.

[0059] When accepting answers, the answer acceptance unit can analyze the user's social media activity and accept relevant answers. This allows relevant answers to be accepted preferentially. The answer acceptance unit can acquire the user's social media activity and filter answers based on that information. For example, the answer acceptance unit can preferentially accept answers related to topics that the user frequently mentions on social media. The answer acceptance unit can also preferentially accept answers from accounts that the user follows. Furthermore, the answer acceptance unit can also preferentially accept answers related to groups or communities in which the user participates. This allows the answer acceptance unit to preferentially accept relevant answers by analyzing the user's social media activity. Some or all of the above-described processing in the answer acceptance unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer acceptance unit inputs the user's social media activity into a generation AI and causes the generation AI to filter relevant answers.

[0060] During the literary style conversion, the literary style conversion unit can adjust the level of detail of the conversion based on the importance of the answer. This allows conversion to a literary style with an appropriate level of detail. The literary style conversion unit can determine the importance of the answer and adjust the level of detail of the conversion based on the importance. For example, the literary style conversion unit can convert an answer with high importance into a literary style that includes detailed explanations. The literary style conversion unit can also convert an answer with low importance into a concise literary style. Furthermore, the literary style conversion unit can convert into a literary style with an appropriate level of detail depending on the importance. This allows conversion to a literary style with an appropriate level of detail by adjusting the level of detail of the conversion based on the importance of the answer. Some or all of the above-described processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the importance of the answer to a generation AI and have the generation AI adjust the level of detail of the conversion.

[0061] When converting the literary style, the literary style conversion unit can apply different conversion algorithms depending on the category of the answer. This allows for conversion to a more appropriate literary style. The literary style conversion unit can determine the category of the answer and apply different conversion algorithms depending on the category. For example, the literary style conversion unit can convert business-related answers into a formal literary style. The literary style conversion unit can also convert private answers into a casual literary style. Furthermore, the literary style conversion unit can convert urgent answers into a literary style that can be quickly understood. This allows for conversion to a more appropriate literary style by applying different conversion algorithms depending on the category of the answer. Some or all of the above-mentioned processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the category of the answer to the generation AI and cause the generation AI to apply different conversion algorithms.

[0062] When converting the literary style, the literary style conversion unit can determine the priority of conversion based on the time of submission of the answer. This allows conversion to literary style in an appropriate order. The literary style conversion unit can obtain the time of submission of the answer and determine the priority of conversion based on that information. For example, the literary style conversion unit can preferentially convert recently submitted answers to literary style. The literary style conversion unit can also convert older submitted answers to literary style later. Furthermore, the literary style conversion unit can convert to literary style in an appropriate priority depending on the time of submission. This allows conversion to literary style in an appropriate order by determining the priority of conversion based on the time of submission of the answer. Some or all of the above-mentioned processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the time of submission of the answer to the generation AI and have the generation AI determine the priority of conversion.

[0063] During the literary style conversion, the literary style conversion unit can adjust the order of conversion based on the relevance of the answers. This allows highly relevant answers to be preferentially converted to a literary style. The literary style conversion unit can determine the relevance of the answers and adjust the order of conversion based on the relevance. For example, the literary style conversion unit can preferentially convert answers related to the user's current project to a literary style. The literary style conversion unit can also preferentially convert answers related to the user's field of interest to a literary style. Furthermore, the literary style conversion unit can preferentially convert important answers to a literary style based on keywords set by the user. This allows the literary style conversion unit to preferentially convert highly relevant answers to a literary style by adjusting the order of conversion based on the relevance of the answers. Some or all of the above-described processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the relevance of the answers to a generation AI and have the generation AI adjust the order of conversion.

[0064] The transmitting unit can determine the transmission priority based on the importance of the answer at the time of transmission. This allows for transmission in an appropriate order. The transmitting unit can determine the importance of the answer and determine the transmission priority based on the importance. For example, the transmitting unit can transmit answers with high importance first. The transmitting unit can also transmit answers with low importance later. Furthermore, the transmitting unit can transmit answers with an appropriate priority according to their importance. This allows for transmission in an appropriate order by determining the transmission priority based on the importance of the answer. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can input the importance of the answer to the generating AI and have the generating AI determine the transmission priority.

[0065] The sending unit can apply different sending algorithms depending on the category of the answer when sending. This allows for sending in a more appropriate manner. The sending unit can determine the category of the answer and apply different sending algorithms depending on the category. For example, the sending unit can apply a formal sending method to a business-related answer. The sending unit can also apply a casual sending method to a private answer. Furthermore, the sending unit can apply an algorithm for quickly sending an urgent answer. This allows for sending in a more appropriate manner by applying different sending algorithms depending on the category of the answer. Some or all of the above-mentioned processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the category of the answer to a generation AI and cause the generation AI to apply different sending algorithms.

[0066] At the time of transmission, the transmitting unit can determine the priority of transmission based on the time of submission of the answers. This allows transmission in an appropriate order. The transmitting unit can obtain the time of submission of the answers and determine the priority of transmission based on that information. For example, the transmitting unit can prioritize transmitting the most recently submitted answers. The transmitting unit can also postpone transmitting answers that were submitted earlier. Furthermore, the transmitting unit can transmit with an appropriate priority depending on the time of submission. This allows transmission in an appropriate order by determining the priority of transmission based on the time of submission of the answers. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can input the time of submission of the answers to the generating AI and have the generating AI determine the priority of transmission.

[0067] The transmitting unit can adjust the order of transmission based on the relevance of the answers at the time of transmission. This allows highly relevant answers to be preferentially transmitted. The transmitting unit can determine the relevance of the answers and adjust the order of transmission based on the relevance. For example, the transmitting unit can preferentially transmit answers related to the user's current project. The transmitting unit can also preferentially transmit answers related to the user's field of interest. Furthermore, the transmitting unit can preferentially transmit important answers based on keywords set by the user. This allows the transmitting unit to preferentially transmit highly relevant answers by adjusting the order of transmission based on the relevance of the answers. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can input the relevance of the answers to a generating AI and have the generating AI adjust the order of transmission.

[0068] The determination unit can adjust the importance level based on the content of the message when making the determination. This enables appropriate importance determination. The determination unit can analyze the content of the message and adjust the importance level based on the content. For example, the determination unit can determine that a business-related message has a high importance level. The determination unit can also determine that a private message has a low importance level. Furthermore, the determination unit can determine that an urgent message has the highest priority in importance. This enables appropriate importance determination by adjusting the importance level based on the content of the message. Some or all of the above-described processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the content of the message to a generation AI and have the generation AI adjust the importance level.

[0069] When making a judgment, the judgment unit can apply different judgment algorithms depending on the message category. This enables more appropriate importance judgment. The judgment unit can judge the message category and apply different judgment algorithms depending on the category. For example, the judgment unit can apply a formal judgment algorithm to business-related messages. The judgment unit can also apply a casual judgment algorithm to private messages. Furthermore, the judgment unit can apply a quick judgment algorithm to urgent messages. This enables more appropriate importance judgment by applying different judgment algorithms depending on the message category. Some or all of the above-mentioned processing in the judgment unit may be performed using AI, for example, or may be performed without using AI. For example, the judgment unit can input the message category to the generation AI and cause the generation AI to apply different judgment algorithms.

[0070] At the time of judgment, the judgment unit can determine the importance level based on the submission time of the message. This enables appropriate importance determination. The judgment unit can obtain the submission time of the message and determine the importance level based on that information. For example, the judgment unit can prioritize recently submitted messages as being of high importance. The judgment unit can also determine that older submitted messages are of low importance. Furthermore, the judgment unit can determine an appropriate importance level depending on the submission time. This enables appropriate importance determination by determining the importance level based on the submission time of the message. Some or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input the submission time of the message to the generation AI and have the generation AI determine the importance level.

[0071] During the determination, the determination unit can adjust the order of importance based on the relevance of the messages. This allows highly relevant messages to be given higher importance. The determination unit can determine the relevance of the messages and adjust the order of importance based on the relevance. For example, the determination unit can prioritize messages related to the user's current project as being more important. The determination unit can also prioritize messages related to the user's field of interest as being more important. Furthermore, the determination unit can prioritize important messages as being more important based on keywords set by the user. This allows the determination unit to prioritize highly relevant messages as being more important by adjusting the order of importance based on the relevance of the messages. Some or all of the above-described processing in the determination unit may be performed using, or without, AI. For example, the determination unit can input the relevance of the messages to a generation AI and have the generation AI adjust the order of importance.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The message conversion system may further include a translation unit. The translation unit may translate a received message into a different language. For example, a message received in English may be translated into Japanese. The translation unit may also prioritize translation into a specific language based on a user's settings. For example, if a user has set French as their preferred language, the translation unit may translate into French. The translation unit may also select an appropriate translation method depending on the content of the message. For example, a formal translation method may be applied to business-related messages, and a casual translation method may be applied to private messages. This allows the message conversion system to facilitate communication between different languages.

[0074] The message conversion system may further include a notification unit. The notification unit may notify the user in real time when the user receives a new message. For example, the notification unit may notify the user of the receipt of a new message through a push notification on a smartphone or a desktop notification on a computer. The notification unit may also notify the user only during specific time periods based on the user's settings. For example, if the user does not want to receive notifications while at work, the notification unit may turn off notifications. The notification unit may also adjust the priority of notifications based on the importance of the message. For example, messages of high importance may be notified immediately, and messages of low importance may be notified later. This allows the message conversion system to prevent the user from missing important messages.

[0075] The message conversion system may further include a filtering unit. The filtering unit may filter accepted messages based on specific criteria. For example, spam messages and advertising messages may be automatically filtered so as not to be displayed to the user. The filtering unit may also accept only messages from specific senders based on user settings. For example, if a user wants to receive only messages related to a specific project, messages from senders related to that project may be accepted with priority. The filtering unit may also determine the importance of a message based on its content and process messages with higher importance with priority. This allows the message conversion system to efficiently obtain the information the user needs.

[0076] The message conversion system may further include an archive unit. The archive unit may automatically store past messages so that they can be searched and referenced as needed. For example, if a user wants to search for messages from a specific period, they can quickly search through the archive unit. The archive unit may also classify and organize messages based on message type or sender. For example, business-related messages and private messages may be stored separately. The archive unit may also adjust the storage period based on the importance of the message. For example, messages of high importance may be stored for a long period of time, and messages of low importance may be deleted after a short period of time. In this way, the message conversion system may enable the user to efficiently manage past messages.

[0077] The message conversion system may further include a customization unit. The customization unit may enable a user to individually configure the system's operation and display method. For example, the user may adjust the message playback speed and tone of voice. The customization unit may also enable a user to configure settings to highlight specific keywords or phrases. For example, by highlighting keywords related to an important project, the user may be able to ensure that important information is not overlooked. The customization unit may also enable a user to individually customize the system's interface. For example, the user may select their preferred colors and layout to achieve an easy-to-use interface. This allows the message conversion system to be flexibly customized to meet the user's needs.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The message reception unit receives email messages or short messages. Email messages and short messages include text messages and messages with images. A user inputs a message received on a smartphone or computer into the system, and the message reception unit receives it. Step 2: The colloquial language conversion unit converts the accepted message from formal to colloquial language. For example, it converts a formal expression such as "Thank you for your help" into a colloquial expression such as "Hello." Using a generative AI, it analyzes the formal message and converts it into a natural colloquial style. Step 3: The playback unit plays the colloquial message converted by the colloquial conversion unit. The playback unit has the function of emphasizing specific keywords and adjusting the tone and speed of the voice based on information set by the user. The generation AI is used to play the colloquial message. Step 4: The answer receiving unit receives the user's answer to the message played by the playback unit. The user's voice is converted into text, and the written language conversion unit converts it into written language. Step 5: The literary style conversion unit converts the answer received by the answer receiving unit into a literary style. For example, a verbal answer such as "Yes, I understand" is converted into a literary style such as "I'll acknowledge that." The verbal answer is converted into a literary style using a generation AI. Step 6: The sending unit automatically sends the response in formal language converted by the formal language conversion unit. It has a function that prompts the user to confirm the content before sending, allowing the user to check the content of the message and make corrections as necessary. The response in formal language is automatically sent using the generation AI.

[0080] (Example 2) A message conversion system according to an embodiment of the present invention translates emails and short messages into colloquial language and plays the translated colloquial message through a speaker. The message conversion system accepts emails or short messages, converts the accepted message from written language to colloquial language, and plays the translated colloquial message aloud. When a user verbally responds to the message, the system converts the response into written language and automatically transmits it. For example, a user inputs a message received on a smartphone or computer into the system. This message is accepted by a message acceptance unit. The accepted message is then converted from written language to colloquial language. The colloquial language conversion unit analyzes the written message and converts it into a more natural colloquial language. For example, a written expression such as "Thank you for your help" is converted into a colloquial language such as "Hello." The translated colloquial message is then played aloud by a playback unit. The playback unit has a function for emphasizing specific keywords and a function for adjusting the tone and speed of the audio based on user settings. For example, important keywords can be emphasized during playback to ensure that the user does not miss important information. When a user verbally responds to a message played back as audio, the response is accepted by the response acceptance unit. The response acceptance unit converts the user's speech into text, which is then converted into written language by the literary style conversion unit. For example, a verbal response such as "Yes, I understand" is converted into written language such as "I understand." Finally, the converted response is automatically transmitted by the transmission unit. The transmission unit has a function to prompt the user for confirmation before transmission. For example, the user can review the content of the message and revise it as necessary. This system facilitates the exchange of emails and short messages, improving user convenience. For example, it enables quick and accurate communication in business situations. It also has the function of accepting multiple messages at once and the function of determining the importance of messages and processing them preferentially, enabling efficient message management. As a result, the message conversion system can translate emails and short messages into colloquial language, play them back aloud, and automatically transmit the verbal response converted into written language.

[0081] A message conversion system according to an embodiment includes a message receiving unit, a colloquial language conversion unit, a playback unit, a response receiving unit, a written language conversion unit, and a transmission unit. The message receiving unit receives an email message or a short message. Examples of the email message or short message include, but are not limited to, a text message or a message with an image. The message receiving unit inputs a message received by a user on a smartphone or a personal computer into the system. The message is received by the message receiving unit. The colloquial language conversion unit converts the received message from written language to colloquial language. The colloquial language conversion unit, for example, analyzes a written message and converts it to a more natural colloquial language. For example, the colloquial language conversion unit converts a written expression such as "Thank you for your help" to a more natural colloquial expression such as "Hello." The colloquial language conversion unit uses a generation AI to analyze the written message and convert it to a more natural colloquial language. The generation AI converts the written message to a colloquial language using a text generation AI (e.g., LLM). The playback unit plays back the colloquial message converted by the colloquial language conversion unit as audio. The playback unit has, for example, a function to highlight specific keywords and a function to adjust the tone and speed of the audio based on information set by the user. For example, by highlighting important keywords during playback, the user does not miss important information. The playback unit uses a generation AI to play back a colloquial message aloud. The generation AI uses a voice generation AI to play back a colloquial message aloud. The answer receiving unit receives a user's answer to the message played back by the playback unit. For example, the answer receiving unit converts the user's voice into text, and then converts it into a written style using a literary style conversion unit. The literary style conversion unit converts the answer received by the answer receiving unit into a written style. For example, the literary style conversion unit converts a verbal answer such as "Yes, I understand" into a written style such as "I understand." The literary style conversion unit converts the verbal answer into a written style using the generation AI. The generation AI converts the verbal answer into a written style using a text generation AI (e.g., LLM). The sending unit automatically sends the answer in formal language converted by the formal language conversion unit. The sending unit has, for example, a function of prompting the user for confirmation before sending.For example, the user can check the content of the transmission and correct it as necessary. The transmission unit uses a generation AI to automatically transmit a response in formal language. The generation AI automatically transmits a response in formal language using a text generation AI (e.g., LLM). As a result, the message conversion system according to the embodiment can translate emails and short messages into colloquial language, play them aloud, and convert verbal responses into formal language and automatically transmit them.

[0082] The message reception unit receives email messages or short messages. Examples of email messages or short messages include, but are not limited to, text messages and messages with images. The message reception unit inputs messages received by users on their smartphones or personal computers into the system. These messages are then received by the message reception unit. The message reception unit analyzes the received messages and identifies their type and content. For example, in the case of text messages, the message content is analyzed and important keywords and phrases are extracted. In the case of messages with images, the image content is analyzed using image recognition technology and relevant text information is extracted. Furthermore, the message reception unit records metadata, such as the sender and date and time of the received message, for use in subsequent processing. The message reception unit uses AI to classify the content of the message and prepare for appropriate processing. For example, the message reception unit uses natural language processing technology to analyze the intent of the message and select the appropriate conversion process. The message reception unit also has a function to filter specific messages based on user settings. For example, it can automatically filter out spam messages and unnecessary notifications, and process only important messages. This allows the message receiving unit to efficiently and accurately receive messages and provide information necessary for subsequent processing.

[0083] The colloquial language conversion unit converts the received message from formal language to colloquial language. For example, the colloquial language conversion unit analyzes a formal message and converts it to a natural colloquial language. For example, it converts a formal expression such as "Thank you for your help" to a colloquial expression such as "Hello." The colloquial language conversion unit uses a generation AI to analyze the formal message and convert it to a natural colloquial language. The generation AI converts the formal message to a colloquial language using a text generation AI (e.g., LLM). Specifically, the generation AI receives a formal message as input and converts it to a colloquial language by applying grammar and vocabulary conversion rules. For example, it replaces honorifics and polite language contained in the formal message with appropriate colloquial expressions. The generation AI can also add appropriate conjunctions and phrases to understand the context and maintain a natural conversational flow. Furthermore, the generation AI can learn user preferences and past message history and perform personalized conversions. For example, it converts to a colloquial language that reflects the expressions and style preferred by a specific user. This allows the colloquial language conversion unit to convert a written message into a natural, easily understandable colloquial language, thereby providing a message that is easy for the user to use.

[0084] The playback unit plays back the colloquial message converted by the colloquial conversion unit. The playback unit has functions, for example, to highlight specific keywords and to adjust the tone and speed of the speech based on user settings. For example, by emphasizing important keywords during playback, the user can ensure that they do not miss important information. The playback unit uses a generation AI to play back the colloquial message. The generation AI uses a speech generation AI to play back the colloquial message. Specifically, the generation AI generates natural pronunciation and intonation when converting text to speech. For example, the speech generation AI understands the context of the text and adds appropriate emotion and emphasis to generate more natural, easy-to-listen speech. The playback unit also has a function to adjust the tone and speed of the speech according to the user's preferences. For example, if a user prefers fast playback, the playback speed can be adjusted to quickly convey the message. The playback unit also has a function to highlight specific keywords and phrases. For example, by highlighting important information or action items, the user can ensure that they do not miss important points. This allows the playback unit to provide users with an easy-to-understand and effective speech message.

[0085] The answer acceptance unit accepts the user's answer to the message played by the playback unit. For example, the answer acceptance unit converts the user's voice into text, and then the literary style conversion unit converts it into literary style. The answer acceptance unit converts the user's voice into text using voice recognition technology. Specifically, a voice recognition AI analyzes the user's speech in real time and converts it into text data. For example, if the user utters "Yes, I understand," the voice recognition AI acquires this as text data. Furthermore, the answer acceptance unit analyzes the content of the user's speech and prepares to convert it into an appropriate literary style. For example, it analyzes the intention and emotion of the speech content and selects an appropriate literary style expression. As a result, the answer acceptance unit can accurately convert the user's voice answer into text and use it for subsequent processing.

[0086] The literary style conversion unit converts the response received by the response receiving unit into a literary style. For example, the literary style conversion unit converts a verbal response such as "Yes, I understand" into a literary style such as "I understand." The literary style conversion unit converts the verbal response into a literary style using a generation AI. The generation AI converts the verbal response into a literary style using a text generation AI (e.g., LLM). Specifically, the generation AI receives the verbal response as input and converts it into a literary style by applying grammar and vocabulary conversion rules. For example, it converts the colloquial expression "I understand" into the literary style "I understand." The generation AI also understands the context and generates more formal literary expressions by adding appropriate honorifics and polite language. Furthermore, the generation AI can learn user preferences and past message history and perform personalized conversions. For example, it converts into a literary style that reflects the expressions and style preferred by a specific user. As a result, the literary style conversion unit converts the verbal response into a natural and appropriate literary style, thereby providing a message that is easy for the user to use.

[0087] The sending unit automatically sends the response in formal language converted by the formal language conversion unit. The sending unit has, for example, a function to prompt the user for confirmation before sending. For example, the user can check the content of the message and correct it if necessary. The sending unit automatically sends the response in formal language using a generation AI. The generation AI automatically sends the response in formal language using a text generation AI (for example, LLM). Specifically, the generation AI receives the response in formal language as input and selects an appropriate recipient and sending method. For example, it automatically extracts an email address or phone number and sends it in an appropriate format. The sending unit also has a function to prompt the user for confirmation before sending. For example, the user can check the content of the message and correct it if necessary. Furthermore, the sending unit has a function to record the sending history and make it available for later reference. This allows the sending unit to accurately and quickly send responses in formal language and provide a message sending function that is easy for users to use.

[0088] The playback unit may have a function for emphasizing specific keywords, thereby preventing the user from missing important information. The playback unit may adjust the tone and volume of the audio to emphasize specific keywords. For example, the playback unit may raise the tone and volume of the audio to emphasize important keywords. The playback unit may also adjust the speed of the audio to emphasize specific keywords. For example, the playback unit may slow down the speed of the audio to emphasize important keywords. This allows the playback unit to play back audio with emphasis on specific keywords, preventing the user from missing important information. Some or all of the above-described processing in the playback unit may be performed using, or without, AI. For example, the playback unit may input audio data to a generation AI to emphasize specific keywords, and have the generation AI adjust the tone and volume of the audio.

[0089] The playback unit may have a function to adjust the tone and speed of the voice based on information set by the user. This enables easier-to-listen voice playback. The playback unit may change the pitch of the voice or emotional expression to adjust the tone of the voice. For example, the playback unit may increase or decrease the pitch of the voice based on information set by the user. The playback unit may also change the playback speed of the voice to adjust the speed of the voice. For example, the playback unit may increase or decrease the playback speed of the voice based on information set by the user. This enables easier-to-listen voice playback by adjusting the tone and speed of the voice based on the information set by the user. Some or all of the above-described processing in the playback unit may be performed using, or without, AI. For example, the playback unit may input voice data to a generation AI and have the generation AI adjust the tone and speed of the voice.

[0090] The transmission unit can have a function to prompt the user for confirmation before transmission. This can prevent erroneous transmission. The transmission unit can use methods such as a pop-up notification or audio confirmation to prompt the user for confirmation. For example, the transmission unit can display a pop-up notification before transmission to prompt the user to confirm the content of the transmission. The transmission unit can also perform audio confirmation before transmission to prompt the user to confirm the content of the transmission. This can prevent erroneous transmission by prompting the user for confirmation before transmission. Some or all of the above-mentioned processing in the transmission unit can be performed using, for example, AI, or can be performed without using AI. For example, the transmission unit can have the generation AI perform a pop-up notification or audio confirmation to prompt the user to confirm the content before transmission.

[0091] The message reception unit can have a function of accepting multiple messages in a batch. This enables efficient message management. The message reception unit can set the number and type of messages to be accepted simultaneously. For example, the message reception unit can set the number of messages to be accepted simultaneously and accept multiple messages in a batch. The message reception unit can also set the type of messages to be accepted simultaneously and accept messages of a specific type in a batch. This enables efficient message management by the message reception unit accepting multiple messages in a batch. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the message reception unit can have the generation AI set the number and type of messages in order to accept multiple messages in a batch.

[0092] The system includes a determination unit that determines the importance of each of the plurality of messages, and the colloquial language conversion unit can convert the plurality of messages from a written style to a colloquial style in descending order of importance determined by the determination unit. The determination unit, for example, determines the importance of the plurality of messages. The importance is determined, for example, based on urgency or the importance of the content, but is not limited to such examples. The determination unit determines the importance of the messages based on urgency, for example. For example, the determination unit prioritizes determining messages with a high urgency as being of high importance. The determination unit can also determine the importance of the messages based on the importance of the content. For example, the determination unit prioritizes determining messages with a high importance as being of high importance. The colloquial language conversion unit converts the plurality of messages from a written style to a colloquial style in descending order of importance determined by the determination unit. For example, the colloquial language conversion unit prioritizes converting messages with a high importance from a written style to a colloquial style. As a result, the colloquial language conversion unit can quickly process important messages by preferentially converting messages with a high importance to a colloquial style. Some or all of the above-described processes in the determination unit and the colloquial language conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit may have the generation AI evaluate the urgency or importance of the content to determine the importance of the message. Furthermore, the colloquial language conversion unit may have the generation AI perform a conversion process to preferentially convert messages with high importance from written language to colloquial language.

[0093] The playback unit can play back messages in the voice of a specific character selected by the user. This enables more familiar voice playback. The playback unit can use a voice customized by the user or the voice of a famous character to select the voice of the specific character. For example, the playback unit can play back messages using a voice customized by the user. The playback unit can also play back messages using the voice of a famous character. This enables more familiar voice playback by playing back messages in the voice of a specific character selected by the user. Some or all of the above-described processing in the playback unit may be performed using, for example, AI or without AI. For example, the playback unit can input the voice of a specific character into a generation AI and cause the generation AI to generate voice data.

[0094] The literary style conversion unit can use appropriate abbreviations depending on the length of the message. This allows conversion to a more concise literary style. The literary style conversion unit can set criteria for using abbreviations depending on the length of the message. For example, the literary style conversion unit can use abbreviations when the length of the message is equal to or greater than a certain level. The literary style conversion unit can also use abbreviations depending on the content of the message. For example, the literary style conversion unit can convert to a more concise literary style by omitting less important parts. This allows the literary style conversion unit to convert to a more concise literary style by using appropriate abbreviations depending on the length of the message. Some or all of the above-mentioned processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can cause the generation AI to set criteria for abbreviations in order to use abbreviations depending on the length of the message.

[0095] The colloquial language conversion unit can convert the message into a dialect corresponding to the user's geographical location. This allows for conversion to a more natural colloquial style. The colloquial language conversion unit can acquire the user's geographical location and convert the message into a dialect corresponding to that location. For example, the colloquial language conversion unit can acquire the user's geographical location from GPS data or an IP address and convert the message into a dialect corresponding to that location. The colloquial language conversion unit can also convert the message into a dialect using a regional dialect list and conversion rules. For example, the colloquial language conversion unit can refer to a regional dialect list and convert the message into the regional dialect. This allows the colloquial language conversion unit to convert the message into a dialect corresponding to the user's geographical location, allowing for conversion to a more natural colloquial style. Some or all of the above-described processing in the colloquial language conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial language conversion unit can input the user's geographical location into a generation AI and have the generation AI perform dialect conversion.

[0096] The message reception unit can estimate the user's emotions and adjust the timing of message reception based on the estimated user emotions. This allows messages to be received at more appropriate times. The message reception unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the message reception unit can analyze the user's voice to estimate the user's emotions. The message reception unit can also recognize the user's facial expressions to estimate the user's emotions. The message reception unit adjusts the timing of message reception based on the estimated emotions. For example, if the user is stressed, the message reception unit can delay message reception so that the user can receive the message in a relaxed state. If the user is relaxed, the message can be received immediately to encourage a prompt response. Furthermore, if the user is busy, the message reception unit can prioritize only messages of high importance. This allows the message reception unit to adjust the timing of message reception according to the user's emotions, allowing messages to be received at more appropriate times. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the message receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the message receiving unit may input voice data or image data to a generation AI to estimate a user's emotion, and have the generation AI perform emotion estimation.

[0097] The message reception unit can analyze the user's past message reception history and select the optimal reception method. This allows the optimal reception method to be selected. The message reception unit can acquire and analyze the past message reception history. For example, the message reception unit can analyze time periods during which the user frequently received messages in the past and prioritize receiving messages during those time periods. The message reception unit can also prioritize receiving message formats (email, short messages, etc.) that the user has previously preferred. Furthermore, the message reception unit can prioritize receiving messages from specific senders based on the user's past message reception history. This allows the message reception unit to select the optimal reception method by analyzing the user's past message reception history. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without AI. For example, the message reception unit can input the user's past message reception history into a generation AI and have the generation AI select the optimal reception method.

[0098] When receiving messages, the message reception unit can filter messages based on the user's current project or area of ​​interest. This allows highly relevant messages to be preferentially received. The message reception unit can acquire the user's current project or area of ​​interest and filter messages based on that information. For example, the message reception unit can preferentially receive messages related to a project the user is currently working on. The message reception unit can also filter and receive highly relevant messages based on the user's area of ​​interest. Furthermore, the message reception unit can preferentially receive important messages based on keywords set by the user. This allows the message reception unit to preferentially receive highly relevant messages by filtering based on the user's current project or area of ​​interest. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the message reception unit can input the user's current project or area of ​​interest into a generation AI and have the generation AI perform filtering.

[0099] The message reception unit can estimate the user's emotions and prioritize messages to be received based on the estimated user emotions. This enables more appropriate message management. The message reception unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the message reception unit can analyze the user's voice to estimate the user's emotions. The message reception unit can also recognize the user's facial expressions to estimate the user's emotions. The message reception unit determines the priority of messages to be received based on the estimated emotions. For example, if the user is stressed, messages of low importance can be postponed. Also, if the user is relaxed, all messages can be received equally. Furthermore, if the user is in a hurry, messages of high importance can be given priority. This enables more appropriate message management by determining the priority of messages to be received based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the message receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the message receiving unit may input voice data or image data to a generation AI to estimate a user's emotion, and have the generation AI perform emotion estimation.

[0100] When receiving messages, the message reception unit can prioritize receiving highly relevant messages by taking into account the user's geographical location information. This enables more appropriate message management. The message reception unit can acquire the user's geographical location information and filter messages based on that information. For example, if the user is in a specific area, the message reception unit can prioritize receiving messages related to that area. Furthermore, if the user is traveling, the message reception unit can prioritize receiving messages related to the travel destination. Furthermore, if the user is at home, the message reception unit can prioritize receiving messages related to the home. This enables more appropriate message management by the message reception unit prioritizing receiving highly relevant messages by taking into account the user's geographical location information. Some or all of the above-described processing in the message reception unit may be performed using AI, for example, or may be performed without using AI. For example, the message reception unit can input the user's geographical location information to a generation AI and cause the generation AI to filter highly relevant messages.

[0101] When receiving a message, the message reception unit can analyze the user's social media activity and receive related messages. This allows for preferential reception of related messages. The message reception unit can acquire the user's social media activity and filter messages based on that information. For example, the message reception unit can preferentially receive messages related to topics that the user frequently mentions on social media. The message reception unit can also preferentially receive messages from accounts the user follows. Furthermore, the message reception unit can preferentially receive messages related to groups or communities in which the user participates. This allows the message reception unit to preferentially receive related messages by analyzing the user's social media activity. Some or all of the above-described processing in the message reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the message reception unit can input the user's social media activity into a generation AI and have the generation AI filter out related messages.

[0102] The colloquial language conversion unit can estimate the user's emotions and adjust the colloquial language expression based on the estimated user emotions. This allows for conversion to a more natural colloquial language. The colloquial language conversion unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the colloquial language conversion unit can analyze the user's voice to estimate the emotions. The colloquial language conversion unit can also recognize the user's facial expressions to estimate the emotions. The colloquial language conversion unit adjusts the colloquial language expression based on the estimated emotions. For example, if the user is relaxed, the colloquial language conversion unit can convert the user's expressions to friendly and casual expressions. If the user is nervous, the colloquial language conversion unit can convert the user's expressions to polite and calm expressions. Furthermore, if the user is excited, the colloquial language conversion unit can convert the user's expressions to energetic and lively expressions. This allows for conversion to a more natural colloquial language by adjusting the colloquial language expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the colloquial language conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial language conversion unit may input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0103] During colloquial conversion, the colloquial conversion unit can adjust the level of detail of the conversion based on the importance of the message. This allows conversion to a colloquial style with an appropriate level of detail. The colloquial conversion unit can determine the importance of the message and adjust the level of detail of the conversion based on the importance. For example, the colloquial conversion unit can convert a message of high importance into a colloquial style that includes detailed explanations. The colloquial conversion unit can also convert a message of low importance into a concise colloquial style. Furthermore, the colloquial conversion unit can convert into a colloquial style with an appropriate level of detail depending on the importance. This allows conversion to a colloquial style with an appropriate level of detail by adjusting the level of detail of the conversion based on the importance of the message. Some or all of the above-described processing in the colloquial conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial conversion unit can input the importance of the message to a generation AI and cause the generation AI to adjust the level of detail of the conversion.

[0104] When converting a message into a colloquial style, the colloquial style conversion unit can apply different conversion algorithms depending on the category of the message. This allows for conversion into a more appropriate colloquial style. The colloquial style conversion unit can determine the category of the message and apply different conversion algorithms depending on the category. For example, the colloquial style conversion unit can convert a business-related message into a formal colloquial style. The colloquial style conversion unit can also convert a private message into a casual colloquial style. Furthermore, the colloquial style conversion unit can convert an urgent message into a colloquial style that can be quickly understood. This allows for conversion into a more appropriate colloquial style by applying different conversion algorithms depending on the category of the message. Some or all of the above-described processing in the colloquial style conversion unit may be performed using, or without, AI. For example, the colloquial style conversion unit can input the message category into a generation AI and cause the generation AI to apply different conversion algorithms.

[0105] The colloquial language conversion unit can estimate the user's emotions and adjust the length of the colloquial language based on the estimated user emotions. This allows for conversion to a more appropriate colloquial language. The colloquial language conversion unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the colloquial language conversion unit can analyze the user's voice to estimate the emotions. The colloquial language conversion unit can also recognize the user's facial expressions to estimate the emotions. The colloquial language conversion unit adjusts the length of the colloquial language based on the estimated emotions. For example, if the user is in a hurry, the colloquial language conversion unit can convert to a short, concise colloquial language. If the user is relaxed, the colloquial language conversion unit can convert to a longer colloquial language that includes detailed explanations. Furthermore, if the user is excited, the colloquial language conversion unit can convert to a colloquial language that includes energetic and lively expressions. This allows for conversion to a more appropriate colloquial language by adjusting the length of the colloquial language based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the colloquial language conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial language conversion unit may input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0106] When converting a message into a colloquial style, the colloquial style conversion unit can determine the priority of conversion based on the time the message was submitted. This allows conversion to a colloquial style in an appropriate order. The colloquial style conversion unit can obtain the time the message was submitted and determine the priority of conversion based on that information. For example, the colloquial style conversion unit can preferentially convert recently submitted messages into a colloquial style. The colloquial style conversion unit can also convert older submitted messages into a colloquial style later. Furthermore, the colloquial style conversion unit can convert messages into a colloquial style in an appropriate priority depending on the time of submission. This allows conversion to a colloquial style in an appropriate order by determining the priority of conversion based on the time the message was submitted. Some or all of the above-described processing in the colloquial style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial style conversion unit can input the time the message was submitted to a generation AI and have the generation AI determine the priority of conversion.

[0107] During colloquial conversion, the colloquial conversion unit can adjust the order of conversion based on the relevance of the messages. This allows highly relevant messages to be preferentially converted to colloquial form. The colloquial conversion unit can determine the relevance of the messages and adjust the order of conversion based on the relevance. For example, the colloquial conversion unit can preferentially convert messages related to the user's current project into colloquial form. The colloquial conversion unit can also preferentially convert messages related to the user's areas of interest into colloquial form. Furthermore, the colloquial conversion unit can preferentially convert important messages into colloquial form based on keywords set by the user. This allows the colloquial conversion unit to preferentially convert highly relevant messages into colloquial form by adjusting the order of conversion based on the relevance of the messages. Some or all of the above-described processing in the colloquial conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the colloquial conversion unit can input the relevance of the messages to a generation AI and have the generation AI adjust the order of conversion.

[0108] The playback unit can estimate the user's emotion and adjust the playback tone based on the estimated user's emotion. This allows the message to be played back in a more appropriate tone. The playback unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotion. For example, the playback unit can analyze the user's voice to estimate the emotion. The playback unit can also recognize the user's facial expression to estimate the emotion. The playback unit adjusts the playback tone based on the estimated emotion. For example, if the user is relaxed, the playback can be played in a calm tone. If the user is nervous, the playback can be played in a subdued tone. Furthermore, if the user is excited, the playback can be played in a lively tone. This allows the playback unit to adjust the playback tone according to the user's emotion, allowing the message to be played back in a more appropriate tone. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the playback unit may be performed using, for example, AI, or without AI. For example, the playback unit can input audio data and image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0109] During playback, the playback unit can adjust the playback speed based on the importance of the message. This allows the message to be played at an appropriate speed. The playback unit can determine the importance of the message and adjust the playback speed based on the importance. For example, the playback unit can play messages of high importance slowly to facilitate understanding. The playback unit can also play messages of low importance faster to improve efficiency. Furthermore, the playback unit can play messages at an appropriate speed depending on the importance. This allows the playback unit to play messages at an appropriate speed by adjusting the playback speed based on the importance of the message. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the importance of the message to the generation AI and have the generation AI adjust the playback speed.

[0110] During playback, the playback unit can apply different playback algorithms depending on the message category. This allows the message to be played back in a more appropriate tone. The playback unit can determine the message category and apply different playback algorithms depending on the category. For example, the playback unit can play back business-related messages in a formal tone. The playback unit can also play back private messages in a casual tone. Furthermore, the playback unit can play back emergency messages in a tone that is quickly understandable. This allows the playback unit to play back messages in a more appropriate tone by applying different playback algorithms depending on the message category. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the message category to a generation AI and cause the generation AI to apply different playback algorithms.

[0111] The playback unit can estimate the user's emotions and adjust the playback order based on the estimated user emotions. This allows messages to be played in a more appropriate order. The playback unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the playback unit can analyze the user's voice to estimate the emotions. The playback unit can also recognize the user's facial expressions to estimate the emotions. The playback unit adjusts the playback order based on the estimated emotions. For example, if the user is stressed, messages of low importance can be postponed. If the user is relaxed, all messages can be played evenly. Furthermore, if the user is in a hurry, messages of high importance can be played preferentially. This allows the playback unit to adjust the playback order according to the user's emotions, allowing messages to be played in a more appropriate order. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input voice data or image data to a generation AI to estimate a user's emotion, and have the generation AI perform emotion estimation.

[0112] During playback, the playback unit can determine the playback priority based on the submission time of the message. This allows messages to be played back in an appropriate order. The playback unit can obtain the submission time of the message and determine the playback priority based on that information. For example, the playback unit can prioritize playback of recently submitted messages. The playback unit can also postpone playback of messages that were submitted earlier. Furthermore, the playback unit can play back messages with an appropriate priority based on the submission time. This allows messages to be played back in an appropriate order by determining the playback priority based on the submission time of the message. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the submission time of the message to the generation AI and have the generation AI determine the playback priority.

[0113] During playback, the playback unit can adjust the playback order based on the relevance of the messages. This allows highly relevant messages to be prioritized for playback. The playback unit can determine the relevance of the messages and adjust the playback order based on the relevance. For example, the playback unit can prioritize playback of messages related to the user's current project. The playback unit can also prioritize playback of messages related to the user's areas of interest. Furthermore, the playback unit can prioritize playback of important messages based on keywords set by the user. This allows the playback unit to prioritize playback of highly relevant messages by adjusting the playback order based on the relevance of the messages. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input the relevance of the messages to a generation AI and have the generation AI adjust the playback order.

[0114] The answer accepting unit can estimate the user's emotion and adjust the answer accepting method based on the estimated user's emotion. This allows answers to be accepted in a more appropriate manner. The answer accepting unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotion. For example, the answer accepting unit can analyze the user's voice to estimate the emotion. The answer accepting unit can also recognize the user's facial expression to estimate the emotion. The answer accepting unit adjusts the answer accepting method based on the estimated emotion. For example, if the user is relaxed, a detailed answer can be accepted. On the other hand, if the user is nervous, a concise answer can be accepted. Furthermore, if the user is in a hurry, voice input can be prioritized to quickly accept an answer. This allows the answer accepting unit to accept answers in a more appropriate manner by adjusting the answer accepting method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answer receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer receiving unit may input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0115] When accepting an answer, the answer accepting unit can analyze the user's past answer history and select the optimal answer accepting method. The answer accepting unit can acquire and analyze the past answer history. For example, the answer accepting unit can preferentially accept answer methods (voice, text, etc.) that the user has frequently used in the past. The answer accepting unit can also predict and suggest an answer method to be used in a specific time period based on the user's past answer history. Furthermore, the answer accepting unit can preferentially accept answer formats that the user has preferred in the past. In this way, the answer accepting unit can select the optimal answer accepting method by analyzing the user's past answer history. Some or all of the above-described processing in the answer accepting unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer accepting unit can input the user's past answer history into a generation AI and have the generation AI select the optimal answer accepting method.

[0116] When receiving answers, the answer receiving unit can filter answers based on the user's current project or area of ​​interest. This allows highly relevant answers to be preferentially received. The answer receiving unit can acquire the user's current project or area of ​​interest and filter answers based on that information. For example, the answer receiving unit can preferentially receive answers related to a project the user is currently working on. The answer receiving unit can also filter and receive highly relevant answers based on the user's area of ​​interest. Furthermore, the answer receiving unit can preferentially receive important answers based on keywords set by the user. This allows the answer receiving unit to preferentially receive highly relevant answers by filtering based on the user's current project or area of ​​interest. Some or all of the above-described processing in the answer receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer receiving unit can input the user's current project or area of ​​interest to a generation AI and have the generation AI perform filtering.

[0117] The answer accepting unit can estimate the user's emotions and determine the priority of answers to be accepted based on the estimated user emotions. This enables more appropriate answer management. The answer accepting unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the answer accepting unit can analyze the user's voice to estimate the emotions. The answer accepting unit can also recognize the user's facial expressions to estimate the emotions. The answer accepting unit determines the priority of answers to be accepted based on the estimated emotions. For example, if the user is stressed, answers with lower importance can be postponed. Furthermore, if the user is relaxed, all answers can be accepted equally. Furthermore, if the user is in a hurry, answers with higher importance can be accepted preferentially. This enables more appropriate answer management by determining the priority of answers to be accepted based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the answer receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer receiving unit may input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0118] When accepting answers, the answer acceptance unit can prioritize accepting highly relevant answers by taking into account the user's geographical location information. This enables more appropriate answer management. The answer acceptance unit can acquire the user's geographical location information and filter answers based on that information. For example, if the user is in a specific area, the answer acceptance unit can prioritize accepting answers related to that area. Furthermore, if the user is traveling, the answer acceptance unit can prioritize accepting answers related to the travel destination. Furthermore, if the user is at home, the answer acceptance unit can prioritize accepting answers related to the home. This enables more appropriate answer management by preferentially accepting highly relevant answers by taking into account the user's geographical location information. Some or all of the above-described processing in the answer acceptance unit may be performed using AI, for example, or may be performed without using AI. For example, the answer acceptance unit can input the user's geographical location information to the generation AI and cause the generation AI to filter highly relevant answers.

[0119] When accepting answers, the answer acceptance unit can analyze the user's social media activity and accept relevant answers. This allows relevant answers to be accepted preferentially. The answer acceptance unit can acquire the user's social media activity and filter answers based on that information. For example, the answer acceptance unit can preferentially accept answers related to topics that the user frequently mentions on social media. The answer acceptance unit can also preferentially accept answers from accounts that the user follows. Furthermore, the answer acceptance unit can also preferentially accept answers related to groups or communities in which the user participates. This allows the answer acceptance unit to preferentially accept relevant answers by analyzing the user's social media activity. Some or all of the above-described processing in the answer acceptance unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer acceptance unit inputs the user's social media activity into a generation AI and causes the generation AI to filter relevant answers.

[0120] The literary style conversion unit can estimate the user's emotions and adjust the literary style expression based on the estimated user emotions. This allows for conversion to a more appropriate literary style. The literary style conversion unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the literary style conversion unit can analyze the user's voice to estimate the emotions. The literary style conversion unit can also recognize the user's facial expressions to estimate the emotions. The literary style conversion unit adjusts the literary style expression based on the estimated emotions. For example, if the user is relaxed, the literary style conversion unit can convert to a friendly and casual literary style. If the user is nervous, the literary style conversion unit can convert to a polite and calm literary style. Furthermore, if the user is excited, the literary style conversion unit can convert to an energetic and lively literary style. This allows for conversion to a more appropriate literary style by adjusting the literary style expression based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit may input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0121] During the literary style conversion, the literary style conversion unit can adjust the level of detail of the conversion based on the importance of the answer. This allows conversion to a literary style with an appropriate level of detail. The literary style conversion unit can determine the importance of the answer and adjust the level of detail of the conversion based on the importance. For example, the literary style conversion unit can convert an answer with high importance into a literary style that includes detailed explanations. The literary style conversion unit can also convert an answer with low importance into a concise literary style. Furthermore, the literary style conversion unit can convert into a literary style with an appropriate level of detail depending on the importance. This allows conversion to a literary style with an appropriate level of detail by adjusting the level of detail of the conversion based on the importance of the answer. Some or all of the above-described processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the importance of the answer to a generation AI and have the generation AI adjust the level of detail of the conversion.

[0122] When converting the literary style, the literary style conversion unit can apply different conversion algorithms depending on the category of the answer. This allows for conversion to a more appropriate literary style. The literary style conversion unit can determine the category of the answer and apply different conversion algorithms depending on the category. For example, the literary style conversion unit can convert business-related answers into a formal literary style. The literary style conversion unit can also convert private answers into a casual literary style. Furthermore, the literary style conversion unit can convert urgent answers into a literary style that can be quickly understood. This allows for conversion to a more appropriate literary style by applying different conversion algorithms depending on the category of the answer. Some or all of the above-mentioned processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the category of the answer to the generation AI and cause the generation AI to apply different conversion algorithms.

[0123] The literary style conversion unit can estimate the user's emotions and adjust the length of the literary style based on the estimated user emotions. This allows for conversion to a more appropriate literary style. The literary style conversion unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the literary style conversion unit can analyze the user's voice to estimate the emotions. The literary style conversion unit can also recognize the user's facial expressions to estimate the emotions. The literary style conversion unit adjusts the length of the literary style based on the estimated emotions. For example, if the user is in a hurry, the literary style conversion unit can convert to a short, to-the-point literary style. If the user is relaxed, the literary style conversion unit can convert to a longer literary style with detailed explanations. Furthermore, if the user is excited, the literary style conversion unit can convert to a literary style with energetic and lively expressions. This allows for conversion to a more appropriate literary style by adjusting the length of the literary style based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit may input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0124] When converting the literary style, the literary style conversion unit can determine the priority of conversion based on the time of submission of the answer. This allows conversion to literary style in an appropriate order. The literary style conversion unit can obtain the time of submission of the answer and determine the priority of conversion based on that information. For example, the literary style conversion unit can preferentially convert recently submitted answers to literary style. The literary style conversion unit can also convert older submitted answers to literary style later. Furthermore, the literary style conversion unit can convert to literary style in an appropriate priority depending on the time of submission. This allows conversion to literary style in an appropriate order by determining the priority of conversion based on the time of submission of the answer. Some or all of the above-mentioned processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the time of submission of the answer to the generation AI and have the generation AI determine the priority of conversion.

[0125] During the literary style conversion, the literary style conversion unit can adjust the order of conversion based on the relevance of the answers. This allows highly relevant answers to be preferentially converted to a literary style. The literary style conversion unit can determine the relevance of the answers and adjust the order of conversion based on the relevance. For example, the literary style conversion unit can preferentially convert answers related to the user's current project to a literary style. The literary style conversion unit can also preferentially convert answers related to the user's field of interest to a literary style. Furthermore, the literary style conversion unit can preferentially convert important answers to a literary style based on keywords set by the user. This allows the literary style conversion unit to preferentially convert highly relevant answers to a literary style by adjusting the order of conversion based on the relevance of the answers. Some or all of the above-described processing in the literary style conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the literary style conversion unit can input the relevance of the answers to a generation AI and have the generation AI adjust the order of conversion.

[0126] The transmitting unit can estimate the user's emotion and adjust the timing of transmission based on the estimated user's emotion. This allows for more appropriate timing for transmission. The transmitting unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotion. For example, the transmitting unit can analyze the user's voice to estimate the emotion. The transmitting unit can also recognize the user's facial expression to estimate the emotion. The transmitting unit adjusts the timing of transmission based on the estimated emotion. For example, if the user is relaxed, the transmitting unit can transmit immediately. If the user is nervous, the transmitting unit can prompt the user to confirm before transmitting. Furthermore, if the user is in a hurry, the transmitting unit can transmit quickly. This allows for more appropriate timing for transmission by adjusting the timing of transmission according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the transmitting unit may be performed using, for example, AI, or without AI. For example, the transmission unit can input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0127] The transmitting unit can determine the transmission priority based on the importance of the answer at the time of transmission. This allows for transmission in an appropriate order. The transmitting unit can determine the importance of the answer and determine the transmission priority based on the importance. For example, the transmitting unit can transmit answers with high importance first. The transmitting unit can also transmit answers with low importance later. Furthermore, the transmitting unit can transmit answers with an appropriate priority according to their importance. This allows for transmission in an appropriate order by determining the transmission priority based on the importance of the answer. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can input the importance of the answer to the generating AI and have the generating AI determine the transmission priority.

[0128] The sending unit can apply different sending algorithms depending on the category of the answer when sending. This allows for sending in a more appropriate manner. The sending unit can determine the category of the answer and apply different sending algorithms depending on the category. For example, the sending unit can apply a formal sending method to a business-related answer. The sending unit can also apply a casual sending method to a private answer. Furthermore, the sending unit can apply an algorithm for quickly sending an urgent answer. This allows for sending in a more appropriate manner by applying different sending algorithms depending on the category of the answer. Some or all of the above-mentioned processing in the sending unit may be performed using AI, for example, or may be performed without using AI. For example, the sending unit can input the category of the answer to a generation AI and cause the generation AI to apply different sending algorithms.

[0129] The transmission unit can estimate the user's emotions and adjust the transmission confirmation method based on the estimated user emotions. This allows for providing a more appropriate confirmation method. The transmission unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotions. For example, the transmission unit can analyze the user's voice to estimate the emotions. The transmission unit can also recognize the user's facial expressions to estimate the emotions. The transmission unit adjusts the transmission confirmation method based on the estimated emotions. For example, if the user is relaxed, a simple confirmation method can be provided. If the user is nervous, a detailed confirmation method can be provided. Furthermore, if the user is in a hurry, a quick confirmation method can be provided. This allows for the transmission unit to adjust the transmission confirmation method according to the user's emotions, allowing for providing a more appropriate confirmation method. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or without AI. For example, the transmission unit can input voice data or image data to the generation AI to estimate the user's emotions, and have the generation AI perform emotion estimation.

[0130] At the time of transmission, the transmitting unit can determine the priority of transmission based on the time of submission of the answers. This allows transmission in an appropriate order. The transmitting unit can obtain the time of submission of the answers and determine the priority of transmission based on that information. For example, the transmitting unit can prioritize transmitting the most recently submitted answers. The transmitting unit can also postpone transmitting answers that were submitted earlier. Furthermore, the transmitting unit can transmit with an appropriate priority depending on the time of submission. This allows transmission in an appropriate order by determining the priority of transmission based on the time of submission of the answers. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can input the time of submission of the answers to the generating AI and have the generating AI determine the priority of transmission.

[0131] The transmitting unit can adjust the order of transmission based on the relevance of the answers at the time of transmission. This allows highly relevant answers to be preferentially transmitted. The transmitting unit can determine the relevance of the answers and adjust the order of transmission based on the relevance. For example, the transmitting unit can preferentially transmit answers related to the user's current project. The transmitting unit can also preferentially transmit answers related to the user's field of interest. Furthermore, the transmitting unit can preferentially transmit important answers based on keywords set by the user. This allows the transmitting unit to preferentially transmit highly relevant answers by adjusting the order of transmission based on the relevance of the answers. Some or all of the above-described processing in the transmitting unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmitting unit can input the relevance of the answers to a generating AI and have the generating AI adjust the order of transmission.

[0132] The determination unit can estimate the user's emotion and determine the importance of a message based on the estimated emotion. This enables more appropriate importance determination. The determination unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotion. For example, the determination unit can analyze the user's voice to estimate the emotion. The determination unit can also recognize the user's facial expression to estimate the emotion. The determination unit determines the importance of a message based on the estimated emotion. For example, if the user is relaxed, the determination unit can equally determine the importance of all messages. Furthermore, if the user is nervous, the determination unit can prioritize messages with higher importance. Furthermore, if the user is in a hurry, the determination unit can quickly determine messages with higher importance. This enables more appropriate importance determination by determining the importance of a message based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input voice data or image data to the generation AI to estimate the user's emotion, and have the generation AI perform emotion estimation.

[0133] The determination unit can adjust the importance level based on the content of the message when making the determination. This enables appropriate importance determination. The determination unit can analyze the content of the message and adjust the importance level based on the content. For example, the determination unit can determine that a business-related message has a high importance level. The determination unit can also determine that a private message has a low importance level. Furthermore, the determination unit can determine that an urgent message has the highest priority in importance. This enables appropriate importance determination by adjusting the importance level based on the content of the message. Some or all of the above-described processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input the content of the message to a generation AI and have the generation AI adjust the importance level.

[0134] When making a judgment, the judgment unit can apply different judgment algorithms depending on the message category. This enables more appropriate importance judgment. The judgment unit can judge the message category and apply different judgment algorithms depending on the category. For example, the judgment unit can apply a formal judgment algorithm to business-related messages. The judgment unit can also apply a casual judgment algorithm to private messages. Furthermore, the judgment unit can apply a quick judgment algorithm to urgent messages. This enables more appropriate importance judgment by applying different judgment algorithms depending on the message category. Some or all of the above-mentioned processing in the judgment unit may be performed using AI, for example, or may be performed without using AI. For example, the judgment unit can input the message category to the generation AI and cause the generation AI to apply different judgment algorithms.

[0135] The determination unit can estimate the user's emotion and adjust the importance determination criteria based on the estimated user emotion. This enables more appropriate importance determination. The determination unit can use technologies such as voice analysis and facial expression recognition to estimate the user's emotion. For example, the determination unit can analyze the user's voice to estimate the emotion. The determination unit can also recognize the user's facial expression to estimate the emotion. The determination unit adjusts the importance determination criteria based on the estimated emotion. For example, if the user is relaxed, all messages can be equally prioritized. Also, if the user is nervous, messages with high importance can be prioritized. Furthermore, if the user is in a hurry, messages with high importance can be quickly prioritized. This enables more appropriate importance determination by adjusting the importance determination criteria according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the determination unit can input voice data or image data to the generation AI to estimate the user's emotion, and have the generation AI perform emotion estimation.

[0136] At the time of judgment, the judgment unit can determine the importance level based on the submission time of the message. This enables appropriate importance determination. The judgment unit can obtain the submission time of the message and determine the importance level based on that information. For example, the judgment unit can prioritize recently submitted messages as being of high importance. The judgment unit can also determine that older submitted messages are of low importance. Furthermore, the judgment unit can determine an appropriate importance level depending on the submission time. This enables appropriate importance determination by determining the importance level based on the submission time of the message. Some or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input the submission time of the message to the generation AI and have the generation AI determine the importance level.

[0137] During the determination, the determination unit can adjust the order of importance based on the relevance of the messages. This allows highly relevant messages to be given higher importance. The determination unit can determine the relevance of the messages and adjust the order of importance based on the relevance. For example, the determination unit can prioritize messages related to the user's current project as being more important. The determination unit can also prioritize messages related to the user's field of interest as being more important. Furthermore, the determination unit can prioritize important messages as being more important based on keywords set by the user. This allows the determination unit to prioritize highly relevant messages as being more important by adjusting the order of importance based on the relevance of the messages. Some or all of the above-described processing in the determination unit may be performed using, or without, AI. For example, the determination unit can input the relevance of the messages to a generation AI and have the generation AI adjust the order of importance.

[0138] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0139] The message conversion system may further include a translation unit. The translation unit may translate a received message into a different language. For example, a message received in English may be translated into Japanese. The translation unit may also prioritize translation into a specific language based on a user's settings. For example, if a user has set French as their preferred language, the translation unit may translate into French. The translation unit may also select an appropriate translation method depending on the content of the message. For example, a formal translation method may be applied to business-related messages, and a casual translation method may be applied to private messages. This allows the message conversion system to facilitate communication between different languages.

[0140] The message conversion system may further include a notification unit. The notification unit may notify the user in real time when the user receives a new message. For example, the notification unit may notify the user of the receipt of a new message through a push notification on a smartphone or a desktop notification on a computer. The notification unit may also notify the user only during specific time periods based on the user's settings. For example, if the user does not want to receive notifications while at work, the notification unit may turn off notifications. The notification unit may also adjust the priority of notifications based on the importance of the message. For example, messages of high importance may be notified immediately, and messages of low importance may be notified later. This allows the message conversion system to prevent the user from missing important messages.

[0141] The message conversion system may further include a filtering unit. The filtering unit may filter accepted messages based on specific criteria. For example, spam messages and advertising messages may be automatically filtered so as not to be displayed to the user. The filtering unit may also accept only messages from specific senders based on user settings. For example, if a user wants to receive only messages related to a specific project, messages from senders related to that project may be accepted with priority. The filtering unit may also determine the importance of a message based on its content and process messages with higher importance with priority. This allows the message conversion system to efficiently obtain the information the user needs.

[0142] The message conversion system may further include an archive unit. The archive unit may automatically store past messages so that they can be searched and referenced as needed. For example, if a user wants to search for messages from a specific period, they can quickly search through the archive unit. The archive unit may also classify and organize messages based on message type or sender. For example, business-related messages and private messages may be stored separately. The archive unit may also adjust the storage period based on the importance of the message. For example, messages of high importance may be stored for a long period of time, and messages of low importance may be deleted after a short period of time. In this way, the message conversion system may enable the user to efficiently manage past messages.

[0143] The message conversion system may further include a customization unit. The customization unit may enable a user to individually configure the system's operation and display method. For example, the user may adjust the message playback speed and tone of voice. The customization unit may also enable a user to configure settings to highlight specific keywords or phrases. For example, by highlighting keywords related to an important project, the user may be able to ensure that important information is not overlooked. The customization unit may also enable a user to individually customize the system's interface. For example, the user may select their preferred colors and layout to achieve an easy-to-use interface. This allows the message conversion system to be flexibly customized to meet the user's needs.

[0144] The message conversion system may further include a sentiment analysis unit. The sentiment analysis unit may estimate the user's sentiment and adjust the message processing method based on the estimated sentiment. For example, if the user is feeling stressed, the system may slow down the message playback speed to allow the user to receive the message in a relaxed state. Alternatively, if the user is relaxed, the system may speed up the message playback speed to encourage a quick response. Furthermore, the sentiment analysis unit may determine the importance of the message based on the user's sentiment and prioritize processing of messages with high importance. This enables the message conversion system to flexibly process messages according to the user's sentiment.

[0145] The message conversion system may further include an emotion feedback unit. The emotion feedback unit may provide the system with feedback about the emotion the user felt toward the message. For example, when the user received a message, the user may input positive or negative emotion into the system. The emotion feedback unit may also adjust the operation of the system based on the user's feedback. For example, if the user felt negative emotion, the system may change the way the message is played back so that the user can receive the message in a more relaxed state. Furthermore, the emotion feedback unit may accumulate the user's feedback and use it in future message processing. This allows the message conversion system to respond flexibly based on the user's emotion.

[0146] The message conversion system may further include an emotion history unit. The emotion history unit may record and analyze the user's past emotion history. For example, the emotion history unit may record the emotions the user has felt in the past and adjust the message processing method based on that history. The emotion history unit may also track changes in the user's emotions and analyze long-term emotional trends. For example, if the user has been feeling stressed for a certain period of time, the message processing method for that period may be adjusted. Furthermore, the emotion history unit may suggest future improvements to message processing based on the user's emotion history. This allows the message conversion system to respond flexibly based on the user's emotion history.

[0147] The message conversion system may further include an emotion prediction unit. The emotion prediction unit can predict future emotions based on the user's current situation and past emotion history. For example, it can predict what emotion the user will feel in a specific situation and adjust the message processing method based on the prediction. The emotion prediction unit can also predict changes in emotions based on the user's schedule and activity history. For example, if the user has a busy schedule, it can predict that the user is likely to feel stressed and adjust the message playback method. Furthermore, the emotion prediction unit can provide messages at appropriate times based on the predicted user emotion. This enables the message conversion system to flexibly respond based on the user's future emotions.

[0148] The message conversion system may further include an emotion adjustment unit. The emotion adjustment unit can adjust the user's emotion to provide a better message receiving experience. For example, if the user is feeling stressed, the system can play relaxing music to calm the user's emotion. Alternatively, if the user is relaxed, the system can play energetic music to lift the user's mood. Furthermore, the emotion adjustment unit can adjust the way messages are played based on the user's emotion. For example, if the user is nervous, the system can play a message in a calm tone to relieve the user's tension. This allows the message conversion system to flexibly respond according to the user's emotion.

[0149] The processing flow of the second embodiment will be briefly explained below.

[0150] Step 1: The message reception unit receives email messages or short messages. Email messages and short messages include text messages and messages with images. A user inputs a message received on a smartphone or computer into the system, and the message reception unit receives it. Step 2: The colloquial language conversion unit converts the accepted message from formal to colloquial language. For example, it converts a formal expression such as "Thank you for your help" into a colloquial expression such as "Hello." Using a generative AI, it analyzes the formal message and converts it into a natural colloquial style. Step 3: The playback unit plays the colloquial message converted by the colloquial conversion unit. The playback unit has the function of emphasizing specific keywords and adjusting the tone and speed of the voice based on information set by the user. The generation AI is used to play the colloquial message. Step 4: The answer receiving unit receives the user's answer to the message played by the playback unit. The user's voice is converted into text, and the written language conversion unit converts it into written language. Step 5: The literary style conversion unit converts the answer received by the answer receiving unit into a literary style. For example, a verbal answer such as "Yes, I understand" is converted into a literary style such as "I'll acknowledge that." The verbal answer is converted into a literary style using a generation AI. Step 6: The sending unit automatically sends the response in formal language converted by the formal language conversion unit. It has a function that prompts the user to confirm the content before sending, allowing the user to check the content of the message and make corrections as necessary. The response in formal language is automatically sent using the generation AI.

[0151] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats including 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. The AIs other than the generation AI are, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but are not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or in whole by AI, but are not limited to these 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.

[0153] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] For example, the message receiving unit is implemented by at least one of the smart device 14 and the data processing device 12. For example, a message can be received using the receiving device 38 or the camera 42 of the smart device 14. The colloquial language conversion unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and converts a written message into a colloquial message. The playback unit is implemented by, for example, the output device 40 of the smart device 14 and plays the converted colloquial message aloud. The answer receiving unit is implemented by, for example, the receiving device 38 of the smart device 14 and converts the user's voice into text. The written language conversion unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and converts a verbal answer into a written answer. The transmission unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and automatically transmits the written answer. The determination unit is implemented by, for example, the specific processing unit 290 of the data processing device 12 and determines the importance of the message. The correspondence between each unit and the device or control unit is not limited to the above example and various modifications are possible.

[0155] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0156] 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.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] 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.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0162] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0163] 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.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0169] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] For example, the message receiving unit is realized by at least one of the smart glasses 214 and the data processing device 12. For example, a message can be received using the microphone 238 or the camera 42 of the smart glasses 214. The colloquial language conversion unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and converts a written message into a colloquial message. The playback unit is realized by, for example, the speaker 240 of the smart glasses 214 and plays the converted colloquial message aloud. The answer receiving unit is realized by, for example, the microphone 238 of the smart glasses 214 and converts the user's voice into text. The written language conversion unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and converts a verbal answer into a written answer. The transmission unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and automatically transmits the written answer. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and determines the importance of the message. The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0172] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0173] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0174] 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.

[0175] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0177] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0178] 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.

[0179] 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.

[0180] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0181] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0182] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0183] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0185] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0186] For example, the message receiving unit is realized by at least one of the headset terminal 314 and the data processing device 12. For example, a message can be received using the microphone 238 or the camera 42 of the headset terminal 314. The colloquial language conversion unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and converts a written message into a colloquial message. The playback unit is realized by, for example, the speaker 240 of the headset terminal 314 and plays the converted colloquial message aloud. The answer receiving unit is realized by, for example, the microphone 238 of the headset terminal 314 and converts the user's voice into text. The written language conversion unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and converts a spoken answer into a written answer. The transmission unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and automatically transmits a written answer. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and determines the importance of the message. The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0188] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0189] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0190] 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.

[0191] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0192] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0193] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0194] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0195] 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.

[0196] 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.

[0197] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0198] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0199] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0200] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0201] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0202] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0203] For example, the message receiving unit is realized by at least one of the robot 414 and the data processing device 12. For example, the message can be received using the microphone 238 or the camera 42 of the robot 414. The colloquial language conversion unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and converts a written message into a colloquial message. The playback unit is realized by, for example, the speaker 240 of the robot 414 and plays the converted colloquial message aloud. The answer receiving unit is realized by, for example, the microphone 238 of the robot 414 and converts the user's voice into text. The written language conversion unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and converts a verbal answer into a written answer. The transmission unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and automatically transmits a written answer. The determination unit is realized by, for example, the specific processing unit 290 of the data processing device 12 and determines the importance of the message. The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0204] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0205] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0206] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0207] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0208] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0209] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0210] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0211] 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.

[0212] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0213] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0214] 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.

[0215] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0216] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0217] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0218] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0219] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0220] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0221] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0222] (Appendix 1) a message reception unit for receiving email messages or short messages; a colloquial language conversion unit that converts the message received by the message receiving unit from formal language to colloquial language; a playback unit that plays back the colloquial message converted by the colloquial language conversion unit by voice; a response receiving unit that receives a user's response to the message reproduced by the reproduction unit; a literary style conversion unit that converts the answer received by the answer receiving unit into literary style; a sending unit that automatically sends the answer in a formal style converted by the formal style conversion unit. A system characterized by: (Appendix 2) The playback unit Has the ability to highlight specific keywords 2. The system of claim 1. (Appendix 3) The playback unit Has the ability to adjust the tone and speed of the voice based on user-defined information 2. The system of claim 1. (Appendix 4) The transmission unit It has a function to prompt the user for confirmation before sending 2. The system of claim 1. (Appendix 5) The message receiving unit Has the ability to accept multiple messages at once 2. The system of claim 1. (Appendix 6) A determination unit is provided, The colloquial language conversion unit The plurality of messages are converted from written language to colloquial language in descending order of importance determined by the determining unit. 2. The system of claim 1. (Appendix 7) The playback unit Plays messages in the voice of a specific character selected by the user 2. The system of claim 1. (Appendix 8) The literary style conversion unit Use appropriate abbreviations depending on the length of the message 2. The system of claim 1. (Appendix 9) The colloquial language conversion unit Convert to a dialect depending on the user's geographic location 2. The system of claim 1. (Appendix 10) The message receiving unit Estimates user emotions and adjusts message acceptance timing based on the estimated user emotions. 2. The system of claim 1. (Appendix 11) The message receiving unit Analyze the user's past message reception history and select the optimal reception method 2. The system of claim 1. (Appendix 12) The message receiving unit Filter incoming messages based on your current projects and interests 2. The system of claim 1. (Appendix 13) The message receiving unit Estimate the user's emotions and prioritize messages based on the estimated user emotions. 2. The system of claim 1. (Appendix 14) The message receiving unit When accepting messages, the system takes into account the user's geographic location information and prioritizes messages that are highly relevant. 2. The system of claim 1. (Appendix 15) The message receiving unit When receiving a message, analyze the user's social media activity and receive relevant messages. 2. The system of claim 1. (Appendix 16) The colloquial language conversion unit Estimating a user's emotions and adjusting colloquial expressions based on the estimated user's emotions 2. The system of claim 1. (Appendix 17) The colloquial language conversion unit When translating colloquial language, adjust the verbosity of the translation based on the importance of the message 2. The system of claim 1. (Appendix 18) The colloquial language conversion unit When converting colloquialisms, apply different conversion algorithms depending on the message category. 2. The system of claim 1. (Appendix 19) The colloquial language conversion unit Estimate the user's emotion and adjust the length of the colloquial style based on the estimated user's emotion. 2. The system of claim 1. (Appendix 20) The colloquial language conversion unit During colloquial conversion, prioritize conversions based on message submission age 2. The system of claim 1. (Appendix 21) The colloquial language conversion unit When converting colloquialisms, adjust the order of conversions based on message relevance 2. The system of claim 1. (Appendix 22) The playback unit Inferring user emotion and adjusting playback tone based on the estimated user emotion 2. The system of claim 1. (Appendix 23) The playback unit During playback, adjust the playback speed based on the importance of the message 2. The system of claim 1. (Appendix 24) The playback unit During playback, apply different playback algorithms depending on the message category 2. The system of claim 1. (Appendix 25) The playback unit Estimate the user's emotions and adjust the playback order based on the estimated user emotions. 2. The system of claim 1. (Appendix 26) The playback unit During playback, prioritize playback based on when messages were submitted 2. The system of claim 1. (Appendix 27) The playback unit During playback, adjust the playback order based on message relevance 2. The system of claim 1. (Appendix 28) The response receiving unit Estimate the user's emotions and adjust the way answers are accepted based on the estimated user emotions. 2. The system of claim 1. (Appendix 29) The response receiving unit When accepting responses, analyze the user's past response history to select the optimal method of acceptance. 2. The system of claim 1. (Appendix 30) The response receiving unit Filter responses based on the user's current projects and interests 2. The system of claim 1. (Appendix 31) The response receiving unit Estimate the user's emotions and prioritize the answers to be accepted based on the estimated user emotions. 2. The system of claim 1. (Appendix 32) The response receiving unit When accepting answers, the system takes into account the user's geographic location information and prioritizes answers that are highly relevant. 2. The system of claim 1. (Appendix 33) The response receiving unit When accepting responses, analyze users' social media activity and accept relevant responses. 2. The system of claim 1. (Appendix 34) The literary style conversion unit Estimate the user's emotions and adjust the written expression based on the estimated user emotions. 2. The system of claim 1. (Appendix 35) The literary style conversion unit When converting written language, adjust the level of detail of the conversion based on the importance of the answer 2. The system of claim 1. (Appendix 36) The literary style conversion unit When converting written language, apply different conversion algorithms depending on the answer category. 2. The system of claim 1. (Appendix 37) The literary style conversion unit Estimate the user's emotions and adjust the length of the written style based on the estimated user emotions. 2. The system of claim 1. (Appendix 38) The literary style conversion unit When converting written language, prioritize conversion based on the time of submission of the answer 2. The system of claim 1. (Appendix 39) The literary style conversion unit When converting written language, adjust the order of conversions based on the relevance of the answer 2. The system of claim 1. (Appendix 40) The transmission unit Estimate the user's emotions and adjust the timing of transmission based on the estimated user emotions. 2. The system of claim 1. (Appendix 41) The transmission unit At the time of submission, prioritize submissions based on the importance of the response 2. The system of claim 1. (Appendix 42) The transmission unit When submitting, apply different submission algorithms depending on the category of the answer 2. The system of claim 1. (Appendix 43) The transmission unit Inferring user sentiment and adjusting the method of confirming transmissions based on the estimated user sentiment 2. The system of claim 1. (Appendix 44) The transmission unit At submission time, prioritize submissions based on when responses are submitted 2. The system of claim 1. (Appendix 45) The transmission unit At submission time, adjust the order of submissions based on the relevance of the answers 2. The system of claim 1. (Appendix 46) The determination unit Estimate the user's emotions and determine the importance of the message based on the estimated user emotions. 2. The system of claim 1. (Appendix 47) The determination unit When judging, adjust the importance based on the message content 2. The system of claim 1. (Appendix 48) The determination unit When judging, different judging algorithms are applied depending on the message category. 2. The system of claim 1. (Appendix 49) The determination unit The user's feelings are estimated, and the criteria for determining importance are adjusted based on the estimated user's feelings. 2. The system of claim 1. (Appendix 50) The determination unit At the time of judgment, the importance is determined based on the time of submission of the message. 2. The system of claim 1. (Appendix 51) The determination unit During judging, adjust the order of importance based on the relevance of the message 2. The system of claim 1. [Explanation of symbols]

[0223] 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. a message reception unit for receiving an e-mail message or a short message; a colloquial language conversion unit that converts the message accepted by the message acceptance unit from written language to colloquial language; a playback unit that plays back the colloquial message converted by the colloquial language conversion unit by voice; a response receiving unit that receives a response from a user to the message reproduced by the reproduction unit; a literary style conversion unit that converts the answer accepted by the answer acceptance unit into a literary style; A sending unit that automatically sends the answer in a literary style converted by the literary style conversion unit. A system characterized by:

2. The reproducing unit is Has the ability to highlight specific keywords 2. The system of claim 1 .

3. The reproducing unit is Ability to adjust voice tone and speed based on user-specified information 2. The system of claim 1 .

4. The transmission unit is Has a function to prompt the user for confirmation before sending 2. The system of claim 1 .

5. The message reception unit Has the ability to accept multiple messages at once 2. The system of claim 1 .

6. a determination unit that determines the importance of each of the plurality of messages; The colloquial language conversion unit is The plurality of messages are converted from written language to colloquial language in the order of importance determined by the determination unit.

6. The system of claim 5.

7. The reproducing unit is Plays messages in the voice of a specific character selected by the user 2. The system of claim 1 .

8. The literary style conversion unit Use appropriate abbreviations depending on the length of your message 2. The system of claim 1 .

9. The colloquial language conversion unit is Convert to dialect depending on the user's geographic location 2. The system of claim 1 .

10. The message reception unit Estimate the user's emotions and adjust the timing of message acceptance based on the estimated user's emotions.

2. The system of claim 1 .

Images