System

Abstract

The object and advantages of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the claims.SOLUTION: A system includes a call content summarization unit, a keyword extraction unit, and a metadata recording unit. The call content summarizing unit summarizes the call content. The keyword extraction unit extracts a keyword from the call content summarized by the call content summarization unit. The metadata recording unit records the date and time of the call, the information of the other party, the summary of the call, and the keyword.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 of making it difficult to efficiently manage and later check the contents of phone calls.

[0005] The system according to the embodiment aims to efficiently manage the contents of calls and enable them to be checked later. [Means for solving the problem]

[0006] The system according to the embodiment includes a call content summarizing unit, a keyword extracting unit, and a metadata recording unit. The call content summarizing unit summarizes the call content. The keyword extracting unit extracts keywords from the call content summarized by the call content summarizing unit. The metadata recording unit records the date and time of the call, information about the call partner, the call summary, and keywords. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently manage the contents of calls and enable them to be checked later. [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) The call content summarization system according to an embodiment of the present invention is a system that can track who, when, and what kind of conversation took place by summarizing the call content and organizing it using keywords without listening to or recording the call content in real time. As a result, the call content summarization system can protect privacy and reduce costs while allowing the call content to be checked later.

[0029] A call content summarization system according to an embodiment includes a call content summarization unit, a keyword extraction unit, and a metadata recording unit. The call content summarization unit summarizes the call content. For example, the generation AI analyzes the audio data of the call content and summarizes the important points. For example, the generation AI extracts keywords such as "contract," "payment," and "deadline" during the call and records them as a call summary. The generation AI can summarize the call content using a text generation AI (e.g., LLM). The generation AI can also summarize the call content using a multimodal generation AI. For example, the generation AI extracts the main points of the call content and summarizes them concisely. The keyword extraction unit extracts keywords from the call content summarized by the call content summarization unit. For example, the generation AI extracts important keywords such as "contract," "payment," and "deadline" from the call content and records them. The generation AI can extract important keywords from the call content using natural language processing technology. For example, the generation AI extracts frequently occurring words and important words and creates a keyword list. The metadata recording unit records the date and time of a call, information about the other party, a call summary, and keywords. For example, the date and time of the call, the other party's phone number, the call summary, and keywords are stored in a single database. The metadata recording unit records call metadata, enabling tracking of who, when, and what kind of conversation took place. As a result, the call content summary system according to the embodiment can track who, when, and what kind of conversation took place by summarizing the call content and organizing it with keywords. For example, the call content can be easily searched and checked.

[0030] In addition to summarizing the call content, the call content summary unit can visualize the progress of the conversation in real time, allowing the user to intuitively grasp the flow of the conversation. In the call content summary unit, for example, the generation AI analyzes the call content in real time and visualizes the progress of the conversation in graph or timeline format. For example, it visually displays the timing when important topics are discussed. In addition to the summary of the call content, it also provides a dashboard that updates the progress of the conversation in real time. For example, it displays each section of the conversation in a color-coded manner, allowing the user to intuitively understand. Furthermore, to visualize the progress of the conversation in real time, the generation AI analyzes the audio data and records the timing and order of speakers' remarks. For example, it displays the speaking time of each speaker in a graph. This allows the user to intuitively grasp the flow of the conversation by visualizing the progress of the conversation in real time.

[0031] The call content summarization unit can provide a summary of the call content not only in text but also in audio or visual notes, allowing the user to select one of these formats. For example, the call content summarization unit builds a system in which a generation AI summarizes the call content and provides the summary in the form of text, audio, or visual notes. For example, the system allows the user to select their preferred format. To provide the call content summary in audio format, the generation AI reads the summary using speech synthesis technology. For example, the call summary may be saved as an audio file so that the user can listen to it later. To provide the call content summary in visual note format, the generation AI expresses the summary in diagrams or illustrations. For example, important points may be indicated with icons or charts. This allows the user to select their preferred format by providing the call content summary in the form of text, audio, or visual notes.

[0032] The call content summarization unit can enable international use by automatically translating call content from different languages ​​and providing summaries in multiple languages. The call content summarization unit, for example, builds a system in which a generation AI summarizes call content and automatically translates the summaries. For example, summaries are provided in multiple languages, such as English, Japanese, and French. In addition, to provide call content summaries in multiple languages, the generation AI integrates a translation engine and performs translation in real time. For example, call summaries are displayed simultaneously in different languages. Furthermore, to enable international use, the generation AI provides call content summaries in multiple languages ​​and provides an interface that allows users to select the language. For example, the summary is displayed in the user's preferred language. This enables international use by automatically translating call content from different languages ​​and providing summaries in multiple languages.

[0033] When extracting keywords, the keyword extraction unit simultaneously extracts synonyms and related words, allowing for the creation of a more comprehensive keyword list. For example, the keyword extraction unit employs an algorithm that simultaneously extracts synonyms and related words when the generation AI analyzes the content of a call and extracts keywords. For example, for the keyword "contract," related words such as "agreement" and "contract" are added to the list. Furthermore, when extracting keywords, the generation AI automatically identifies synonyms and related words using natural language processing technology. For example, for the keyword "payment," related words such as "settlement" and "remittance" are extracted. Furthermore, when the generation AI analyzes the content of a call and creates a keyword list, it generates a comprehensive list that includes synonyms and related words. For example, for the keyword "deadline," related words such as "deadline" and "deadline" are added. This allows for the creation of a more comprehensive keyword list by simultaneously extracting synonyms and related words.

[0034] The keyword extraction unit can automatically evaluate the importance of keywords and prioritize the display of keywords according to their importance. For example, the keyword extraction unit introduces an algorithm in which the generation AI analyzes the content of a call and automatically evaluates the importance of keywords. For example, it scores importance based on frequency and context. In addition, a system is constructed in which the generation AI prioritizes the display of keywords according to their importance. For example, it displays keywords with high importance in bold or color. Furthermore, when the generation AI analyzes the content of a call and evaluates the importance of keywords, it learns from past data and sets standards for importance. For example, it evaluates keywords that frequently appeared in past calls as having high importance. This automatically evaluates the importance of keywords and prioritizes their display according to their importance, allowing users to quickly grasp important information.

[0035] The keyword extraction unit extracts and records keywords not only from text but also from images and audio data, making it possible to utilize multimodal information. For example, the generation AI analyzes the contents of phone calls and builds a system in which it extracts keywords not only from text but also from images and audio data. For example, it extracts keywords from images and audio notes shared during calls. To utilize multimodal information, the generation AI integrates image recognition and audio analysis technologies to extract keywords. For example, it analyzes the content of text within images and audio data to record keywords. Furthermore, a system will be developed in which the generation AI analyzes the contents of phone calls and integrates and records keywords extracted from text, images, and audio data. For example, it will combine keywords extracted from different data formats into a single list. This allows multimodal information to be utilized by extracting keywords not only from text but also from images and audio data.

[0036] The keyword extraction unit can automatically recognize technical terms from different industries and fields and add them to the keyword list. For example, the generation AI analyzes the content of the call and introduces an algorithm that automatically recognizes technical terms from different industries and fields. For example, it identifies technical terms such as medical, legal, and technical. Furthermore, to automatically recognize technical terms and add them to the keyword list, the generation AI references industry-specific databases. For example, it uses a medical terminology dictionary or technical glossary. Furthermore, as the generation AI analyzes the content of the call and automatically recognizes technical terms from different industries and fields, it learns from past data and updates the list of technical terms. For example, newly emerged technical terms are added to the list. In this way, a more comprehensive keyword list can be created by automatically recognizing technical terms from different industries and fields and adding them to the keyword list.

[0037] The metadata recording unit can also record background and environmental sounds during a call in the call metadata, allowing for a more detailed understanding of the call situation. For example, the metadata recording unit constructs a system in which a generation AI analyzes the content of a call and records background and environmental sounds during the call. For example, car sounds and human voices heard during a call are saved as metadata. To include background and environmental sounds in the call metadata, the generation AI analyzes audio data and introduces an algorithm to identify specific sounds. For example, it records noise levels and specific sounds during a call. Furthermore, to provide a more detailed understanding of the call situation, the generation AI analyzes background and environmental sounds during a call in real time and records them as metadata. For example, it tracks changes in environmental sounds during a call. This allows for a more detailed understanding of the call situation by recording background and environmental sounds during the call.

[0038] The metadata recording unit can link call metadata with content and keywords to improve searchability. For example, the metadata recording unit constructs a system in which a generation AI analyzes call content and links call metadata with content and keywords. For example, it associates and saves call summaries and keywords with metadata. Furthermore, to link call metadata with content and keywords, the generation AI analyzes relevance using natural language processing technology. For example, it tags metadata based on the content of the call. Furthermore, to improve call searchability, the generation AI links call metadata with content and keywords and provides an interface that allows users to easily search. For example, a keyword search displays metadata of related calls. This improves searchability by linking call metadata with content and keywords.

[0039] The metadata recording unit can integrate call metadata with other databases to enable a broader understanding of the context of the call. For example, the metadata recording unit builds a system in which the generation AI analyzes the content of the call and integrates the call metadata with a calendar or contacts. For example, the generation AI links the date and time of the call and information about the other party with a calendar event. To integrate the call metadata with other databases, the generation AI also uses an API to link data. For example, it obtains detailed information about the other party from a contacts database. Furthermore, to gain a broader understanding of the context of the call, the generation AI integrates the call metadata with other databases and provides an interface that allows the user to view related information at a glance. For example, it displays call history and calendar events in an integrated manner. This allows the call metadata to be integrated with other databases to enable a broader understanding of the context of the call.

[0040] The metadata recording unit can visualize and display call metadata, allowing users to intuitively understand it. For example, the generation AI analyzes the content of a call and builds a system that visualizes the call metadata. For example, it displays a call summary and keywords in graphs and charts. In addition, to visualize and display the call metadata, the generation AI uses data visualization technology. For example, it displays the date and time of the call and information about the other party in a timeline format. Furthermore, the generation AI develops an interface that provides visualized metadata so that users can intuitively understand the call metadata. For example, it displays emotional changes during a call in different colors. In this way, the visualization and display of the call metadata allows users to intuitively understand it.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The call summary unit can refer to background information about the call content to improve the accuracy of the summary. For example, it can analyze emails and messages sent before and after the call to understand the context of the call. It can also refer to past call history related to the call summary to identify similar conversation patterns. It can also reference external databases related to the call summary to complement the background information about the call content. For example, in the case of a business conversation, it can generate a more detailed summary by referring to related market data and news articles.

[0043] The call summary unit can combine and use multiple summarization algorithms to improve the reliability of the summary. For example, it can run summarization algorithms using different natural language processing techniques in parallel and integrate their results. It also collects user feedback to evaluate the accuracy of the summary and use it to improve the algorithm. Furthermore, to improve the reliability of the summary, a system is built in which the generation AI verifies the summary results and corrects errors. For example, it checks whether the summary content matches the actual content of the call.

[0044] The call summary unit can highlight important points to visually emphasize the summary content. For example, important keywords and phrases in the summary text can be displayed in color. Also, to visually emphasize the summary content, important points can be indicated with icons or graphics. Furthermore, to visually emphasize the summary content, the generation AI analyzes the summary text and builds a system that automatically highlights important points. For example, important keywords and phrases in the summary text can be displayed in bold.

[0045] The call summary unit can link the summary to the user's schedule. For example, it can automatically add the call summary as a calendar event so that the user can check it later. It can also add the call summary to a task list so that the user can manage actions to be taken after the call. It can also set the call summary as a reminder so that the user does not forget important points. For example, it can automatically generate reminders set by the user based on the call summary.

[0046] The call summary module can customize the summary content according to user preferences. For example, the user can set it to emphasize specific keywords or phrases. The summary content can also be filtered according to user preferences to remove unnecessary information. Furthermore, the summary content can be formatted according to user preferences to provide an easy-to-read format. For example, the summary content can be displayed in bullet points or paragraph format.

[0047] The call content summarization unit can link the summary content with other applications. For example, the summary content can be automatically added to a project management tool and managed as a task. The summary content can also be linked to a CRM system and saved as customer information. Furthermore, the summary content can be linked to a document management system and saved as a call record. For example, the summary content can be automatically generated and saved as a document.

[0048] The call content summarization unit can improve the content of the summary based on user feedback. For example, the user can rate the content of the summary, and the accuracy of the summary can be improved based on that rating. In addition, an algorithm can be developed to collect user feedback and improve the content of the summary. Furthermore, a system can be built that automatically corrects the content of the summary based on user feedback. For example, errors pointed out by the user can be automatically corrected.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The call content summarization unit summarizes the call content. For example, the generation AI analyzes the audio data of the call content and summarizes the important points. The generation AI can summarize the call content using text generation AI (e.g., LLM) or multimodal generation AI. Step 2: The Keyword Extraction Unit extracts keywords from the call content summarized by the Call Content Summarization Unit. For example, the Generative AI uses natural language processing technology to extract important keywords such as "contract," "payment," and "deadline" from the call content and records them. Step 3: The metadata recorder records the call date and time, the caller's information, the call summary, and keywords. For example, the call date and time, the caller's phone number, the call summary, and keywords are stored in a database.

[0051] (Example 2) The call content summarization system according to an embodiment of the present invention is a system that can track who, when, and what kind of conversation took place by summarizing the call content and organizing it using keywords without listening to or recording the call content in real time. As a result, the call content summarization system can protect privacy and reduce costs while allowing the call content to be checked later.

[0052] A call content summarization system according to an embodiment includes a call content summarization unit, a keyword extraction unit, and a metadata recording unit. The call content summarization unit summarizes the call content. For example, the generation AI analyzes the audio data of the call content and summarizes the important points. For example, the generation AI extracts keywords such as "contract," "payment," and "deadline" during the call and records them as a call summary. The generation AI can summarize the call content using a text generation AI (e.g., LLM). The generation AI can also summarize the call content using a multimodal generation AI. For example, the generation AI extracts the main points of the call content and summarizes them concisely. The keyword extraction unit extracts keywords from the call content summarized by the call content summarization unit. For example, the generation AI extracts important keywords such as "contract," "payment," and "deadline" from the call content and records them. The generation AI can extract important keywords from the call content using natural language processing technology. For example, the generation AI extracts frequently occurring words and important words and creates a keyword list. The metadata recording unit records the date and time of a call, information about the other party, a call summary, and keywords. For example, the date and time of the call, the other party's phone number, the call summary, and keywords are stored in a single database. The metadata recording unit records call metadata, enabling tracking of who, when, and what kind of conversation took place. As a result, the call content summary system according to the embodiment can track who, when, and what kind of conversation took place by summarizing the call content and organizing it with keywords. For example, the call content can be easily searched and checked.

[0053] The call content summarizer understands the context of the conversation and can reflect not only the key points but also the tone and emotion of the conversation in the summary. For example, the call content summarizer uses natural language processing technology to allow the generation AI to analyze the content of the call and understand the context of the conversation. For example, it grasps the flow of the conversation and the speaker's intention, and reflects the tone and emotion of the conversation along with the key points in the summary. It also analyzes the audio data of the call and introduces an algorithm to detect the speaker's tone of voice and emotion. For example, it includes emotional changes, such as when the speaker is excited or calm, in the summary. Furthermore, to understand the context of the conversation, the generation AI learns from past call data and identifies similar conversation patterns. For example, it generates summaries tailored to different contexts, such as business conversations and personal conversations. This allows the tone and emotion of the conversation to be reflected in the summary, enabling a more detailed understanding of the call content.

[0054] In addition to summarizing the call content, the call content summary unit can visualize the progress of the conversation in real time, allowing the user to intuitively grasp the flow of the conversation. In the call content summary unit, for example, the generation AI analyzes the call content in real time and visualizes the progress of the conversation in graph or timeline format. For example, it visually displays the timing when important topics are discussed. In addition to the summary of the call content, it also provides a dashboard that updates the progress of the conversation in real time. For example, it displays each section of the conversation in a color-coded manner, allowing the user to intuitively understand. Furthermore, to visualize the progress of the conversation in real time, the generation AI analyzes the audio data and records the timing and order of speakers' remarks. For example, it displays the speaking time of each speaker in a graph. This allows the user to intuitively grasp the flow of the conversation by visualizing the progress of the conversation in real time.

[0055] The call content summarization unit can use the emotion estimation function to analyze changes in emotions during a call and include emotional peaks and important emotional moments in the summary. For example, the call content summarization unit uses a generation AI to analyze the content of a call and uses the emotion estimation function to detect changes in the speaker's emotions. For example, it identifies moments when the speaker felt anger or joy and includes those emotional peaks in the summary. It also analyzes emotional changes during a call in real time and reflects important emotional moments in the summary. For example, it highlights parts where the speaker had a strong emotional reaction and includes them in the summary. Furthermore, it uses the emotion estimation function to visualize emotional changes during a call in graph or chart format and incorporate them into the summary. For example, it visually displays emotional peaks and trends. This allows the unit to analyze emotional changes during a call and include emotional peaks and important emotional moments in the summary, making it possible to understand the content of the call in more detail.

[0056] The call content summarization unit can provide a summary of the call content not only in text but also in audio or visual notes, allowing the user to select one of these formats. For example, the call content summarization unit builds a system in which a generation AI summarizes the call content and provides the summary in the form of text, audio, or visual notes. For example, the system allows the user to select their preferred format. To provide the call content summary in audio format, the generation AI reads the summary using speech synthesis technology. For example, the call summary may be saved as an audio file so that the user can listen to it later. To provide the call content summary in visual note format, the generation AI expresses the summary in diagrams or illustrations. For example, important points may be indicated with icons or charts. This allows the user to select their preferred format by providing the call content summary in the form of text, audio, or visual notes.

[0057] The call content summarization unit can enable international use by automatically translating call content from different languages ​​and providing summaries in multiple languages. The call content summarization unit, for example, builds a system in which a generation AI summarizes call content and automatically translates the summaries. For example, summaries are provided in multiple languages, such as English, Japanese, and French. In addition, to provide call content summaries in multiple languages, the generation AI integrates a translation engine and performs translation in real time. For example, call summaries are displayed simultaneously in different languages. Furthermore, to enable international use, the generation AI provides call content summaries in multiple languages ​​and provides an interface that allows users to select the language. For example, the summary is displayed in the user's preferred language. This enables international use by automatically translating call content from different languages ​​and providing summaries in multiple languages.

[0058] The call content summarization unit uses the emotion estimation function to collect users' emotional reactions to the call content summary, thereby improving the accuracy of the summary. For example, the call content summarization unit constructs a system in which a generation AI generates a call content summary and collects users' emotional reactions to that summary. For example, it records an emotion score after the user reads the summary. In addition, it uses the emotion estimation function to analyze users' emotional reactions in real time when reading the call content summary, and improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summaries with a high number of positive reactions. Furthermore, it develops a system that collects users' emotional reaction data and identifies areas for improvement in the summary based on the results. For example, it makes suggestions to correct parts with low emotion scores. In this way, by collecting users' emotional reactions to the call content summary and improving the accuracy of the summary, more accurate summaries are possible.

[0059] When extracting keywords, the keyword extraction unit simultaneously extracts synonyms and related words, allowing for the creation of a more comprehensive keyword list. For example, the keyword extraction unit employs an algorithm that simultaneously extracts synonyms and related words when the generation AI analyzes the content of a call and extracts keywords. For example, for the keyword "contract," related words such as "agreement" and "contract" are added to the list. Furthermore, when extracting keywords, the generation AI automatically identifies synonyms and related words using natural language processing technology. For example, for the keyword "payment," related words such as "settlement" and "remittance" are extracted. Furthermore, when the generation AI analyzes the content of a call and creates a keyword list, it generates a comprehensive list that includes synonyms and related words. For example, for the keyword "deadline," related words such as "deadline" and "deadline" are added. This allows for the creation of a more comprehensive keyword list by simultaneously extracting synonyms and related words.

[0060] The keyword extraction unit can automatically evaluate the importance of keywords and prioritize the display of keywords according to their importance. For example, the keyword extraction unit introduces an algorithm in which the generation AI analyzes the content of a call and automatically evaluates the importance of keywords. For example, it scores importance based on frequency and context. In addition, a system is constructed in which the generation AI prioritizes the display of keywords according to their importance. For example, it displays keywords with high importance in bold or color. Furthermore, when the generation AI analyzes the content of a call and evaluates the importance of keywords, it learns from past data and sets standards for importance. For example, it evaluates keywords that frequently appeared in past calls as having high importance. This automatically evaluates the importance of keywords and prioritizes their display according to their importance, allowing users to quickly grasp important information.

[0061] The keyword extraction unit can use the emotion estimation function to identify and highlight emotionally significant keywords. For example, the generation AI analyzes the content of a call and uses the emotion estimation function to identify emotionally significant keywords. For example, it extracts keywords from parts where the speaker shows strong emotions. In addition, the emotion estimation function is used to build a system that analyzes changes in emotions during a call and highlights emotionally significant keywords. For example, keywords that appear at the peak of emotions are displayed in color. Furthermore, when the generation AI analyzes the content of a call and identifies emotionally significant keywords, it evaluates the keywords based on their emotion scores. For example, keywords with high emotion scores are displayed preferentially. In this way, emotionally significant keywords are identified and highlighted, allowing users to quickly grasp important emotional information.

[0062] The keyword extraction unit extracts and records keywords not only from text but also from images and audio data, making it possible to utilize multimodal information. For example, the generation AI analyzes the contents of phone calls and builds a system in which it extracts keywords not only from text but also from images and audio data. For example, it extracts keywords from images and audio notes shared during calls. To utilize multimodal information, the generation AI integrates image recognition and audio analysis technologies to extract keywords. For example, it analyzes the content of text within images and audio data to record keywords. Furthermore, a system will be developed in which the generation AI analyzes the contents of phone calls and integrates and records keywords extracted from text, images, and audio data. For example, it will combine keywords extracted from different data formats into a single list. This allows multimodal information to be utilized by extracting keywords not only from text but also from images and audio data.

[0063] The keyword extraction unit can automatically recognize technical terms from different industries and fields and add them to the keyword list. For example, the generation AI analyzes the content of the call and introduces an algorithm that automatically recognizes technical terms from different industries and fields. For example, it identifies technical terms such as medical, legal, and technical. Furthermore, to automatically recognize technical terms and add them to the keyword list, the generation AI references industry-specific databases. For example, it uses a medical terminology dictionary or technical glossary. Furthermore, as the generation AI analyzes the content of the call and automatically recognizes technical terms from different industries and fields, it learns from past data and updates the list of technical terms. For example, newly emerged technical terms are added to the list. In this way, a more comprehensive keyword list can be created by automatically recognizing technical terms from different industries and fields and adding them to the keyword list.

[0064] The keyword extraction unit can use the emotion estimation function to analyze emotional responses to keywords entered by the user in real time and make suggestions that elicit positive emotions. The keyword extraction unit, for example, builds a system in which a generation AI analyzes emotional responses to keywords entered by the user in real time and makes suggestions that elicit positive emotions. For example, it displays encouraging messages in response to keywords entered by the user. The emotion estimation function is also used to analyze emotional responses to keywords entered by the user and provide advice to elicit positive emotions. For example, it presents positive alternatives when the user enters negative keywords. Furthermore, the generation AI monitors emotional responses to keywords entered by the user in real time and provides an interface for eliciting positive emotions. For example, it displays positive feedback in response to the keywords entered by the user. In this way, the generation AI analyzes emotional responses to keywords entered by the user in real time and makes suggestions that elicit positive emotions, thereby improving user satisfaction.

[0065] The metadata recording unit can also record background and environmental sounds during a call in the call metadata, allowing for a more detailed understanding of the call situation. For example, the metadata recording unit constructs a system in which a generation AI analyzes the content of a call and records background and environmental sounds during the call. For example, car sounds and human voices heard during a call are saved as metadata. To include background and environmental sounds in the call metadata, the generation AI analyzes audio data and introduces an algorithm to identify specific sounds. For example, it records noise levels and specific sounds during a call. Furthermore, to provide a more detailed understanding of the call situation, the generation AI analyzes background and environmental sounds during a call in real time and records them as metadata. For example, it tracks changes in environmental sounds during a call. This allows for a more detailed understanding of the call situation by recording background and environmental sounds during the call.

[0066] The metadata recording unit can link call metadata with content and keywords to improve searchability. For example, the metadata recording unit constructs a system in which a generation AI analyzes call content and links call metadata with content and keywords. For example, it associates and saves call summaries and keywords with metadata. Furthermore, to link call metadata with content and keywords, the generation AI analyzes relevance using natural language processing technology. For example, it tags metadata based on the content of the call. Furthermore, to improve call searchability, the generation AI links call metadata with content and keywords and provides an interface that allows users to easily search. For example, a keyword search displays metadata of related calls. This improves searchability by linking call metadata with content and keywords.

[0067] The metadata recording unit can use the emotion estimation function to record emotional changes during a call as metadata, enabling emotional trends to be tracked. The metadata recording unit, for example, builds a system in which a generation AI analyzes the content of a call and uses the emotion estimation function to record emotional changes during a call as metadata. For example, peaks and changes in the speaker's emotions are included in the metadata. The generation AI also introduces an emotion estimation algorithm to analyze emotional changes during a call in real time and record emotional trends as metadata. For example, the emotion changes during a call are displayed in a graph. Furthermore, a system is developed that uses the emotion estimation function to record emotional changes during a call as metadata and track emotional trends. For example, the emotional trends of a call are analyzed and saved as metadata. This makes it possible to record emotional changes during a call as metadata and track emotional trends.

[0068] The metadata recording unit can integrate call metadata with other databases to enable a broader understanding of the context of the call. For example, the metadata recording unit builds a system in which the generation AI analyzes the content of the call and integrates the call metadata with a calendar or contacts. For example, the generation AI links the date and time of the call and information about the other party with a calendar event. To integrate the call metadata with other databases, the generation AI also uses an API to link data. For example, it obtains detailed information about the other party from a contacts database. Furthermore, to gain a broader understanding of the context of the call, the generation AI integrates the call metadata with other databases and provides an interface that allows the user to view related information at a glance. For example, it displays call history and calendar events in an integrated manner. This allows the call metadata to be integrated with other databases to enable a broader understanding of the context of the call.

[0069] The metadata recording unit can visualize and display call metadata, allowing users to intuitively understand it. For example, the generation AI analyzes the content of a call and builds a system that visualizes the call metadata. For example, it displays a call summary and keywords in graphs and charts. In addition, to visualize and display the call metadata, the generation AI uses data visualization technology. For example, it displays the date and time of the call and information about the other party in a timeline format. Furthermore, the generation AI develops an interface that provides visualized metadata so that users can intuitively understand the call metadata. For example, it displays emotional changes during a call in different colors. In this way, the visualization and display of the call metadata allows users to intuitively understand it.

[0070] The metadata recording unit can use the emotion estimation function to collect users' emotional reactions to call metadata and improve the metadata recording method. For example, the metadata recording unit builds a system in which a generation AI analyzes call content and uses the emotion estimation function to collect users' emotional reactions to call metadata. For example, the unit records an emotion score when a user checks the metadata. The emotion estimation function also analyzes users' emotional reactions in real time when checking call metadata and improves the metadata recording method based on that data. For example, a display method for metadata with a high number of positive reactions is adopted. Furthermore, a system is developed that collects users' emotional reaction data and improves the call metadata recording method based on the results. For example, it makes suggestions to modify metadata with low emotion scores. In this way, by collecting users' emotional reactions to call metadata and improving the metadata recording method, it becomes possible to record metadata that is more suitable for users.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The call summary unit can refer to background information about the call content to improve the accuracy of the summary. For example, it can analyze emails and messages sent before and after the call to understand the context of the call. It can also refer to past call history related to the call summary to identify similar conversation patterns. It can also reference external databases related to the call summary to complement the background information about the call content. For example, in the case of a business conversation, it can generate a more detailed summary by referring to related market data and news articles.

[0073] The call content summarization unit can customize the style of the summary according to the individual needs of the user. For example, it can provide a summary that emphasizes the key points of a contract or negotiation for a business user, or a summary that emphasizes the emotional aspects of a conversation with family or friends for an individual user. Furthermore, it provides an interface that allows the user to select the summary style, and can generate a summary according to the user's preferences. For example, it can allow the user to select the level of detail and format of the summary.

[0074] The call summary unit can combine and use multiple summarization algorithms to improve the reliability of the summary. For example, it can run summarization algorithms using different natural language processing techniques in parallel and integrate their results. It also collects user feedback to evaluate the accuracy of the summary and use it to improve the algorithm. Furthermore, to improve the reliability of the summary, a system is built in which the generation AI verifies the summary results and corrects errors. For example, it checks whether the summary content matches the actual content of the call.

[0075] The call summary unit can highlight important points to visually emphasize the summary content. For example, important keywords and phrases in the summary text can be displayed in color. Also, to visually emphasize the summary content, important points can be indicated with icons or graphics. Furthermore, to visually emphasize the summary content, the generation AI analyzes the summary text and builds a system that automatically highlights important points. For example, important keywords and phrases in the summary text can be displayed in bold.

[0076] The call summary unit can link the summary to the user's schedule. For example, it can automatically add the call summary as a calendar event so that the user can check it later. It can also add the call summary to a task list so that the user can manage actions to be taken after the call. It can also set the call summary as a reminder so that the user does not forget important points. For example, it can automatically generate reminders set by the user based on the call summary.

[0077] The call content summarization unit can use the emotion estimation function to collect the user's emotional response to the call content summary and improve the accuracy of the summary. For example, it records the emotion score after the user reads the summary. In addition, it uses the emotion estimation function to analyze the user's emotional response in real time when reading the call content summary and improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summaries with a high number of positive responses. Furthermore, it collects user emotional response data and develops a system that identifies areas for improvement in the summary based on the results. For example, it makes suggestions to correct parts with low emotion scores.

[0078] The call summary module can customize the summary content according to user preferences. For example, the user can set it to emphasize specific keywords or phrases. The summary content can also be filtered according to user preferences to remove unnecessary information. Furthermore, the summary content can be formatted according to user preferences to provide an easy-to-read format. For example, the summary content can be displayed in bullet points or paragraph format.

[0079] The call content summarization unit can link the summary content with other applications. For example, the summary content can be automatically added to a project management tool and managed as a task. The summary content can also be linked to a CRM system and saved as customer information. Furthermore, the summary content can be linked to a document management system and saved as a call record. For example, the summary content can be automatically generated and saved as a document.

[0080] The call content summarization unit can improve the content of the summary based on user feedback. For example, the user can rate the content of the summary, and the accuracy of the summary can be improved based on that rating. In addition, an algorithm can be developed to collect user feedback and improve the content of the summary. Furthermore, a system can be built that automatically corrects the content of the summary based on user feedback. For example, errors pointed out by the user can be automatically corrected.

[0081] The call content summarization unit can use the emotion estimation function to collect the user's emotional response to the call content summary and improve the accuracy of the summary. For example, it records the emotion score after the user reads the summary. In addition, it uses the emotion estimation function to analyze the user's emotional response in real time when reading the call content summary and improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summaries with a high number of positive responses. Furthermore, it collects user emotional response data and develops a system that identifies areas for improvement in the summary based on the results. For example, it makes suggestions to correct parts with low emotion scores.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The call content summarization unit summarizes the call content. For example, the generation AI analyzes the audio data of the call content and summarizes the important points. The generation AI can summarize the call content using text generation AI (e.g., LLM) or multimodal generation AI. Step 2: The Keyword Extraction Unit extracts keywords from the call content summarized by the Call Content Summarization Unit. For example, the Generative AI uses natural language processing technology to extract important keywords such as "contract," "payment," and "deadline" from the call content and records them. Step 3: The metadata recorder records the call date and time, the caller's information, the call summary, and keywords. For example, the call date and time, the caller's phone number, the call summary, and keywords are stored in a database.

[0084] 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.

[0085] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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. [Explanation of symbols]

[0151] 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 call content summarizing unit that summarizes the call content; a keyword extraction unit that extracts keywords from the call content summarized by the call content summarization unit; a metadata recording unit that records the date and time of the call, information about the other party, a summary of the call, and keywords. A system characterized by:

2. The call content summarizing unit Understand the context of the conversation and ensure your summary captures not only the key points but also the tone and emotion of the conversation 2. The system of claim 1.

3. The call content summarizing unit In addition to summarizing the call, the progress of the conversation is visualized in real time, allowing users to intuitively grasp the flow of the conversation.

2. The system of claim 1.

4. The call content summarizing unit Analyze emotional changes during the call and include emotional peaks and key emotional moments in the summary 2. The system of claim 1.

5. The call content summarizing unit Provide call summaries as audio or visual notes, as well as text, allowing users to choose 2. The system of claim 1.

Images