System

Abstract

An object of a system according to an embodiment is to efficiently summarize call content and provide the summarized call content to a user.SOLUTION: A system includes a recording part, an analysis part, a summarization part, and a provision part. The recording unit records a call from a user. The analysis unit analyzes the call content recorded by the recording unit. The summarization unit generates a summary based on the call content analyzed by the analysis unit. The providing unit provides the summary generated by the summarizing unit in a chat format.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that it is difficult to efficiently summarize the contents of a call and provide it to a user.

[0005] The system according to the embodiment aims to efficiently summarize the contents of a call and provide it to a user. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an analysis unit, a summarization unit, and a providing unit. The recording unit records a call from a user. The analysis unit analyzes the content of the call recorded by the recording unit. The summarization unit generates a summary based on the content of the call analyzed by the analysis unit. The providing unit provides the summary generated by the summarization unit in a chat format. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently summarize the contents of a call and provide it to the user. [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 call summary system according to an embodiment of the present invention records calls from users, analyzes the call content, and provides a summary in chat format. In this system, a user initiates a call from the AI ​​phone menu of an app. When the call ends, a recording file is generated and provided in chat format. Next, the AI ​​analyzes the call content and generates a one-line summary corresponding to the overall theme of the call, a detailed summary of the call by paragraph, and a representative tag for each call. Furthermore, the AI ​​also suggests patterns related to dates, phone numbers, account numbers, and other references mentioned during the call. For example, when a user calls a friend, the call summary system initiates the call from the AI ​​phone menu of the app, and automatically generates a recording file when the call ends. The generated recording file is then provided in chat format, with the call content displayed in text format. Furthermore, the AI ​​analyzes the call content and generates a one-line summary corresponding to the overall theme of the call. For example, if the call content is about "travel plans," the AI ​​generates a one-line summary such as "We talked about travel plans." The AI ​​also generates detailed summaries of phone calls by paragraph. For example, if a caller talks about "travel destinations" at the beginning, "accommodation" in the middle, and "transportation" at the end, a detailed summary corresponding to each paragraph will be generated. Furthermore, the AI ​​generates representative tags for each call, such as "travel," "accommodation," and "transportation." Finally, the AI ​​also makes suggestions based on patterns mentioned during the call, such as dates, phone numbers, and account numbers, suggesting, for example, "We have plans to meet next Monday." By analyzing and summarizing call content, the call summary system can provide new telephone services and support efficient communication for users. The call summary system automatically summarizes user call content to support efficient communication. For example, users can easily review call content and manage it without missing important information. Furthermore, call summaries are provided in chat format, allowing users to easily search through call content and quickly obtain the information they need.

[0029] A call summarizing system according to an embodiment includes a recording unit, an analysis unit, a summarizing unit, and a providing unit. The recording unit records a call from a user. For example, the recording unit starts recording simultaneously with the start of the call. The recording unit can also stop recording simultaneously with the end of the call and generate a recording file. The recording unit also has a function for adjusting the quality of the recording. For example, the recording unit can dynamically adjust the quality of the recording depending on the content of the call. The analysis unit analyzes the content of the call recorded by the recording unit. For example, the analysis unit generates text data of the content of the call and extracts the theme and important information of the content of the call. The analysis unit can also analyze the context of the content of the call and extract important keywords. The analysis unit can also analyze the emotional tone of the content of the call and visualize changes in emotion. The summarizing unit generates a summary based on the content of the call analyzed by the analysis unit. For example, the summarizing unit generates a one-line summary corresponding to the theme of the content of the call. The summarizing unit can also generate a detailed summary of the call by paragraph. Furthermore, the summarizing unit generates a representative tag for each call, allowing the call content to be easily searched by the tag. The providing unit provides the summary generated by the summarizing unit in a chat format. The providing unit, for example, displays the generated summary in a text format, allowing the user to easily check the call content. The providing unit can also estimate the user's emotions and adjust the display method of the summary based on the estimated emotions. As a result, the call summarizing system according to the embodiment can efficiently record, analyze, summarize, and provide the user's call content. For example, the user can easily check the call content and manage it without missing important information. Furthermore, since the call content summary is provided in a chat format, the user can easily search the call content and quickly obtain necessary information.

[0030] The analysis unit can generate a one-line summary corresponding to the theme of the call content. For example, the analysis unit generates text data of the call content and extracts the theme of the call content. For example, if the call content is about "travel plans," the analysis unit generates a one-line summary such as "We talked about travel plans." The analysis unit can also extract important information from the call content and reflect it in the one-line summary. For example, the analysis unit can select particularly important information from the call content and generate a one-line summary based on that information. This allows the theme of the call content to be concisely understood. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the text data of the call content into a generation AI and cause the generation AI to execute a process to extract the theme of the call content.

[0031] The analysis unit can generate a detailed summary of each paragraph of a call. For example, the analysis unit generates text data of the call content and generates a detailed summary for each paragraph of the call. For example, if the first part of the call talks about "travel destinations," the middle part talks about "accommodations," and the last part talks about "transportation," the analysis unit generates a detailed summary for each paragraph. The analysis unit can also analyze the context of the call content and extract important information for each paragraph. For example, the analysis unit can select particularly important information from the call content and generate a detailed summary for each paragraph based on that information. This allows the call content to be understood in detail for each paragraph. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the text data of the call content into a generation AI and cause the generation AI to execute a process of generating a detailed summary for each paragraph.

[0032] The analysis unit can generate representative tags for each call. For example, the analysis unit generates text data of the call content and generates representative tags based on the call content. For example, the analysis unit generates tags for call content such as "travel," "accommodation," and "transportation." The analysis unit can also extract important information from the call content and generate representative tags based on that information. For example, the analysis unit picks out particularly important information from the call content and generates representative tags based on that information. This allows the call content to be easily searched by tag. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data of the call content into a generation AI and have the generation AI execute a process to generate representative tags.

[0033] The analysis unit can make suggestions based on patterns of dates, phone numbers, or account numbers mentioned during a call. For example, the analysis unit generates text data of the call content and extracts patterns of dates, phone numbers, account numbers, etc. mentioned during the call. For example, if "Let's meet next Monday" is mentioned during a call, the analysis unit can make a suggestion such as "We have plans to meet next Monday." The analysis unit can also extract important information from the call content and make suggestions based on that information. For example, the analysis unit can select particularly important information from the call content and make suggestions based on that information. This allows for efficient management of important information during a call. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the text data of the call content into a generation AI and cause the generation AI to execute a process to extract patterns of dates, phone numbers, and account numbers.

[0034] The providing unit can provide the generated summary in a chat format. For example, the providing unit can display the generated summary in a text format, allowing the user to easily check the contents of the call. For example, the providing unit can display the generated summary in a chat format, allowing the user to easily search the contents of the call. The providing unit can also estimate the user's emotions and adjust the display method of the summary based on the estimated emotions. For example, if the user is nervous, the providing unit can provide a simple, highly visible display method. If the user is relaxed, the providing unit can also provide a display method including detailed information. This allows the user to easily check the contents of the call by providing the summary in a chat format. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the generated summary to a generation AI and cause the generation AI to display it in a chat format.

[0035] The recording unit can dynamically adjust the quality of the recording depending on the content of the call. For example, if the content of the call is business-related, the recording unit performs high-quality recording. Alternatively, if the content of the call is a private conversation, the recording unit can perform standard-quality recording. Furthermore, if the content of the call contains important information, the recording unit can perform highest-quality recording. This makes it possible to provide optimal recording quality depending on the content of the call. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input text data of the content of the call to a generation AI and cause the generation AI to perform processing to dynamically adjust the quality of the recording.

[0036] The recording unit can automatically filter background noise during a call to record clear audio. For example, the recording unit can analyze background noise during a call in real time and remove noise. The recording unit can also filter sounds in a specific frequency band during a call to record clear audio. Furthermore, the recording unit can reduce environmental noise during a call and emphasize the speaker's voice. This allows for clear audio recording by filtering background noise. Some or all of the above-described processing in the recording unit can be performed using, for example, AI, or can be performed without using AI. For example, the recording unit can input audio data during a call to a generation AI and have the generation AI filter the background noise.

[0037] The recording unit can automatically mark and emphasize important parts of a call during recording. For example, the recording unit can detect keywords during a call and emphasize those parts before recording. The recording unit can also automatically mark the speaker's tone and emphasized parts during a call. Furthermore, the recording unit can detect important phrases or sentences during a call and mark them for easy later retrieval. This allows for easy later retrieval by highlighting important parts of the call. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input audio data during a call into a generation AI and have the generation AI mark important parts.

[0038] The recording unit can automatically divide the recording based on the content of the call during recording. For example, the recording unit divides the recording each time the content of the call changes to a different topic. The recording unit can also divide the recording for each important part of the call. Furthermore, the recording unit can divide the recording at regular intervals depending on the elapsed time of the call. By dividing the recording based on the content of the call, later search and playback become easier. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input text data of the content of the call into a generation AI and have the generation AI divide the recording.

[0039] The recording unit can identify the voice of the other party during a call and record it separately. For example, the recording unit can separate the voice of each speaker during a call and record it separately. The recording unit can also identify the voice of each speaker during a call and save the voice of each speaker in a separate file. Furthermore, the recording unit can analyze the voice of each speaker during a call in real time and record it separately. This allows the voice of the other party during a call to be recorded separately, making it easier to analyze and play back later. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input audio data during a call into a generation AI and have the generation AI identify the speaker's voice and record it separately.

[0040] The recording unit can automatically select a recording format based on the content of the call when recording. For example, if the content of the call is business-related, the recording unit records in a high-quality format. The recording unit can also record in a standard-quality format if the content of the call is a private conversation. Furthermore, if the content of the call contains important information, the recording unit can also record in the highest-quality format. This improves the quality of the recording by selecting the optimal recording format based on the content of the call. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input text data of the content of the call to a generation AI and have the generation AI select the recording format.

[0041] The analysis unit can analyze the context of the call content and extract important keywords. The analysis unit, for example, generates text data of the call content and analyzes the context of the call content. The analysis unit can also extract particularly important keywords from the call content. Furthermore, the analysis unit can refer to related background information to understand the context of the call content. In this way, important keywords can be extracted by analyzing the context of the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text data of the call content to a generation AI and have the generation AI analyze the context and extract keywords.

[0042] The analysis unit can analyze the emotional tone of the call content and visualize changes in emotion. The analysis unit, for example, generates text data of the call content and analyzes the emotional tone of the call content. The analysis unit can also analyze the emotional tone of the speaker during the call in real time and display it in a graph. Furthermore, the analysis unit can visualize changes in emotion during the call in chronological order. In this way, by analyzing the emotional tone of the call content, changes in emotion can be visualized. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text data of the call content to a generation AI and have the generation AI analyze and visualize the emotional tone.

[0043] The analysis unit can analyze the speech time of each speaker in the call content and calculate the speaker's speech ratio. The analysis unit, for example, generates text data of the call content and analyzes the speech time of each speaker in the call content. The analysis unit can also display the speech time of each speaker during the call in a graph. Furthermore, the analysis unit can analyze the speech ratio of each speaker during the call and evaluate the balance. In this way, the speech ratio of each speaker can be calculated by analyzing the speech time of each speaker in the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text data of the call content to a generation AI and have the generation AI analyze the speech time and calculate the speech ratio.

[0044] The analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. For example, the analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. The analysis unit can also identify multiple languages ​​used in the call and apply an appropriate analysis algorithm for each. Furthermore, the analysis unit can identify the language of the call content in real time and dynamically switch the analysis algorithm. This enables appropriate analysis by automatically identifying the language of the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input audio data of the call content to a generation AI and have the generation AI identify the language and apply the analysis algorithm.

[0045] The analysis unit can improve the accuracy of the analysis by referring to background information of the call content. For example, the analysis unit can improve the accuracy of the analysis by referring to background information of the call content. The analysis unit can also perform analysis by referring to background information related to a specific topic during the call. Furthermore, the analysis unit can automatically acquire and analyze related background information to understand the context of the call content. As a result, the accuracy of the analysis is improved by referring to the background information of the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data of the call content into the generation AI and have the generation AI refer to and analyze the background information.

[0046] The analysis unit can convert the voice data of the call content into text data and perform text analysis. For example, the analysis unit can convert the voice data of the call content into text data in real time. The analysis unit can also convert the voice data of the call content into text data and extract keywords. Furthermore, the analysis unit can convert the voice data of the call content into text data and analyze the context. This makes it possible to perform text analysis by converting the voice data into text data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the voice data of the call content into a generation AI and have the generation AI perform conversion to text data and text analysis.

[0047] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the call content. For example, if the call content is important, the summarization unit can provide a detailed summary. If the call content is general, the summarization unit can also provide a standard summary. Furthermore, if the call content is minor, the summarization unit can also provide a concise summary. In this way, an appropriate summary can be provided by adjusting the level of detail of the summary based on the importance of the call content. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to perform processing to adjust the level of detail of the summary.

[0048] When generating a summary, the summarization unit can apply different summarization algorithms depending on the category of the call content. For example, in the case of a business-related call, the summarization unit can apply a business summarization algorithm. In addition, in the case of a private call, the summarization unit can also apply a private summarization algorithm. Furthermore, in the case of an academic call, the summarization unit can also apply an academic summarization algorithm. In this way, an appropriate summary is provided by applying a summarization algorithm depending on the category of the call content. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to apply a summarization algorithm depending on the category.

[0049] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. For example, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit can also learn specific patterns from the user's past summarization results and improve the accuracy of the summary. Furthermore, the summarization unit can adjust the summarization algorithm based on the user's past summarization results. In this way, the accuracy of the summary is improved by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input the user's past summarization results into the generation AI and cause the generation AI to perform processing to improve the accuracy of the summary.

[0050] When generating a summary, the summarization unit can determine the priority of summaries based on the submission time of the call content. For example, the summarization unit prioritizes summarization of call content with an upcoming submission deadline. The summarization unit can also postpone summarization of call content with a more distant submission deadline. Furthermore, the summarization unit can adjust the level of detail of the summary based on the submission time. In this way, by determining the priority of summaries based on the submission time of the call content, summaries are provided at an appropriate time. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to execute a process of determining the priority of summaries based on the submission time.

[0051] When generating a summary, the summarization unit can adjust the order of summaries based on the relevance of the call content. For example, the summarization unit prioritizes summarization of highly relevant call content. The summarization unit can also postpone summarization of less relevant call content. Furthermore, the summarization unit can automatically adjust the order of summaries based on the relevance of the call content. In this way, by adjusting the order of summaries based on the relevance of the call content, summaries are provided in an appropriate order. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to perform processing to adjust the order of summaries based on relevance.

[0052] When generating a summary, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. For example, if the user is an expert, the summarization unit can provide a summary that uses a lot of technical terms. Alternatively, if the user is a layperson, the summarization unit can provide a summary that avoids technical terms. Furthermore, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. This allows for an appropriate summary to be provided by adjusting the use of technical terms in the summary according to the user's level of expertise. Some or all of the above-described processing in the summarization unit may be performed using, or without, AI. For example, the summarization unit can input the user's level of expertise into the generation AI and cause the generation AI to perform a process of adjusting the use of technical terms.

[0053] When providing the display method, the providing unit can select the optimal display method by referring to the user's past operation history. For example, the providing unit preferentially provides a display method that the user has used favorably in the past. The providing unit can also suggest the optimal display method from the user's past operation history. Furthermore, the providing unit can customize the display method based on the user's past operation history. In this way, the optimal display method is provided by referring to the user's past operation history. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the user's operation history data to the generation AI and cause the generation AI to execute processing to select the optimal display method.

[0054] The providing unit can customize the display content according to the user's current task when providing the information. For example, when the user is at work, the providing unit can prioritize displaying information related to work. Furthermore, when the user is spending private time, the providing unit can also prioritize displaying information related to private life. Furthermore, the providing unit can dynamically customize the display content according to the user's current task. As a result, appropriate information is provided by customizing the display content according to the user's current task. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's task data into the generating AI and cause the generating AI to perform processing to customize the display content.

[0055] The providing unit can improve the display method by reflecting user feedback when providing the data. The providing unit improves the display method based on user feedback, for example. The providing unit can also reflect user feedback in real time and adjust the display method. Furthermore, the providing unit can analyze user feedback and propose an optimal display method. In this way, the display method is improved by reflecting user feedback. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input user feedback data into the generating AI and cause the generating AI to execute processing to improve the display method.

[0056] The providing unit can select the optimal display method based on the user's device information at the time of providing. For example, if the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the providing unit can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can also provide a simple and highly visible display method. This improves visibility by providing the optimal display method based on the user's device information. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the user's device information into the generation AI and cause the generation AI to execute a process of selecting the optimal display method.

[0057] The providing unit can make the display content multilingual according to the user's language setting when providing the display content. The providing unit automatically sets the display content based on, for example, the language setting of the user's device. The providing unit can also provide a language switching function when the user uses multiple languages. Furthermore, when the user selects a specific language, the providing unit can provide the display content in that language. In this way, by making the display content multilingual according to the user's language setting, information is provided in an appropriate language. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the user's language setting data into a generation AI and cause the generation AI to execute multilingual display content.

[0058] The providing unit can customize the display format according to the user's visual preferences when providing the display format. The providing unit customizes the display format using, for example, the user's preferred colors and fonts. The providing unit can also adjust the display layout according to the user's visual preferences. Furthermore, the providing unit can also suggest an optimal display format based on the user's past selection history. This improves visibility by customizing the display format according to the user's visual preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's visual preference data into the generating AI and cause the generating AI to execute processing to customize the display format.

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

[0060] The analysis unit can analyze background sounds of the call content and detect specific environmental sounds. For example, if the analysis unit hears the sound of a car during a call, it generates a tag indicating that the call was made while moving. Also, if music is playing during a call, the analysis unit can generate a tag indicating that the call was made in a relaxed environment. Furthermore, if there is a lot of noise during a call, the analysis unit can generate a tag indicating that the call was made in a noisy environment. This makes it possible to perform analysis according to the environment of the call.

[0061] The summarization unit can adjust the order of summarization based on the importance of the call content. For example, the summarization unit can first summarize parts containing important information, and then summarize general information. The summarization unit can also prioritize summarizing topics that the user is particularly interested in. Furthermore, the summarization unit can adjust the level of detail of the summary based on the importance of the call content. This allows important information to be provided preferentially.

[0062] The recording unit can detect specific keywords in a call and automatically highlight those parts. For example, if keywords such as "important" or "urgent" appear during a call, the recording unit will highlight those parts. The recording unit can also highlight parts when specific names or places are mentioned during a call. Furthermore, the recording unit can detect specific phrases or sentences in a call and mark them for easy later retrieval. This highlights important information and makes it easier to search for later.

[0063] The providing unit can select the optimal display method by referring to the user's past operation history. For example, the providing unit can preferentially provide a display method that the user has used favorably in the past. The providing unit can also suggest the optimal display method based on the user's past operation history. Furthermore, the providing unit can customize the display method based on the user's past operation history. In this way, the optimal display method is provided by referring to the user's past operation history.

[0064] The analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. For example, the analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. The analysis unit can also identify multiple languages ​​used in a call and apply an appropriate analysis algorithm for each language. Furthermore, the analysis unit can identify the language of the call content in real time and dynamically switch the analysis algorithm. This makes it possible to perform appropriate analysis by automatically identifying the language of the call content.

[0065] The providing unit can select the optimal display method based on the user's device information. For example, if the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Also, if the user is using a tablet, the providing unit can provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can provide a simple and highly visible display method. This improves visibility by providing the optimal display method based on the user's device information.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The recording unit records the call from the user. The recording unit starts recording when the call starts and stops recording when the call ends. The recording unit also generates a recording file and has the function of adjusting the recording quality. For example, it can dynamically adjust the recording quality depending on the content of the call. Step 2: The analysis unit analyzes the call content recorded by the recording unit. The analysis unit generates text data of the call content and extracts themes and important information from the call content. It can also analyze the context of the call content, extract important keywords and emotional tones, and visualize changes in emotions. Step 3: The summarization unit generates a summary based on the call content analyzed by the analysis unit. The summarization unit generates a one-line summary or a detailed summary by paragraph that corresponds to the theme of the call content. It also generates a representative tag for each call, making it easy to search for the call content by tag. Step 4: The providing unit provides the summary generated by the summarizing unit in a chat format. The providing unit displays the generated summary in a text format so that the user can easily check the contents of the call. The providing unit can also estimate the user's emotions and adjust the display method of the summary based on the estimated emotions.

[0068] (Example 2) A call summary system according to an embodiment of the present invention records calls from users, analyzes the call content, and provides a summary in chat format. In this system, a user initiates a call from the AI ​​phone menu of an app. When the call ends, a recording file is generated and provided in chat format. Next, the AI ​​analyzes the call content and generates a one-line summary corresponding to the overall theme of the call, a detailed summary of the call by paragraph, and a representative tag for each call. Furthermore, the AI ​​also suggests patterns related to dates, phone numbers, account numbers, and other references mentioned during the call. For example, when a user calls a friend, the call summary system initiates the call from the AI ​​phone menu of the app, and automatically generates a recording file when the call ends. The generated recording file is then provided in chat format, with the call content displayed in text format. Furthermore, the AI ​​analyzes the call content and generates a one-line summary corresponding to the overall theme of the call. For example, if the call content is about "travel plans," the AI ​​generates a one-line summary such as "We talked about travel plans." The AI ​​also generates detailed summaries of phone calls by paragraph. For example, if a caller talks about "travel destinations" at the beginning, "accommodation" in the middle, and "transportation" at the end, a detailed summary corresponding to each paragraph will be generated. Furthermore, the AI ​​generates representative tags for each call, such as "travel," "accommodation," and "transportation." Finally, the AI ​​also makes suggestions based on patterns mentioned during the call, such as dates, phone numbers, and account numbers, suggesting, for example, "We have plans to meet next Monday." By analyzing and summarizing call content, the call summary system can provide new telephone services and support efficient communication for users. The call summary system automatically summarizes user call content to support efficient communication. For example, users can easily review call content and manage it without missing important information. Furthermore, call summaries are provided in chat format, allowing users to easily search through call content and quickly obtain the information they need.

[0069] A call summarizing system according to an embodiment includes a recording unit, an analysis unit, a summarizing unit, and a providing unit. The recording unit records a call from a user. For example, the recording unit starts recording simultaneously with the start of the call. The recording unit can also stop recording simultaneously with the end of the call and generate a recording file. The recording unit also has a function for adjusting the quality of the recording. For example, the recording unit can dynamically adjust the quality of the recording depending on the content of the call. The analysis unit analyzes the content of the call recorded by the recording unit. For example, the analysis unit generates text data of the content of the call and extracts the theme and important information of the content of the call. The analysis unit can also analyze the context of the content of the call and extract important keywords. The analysis unit can also analyze the emotional tone of the content of the call and visualize changes in emotion. The summarizing unit generates a summary based on the content of the call analyzed by the analysis unit. For example, the summarizing unit generates a one-line summary corresponding to the theme of the content of the call. The summarizing unit can also generate a detailed summary of the call by paragraph. Furthermore, the summarizing unit generates a representative tag for each call, allowing the call content to be easily searched by the tag. The providing unit provides the summary generated by the summarizing unit in a chat format. The providing unit, for example, displays the generated summary in a text format, allowing the user to easily check the call content. The providing unit can also estimate the user's emotions and adjust the display method of the summary based on the estimated emotions. As a result, the call summarizing system according to the embodiment can efficiently record, analyze, summarize, and provide the user's call content. For example, the user can easily check the call content and manage it without missing important information. Furthermore, since the call content summary is provided in a chat format, the user can easily search the call content and quickly obtain necessary information.

[0070] The analysis unit can generate a one-line summary corresponding to the theme of the call content. For example, the analysis unit generates text data of the call content and extracts the theme of the call content. For example, if the call content is about "travel plans," the analysis unit generates a one-line summary such as "We talked about travel plans." The analysis unit can also extract important information from the call content and reflect it in the one-line summary. For example, the analysis unit can select particularly important information from the call content and generate a one-line summary based on that information. This allows the theme of the call content to be concisely understood. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the text data of the call content into a generation AI and cause the generation AI to execute a process to extract the theme of the call content.

[0071] The analysis unit can generate a detailed summary of each paragraph of a call. For example, the analysis unit generates text data of the call content and generates a detailed summary for each paragraph of the call. For example, if the first part of the call talks about "travel destinations," the middle part talks about "accommodations," and the last part talks about "transportation," the analysis unit generates a detailed summary for each paragraph. The analysis unit can also analyze the context of the call content and extract important information for each paragraph. For example, the analysis unit can select particularly important information from the call content and generate a detailed summary for each paragraph based on that information. This allows the call content to be understood in detail for each paragraph. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the text data of the call content into a generation AI and cause the generation AI to execute a process of generating a detailed summary for each paragraph.

[0072] The analysis unit can generate representative tags for each call. For example, the analysis unit generates text data of the call content and generates representative tags based on the call content. For example, the analysis unit generates tags for call content such as "travel," "accommodation," and "transportation." The analysis unit can also extract important information from the call content and generate representative tags based on that information. For example, the analysis unit picks out particularly important information from the call content and generates representative tags based on that information. This allows the call content to be easily searched by tag. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data of the call content into a generation AI and have the generation AI execute a process to generate representative tags.

[0073] The analysis unit can make suggestions based on patterns of dates, phone numbers, or account numbers mentioned during a call. For example, the analysis unit generates text data of the call content and extracts patterns of dates, phone numbers, account numbers, etc. mentioned during the call. For example, if "Let's meet next Monday" is mentioned during a call, the analysis unit can make a suggestion such as "We have plans to meet next Monday." The analysis unit can also extract important information from the call content and make suggestions based on that information. For example, the analysis unit can select particularly important information from the call content and make suggestions based on that information. This allows for efficient management of important information during a call. Some or all of the above-described processing by the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the text data of the call content into a generation AI and cause the generation AI to execute a process to extract patterns of dates, phone numbers, and account numbers.

[0074] The providing unit can provide the generated summary in a chat format. For example, the providing unit can display the generated summary in a text format, allowing the user to easily check the contents of the call. For example, the providing unit can display the generated summary in a chat format, allowing the user to easily search the contents of the call. The providing unit can also estimate the user's emotions and adjust the display method of the summary based on the estimated emotions. For example, if the user is nervous, the providing unit can provide a simple, highly visible display method. If the user is relaxed, the providing unit can also provide a display method including detailed information. This allows the user to easily check the contents of the call by providing the summary in a chat format. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the generated summary to a generation AI and cause the generation AI to display it in a chat format.

[0075] The recording unit can estimate the user's emotion and adjust the start timing of recording based on the estimated user emotion. For example, the recording unit estimates the user's emotion and adjusts the start timing of recording based on the estimated emotion. For example, if the user is nervous, the recording unit starts recording a few seconds after the call begins. Alternatively, if the user is relaxed, the recording unit can start recording at the same time as the call begins. Furthermore, if the user is in a hurry, the recording unit can prepare for recording before the call begins and start recording at the same time as the call begins. This allows for more appropriate recording by adjusting the start timing of recording according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or without AI. For example, the recording unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process to adjust the start timing of recording.

[0076] The recording unit can dynamically adjust the quality of the recording depending on the content of the call. For example, if the content of the call is business-related, the recording unit performs high-quality recording. Alternatively, if the content of the call is a private conversation, the recording unit can perform standard-quality recording. Furthermore, if the content of the call contains important information, the recording unit can perform highest-quality recording. This makes it possible to provide optimal recording quality depending on the content of the call. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input text data of the content of the call to a generation AI and cause the generation AI to perform processing to dynamically adjust the quality of the recording.

[0077] The recording unit can automatically filter background noise during a call to record clear audio. For example, the recording unit can analyze background noise during a call in real time and remove noise. The recording unit can also filter sounds in a specific frequency band during a call to record clear audio. Furthermore, the recording unit can reduce environmental noise during a call and emphasize the speaker's voice. This allows for clear audio recording by filtering background noise. Some or all of the above-described processing in the recording unit can be performed using, for example, AI, or can be performed without using AI. For example, the recording unit can input audio data during a call to a generation AI and have the generation AI filter the background noise.

[0078] The recording unit can automatically mark and emphasize important parts of a call during recording. For example, the recording unit can detect keywords during a call and emphasize those parts before recording. The recording unit can also automatically mark the speaker's tone and emphasized parts during a call. Furthermore, the recording unit can detect important phrases or sentences during a call and mark them for easy later retrieval. This allows for easy later retrieval by highlighting important parts of the call. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input audio data during a call into a generation AI and have the generation AI mark important parts.

[0079] The recording unit can estimate the user's emotion and adjust the storage period of the recording based on the estimated user emotion. For example, the recording unit estimates the user's emotion and adjusts the storage period of the recording based on the estimated emotion. For example, if the user is nervous, the recording unit can store the recording for a short period of time. Furthermore, if the user is relaxed, the recording unit can store the recording for a long period of time. Furthermore, if the user is in a hurry, the recording unit can temporarily store the recording so that it can be reviewed later. This enables appropriate storage management by adjusting the storage period of the recording according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or without AI. For example, the recording unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process to adjust the storage period of the recording.

[0080] The recording unit can automatically divide the recording based on the content of the call during recording. For example, the recording unit divides the recording each time the content of the call changes to a different topic. The recording unit can also divide the recording for each important part of the call. Furthermore, the recording unit can divide the recording at regular intervals depending on the elapsed time of the call. By dividing the recording based on the content of the call, later search and playback become easier. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input text data of the content of the call into a generation AI and have the generation AI divide the recording.

[0081] The recording unit can identify the voice of the other party during a call and record it separately. For example, the recording unit can separate the voice of each speaker during a call and record it separately. The recording unit can also identify the voice of each speaker during a call and save the voice of each speaker in a separate file. Furthermore, the recording unit can analyze the voice of each speaker during a call in real time and record it separately. This allows the voice of the other party during a call to be recorded separately, making it easier to analyze and play back later. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input audio data during a call into a generation AI and have the generation AI identify the speaker's voice and record it separately.

[0082] The recording unit can automatically select a recording format based on the content of the call when recording. For example, if the content of the call is business-related, the recording unit records in a high-quality format. The recording unit can also record in a standard-quality format if the content of the call is a private conversation. Furthermore, if the content of the call contains important information, the recording unit can also record in the highest-quality format. This improves the quality of the recording by selecting the optimal recording format based on the content of the call. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can input text data of the content of the call to a generation AI and have the generation AI select the recording format.

[0083] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated emotions. For example, if the user is nervous, the analysis unit prioritizes analyzing important call content. Furthermore, if the user is relaxed, the analysis unit can analyze the entire call content evenly. Furthermore, if the user is in a hurry, the analysis unit can prioritize analyzing key points. Thus, by determining the analysis priority based on the user's emotions, important call content can be analyzed preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process of determining the analysis priority.

[0084] The analysis unit can analyze the context of the call content and extract important keywords. The analysis unit, for example, generates text data of the call content and analyzes the context of the call content. The analysis unit can also extract particularly important keywords from the call content. Furthermore, the analysis unit can refer to related background information to understand the context of the call content. In this way, important keywords can be extracted by analyzing the context of the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text data of the call content to a generation AI and have the generation AI analyze the context and extract keywords.

[0085] The analysis unit can analyze the emotional tone of the call content and visualize changes in emotion. The analysis unit, for example, generates text data of the call content and analyzes the emotional tone of the call content. The analysis unit can also analyze the emotional tone of the speaker during the call in real time and display it in a graph. Furthermore, the analysis unit can visualize changes in emotion during the call in chronological order. In this way, by analyzing the emotional tone of the call content, changes in emotion can be visualized. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text data of the call content to a generation AI and have the generation AI analyze and visualize the emotional tone.

[0086] The analysis unit can analyze the speech time of each speaker in the call content and calculate the speaker's speech ratio. The analysis unit, for example, generates text data of the call content and analyzes the speech time of each speaker in the call content. The analysis unit can also display the speech time of each speaker during the call in a graph. Furthermore, the analysis unit can analyze the speech ratio of each speaker during the call and evaluate the balance. In this way, the speech ratio of each speaker can be calculated by analyzing the speech time of each speaker in the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text data of the call content to a generation AI and have the generation AI analyze the speech time and calculate the speech ratio.

[0087] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This enables highly visible display by adjusting the display method of the analysis results according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process of adjusting the display method of the analysis results.

[0088] The analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. For example, the analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. The analysis unit can also identify multiple languages ​​used in the call and apply an appropriate analysis algorithm for each. Furthermore, the analysis unit can identify the language of the call content in real time and dynamically switch the analysis algorithm. This enables appropriate analysis by automatically identifying the language of the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input audio data of the call content to a generation AI and have the generation AI identify the language and apply the analysis algorithm.

[0089] The analysis unit can improve the accuracy of the analysis by referring to background information of the call content. For example, the analysis unit can improve the accuracy of the analysis by referring to background information of the call content. The analysis unit can also perform analysis by referring to background information related to a specific topic during the call. Furthermore, the analysis unit can automatically acquire and analyze related background information to understand the context of the call content. As a result, the accuracy of the analysis is improved by referring to the background information of the call content. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input text data of the call content into the generation AI and have the generation AI refer to and analyze the background information.

[0090] The analysis unit can convert the voice data of the call content into text data and perform text analysis. For example, the analysis unit can convert the voice data of the call content into text data in real time. The analysis unit can also convert the voice data of the call content into text data and extract keywords. Furthermore, the analysis unit can convert the voice data of the call content into text data and analyze the context. This makes it possible to perform text analysis by converting the voice data into text data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the voice data of the call content into a generation AI and have the generation AI perform conversion to text data and text analysis.

[0091] The summarization unit can estimate the user's emotion and adjust the summary presentation style based on the estimated user emotion. For example, the summarization unit can estimate the user's emotion and adjust the summary presentation style based on the estimated emotion. For example, if the user is nervous, the summarization unit can provide a simple, highly visible summary. If the user is relaxed, the summarization unit can also provide a summary with detailed information. Furthermore, if the user is in a hurry, the summarization unit can also provide a summary that focuses on the main points. By adjusting the summary presentation style according to the user's emotion, a highly visible summary can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the summarization unit can be performed using, for example, AI, or without AI. For example, the summarization unit can input the user's emotion data into the generation AI and cause the generation AI to perform a process of adjusting the summary presentation style.

[0092] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the call content. For example, if the call content is important, the summarization unit can provide a detailed summary. If the call content is general, the summarization unit can also provide a standard summary. Furthermore, if the call content is minor, the summarization unit can also provide a concise summary. In this way, an appropriate summary can be provided by adjusting the level of detail of the summary based on the importance of the call content. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to perform processing to adjust the level of detail of the summary.

[0093] When generating a summary, the summarization unit can apply different summarization algorithms depending on the category of the call content. For example, in the case of a business-related call, the summarization unit can apply a business summarization algorithm. In addition, in the case of a private call, the summarization unit can also apply a private summarization algorithm. Furthermore, in the case of an academic call, the summarization unit can also apply an academic summarization algorithm. In this way, an appropriate summary is provided by applying a summarization algorithm depending on the category of the call content. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to apply a summarization algorithm depending on the category.

[0094] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. For example, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit can also learn specific patterns from the user's past summarization results and improve the accuracy of the summary. Furthermore, the summarization unit can adjust the summarization algorithm based on the user's past summarization results. In this way, the accuracy of the summary is improved by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input the user's past summarization results into the generation AI and cause the generation AI to perform processing to improve the accuracy of the summary.

[0095] The summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user emotion. For example, the summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated emotion. For example, if the user is nervous, the summarization unit can provide a short, concise summary. If the user is relaxed, the summarization unit can also provide a detailed summary. Furthermore, if the user is in a hurry, the summarization unit can also provide a concise summary. By adjusting the length of the summary according to the user's emotion, an appropriate summary can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the summarization unit can be performed using, for example, AI, or without AI. For example, the summarization unit can input user emotion data into the generation AI and cause the generation AI to adjust the length of the summary.

[0096] When generating a summary, the summarization unit can determine the priority of summaries based on the submission time of the call content. For example, the summarization unit prioritizes summarization of call content with an upcoming submission deadline. The summarization unit can also postpone summarization of call content with a more distant submission deadline. Furthermore, the summarization unit can adjust the level of detail of the summary based on the submission time. In this way, by determining the priority of summaries based on the submission time of the call content, summaries are provided at an appropriate time. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to execute a process of determining the priority of summaries based on the submission time.

[0097] When generating a summary, the summarization unit can adjust the order of summaries based on the relevance of the call content. For example, the summarization unit prioritizes summarization of highly relevant call content. The summarization unit can also postpone summarization of less relevant call content. Furthermore, the summarization unit can automatically adjust the order of summaries based on the relevance of the call content. In this way, by adjusting the order of summaries based on the relevance of the call content, summaries are provided in an appropriate order. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input text data of the call content into the generation AI and cause the generation AI to perform processing to adjust the order of summaries based on relevance.

[0098] When generating a summary, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. For example, if the user is an expert, the summarization unit can provide a summary that uses a lot of technical terms. Alternatively, if the user is a layperson, the summarization unit can provide a summary that avoids technical terms. Furthermore, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. This allows for an appropriate summary to be provided by adjusting the use of technical terms in the summary according to the user's level of expertise. Some or all of the above-described processing in the summarization unit may be performed using, or without, AI. For example, the summarization unit can input the user's level of expertise into the generation AI and cause the generation AI to perform a process of adjusting the use of technical terms.

[0099] The providing unit can estimate the user's emotion and adjust the display method of the summary to be provided based on the estimated user emotion. For example, the providing unit can estimate the user's emotion and adjust the display method of the summary to be provided based on the estimated emotion. For example, if the user is nervous, the providing unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the providing unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can provide a display method that focuses on the main points. This enables highly visible display by adjusting the summary display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, an AI. For example, the providing unit can input the user's emotion data into the generation AI and cause the generation AI to execute a process of adjusting the summary display method.

[0100] When providing the display method, the providing unit can select the optimal display method by referring to the user's past operation history. For example, the providing unit preferentially provides a display method that the user has used favorably in the past. The providing unit can also suggest the optimal display method from the user's past operation history. Furthermore, the providing unit can customize the display method based on the user's past operation history. In this way, the optimal display method is provided by referring to the user's past operation history. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the user's operation history data to the generation AI and cause the generation AI to execute processing to select the optimal display method.

[0101] The providing unit can customize the display content according to the user's current task when providing the information. For example, when the user is at work, the providing unit can prioritize displaying information related to work. Furthermore, when the user is spending private time, the providing unit can also prioritize displaying information related to private life. Furthermore, the providing unit can dynamically customize the display content according to the user's current task. As a result, appropriate information is provided by customizing the display content according to the user's current task. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's task data into the generating AI and cause the generating AI to perform processing to customize the display content.

[0102] The providing unit can improve the display method by reflecting user feedback when providing the data. The providing unit improves the display method based on user feedback, for example. The providing unit can also reflect user feedback in real time and adjust the display method. Furthermore, the providing unit can analyze user feedback and propose an optimal display method. In this way, the display method is improved by reflecting user feedback. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input user feedback data into the generating AI and cause the generating AI to execute processing to improve the display method.

[0103] The providing unit can estimate the user's emotions and determine the priority of summaries to be provided based on the estimated user emotions. The providing unit, for example, estimates the user's emotions and determines the priority of summaries to be provided based on the estimated emotions. For example, when the user is nervous, the providing unit can prioritize providing important summaries. Furthermore, when the user is relaxed, the providing unit can also provide overall summaries evenly. Furthermore, when the user is in a hurry, the providing unit can prioritize providing summaries that focus on the main points. In this way, by determining the priority of summaries according to the user's emotions, important summaries are provided preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input user emotion data into the generation AI and cause the generation AI to execute a process of determining the priority of summaries.

[0104] The providing unit can select the optimal display method based on the user's device information at the time of providing. For example, if the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Furthermore, if the user is using a tablet, the providing unit can also provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can also provide a simple and highly visible display method. This improves visibility by providing the optimal display method based on the user's device information. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the user's device information into the generation AI and cause the generation AI to execute a process of selecting the optimal display method.

[0105] The providing unit can make the display content multilingual according to the user's language setting when providing the display content. The providing unit automatically sets the display content based on, for example, the language setting of the user's device. The providing unit can also provide a language switching function when the user uses multiple languages. Furthermore, when the user selects a specific language, the providing unit can provide the display content in that language. In this way, by making the display content multilingual according to the user's language setting, information is provided in an appropriate language. Some or all of the above-described processing by the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the user's language setting data into a generation AI and cause the generation AI to execute multilingual display content.

[0106] The providing unit can customize the display format according to the user's visual preferences when providing the display format. The providing unit customizes the display format using, for example, the user's preferred colors and fonts. The providing unit can also adjust the display layout according to the user's visual preferences. Furthermore, the providing unit can also suggest an optimal display format based on the user's past selection history. This improves visibility by customizing the display format according to the user's visual preferences. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's visual preference data into the generating AI and cause the generating AI to execute processing to customize the display format. === Hard Collateral 1-1 === Each of the multiple elements, including the recording unit, analysis unit, summarization unit, and provision 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 recording unit can record a call from a user using the microphone 38B of the smart device 14 and generate a recording file using the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the recorded call content using the specific processing unit 290 of the data processing device 12 and generate text data of the call content. For example, the summarization unit can generate a one-line summary or a detailed summary by paragraphs corresponding to the theme of the call content using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the summary generated by the control unit 46A of the smart device 14 in a chat format, allowing the user to easily check the call content. === Hard Collateral 1-2 === Each of the multiple elements, including the recording unit, analysis unit, summarization unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit can record a call from a user using the microphone 238 of the smart glasses 214 and generate a recording file using the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the recorded call content using the specific processing unit 290 of the data processing device 12 and generate text data of the call content. For example, the summarization unit can generate a one-line summary or a detailed summary by paragraphs corresponding to the theme of the call content using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the summary generated by the control unit 46A of the smart glasses 214 in a chat format, allowing the user to easily check the call content. === Hard Collateral 1-3 === Each of the multiple elements, including the recording unit, analysis unit, summarization unit, and provision unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the recording unit can record a call from a user using the microphone 238 of the headset-type terminal 314 and generate a recording file using the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the recorded call content using the specific processing unit 290 of the data processing device 12 and generate text data of the call content. For example, the summarization unit can generate a one-line summary or a detailed summary by paragraph that corresponds to the theme of the call content using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the summary generated by the control unit 46A of the headset-type terminal 314 in a chat format, allowing the user to easily check the call content. === Hard Collateral 1-4 === Each of the multiple elements, including the recording unit, analysis unit, summarization unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the recording unit can record a call from a user using the microphone 238 of the robot 414 and generate a recording file using the specific processing unit 290 of the data processing device 12. For example, the analysis unit can analyze the recorded call content using the specific processing unit 290 of the data processing device 12 and generate text data of the call content. For example, the summarization unit can generate a one-line summary or a detailed summary by paragraph that corresponds to the theme of the call content using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the summary generated by the control unit 46A of the robot 414 in a chat format, allowing the user to easily check the call content.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The recording unit can estimate the importance of a call by analyzing the tone and speed of the user's voice. For example, if the user speaks quickly, the recording unit can mark the call as high importance. On the other hand, if the user speaks calmly, the recording unit can mark the call as low importance. Furthermore, if the user's tone of voice changes, the recording unit can highlight that part as particularly important. This makes it possible to manage recordings according to the importance of the call.

[0109] The analysis unit can analyze background sounds of the call content and detect specific environmental sounds. For example, if the analysis unit hears the sound of a car during a call, it generates a tag indicating that the call was made while moving. Also, if music is playing during a call, the analysis unit can generate a tag indicating that the call was made in a relaxed environment. Furthermore, if there is a lot of noise during a call, the analysis unit can generate a tag indicating that the call was made in a noisy environment. This makes it possible to perform analysis according to the environment of the call.

[0110] The summarization unit can adjust the order of summarization based on the importance of the call content. For example, the summarization unit can first summarize parts containing important information, and then summarize general information. The summarization unit can also prioritize summarizing topics that the user is particularly interested in. Furthermore, the summarization unit can adjust the level of detail of the summary based on the importance of the call content. This allows important information to be provided preferentially.

[0111] The providing unit can estimate the user's emotions and customize the summary display method based on the estimated emotions. For example, if the user is feeling stressed, the providing unit can provide a simple, highly visible display method. If the user is feeling relaxed, the providing unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can also provide a display method that focuses on the main points. This makes it possible to display the most appropriate summary according to the user's emotions.

[0112] The recording unit can detect specific keywords in a call and automatically highlight those parts. For example, if keywords such as "important" or "urgent" appear during a call, the recording unit will highlight those parts. The recording unit can also highlight parts when specific names or places are mentioned during a call. Furthermore, the recording unit can detect specific phrases or sentences in a call and mark them for easy later retrieval. This highlights important information and makes it easier to search for later.

[0113] The analysis unit can analyze the emotional tone of the call content and visualize changes in emotion over time. For example, the analysis unit can analyze the emotional tone of the speaker during a call in real time and display it in a graph. The analysis unit can also visualize changes in emotion during a call over time. Furthermore, the analysis unit can identify peaks and drops in emotion during a call and highlight those parts. In this way, changes in emotion can be visualized by analyzing the emotional tone of the call content.

[0114] The providing unit can select the optimal display method by referring to the user's past operation history. For example, the providing unit can preferentially provide a display method that the user has used favorably in the past. The providing unit can also suggest the optimal display method based on the user's past operation history. Furthermore, the providing unit can customize the display method based on the user's past operation history. In this way, the optimal display method is provided by referring to the user's past operation history.

[0115] The analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. For example, the analysis unit can automatically identify the language of the call content and apply an appropriate language analysis algorithm. The analysis unit can also identify multiple languages ​​used in a call and apply an appropriate analysis algorithm for each language. Furthermore, the analysis unit can identify the language of the call content in real time and dynamically switch the analysis algorithm. This makes it possible to perform appropriate analysis by automatically identifying the language of the call content.

[0116] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is nervous, the summarization unit can provide a simple, highly visible summary. If the user is relaxed, the summarization unit can also provide a summary that includes detailed information. Furthermore, if the user is in a hurry, the summarization unit can also provide a summary that focuses on the main points. In this way, by adjusting the way the summary is presented according to the user's emotions, a highly visible summary can be provided.

[0117] The providing unit can select the optimal display method based on the user's device information. For example, if the user is using a smartphone, the providing unit can provide a display method that matches the screen size. Also, if the user is using a tablet, the providing unit can provide a display method that is optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can provide a simple and highly visible display method. This improves visibility by providing the optimal display method based on the user's device information.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The recording unit records the call from the user. The recording unit starts recording when the call starts and stops recording when the call ends. The recording unit also generates a recording file and has the function of adjusting the recording quality. For example, it can dynamically adjust the recording quality depending on the content of the call. Step 2: The analysis unit analyzes the call content recorded by the recording unit. The analysis unit generates text data of the call content and extracts themes and important information from the call content. It can also analyze the context of the call content, extract important keywords and emotional tones, and visualize changes in emotions. Step 3: The summarization unit generates a summary based on the call content analyzed by the analysis unit. The summarization unit generates a one-line summary or a detailed summary by paragraph that corresponds to the theme of the call content. It also generates a representative tag for each call, making it easy to search for the call content by tag. Step 4: The providing unit provides the summary generated by the summarizing unit in a chat format. The providing unit displays the generated summary in a text format so that the user can easily check the contents of the call. The providing unit can also estimate the user's emotions and adjust the display method of the summary based on the estimated emotions.

[0120] 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.

[0121] 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.

[0122] 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.

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

[0125] 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.

[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 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.

[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. 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.

[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 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.

[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 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.

[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 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.

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

[0141] 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.

[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 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.

[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 (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).

[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] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 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 recording unit for recording calls from users; an analysis unit that analyzes the contents of the call recorded by the recording unit; a summarizing unit that generates a summary based on the call content analyzed by the analyzing unit; a providing unit that provides the summary generated by the summarizing unit in a chat format. A system characterized by:

2. The analysis unit Generate a one-line summary that fits the topic of the call 2. The system of claim 1.

3. The analysis unit Generate a detailed paragraph-by-paragraph summary of the call 2. The system of claim 1.

4. The analysis unit Generate a representative tag for each call 2. The system of claim 1.

5. The analysis unit Make suggestions based on patterns of dates, phone numbers, or account numbers mentioned during the call 2. The system of claim 1.

6. The providing unit Provide generated summaries in chat format 2. The system of claim 1.

7. The recording unit Estimate the user's emotion and adjust the start timing of recording based on the estimated user emotion.

2. The system of claim 1.

8. The recording unit Dynamically adjust recording quality based on call content 2. The system of claim 1.

9. The recording unit When recording, automatically filters background noise from calls to record clear audio 2. The system of claim 1.

10. The recording unit Automatically mark and highlight important parts of calls as you record 2. The system of claim 1.

Images