system

Abstract

An object of the system according to the embodiment is to quickly summarize a message recorded in an answering machine and transmit the message by SMS.SOLUTION: A system according to an embodiment includes a conversion unit, a summarization unit, and a transmission unit. The conversion unit converts the voice data recorded in the answering machine into text. The summarizing unit summarizes the text converted by the converting unit. The transmitting unit transmits the summary generated by the summarizing unit as an SMS.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had problems such as delays in checking messages recorded on answering machines and the hassle of playing and listening to them.

[0005] The system according to the embodiment aims to quickly summarize messages recorded on an answering machine and send them via SMS. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversion unit, a summarization unit, and a transmission unit. The conversion unit converts voice data recorded on an answering machine into text. The summarization unit summarizes the text converted by the conversion unit. The transmission unit transmits the summary generated by the summarization unit as an SMS. [Effects of the Invention]

[0007] An embodiment of the system can quickly summarize messages recorded on an answering machine and send them via SMS. [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 summarization system according to an embodiment of the present invention automatically summarizes messages recorded on an answering machine and sends them via SMS. The message summarization system converts voice data recorded on an answering machine into text, summarizes the text, and sends it as an SMS. For example, in the message summarization system, a generation AI analyzes recorded voice data and converts it into text. The generation AI converts the voice data into text and summarizes the text. For example, the generation AI extracts important points from a long message and creates a concise summary. The message summarization system then sends the summary created by the generation AI as an SMS. This allows users to immediately check the contents of their answering machine messages. For example, even in environments where they cannot answer the phone, such as during a meeting or on a train, they can receive summaries via SMS, so they will not miss important messages. Furthermore, even people with hearing impairments can immediately check the contents of messages by converting recorded messages into text, summarizing them, and sending them via SMS. In this way, the message summarization system allows users to quickly understand the contents of messages by having a generation AI summarize voicemail messages and send them via SMS. This means you won't miss important messages even if you're in an environment where you can't answer the phone or play back the recording.

[0029] A message summarization system according to an embodiment includes a conversion unit, a summarization unit, and a transmission unit. The conversion unit converts voice data recorded on an answering machine into text. Examples of voice data include, but are not limited to, WAV and MP3 formats. The conversion unit converts voice data into text using, for example, voice recognition technology. For example, the conversion unit uses a generation AI to analyze voice data and convert it into text. The generation AI receives the voice data as input and outputs the text. The summarization unit summarizes the text converted by the conversion unit. The summarization is performed based on, for example, the length of the sentence and the importance of the information to be summarized, but is not limited to, examples. For example, the summarization unit uses a generation AI to analyze text and extract key points to generate a summary. The generation AI receives the text as input and outputs the summary. The transmission unit transmits the summary generated by the summarization unit as an SMS. For example, the transmission is performed using an SMS gateway, but is not limited to, examples. For example, the transmission unit uses a generation AI to transmit the summary as an SMS. The generation AI receives the summary as input and outputs the SMS. As a result, the message summarization system according to the embodiment can automatically summarize messages recorded on an answering machine and send them via SMS, allowing users to quickly understand the contents of their answering machine messages.

[0030] The conversion unit can convert recorded voice data into text. Recorded voice data includes, but is not limited to, digital recordings and analog recordings. The conversion unit converts voice data into text using, for example, voice recognition technology. For example, the conversion unit uses a generation AI to analyze voice data and convert it into text. The generation AI takes voice data as input and outputs text. By converting voice data into text, the content of the message can be handled as text. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0031] The summarization unit can extract important points from the converted text and generate a summary. Examples of extracting important points include, but are not limited to, keyword extraction and context analysis. In the summarization unit, for example, a generation AI analyzes the text, extracts important points, and generates a summary. The generation AI takes the text as input and outputs a summary. In this way, by extracting important points and generating a summary, the gist of the message can be grasped concisely. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0032] The sending unit can send the generated summary as an SMS. Examples of sending as an SMS include, but are not limited to, using an SMS gateway and timing of sending. In the sending unit, for example, the generation AI sends the summary as an SMS. The generation AI takes the summary as input and outputs an SMS. By sending the summary as an SMS, the user can immediately check the content of the message. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0033] The summarization unit may use an algorithm to ensure the accuracy of the summary. Examples of algorithms for ensuring accuracy include, but are not limited to, machine learning algorithms and evaluation metrics. The summarization unit may use, for example, an algorithm that allows the generation AI to ensure the accuracy and quality of the summary. The generation AI takes the summary as input and evaluates its accuracy and quality. This ensures the accuracy and quality of the summary, making it possible to provide a highly reliable summary. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0034] The message summarization system adds a filtering function that removes background noise when the conversion unit converts voice data. For example, the conversion unit uses a generation AI to automatically detect and remove background noise from recorded voice data. The conversion unit can also prioritize human voice extraction from the voice data and reduce noise. The conversion unit can also use the generation AI to apply multiple filtering algorithms and select the optimal noise removal method. This removes background noise, improving the conversion accuracy of the voice data. Background noise is removed using, for example, white noise, environmental sounds, or noise filtering technology. Some or all of the above-described processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0035] In the message summarization system, when converting voice data, the conversion unit analyzes the characteristics of the speaker's voice and applies the optimal conversion algorithm for each speaker. For example, the generation AI of the conversion unit analyzes the tone and pitch of the speaker's voice and selects the optimal conversion algorithm. The conversion unit can also improve conversion accuracy by having the generation AI take into account the speed and rhythm of the speaker's voice. The conversion unit can also learn the characteristics of the speaker's voice and apply an individually optimized conversion algorithm. This improves conversion accuracy by applying the optimal conversion algorithm for each speaker. The analysis of the speaker's voice characteristics is performed using, for example, voice pitch, tone, and spectrum analysis. Some or all of the above-mentioned processing in the conversion unit may be performed using or without the generation AI.

[0036] In the message summarization system, when the conversion unit converts voice data, it adjusts the conversion algorithm based on the recording time and the recording environment. For example, the generation AI in the conversion unit adjusts the conversion algorithm based on the recording time period (daytime, nighttime, etc.). The conversion unit can also apply noise reduction and voice enhancement algorithms based on the recording environment (indoor, outdoor, etc.). The conversion unit can also optimize the conversion algorithm based on the type of recording device (smartphone, landline, etc.). This improves conversion accuracy by adjusting the conversion algorithm based on the recording time and the recording environment. The recording time and the recording environment are adjusted taking into account, for example, the difference between day and night, the indoor and outdoor environment, etc. Some or all of the above-mentioned processing in the conversion unit may be performed using or without the generation AI.

[0037] In the message summarization system, when the conversion unit converts voice data, the conversion accuracy is improved based on information about the location where the voice was recorded. For example, the conversion unit improves the conversion accuracy by having the generation AI predict a specific noise pattern based on the information about the recording location. The conversion unit can also analyze the environmental sounds of the recording location and apply an appropriate noise removal algorithm. The conversion unit can also optimize the conversion accuracy of the voice data by having the generation AI take into account the acoustic characteristics of the recording location. In this way, by taking into account the information about the recording location, the conversion accuracy is improved. The information about the recording location is taken into account using, for example, GPS data, indoor and outdoor environmental information, etc. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0038] In the message summarization system, when the conversion unit converts voice data, it applies the optimal conversion algorithm depending on the speaker's language and dialect. For example, the conversion unit uses a generation AI to automatically detect the speaker's language and apply an appropriate conversion algorithm. The conversion unit can also analyze the speaker's dialect and apply a conversion algorithm corresponding to the dialect. The conversion unit can also use a multilingual conversion algorithm to perform optimal conversion depending on the speaker's language. This improves conversion accuracy by applying the optimal conversion algorithm depending on the speaker's language and dialect. The speaker's language and dialect are detected using, for example, a language model for each region, a dialect dictionary, etc. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0039] In the message summarization system, when a conversion unit converts voice data, the conversion accuracy is improved based on the user's past conversion history. The conversion unit, for example, uses a generation AI to analyze the user's past conversion history and learn specific patterns to improve conversion accuracy. The conversion unit can also prioritize frequently used words and phrases from the user's past conversion history. The conversion unit can also apply an individually optimized conversion algorithm based on the user's past conversion history. This improves conversion accuracy by referring to the past conversion history. The reference to the past conversion history is performed using, for example, a method for saving history data or a method for analyzing history data. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0040] In the message summarization system, when the summarization unit generates a summary, it adjusts the level of detail of the summary based on the importance of the message. For example, the summarization unit uses a generation AI to analyze the importance of the message and create a detailed summary for important messages. The summarization unit can also use the generation AI to create a concise summary for normal messages. The summarization unit can also use the generation AI to create a summary that can be quickly understood for urgent messages. In this way, by adjusting the level of detail of the summary based on the importance of the message, important messages can be understood in more detail. The analysis of the importance of the message is performed using, for example, the importance of keywords, the importance of the sender, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0041] In the message summarization system, when the summarization unit generates a summary, it applies different summarization algorithms depending on the message category. For example, the generation AI in the summarization unit creates summaries including technical terms for business-related messages. The generation AI in the summarization unit can also create summaries using familiar expressions for personal messages. The summarization unit can also create summaries that can be quickly understood for urgent messages. In this way, by applying the summarization algorithm depending on the message category, more appropriate summaries are generated. Message categories are classified using, for example, business, personal, urgent, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0042] In a message summarization system, when a summarization unit generates a summary, it improves the accuracy of the summary based on the user's past summarization results. For example, the summarization unit uses a generation AI to analyze the user's past summarization results and learn specific patterns to improve the accuracy of the summary. The summarization unit can also prioritize frequently used expressions from the user's past summarization results. The summarization unit can also apply an individually optimized summarization algorithm based on the user's past summarization results. This improves the accuracy of the summary by referring to the past summarization results. The reference to the past summarization results is performed, for example, using a method for saving historical data, a method for analyzing historical data, etc. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0043] In the message summarization system, when the summarization unit generates a summary, it determines the priority of the summary based on the time the message was recorded. For example, the summarization unit has a generation AI that prioritizes summarizing and transmitting the most recent message. The summarization unit can also have the generation AI prioritize summarizing messages recorded during a specific time period. The summarization unit can also have the generation AI analyze past messages and determine the priority of summaries based on their importance. In this way, by determining the priority of summaries based on the time the message was recorded, the most recent important messages can be processed preferentially. The time the message was recorded is taken into consideration using, for example, the date and time of recording, the timestamp of the recording, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0044] In the message summarization system, when the summarization unit generates summaries, it adjusts the order of summaries based on the relevance of the messages. For example, the summarization unit has a generation AI that prioritizes summarizing and transmitting highly relevant messages. The summarization unit can also have the generation AI summarize less relevant messages later. The summarization unit can also have the generation AI analyze the content of the messages and adjust the order of summaries based on their relevance. In this way, by adjusting the order of summaries based on the relevance of the messages, highly relevant messages can be processed preferentially. The relevance of messages is evaluated using, for example, common keywords, related topics, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0045] In the message summarization system, when the summarization unit generates a summary, it adjusts the use of technical terms in the summary according to the user's level of expertise. For example, the summarization unit uses a generation AI to analyze the user's level of expertise and create a summary using appropriate technical terms. The summarization unit can also create summaries using simple expressions for users with low expertise. The summarization unit can also create summaries including detailed technical terms for users with high expertise. By adjusting the use of technical terms according to the user's level of expertise, a more appropriate summary is generated. The user's level of expertise is evaluated using, for example, survey results, past usage history, etc. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0046] In the message summarization system, when a sending unit sends a message, the sending unit determines the priority of the message based on its importance. For example, the sending unit allows the generation AI to send important messages with priority. The sending unit can also allow the generation AI to send normal messages with normal priority. The sending unit can also allow the generation AI to send highly urgent messages with top priority. In this way, by determining the priority of the message based on its importance, important messages can be sent with priority. The importance of the message is evaluated using, for example, the importance of keywords, the importance of the sender, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0047] In the message summarization system, the transmitting unit selects a transmission method based on the user's current situation when transmitting a message. For example, the generating AI detects that the user is in a meeting and transmits the message in silent mode. The transmitting unit can also detect that the user is moving and transmit the message in vibration mode. The transmitting unit can also detect that the user is taking a break and transmit the message with a normal notification sound. In this way, by selecting a transmission method based on the user's current situation, the message can be sent in a more appropriate manner. The user's current situation is evaluated using, for example, whether the user is in a meeting, moving, or taking a break. Some or all of the above-mentioned processing in the transmitting unit may be performed using the generating AI, or may be performed without using the generating AI.

[0048] In the message summarization system, the sending unit optimizes the sending method based on the user's past sending history when sending a message. For example, the generation AI analyzes the user's past sending history and selects the optimal sending method. The sending unit can also preferentially apply frequently used sending methods from the user's past sending history. The sending unit can also suggest an individually optimized sending method based on the user's past sending history. This allows the sending method to be optimized by referring to the past sending history. The past sending history is referred to using, for example, a method for saving history data or a method for analyzing history data. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0049] In the message summarization system, the sending unit selects the optimal sending method based on the user's geographical location information when sending a message. For example, the generation AI of the sending unit detects that the user is overseas and selects the sending method taking into account international SMS charges. The sending unit can also detect that the user is in a specific area and select the sending method based on the communication conditions in that area. The sending unit can also detect that the user is at home and apply the normal sending method. This allows the optimal sending method to be selected by taking into account the geographical location information. The geographical location information is taken into account using, for example, GPS data, location information services, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0050] In the message summarization system, when a sending unit sends a message, the sending unit selects the optimal sending format based on the user's device information. For example, the sending unit may detect that the generation AI is using a smartphone and send the message in SMS format. Alternatively, the sending unit may detect that the user is using a tablet and send the message in email format. Alternatively, the sending unit may detect that the generation AI is using a smartwatch and send the message in a concise notification format. This allows the optimal sending format to be selected by taking into account device information. The device information may be taken into account using, for example, the device type, OS version, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0051] In the message summarization system, when a message is sent, the sending unit makes the message multilingual according to the user's language setting. For example, the generation AI detects the language setting of the user's device and sends the message in that language. The sending unit can also provide a language switching function when the user uses multiple languages. The sending unit can also send the message in a specific language when the user selects that language. This makes the message multilingual according to the language setting, allowing the user to receive the message in a language that is easy to understand. The language setting is taken into consideration using, for example, the user's default language, regional settings, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

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

[0053] When the conversion unit of the message summarization system converts voice data, it can analyze the intonation and emphasized parts of the voice and emphasize important information. For example, the generation AI can detect particularly emphasized parts of the voice data and convert those parts to text preferentially. The generation AI can also analyze the intonation of the voice and apply a text format to emphasize important points. Furthermore, the generation AI can prioritize including important information when summarizing based on the emphasized parts of the voice. This allows more important information to be conveyed accurately by taking into account the intonation and emphasized parts of the voice.

[0054] The message summarization system can also adjust the format of the summary based on the content of the message when the summarization unit generates the summary. For example, the generation AI can create a summary in bullet point format for business-related messages. The generation AI can also create a summary in a familiar sentence format for personal messages. Furthermore, the generation AI can create a summary in a concise format for urgent messages so that it can be understood quickly. In this way, by adjusting the summary format according to the content of the message, more appropriate summaries can be generated. Analysis of the content of the message is performed using, for example, keyword extraction and context analysis.

[0055] The message summarization system can also determine the priority of transmission based on the importance of the message when the sending unit sends it. For example, the generation AI can send important messages with priority. The generation AI can also send normal messages with normal priority. Furthermore, the generation AI can send highly urgent messages with top priority. In this way, by determining the priority of transmission based on the importance of the message, important messages can be sent with priority. The importance of the message is evaluated using, for example, the importance of keywords or the importance of the sender.

[0056] The message summarization system also allows the sending unit to select a sending method based on the user's current situation when sending a message. For example, the generation AI may detect that the user is in a meeting and send the message in silent mode. The generation AI may also detect that the user is on the move and send the message in vibration mode. Furthermore, the generation AI may detect that the user is on a break and send the message with a normal notification sound. This allows the sending method to be selected based on the user's current situation, enabling the message to be sent in a more appropriate manner. The user's current situation may be evaluated using, for example, whether the user is in a meeting, on the move, or on a break.

[0057] The message summarization system can also select the optimal sending method based on the user's geographical location information when the sending unit sends a message. For example, the generation AI can detect that the user is overseas and select the sending method taking into account international SMS charges. The generation AI can also detect that the user is in a specific area and select the sending method based on the communication conditions in that area. Furthermore, the generation AI can detect that the user is at home and apply the normal sending method. This allows the optimal sending method to be selected by taking into account the geographical location information. The geographical location information can be taken into account using, for example, GPS data or location information services.

[0058] The message summarization system can also select the optimal transmission format based on the user's device information when the sending unit sends a message. For example, the generation AI can detect that the user is using a smartphone and send the message in SMS format. The generation AI can also detect that the user is using a tablet and send the message in email format. Furthermore, the generation AI can detect that the user is using a smartwatch and send the message in a concise notification format. This allows the optimal transmission format to be selected by taking device information into consideration. Device information can be taken into consideration using, for example, the device type and OS version.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The conversion unit converts the voice data recorded on the answering machine into text. Examples of voice data include, but are not limited to, WAV and MP3 formats. The conversion unit converts the voice data into text using voice recognition technology. For example, a generation AI analyzes the voice data and converts it into text. Step 2: The summarization unit summarizes the text converted by the conversion unit. The summarization is based on the length of the text and the importance of the information being summarized. For example, a generation AI analyzes the text, extracts key points, and generates a summary. Step 3: The sending unit sends the summary generated by the summarizing unit as an SMS. The sending is performed, for example, using an SMS gateway. The generating AI sends the summary as an SMS.

[0061] (Example 2) A message summarization system according to an embodiment of the present invention automatically summarizes messages recorded on an answering machine and sends them via SMS. The message summarization system converts voice data recorded on an answering machine into text, summarizes the text, and sends it as an SMS. For example, in the message summarization system, a generation AI analyzes recorded voice data and converts it into text. The generation AI converts the voice data into text and summarizes the text. For example, the generation AI extracts important points from a long message and creates a concise summary. The message summarization system then sends the summary created by the generation AI as an SMS. This allows users to immediately check the contents of their answering machine messages. For example, even in environments where they cannot answer the phone, such as during a meeting or on a train, they can receive summaries via SMS, so they will not miss important messages. Furthermore, even people with hearing impairments can immediately check the contents of messages by converting recorded messages into text, summarizing them, and sending them via SMS. In this way, the message summarization system allows users to quickly understand the contents of messages by having a generation AI summarize voicemail messages and send them via SMS. This means you won't miss important messages even if you're in an environment where you can't answer the phone or play back the recording.

[0062] A message summarization system according to an embodiment includes a conversion unit, a summarization unit, and a transmission unit. The conversion unit converts voice data recorded on an answering machine into text. Examples of voice data include, but are not limited to, WAV and MP3 formats. The conversion unit converts voice data into text using, for example, voice recognition technology. For example, the conversion unit uses a generation AI to analyze voice data and convert it into text. The generation AI receives the voice data as input and outputs the text. The summarization unit summarizes the text converted by the conversion unit. The summarization is performed based on, for example, the length of the sentence and the importance of the information to be summarized, but is not limited to, examples. For example, the summarization unit uses a generation AI to analyze text and extract key points to generate a summary. The generation AI receives the text as input and outputs the summary. The transmission unit transmits the summary generated by the summarization unit as an SMS. For example, the transmission is performed using an SMS gateway, but is not limited to, examples. For example, the transmission unit uses a generation AI to transmit the summary as an SMS. The generation AI receives the summary as input and outputs the SMS. As a result, the message summarization system according to the embodiment can automatically summarize messages recorded on an answering machine and send them via SMS, allowing users to quickly understand the contents of their answering machine messages.

[0063] The conversion unit can convert recorded voice data into text. Recorded voice data includes, but is not limited to, digital recordings and analog recordings. The conversion unit converts voice data into text using, for example, voice recognition technology. For example, the conversion unit uses a generation AI to analyze voice data and convert it into text. The generation AI takes voice data as input and outputs text. By converting voice data into text, the content of the message can be handled as text. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0064] The summarization unit can extract important points from the converted text and generate a summary. Examples of extracting important points include, but are not limited to, keyword extraction and context analysis. In the summarization unit, for example, a generation AI analyzes the text, extracts important points, and generates a summary. The generation AI takes the text as input and outputs a summary. In this way, by extracting important points and generating a summary, the gist of the message can be grasped concisely. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0065] The sending unit can send the generated summary as an SMS. Examples of sending as an SMS include, but are not limited to, using an SMS gateway and timing of sending. In the sending unit, for example, the generation AI sends the summary as an SMS. The generation AI takes the summary as input and outputs an SMS. By sending the summary as an SMS, the user can immediately check the content of the message. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0066] The summarization unit may use an algorithm to ensure the accuracy of the summary. Examples of algorithms for ensuring accuracy include, but are not limited to, machine learning algorithms and evaluation metrics. The summarization unit may use, for example, an algorithm that allows the generation AI to ensure the accuracy and quality of the summary. The generation AI takes the summary as input and evaluates its accuracy and quality. This ensures the accuracy and quality of the summary, making it possible to provide a highly reliable summary. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0067] In a message summarization system, a conversion unit estimates a user's emotions and adjusts the conversion accuracy of the voice data based on the estimated user emotions. For example, if the user is feeling stressed, the conversion unit uses a generation AI to increase the conversion accuracy of the voice data and minimize conversion errors. Furthermore, if the user is relaxed, the conversion unit can set the conversion accuracy to a normal level to prioritize processing speed. Furthermore, if the user is in a hurry, the conversion unit can increase the conversion accuracy and perform text conversion quickly. This allows for more appropriate text conversion by adjusting the conversion accuracy according to the user's emotions. The user's emotions are estimated using technologies such as voice tone analysis and facial expression recognition. Some or all of the above-described processing in the conversion unit may be performed using or without the generation AI.

[0068] The message summarization system adds a filtering function that removes background noise when the conversion unit converts voice data. For example, the conversion unit uses a generation AI to automatically detect and remove background noise from recorded voice data. The conversion unit can also prioritize human voice extraction from the voice data and reduce noise. The conversion unit can also use the generation AI to apply multiple filtering algorithms and select the optimal noise removal method. This removes background noise, improving the conversion accuracy of the voice data. Background noise is removed using, for example, white noise, environmental sounds, or noise filtering technology. Some or all of the above-described processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0069] In the message summarization system, when converting voice data, the conversion unit analyzes the characteristics of the speaker's voice and applies the optimal conversion algorithm for each speaker. For example, the generation AI of the conversion unit analyzes the tone and pitch of the speaker's voice and selects the optimal conversion algorithm. The conversion unit can also improve conversion accuracy by having the generation AI take into account the speed and rhythm of the speaker's voice. The conversion unit can also learn the characteristics of the speaker's voice and apply an individually optimized conversion algorithm. This improves conversion accuracy by applying the optimal conversion algorithm for each speaker. The analysis of the speaker's voice characteristics is performed using, for example, voice pitch, tone, and spectrum analysis. Some or all of the above-mentioned processing in the conversion unit may be performed using or without the generation AI.

[0070] In the message summarization system, when the conversion unit converts voice data, it adjusts the conversion algorithm based on the recording time and the recording environment. For example, the generation AI in the conversion unit adjusts the conversion algorithm based on the recording time period (daytime, nighttime, etc.). The conversion unit can also apply noise reduction and voice enhancement algorithms based on the recording environment (indoor, outdoor, etc.). The conversion unit can also optimize the conversion algorithm based on the type of recording device (smartphone, landline, etc.). This improves conversion accuracy by adjusting the conversion algorithm based on the recording time and the recording environment. The recording time and the recording environment are adjusted taking into account, for example, the difference between day and night, the indoor and outdoor environment, etc. Some or all of the above-mentioned processing in the conversion unit may be performed using or without the generation AI.

[0071] In the message summarization system, the conversion unit estimates the user's emotions and prioritizes the converted text based on the estimated user emotions. For example, if the user is feeling stressed, the conversion unit causes the generation AI to convert and notify important messages preferentially. Furthermore, if the user is relaxed, the conversion unit can also convert and send text with normal priority. Furthermore, if the user is in a hurry, the conversion unit can also convert and send urgent messages preferentially. This allows important messages to be processed preferentially by prioritizing text according to the user's emotions. The user's emotions are estimated using, for example, technologies such as voice tone analysis and facial expression recognition. Some or all of the above-described processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0072] In the message summarization system, when the conversion unit converts voice data, the conversion accuracy is improved based on information about the location where the voice was recorded. For example, the conversion unit improves the conversion accuracy by having the generation AI predict a specific noise pattern based on the information about the recording location. The conversion unit can also analyze the environmental sounds of the recording location and apply an appropriate noise removal algorithm. The conversion unit can also optimize the conversion accuracy of the voice data by having the generation AI take into account the acoustic characteristics of the recording location. In this way, by taking into account the information about the recording location, the conversion accuracy is improved. The information about the recording location is taken into account using, for example, GPS data, indoor and outdoor environmental information, etc. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0073] In the message summarization system, when the conversion unit converts voice data, it applies the optimal conversion algorithm depending on the speaker's language and dialect. For example, the conversion unit uses a generation AI to automatically detect the speaker's language and apply an appropriate conversion algorithm. The conversion unit can also analyze the speaker's dialect and apply a conversion algorithm corresponding to the dialect. The conversion unit can also use a multilingual conversion algorithm to perform optimal conversion depending on the speaker's language. This improves conversion accuracy by applying the optimal conversion algorithm depending on the speaker's language and dialect. The speaker's language and dialect are detected using, for example, a language model for each region, a dialect dictionary, etc. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0074] In the message summarization system, when a conversion unit converts voice data, the conversion accuracy is improved based on the user's past conversion history. The conversion unit, for example, uses a generation AI to analyze the user's past conversion history and learn specific patterns to improve conversion accuracy. The conversion unit can also prioritize frequently used words and phrases from the user's past conversion history. The conversion unit can also apply an individually optimized conversion algorithm based on the user's past conversion history. This improves conversion accuracy by referring to the past conversion history. The reference to the past conversion history is performed using, for example, a method for saving history data or a method for analyzing history data. Some or all of the above-mentioned processing in the conversion unit may be performed using the generation AI, or may be performed without using the generation AI.

[0075] In a message summarization system, a summarization unit estimates a user's emotions and adjusts the presentation style of the summary based on the estimated user emotions. For example, if the user is feeling stressed, the summarization unit generates a concise summary that focuses on the main points. Furthermore, if the user is relaxed, the summarization unit can also generate a summary that includes detailed information. Furthermore, if the user is in a hurry, the summarization unit can also adjust the presentation style of the summary so that the generation AI can quickly understand it. In this way, by adjusting the presentation style of the summary according to the user's emotions, a more appropriate summary is generated. The user's emotions are estimated using, for example, technologies such as voice tone analysis and facial expression recognition. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0076] In the message summarization system, when the summarization unit generates a summary, it adjusts the level of detail of the summary based on the importance of the message. For example, the summarization unit uses a generation AI to analyze the importance of the message and create a detailed summary for important messages. The summarization unit can also use the generation AI to create a concise summary for normal messages. The summarization unit can also use the generation AI to create a summary that can be quickly understood for urgent messages. In this way, by adjusting the level of detail of the summary based on the importance of the message, important messages can be understood in more detail. The analysis of the importance of the message is performed using, for example, the importance of keywords, the importance of the sender, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0077] In the message summarization system, when the summarization unit generates a summary, it applies different summarization algorithms depending on the message category. For example, the generation AI in the summarization unit creates summaries including technical terms for business-related messages. The generation AI in the summarization unit can also create summaries using familiar expressions for personal messages. The summarization unit can also create summaries that can be quickly understood for urgent messages. In this way, by applying the summarization algorithm depending on the message category, more appropriate summaries are generated. Message categories are classified using, for example, business, personal, urgent, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0078] In a message summarization system, when a summarization unit generates a summary, it improves the accuracy of the summary based on the user's past summarization results. For example, the summarization unit uses a generation AI to analyze the user's past summarization results and learn specific patterns to improve the accuracy of the summary. The summarization unit can also prioritize frequently used expressions from the user's past summarization results. The summarization unit can also apply an individually optimized summarization algorithm based on the user's past summarization results. This improves the accuracy of the summary by referring to the past summarization results. The reference to the past summarization results is performed, for example, using a method for saving historical data, a method for analyzing historical data, etc. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0079] In a message summarization system, a summarization unit estimates a user's emotions and adjusts the length of the summary based on the estimated user emotions. For example, if the user is feeling stressed, the summarization unit generates a short, concise summary using a generation AI. Alternatively, if the user is relaxed, the summarization unit can generate a longer summary with more detailed information. Alternatively, if the user is in a hurry, the summarization unit can generate a short summary that can be quickly understood. This allows for the generation of a more appropriate summary by adjusting the length of the summary according to the user's emotions. The user's emotions are estimated using, for example, techniques such as voice tone analysis and facial expression recognition. Some or all of the above-described processing in the summarization unit may be performed using or without the generation AI.

[0080] In the message summarization system, when the summarization unit generates a summary, it determines the priority of the summary based on the time the message was recorded. For example, the summarization unit has a generation AI that prioritizes summarizing and transmitting the most recent message. The summarization unit can also have the generation AI prioritize summarizing messages recorded during a specific time period. The summarization unit can also have the generation AI analyze past messages and determine the priority of summaries based on their importance. In this way, by determining the priority of summaries based on the time the message was recorded, the most recent important messages can be processed preferentially. The time the message was recorded is taken into consideration using, for example, the date and time of recording, the timestamp of the recording, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0081] In the message summarization system, when the summarization unit generates summaries, it adjusts the order of summaries based on the relevance of the messages. For example, the summarization unit has a generation AI that prioritizes summarizing and transmitting highly relevant messages. The summarization unit can also have the generation AI summarize less relevant messages later. The summarization unit can also have the generation AI analyze the content of the messages and adjust the order of summaries based on their relevance. In this way, by adjusting the order of summaries based on the relevance of the messages, highly relevant messages can be processed preferentially. The relevance of messages is evaluated using, for example, common keywords, related topics, etc. Some or all of the above-mentioned processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0082] In the message summarization system, when the summarization unit generates a summary, it adjusts the use of technical terms in the summary according to the user's level of expertise. For example, the summarization unit uses a generation AI to analyze the user's level of expertise and create a summary using appropriate technical terms. The summarization unit can also create summaries using simple expressions for users with low expertise. The summarization unit can also create summaries including detailed technical terms for users with high expertise. By adjusting the use of technical terms according to the user's level of expertise, a more appropriate summary is generated. The user's level of expertise is evaluated using, for example, survey results, past usage history, etc. Some or all of the above-described processing in the summarization unit may be performed using the generation AI, or may be performed without using the generation AI.

[0083] In the message summarization system, the sending unit estimates the user's emotions and adjusts the timing of sending based on the estimated user emotions. For example, if the user is feeling stressed, the sending unit has the generation AI send an important message immediately. Also, if the user is relaxed, the sending unit can have the generation AI send a message at a normal timing. Also, if the user is in a hurry, the sending unit can have the generation AI send a message quickly. This allows the message to be sent at a more appropriate time by adjusting the sending timing according to the user's emotions. The user's emotions are estimated using technologies such as voice tone analysis and facial expression recognition. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI or without the generation AI.

[0084] In the message summarization system, when a sending unit sends a message, the sending unit determines the priority of the message based on its importance. For example, the sending unit allows the generation AI to send important messages with priority. The sending unit can also allow the generation AI to send normal messages with normal priority. The sending unit can also allow the generation AI to send highly urgent messages with top priority. In this way, by determining the priority of the message based on its importance, important messages can be sent with priority. The importance of the message is evaluated using, for example, the importance of keywords, the importance of the sender, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0085] In the message summarization system, the transmitting unit selects a transmission method based on the user's current situation when transmitting a message. For example, the generating AI detects that the user is in a meeting and transmits the message in silent mode. The transmitting unit can also detect that the user is moving and transmit the message in vibration mode. The transmitting unit can also detect that the user is taking a break and transmit the message with a normal notification sound. In this way, by selecting a transmission method based on the user's current situation, the message can be sent in a more appropriate manner. The user's current situation is evaluated using, for example, whether the user is in a meeting, moving, or taking a break. Some or all of the above-mentioned processing in the transmitting unit may be performed using the generating AI, or may be performed without using the generating AI.

[0086] In the message summarization system, the sending unit optimizes the sending method based on the user's past sending history when sending a message. For example, the generation AI analyzes the user's past sending history and selects the optimal sending method. The sending unit can also preferentially apply frequently used sending methods from the user's past sending history. The sending unit can also suggest an individually optimized sending method based on the user's past sending history. This allows the sending method to be optimized by referring to the past sending history. The past sending history is referred to using, for example, a method for saving history data or a method for analyzing history data. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0087] In the message summarization system, a sending unit estimates a user's emotions and adjusts the format of the message to be sent based on the estimated user emotions. For example, if the user is feeling stressed, the sending unit has the generation AI select a concise and to-the-point message format. Alternatively, if the user is relaxed, the sending unit can select a message format that includes detailed information. Alternatively, if the user is in a hurry, the sending unit can select a short message format that the generation AI can quickly understand. This allows the message to be sent in a more appropriate format by adjusting the message format according to the user's emotions. The user's emotions are estimated using, for example, techniques such as voice tone analysis and facial expression recognition. Some or all of the above-described processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0088] In the message summarization system, the sending unit selects the optimal sending method based on the user's geographical location information when sending a message. For example, the generation AI of the sending unit detects that the user is overseas and selects the sending method taking into account international SMS charges. The sending unit can also detect that the user is in a specific area and select the sending method based on the communication conditions in that area. The sending unit can also detect that the user is at home and apply the normal sending method. This allows the optimal sending method to be selected by taking into account the geographical location information. The geographical location information is taken into account using, for example, GPS data, location information services, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0089] In the message summarization system, when a sending unit sends a message, the sending unit selects the optimal sending format based on the user's device information. For example, the sending unit may detect that the generation AI is using a smartphone and send the message in SMS format. Alternatively, the sending unit may detect that the user is using a tablet and send the message in email format. Alternatively, the sending unit may detect that the generation AI is using a smartwatch and send the message in a concise notification format. This allows the optimal sending format to be selected by taking into account device information. The device information may be taken into account using, for example, the device type, OS version, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI.

[0090] In the message summarization system, when a message is sent, the sending unit makes the message multilingual according to the user's language setting. For example, the generation AI detects the language setting of the user's device and sends the message in that language. The sending unit can also provide a language switching function when the user uses multiple languages. The sending unit can also send the message in a specific language when the user selects that language. This makes the message multilingual according to the language setting, allowing the user to receive the message in a language that is easy to understand. The language setting is taken into consideration using, for example, the user's default language, regional settings, etc. Some or all of the above-mentioned processing in the sending unit may be performed using the generation AI, or may be performed without using the generation AI. === Hard Collateral 1-1 === Each of the multiple elements including the conversion unit, summarization unit, and transmission unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the smart device 14 and converts voice data into text. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the text. The transmission unit is realized, for example, by the control unit 46A of the smart device 14 and transmits the summary as an SMS. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned conversion unit, summarization unit, and transmission unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the smart glasses 214 and converts voice data into text. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the text. The transmission unit is realized, for example, by the control unit 46A of the smart glasses 214 and transmits the summary as an SMS. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned conversion unit, summarization unit, and transmission unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the headset type terminal 314 and converts voice data into text. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the text. The transmission unit is realized, for example, by the control unit 46A of the headset type terminal 314 and transmits the summary as an SMS. === Hard Collateral 1-4 === Each of the multiple elements including the conversion unit, summarization unit, and transmission unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversion unit is realized by the processor 46 of the robot 414 and converts voice data into text. The summarization unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and summarizes the text. The transmission unit is realized, for example, by the control unit 46A of the robot 414 and transmits the summary as an SMS.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The message summarization system can also estimate the speaker's emotions when converting voice data and adjust the conversion algorithm based on the estimated emotions. For example, if the speaker is nervous, the generation AI applies specific filtering to improve voice clarity. If the speaker is relaxed, the generation AI can use a standard conversion algorithm. Furthermore, if the speaker is in a hurry, the generation AI can apply an algorithm for quicker conversion. This allows for more accurate text conversion by adjusting the conversion algorithm according to the speaker's emotions. Emotions can be estimated using, for example, voice tone analysis or changes in the speaker's speaking rate.

[0093] When the conversion unit of the message summarization system converts voice data, it can analyze the intonation and emphasized parts of the voice and emphasize important information. For example, the generation AI can detect particularly emphasized parts of the voice data and convert those parts to text preferentially. The generation AI can also analyze the intonation of the voice and apply a text format to emphasize important points. Furthermore, the generation AI can prioritize including important information when summarizing based on the emphasized parts of the voice. This allows more important information to be conveyed accurately by taking into account the intonation and emphasized parts of the voice.

[0094] The message summarization system can also estimate the user's emotions when generating a summary, and adjust the tone and style of the summary based on the estimated emotions. For example, if the user is feeling stressed, the generation AI can create a concise summary that focuses on the main points. Alternatively, if the user is relaxed, the generation AI can create a summary that includes detailed information. Furthermore, if the user is in a hurry, the generation AI can adjust the tone of the summary to make it easier to understand. This allows for the generation of more appropriate summaries by adjusting the tone and style of the summary according to the user's emotions. Emotions can be estimated using technologies such as voice tone analysis and facial expression recognition.

[0095] The message summarization system can also adjust the format of the summary based on the content of the message when the summarization unit generates the summary. For example, the generation AI can create a summary in bullet point format for business-related messages. The generation AI can also create a summary in a familiar sentence format for personal messages. Furthermore, the generation AI can create a summary in a concise format for urgent messages so that it can be understood quickly. In this way, by adjusting the summary format according to the content of the message, more appropriate summaries can be generated. Analysis of the content of the message is performed using, for example, keyword extraction and context analysis.

[0096] The message summarization system can also estimate the user's emotions when generating a summary, and adjust the level of detail of the summary based on the estimated emotions. For example, if the user is feeling stressed, the generation AI can create a concise summary that covers the main points. Alternatively, if the user is relaxed, the generation AI can create a summary that includes detailed information. Furthermore, if the user is in a hurry, the generation AI can create a short summary that can be quickly understood. This allows the generation of a more appropriate summary by adjusting the level of detail of the summary according to the user's emotions. Emotions are estimated using technologies such as voice tone analysis and facial expression recognition.

[0097] The message summarization system can also estimate the user's emotions when the sender sends a message and adjust the format of the message to be sent based on the estimated emotions. For example, if the user is feeling stressed, the generation AI can select a concise and to-the-point message format. Alternatively, if the user is relaxed, the generation AI can select a message format that includes detailed information. Furthermore, if the user is in a hurry, the generation AI can select a short message format that can be quickly understood. This allows the message to be sent in a more appropriate format by adjusting the message format according to the user's emotions. Emotions are estimated using technologies such as voice tone analysis and facial expression recognition.

[0098] The message summarization system can also determine the priority of transmission based on the importance of the message when the sending unit sends it. For example, the generation AI can send important messages with priority. The generation AI can also send normal messages with normal priority. Furthermore, the generation AI can send highly urgent messages with top priority. In this way, by determining the priority of transmission based on the importance of the message, important messages can be sent with priority. The importance of the message is evaluated using, for example, the importance of keywords or the importance of the sender.

[0099] The message summarization system also allows the sending unit to select a sending method based on the user's current situation when sending a message. For example, the generation AI may detect that the user is in a meeting and send the message in silent mode. The generation AI may also detect that the user is on the move and send the message in vibration mode. Furthermore, the generation AI may detect that the user is on a break and send the message with a normal notification sound. This allows the sending method to be selected based on the user's current situation, enabling the message to be sent in a more appropriate manner. The user's current situation may be evaluated using, for example, whether the user is in a meeting, on the move, or on a break.

[0100] The message summarization system can also select the optimal sending method based on the user's geographical location information when the sending unit sends a message. For example, the generation AI can detect that the user is overseas and select the sending method taking into account international SMS charges. The generation AI can also detect that the user is in a specific area and select the sending method based on the communication conditions in that area. Furthermore, the generation AI can detect that the user is at home and apply the normal sending method. This allows the optimal sending method to be selected by taking into account the geographical location information. The geographical location information can be taken into account using, for example, GPS data or location information services.

[0101] The message summarization system can also select the optimal transmission format based on the user's device information when the sending unit sends a message. For example, the generation AI can detect that the user is using a smartphone and send the message in SMS format. The generation AI can also detect that the user is using a tablet and send the message in email format. Furthermore, the generation AI can detect that the user is using a smartwatch and send the message in a concise notification format. This allows the optimal transmission format to be selected by taking device information into consideration. Device information can be taken into consideration using, for example, the device type and OS version.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The conversion unit converts the voice data recorded on the answering machine into text. Examples of voice data include, but are not limited to, WAV and MP3 formats. The conversion unit converts the voice data into text using voice recognition technology. For example, a generation AI analyzes the voice data and converts it into text. Step 2: The summarization unit summarizes the text converted by the conversion unit. The summarization is based on the length of the text and the importance of the information being summarized. For example, a generation AI analyzes the text, extracts key points, and generates a summary. Step 3: The sending unit sends the summary generated by the summarizing unit as an SMS. The sending is performed, for example, using an SMS gateway. The generating AI sends the summary as an SMS.

[0104] 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.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] 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.

[0107] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] 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.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] [Explanation of symbols]

[0176] 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 conversion unit that converts voice data recorded on an answering machine into text; a summarizing unit that summarizes the text converted by the converting unit; a sending unit that sends the summary generated by the summarizing unit as an SMS; Equipped with A system characterized by:

2. The conversion unit Converting recorded audio data into text 2. The system of claim 1.

3. The summary section Extract key points from the converted text and generate a summary 2. The system of claim 1.

4. The transmission unit Send the generated summary as an SMS 2. The system of claim 1.

5. The summary section Uses algorithms to ensure accuracy of summaries 2. The system of claim 1.

6. The conversion unit Estimate the user's emotion and adjust the conversion accuracy of the voice data based on the estimated user's emotion.

2. The system of claim 1.

7. The conversion unit Add a filtering function to remove background noise when converting audio data.

2. The system of claim 1.

8. The conversion unit When converting voice data, the speaker's voice characteristics are analyzed and the optimal conversion algorithm is applied for each speaker.

2. The system of claim 1.

Images