System

Abstract

An object of a system according to an embodiment is to efficiently summarize a chat history and provide the chat history in a story form.SOLUTION: A system includes a chat history analysis part, a summary generation part, a story generation part, and a provision part. The chat history analysis unit analyzes the chat history. The summary generation unit summarizes the chat history analyzed by the chat history analysis unit. The story generation unit converts the summary generated by the summary generation unit into a narrative sentence. The provision unit randomly provides or designates and provides the sentence in the story form generated by the story generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have been unable to efficiently summarize chat histories and provide them in a narrative format, making it difficult to look back on past interactions.

[0005] The system according to the embodiment aims to efficiently summarize chat histories and provide them in a narrative format. [Means for solving the problem]

[0006] The system according to the embodiment includes a chat history analysis unit, a summary generation unit, a story generation unit, and a providing unit. The chat history analysis unit analyzes the chat history. The summary generation unit summarizes the chat history analyzed by the chat history analysis unit. The story generation unit converts the summary generated by the summary generation unit into a story-style sentence. The providing unit randomly or specifically provides the story-style sentence generated by the story generation unit. [Effects of the Invention]

[0007] An embodiment of the system can efficiently summarize chat histories and present them in a narrative format. [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 automatic summarization system according to an embodiment of the present invention is a system in which a generation AI implemented in LINE (registered trademark) automatically summarizes interactions between users or within a group on LINE (registered trademark) and provides the chat as a single story (text). As a result, the automatic summarization system analyzes the user's chat history and provides a summary in the form of a story, thereby providing an emotional experience.

[0029] An automatic summarization system according to an embodiment includes a chat history analysis unit, a summary generation unit, a story generation unit, and a providing unit. The chat history analysis unit analyzes the chat history. For example, the chat history analysis unit analyzes text messages between users and extracts important exchanges. The chat history analysis unit can also analyze the frequency of use of images and stamps. The summary generation unit summarizes the chat history analyzed by the chat history analysis unit. For example, the summary generation unit uses a generation AI to concisely summarize important exchanges. The summary generation unit can also use an emotion estimation function to reflect emotional peaks in the summary. The story generation unit converts the summary generated by the summary generation unit into a story-like sentence. For example, the story generation unit uses a generation AI to write the summary in a story-like style. The story generation unit can also learn a user's past chat style and language usage and generate a story-like sentence that reflects that. The providing unit randomly or specifically provides the story-like sentence generated by the story generation unit. For example, the providing unit summarizes a randomly selected chat history and provides it as a story-like sentence. The providing unit can also generate a summary based on the person or period specified by the user and provide the summary as a story-like text. This allows the automatic summarization system according to the embodiment to analyze the user's chat history and provide the summary as a story-like text, thereby providing an emotional experience.

[0030] The chat history analysis unit calculates the frequency of specific keywords and phrases and can extract important exchanges based on that. For example, the chat history analysis unit uses a generation AI to analyze chat history and calculate the frequency of specific keywords and phrases. For example, it extracts important exchanges based on frequently occurring phrases such as "thank you" and "congratulations." The chat history analysis unit also identifies parts of the chat history where specific keywords are frequently used and includes those parts in the summary. For example, it extracts keywords related to the theme or topic of the conversation. The chat history analysis unit also analyzes keyword frequency to build a system that automatically extracts important exchanges. For example, it includes highlights of the conversation based on frequently occurring keywords in the summary. This allows for the extraction of important exchanges based on the frequency of specific keywords and phrases, improving the accuracy of the summary.

[0031] The chat history analysis unit can generate summaries that include visual elements by taking into account the frequency of use of images and stamps. For example, the chat history analysis unit can consider the frequency of use of images and stamps when analyzing chat history. For example, frequently used stamps and images can be included in the summary. The chat history analysis unit can also use image recognition technology to analyze the content of images included in the chat history and reflect important images in the summary. For example, images that show specific events or occurrences can be included in the summary. The chat history analysis unit can also analyze the frequency of use of stamps and build a system that extracts important exchanges. For example, parts where stamps expressing emotions are frequently used can be included in the summary. In this way, by taking into account the frequency of use of images and stamps, it is possible to generate summaries that include visual elements.

[0032] The chat history analysis unit can analyze chat histories in different languages ​​and generate summaries in multiple languages. The chat history analysis unit, for example, builds a system that analyzes chat histories in different languages ​​and generates summaries in multiple languages. For example, chat histories in English and Chinese are translated into Japanese and summarized. The chat history analysis unit also uses automatic translation technology to analyze chat histories in different languages ​​and generate summaries. For example, conversations conducted in multiple languages ​​are summarized into a single summary. The chat history analysis unit also develops a multilingual summary generation system and analyzes chat histories in different languages. For example, a summary is provided in a language specified by the user. This makes it possible to analyze chat histories in different languages ​​and generate summaries in multiple languages.

[0033] The story generation unit can learn a user's past chat style and language usage and generate story-style sentences that reflect that. For example, the story generation unit uses a generation AI to learn a user's past chat style and language usage and generate story-style sentences that reflect that. For example, the story generation unit incorporates the user's unique expressions and tone of voice into the story. The story generation unit also analyzes past chat history and builds a system that learns the user's language usage and style. For example, the story generation unit reflects the user's characteristic phrases and expressions in the story. The story generation unit also uses a generation AI to learn a user's past chat style and generate story-style sentences based on that. For example, the story generation unit provides a story that reflects the user's personality. This makes it possible to generate story-style sentences that reflect the user's past chat style and language usage.

[0034] The story generation unit can enhance the appeal of a story by automatically generating characters and scenarios that users can easily empathize with. For example, the story generation unit uses a generation AI to automatically generate characters and scenarios that users can easily empathize with, thereby enhancing the appeal of the story. For example, it introduces characters that match the user's preferences. The story generation unit also builds a system that automatically generates scenarios that users can easily empathize with based on the user's past chat history. For example, it provides stories based on the user's interests and concerns. The story generation unit can also enhance the appeal of a story by automatically generating characters and scenarios that users can easily empathize with using a generation AI. For example, it incorporates scenarios that appeal to the user's emotions into the story. This allows the automatic generation of characters and scenarios that users can easily empathize with, thereby enhancing the appeal of the story.

[0035] The story generation unit can provide the generated story in audiobook format using voice synthesis technology. The story generation unit, for example, builds a system that provides the generated story in audiobook format using voice synthesis technology. For example, it adds a function to play the story aloud. The story generation unit also provides the generated story in audiobook format using voice synthesis technology. For example, it enables a user to listen to the story. The story generation unit also provides the generated story in audiobook format using voice synthesis technology. For example, it enables a user to listen to the story. In this way, the generated story can be provided in audiobook format using voice synthesis technology.

[0036] The story generation unit can provide story-form text as a comic or a storyboard with illustrations. The story generation unit, for example, builds a system that provides the generated story as a comic or a storyboard with illustrations. For example, it represents scenes of the story with illustrations. The story generation unit also provides story-form text as a comic or a storyboard with illustrations. For example, it allows the user to enjoy the content of the story visually. The story generation unit also provides the generated story as a comic or a storyboard with illustrations. For example, it represents scenes of the story with illustrations so that the user can enjoy the content visually. In this way, it is possible to provide story-form text as a comic or a storyboard with illustrations.

[0037] The providing unit can learn the user's past browsing history and interests when randomly providing summaries, and provide more personalized summaries. The providing unit, for example, builds a system that learns the user's past browsing history and interests when randomly providing summaries, and provides more personalized summaries. For example, a summary based on the user's interests is provided. The providing unit also analyzes the user's past browsing history and provides summaries based on the interests. For example, a summary related to a topic that the user is interested in is provided. The providing unit also learns the user's interests when randomly providing summaries, and provides personalized summaries. For example, a summary tailored to the user's preferences is provided. In this way, the providing unit can learn the user's past browsing history and interests, and provide more personalized summaries.

[0038] The providing unit can generate a summary focusing on a specific theme or topic based on a period or person designated by the user when providing the specified summary. The providing unit, for example, builds a system for generating a summary focusing on a specific theme or topic based on a period or person designated by the user when providing the specified summary. For example, the providing unit provides a summary related to a specific event or occurrence. The providing unit also generates a summary focusing on a specific theme based on a period or person designated by the user. For example, important exchanges within a period designated by the user are included in the summary. The providing unit also generates a summary focusing on a specific topic based on a person or period designated by the user when providing the specified summary. For example, highlights of a conversation with a specific person are included in the summary. In this way, a summary focusing on a specific theme or topic can be generated based on a period or person designated by the user.

[0039] The providing unit can provide summaries that match the user's current mood and situation when randomly providing summaries. The providing unit, for example, builds a system that provides summaries that match the user's current mood and situation when randomly providing summaries. For example, when the user wants to relax, the providing unit includes fun interactions in the summary. The providing unit also analyzes the user's current mood and provides summaries that match the mood. For example, when the user wants to be moved, the providing unit includes moving interactions in the summary. The providing unit also provides summaries that match the user's situation when randomly providing summaries. For example, when the user is feeling stressed, the providing unit includes relaxing interactions in the summary. In this way, it is possible to provide summaries that match the user's current mood and situation.

[0040] The providing unit can provide interactions related to an event specified by the user as a summary when specifying the information to be provided. For example, the providing unit builds a system that summarizes interactions related to an event specified by the user when specifying the information to be provided. For example, interactions on birthdays or anniversaries are included in the summary. The providing unit also summarizes related interactions based on an event specified by the user. For example, conversations related to a specific event are included in the summary. The providing unit also summarizes interactions related to an event specified by the user when specifying the information to be provided. For example, interactions on anniversaries or special days are included in the summary. This makes it possible to provide interactions related to an event specified by the user as a summary.

[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 chat history analysis unit can analyze a user's chat history and extract activity patterns during specific time periods. For example, it can identify the time periods when a user is most active in chatting and include the exchanges during those time periods in the summary. The chat history analysis unit can also extract important exchanges during specific time periods based on the user's activity patterns. For example, it can include important conversations that took place at night in the summary. The chat history analysis unit can also analyze a user's activity patterns and track changes in emotions during specific time periods. For example, it can include exchanges that caused emotional excitement late at night in the summary. This makes it possible to reflect important exchanges during specific time periods in the summary based on the user's activity patterns.

[0043] The summary generation unit can analyze a user's chat history and generate a summary based on a specific theme. For example, it can extract interactions related to travel and generate a summary like a travelogue. The summary generation unit can also extract interactions related to a specific event from the user's chat history and generate a summary focused on that event. For example, it can include interactions about a birthday party in the summary. The summary generation unit can also analyze a user's chat history and extract interactions related to a specific topic and generate a summary based on that topic. For example, it can include interactions related to work in the summary. This makes it possible to generate a summary based on a specific theme or topic.

[0044] The story generation unit can analyze a user's chat history and generate a story centered on a specific character. For example, a person frequently mentioned by the user can appear in the story as a character. The story generation unit can also extract the actions and statements of a specific character from the user's chat history and generate a story centered on that character. For example, it can generate a story based on interactions with friends. The story generation unit can also analyze a user's chat history and generate a story that reflects the changes in the emotions of a specific character. For example, it can generate a story centered on a moving exchange. This makes it possible to generate a story centered on a specific character.

[0045] The providing unit can analyze the user's chat history and provide summaries of interactions over a specific period. For example, interactions over the past week can be included in the summary. The providing unit can also provide summaries of interactions over a specific period based on a period specified by the user. For example, important interactions over the past month can be included in the summary. The providing unit can also analyze the user's chat history and provide summaries that reflect changes in emotions over a specific period. For example, moving interactions over a specific period can be included in the summary. In this way, summaries of interactions over a specific period can be provided.

[0046] The chat history analysis unit can analyze a user's chat history and extract interactions related to a specific location. For example, interactions at a travel destination can be included in the summary. The chat history analysis unit can also extract interactions related to a specific location from the user's chat history and generate a summary focused on that location. For example, interactions at a restaurant can be included in the summary. The chat history analysis unit can also analyze a user's chat history and provide a summary that reflects changes in emotions related to a specific location. For example, moving interactions at a travel destination can be included in the summary. This makes it possible to provide a summary of interactions related to a specific location.

[0047] The summary generation unit can analyze a user's chat history and extract interactions related to a specific event. For example, interactions from a birthday party can be included in the summary. The summary generation unit can also extract interactions related to a specific event from a user's chat history and generate a summary that focuses on that event. For example, interactions from a wedding can be included in the summary. The summary generation unit can also analyze a user's chat history and provide a summary that reflects changes in emotions related to a specific event. For example, interactions from an emotional event can be included in the summary. This makes it possible to provide a summary of interactions related to a specific event.

[0048] The story generation unit can analyze a user's chat history and generate a story based on a specific theme. For example, it can extract exchanges related to love and generate a story like a romance novel. The story generation unit can also extract exchanges related to a specific theme from the user's chat history and generate a story based on that theme. For example, it can include exchanges related to adventure in the story. The story generation unit can also analyze a user's chat history and provide a story that reflects changes in emotions related to a specific theme. For example, it can include exchanges on a moving theme in the story. This makes it possible to generate a story based on a specific theme.

[0049] The providing unit can analyze the user's chat history and provide summaries of interactions over a specific period. For example, interactions over the past week can be included in the summary. The providing unit can also provide summaries of interactions over a specific period based on a period specified by the user. For example, important interactions over the past month can be included in the summary. The providing unit can also analyze the user's chat history and provide summaries that reflect changes in emotions over a specific period. For example, moving interactions over a specific period can be included in the summary. In this way, summaries of interactions over a specific period can be provided.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The chat history analysis unit analyzes the chat history. For example, the chat history analysis unit analyzes text messages between users and extracts important exchanges. The chat history analysis unit can also analyze the frequency of use of images and stamps. Step 2: The summary generator summarizes the chat history analyzed by the chat history analyzer. For example, the summary generator uses a generation AI to concisely summarize important exchanges. The summary generator can also use an emotion estimation function to reflect emotional peaks in the summary. Step 3: The story generation unit converts the summary generated by the summary generation unit into a story-like text. For example, the story generation unit uses a generation AI to write the summary in a story-like format. The story generation unit can also learn the user's past chat style and language usage and generate story-like text that reflects that. Step 4: The providing unit randomly or specifically provides the story-style text generated by the story generation unit. For example, the providing unit summarizes a randomly selected chat history and provides it as a story-style text. The providing unit can also generate a summary based on a person or period specified by the user and provide it as a story-style text.

[0052] (Example 2) The automatic summarization system according to an embodiment of the present invention is a system in which a generation AI implemented in LINE (registered trademark) automatically summarizes interactions between users or within a group on LINE (registered trademark) and provides the chat as a single story (text). As a result, the automatic summarization system analyzes the user's chat history and provides a summary in the form of a story, thereby providing an emotional experience.

[0053] An automatic summarization system according to an embodiment includes a chat history analysis unit, a summary generation unit, a story generation unit, and a providing unit. The chat history analysis unit analyzes the chat history. For example, the chat history analysis unit analyzes text messages between users and extracts important exchanges. The chat history analysis unit can also analyze the frequency of use of images and stamps. The summary generation unit summarizes the chat history analyzed by the chat history analysis unit. For example, the summary generation unit uses a generation AI to concisely summarize important exchanges. The summary generation unit can also use an emotion estimation function to reflect emotional peaks in the summary. The story generation unit converts the summary generated by the summary generation unit into a story-like sentence. For example, the story generation unit uses a generation AI to write the summary in a story-like style. The story generation unit can also learn a user's past chat style and language usage and generate a story-like sentence that reflects that. The providing unit randomly or specifically provides the story-like sentence generated by the story generation unit. For example, the providing unit summarizes a randomly selected chat history and provides it as a story-like sentence. The providing unit can also generate a summary based on the person or period specified by the user and provide the summary as a story-like text. This allows the automatic summarization system according to the embodiment to analyze the user's chat history and provide the summary as a story-like text, thereby providing an emotional experience.

[0054] The chat history analysis unit can track changes in a user's emotions and reflect emotional peaks in the summary. For example, the chat history analysis unit uses a generation AI to analyze chat history and track changes in a user's emotions. For example, it identifies moments in a conversation when a user expresses joy or sadness and reflects those emotional peaks in the summary. The chat history analysis unit also performs emotion analysis and graphs changes in a user's emotions. For example, it can include high emotional peaks in the summary to emphasize emotional moments. The chat history analysis unit also uses an emotion estimation function to identify moments when a user's emotions were highest and generate a summary centered around those moments. For example, it can include moving exchanges and important conversations in the summary. This allows emotional moments to be emphasized by reflecting the user's emotional peaks in the summary.

[0055] The chat history analysis unit calculates the frequency of specific keywords and phrases and can extract important exchanges based on that. For example, the chat history analysis unit uses a generation AI to analyze chat history and calculate the frequency of specific keywords and phrases. For example, it extracts important exchanges based on frequently occurring phrases such as "thank you" and "congratulations." The chat history analysis unit also identifies parts of the chat history where specific keywords are frequently used and includes those parts in the summary. For example, it extracts keywords related to the theme or topic of the conversation. The chat history analysis unit also analyzes keyword frequency to build a system that automatically extracts important exchanges. For example, it includes highlights of the conversation based on frequently occurring keywords in the summary. This allows for the extraction of important exchanges based on the frequency of specific keywords and phrases, improving the accuracy of the summary.

[0056] The chat history analysis unit can use the emotion estimation function to identify the moment when the user's emotion was at its highest and generate a summary centered on that moment. The chat history analysis unit, for example, uses the emotion estimation function to identify the moment when the user's emotion was at its highest. For example, the summary includes a moment in a conversation when the user was moved. The chat history analysis unit also reflects the part where the user's emotion reached its peak in the summary based on the emotion estimation data. For example, phrases and expressions that indicate heightened emotion are included in the summary. The chat history analysis unit also uses the emotion estimation function to build a system that generates a summary centered on the moment when the user's emotion was at its highest. For example, the part that indicates the peak of emotion is emphasized. In this way, by generating a summary centered on the moment when the user's emotion was at its highest, emotional moments can be emphasized.

[0057] The chat history analysis unit can generate summaries that include visual elements by taking into account the frequency of use of images and stamps. For example, the chat history analysis unit can consider the frequency of use of images and stamps when analyzing chat history. For example, frequently used stamps and images can be included in the summary. The chat history analysis unit can also use image recognition technology to analyze the content of images included in the chat history and reflect important images in the summary. For example, images that show specific events or occurrences can be included in the summary. The chat history analysis unit can also analyze the frequency of use of stamps and build a system that extracts important exchanges. For example, parts where stamps expressing emotions are frequently used can be included in the summary. In this way, by taking into account the frequency of use of images and stamps, it is possible to generate summaries that include visual elements.

[0058] The chat history analysis unit can analyze chat histories in different languages ​​and generate summaries in multiple languages. The chat history analysis unit, for example, builds a system that analyzes chat histories in different languages ​​and generates summaries in multiple languages. For example, chat histories in English and Chinese are translated into Japanese and summarized. The chat history analysis unit also uses automatic translation technology to analyze chat histories in different languages ​​and generate summaries. For example, conversations conducted in multiple languages ​​are summarized into a single summary. The chat history analysis unit also develops a multilingual summary generation system and analyzes chat histories in different languages. For example, a summary is provided in a language specified by the user. This makes it possible to analyze chat histories in different languages ​​and generate summaries in multiple languages.

[0059] The chat history analysis unit uses the emotion estimation function to filter interactions in which the user has a specific emotion and can provide a summary based on that emotion. The chat history analysis unit, for example, uses the emotion estimation function to filter interactions in which the user has a specific emotion. For example, interactions that show joy or emotion are included in the summary. The chat history analysis unit also extracts interactions in which the user has a specific emotion based on the emotion estimation data and provides a summary based on that emotion. For example, parts that show an increase in emotion are included in the summary. The chat history analysis unit also uses the emotion estimation function to build a system that filters interactions in which the user has a specific emotion and generates a summary based on that emotion. For example, parts that show the peak of emotion are emphasized. This makes it possible to filter interactions in which the user has a specific emotion and provide a summary based on that emotion.

[0060] The story generation unit can learn a user's past chat style and language usage and generate story-style sentences that reflect that. For example, the story generation unit uses a generation AI to learn a user's past chat style and language usage and generate story-style sentences that reflect that. For example, the story generation unit incorporates the user's unique expressions and tone of voice into the story. The story generation unit also analyzes past chat history and builds a system that learns the user's language usage and style. For example, the story generation unit reflects the user's characteristic phrases and expressions in the story. The story generation unit also uses a generation AI to learn a user's past chat style and generate story-style sentences based on that. For example, the story generation unit provides a story that reflects the user's personality. This makes it possible to generate story-style sentences that reflect the user's past chat style and language usage.

[0061] The story generation unit can enhance the appeal of a story by automatically generating characters and scenarios that users can easily empathize with. For example, the story generation unit uses a generation AI to automatically generate characters and scenarios that users can easily empathize with, thereby enhancing the appeal of the story. For example, it introduces characters that match the user's preferences. The story generation unit also builds a system that automatically generates scenarios that users can easily empathize with based on the user's past chat history. For example, it provides stories based on the user's interests and concerns. The story generation unit can also enhance the appeal of a story by automatically generating characters and scenarios that users can easily empathize with using a generation AI. For example, it incorporates scenarios that appeal to the user's emotions into the story. This allows the automatic generation of characters and scenarios that users can easily empathize with, thereby enhancing the appeal of the story.

[0062] The story generation unit can use the emotion estimation function to adjust the tone and atmosphere of the story to match the user's emotions. For example, the story generation unit uses the emotion estimation function to adjust the tone and atmosphere of the story to match the user's emotions. For example, if the user is moved, an emotional tone is emphasized. The story generation unit also builds a system that adjusts the tone and atmosphere of the story based on the user's emotion estimation data. For example, the atmosphere of the story changes depending on the user's emotions. The story generation unit also uses the emotion estimation function to adjust the tone and atmosphere of the story to match the user's emotions. For example, if the user is happy, a bright tone is emphasized. This makes it possible to adjust the tone and atmosphere of the story to match the user's emotions.

[0063] The story generation unit can provide the generated story in audiobook format using voice synthesis technology. The story generation unit, for example, builds a system that provides the generated story in audiobook format using voice synthesis technology. For example, it adds a function to play the story aloud. The story generation unit also provides the generated story in audiobook format using voice synthesis technology. For example, it enables a user to listen to the story. The story generation unit also provides the generated story in audiobook format using voice synthesis technology. For example, it enables a user to listen to the story. In this way, the generated story can be provided in audiobook format using voice synthesis technology.

[0064] The story generation unit can provide story-form text as a comic or a storyboard with illustrations. The story generation unit, for example, builds a system that provides the generated story as a comic or a storyboard with illustrations. For example, it represents scenes of the story with illustrations. The story generation unit also provides story-form text as a comic or a storyboard with illustrations. For example, it allows the user to enjoy the content of the story visually. The story generation unit also provides the generated story as a comic or a storyboard with illustrations. For example, it represents scenes of the story with illustrations so that the user can enjoy the content visually. In this way, it is possible to provide story-form text as a comic or a storyboard with illustrations.

[0065] The story generation unit can use the emotion estimation function to generate a scenario for a short film centered on the interaction that moved the user the most. The story generation unit, for example, uses the emotion estimation function to generate a scenario for a short film centered on the interaction that moved the user the most. For example, a scenario that emphasizes moving scenes is created. The story generation unit also builds a system that generates a scenario for a short film centered on the interaction that moved the user the most, based on the user's emotion estimation data. For example, a scene that shows the peak of the emotion is included in the scenario. The story generation unit also uses the emotion estimation function to generate a scenario for a short film centered on the interaction that moved the user the most. For example, a scenario that emphasizes moving moments is created. This makes it possible to generate a scenario for a short film centered on the interaction that moved the user the most.

[0066] The providing unit can learn the user's past browsing history and interests when randomly providing summaries, and provide more personalized summaries. The providing unit, for example, builds a system that learns the user's past browsing history and interests when randomly providing summaries, and provides more personalized summaries. For example, a summary based on the user's interests is provided. The providing unit also analyzes the user's past browsing history and provides summaries based on the interests. For example, a summary related to a topic that the user is interested in is provided. The providing unit also learns the user's interests when randomly providing summaries, and provides personalized summaries. For example, a summary tailored to the user's preferences is provided. In this way, the providing unit can learn the user's past browsing history and interests, and provide more personalized summaries.

[0067] The providing unit can generate a summary focusing on a specific theme or topic based on a period or person designated by the user when providing the specified summary. The providing unit, for example, builds a system for generating a summary focusing on a specific theme or topic based on a period or person designated by the user when providing the specified summary. For example, the providing unit provides a summary related to a specific event or occurrence. The providing unit also generates a summary focusing on a specific theme based on a period or person designated by the user. For example, important exchanges within a period designated by the user are included in the summary. The providing unit also generates a summary focusing on a specific topic based on a person or period designated by the user when providing the specified summary. For example, highlights of a conversation with a specific person are included in the summary. In this way, a summary focusing on a specific theme or topic can be generated based on a period or person designated by the user.

[0068] The providing unit can use the emotion estimation function to preferentially provide interactions to which the user responded most emotionally. The providing unit, for example, uses the emotion estimation function to build a system that preferentially provides interactions to which the user responded most emotionally. For example, interactions that indicate emotional peaks are included in summaries. The providing unit also extracts interactions to which the user responded most emotionally based on the user's emotion estimation data and provides them preferentially. For example, moving moments are included in summaries. The providing unit also uses the emotion estimation function to preferentially provide interactions to which the user responded most emotionally. For example, parts that indicate heightened emotions are included in summaries. This makes it possible to preferentially provide interactions to which the user responded most emotionally.

[0069] The providing unit can provide summaries that match the user's current mood and situation when randomly providing summaries. The providing unit, for example, builds a system that provides summaries that match the user's current mood and situation when randomly providing summaries. For example, when the user wants to relax, the providing unit includes fun interactions in the summary. The providing unit also analyzes the user's current mood and provides summaries that match the mood. For example, when the user wants to be moved, the providing unit includes moving interactions in the summary. The providing unit also provides summaries that match the user's situation when randomly providing summaries. For example, when the user is feeling stressed, the providing unit includes relaxing interactions in the summary. In this way, it is possible to provide summaries that match the user's current mood and situation.

[0070] The providing unit can provide interactions related to an event specified by the user as a summary when specifying the information to be provided. For example, the providing unit builds a system that summarizes interactions related to an event specified by the user when specifying the information to be provided. For example, interactions on birthdays or anniversaries are included in the summary. The providing unit also summarizes related interactions based on an event specified by the user. For example, conversations related to a specific event are included in the summary. The providing unit also summarizes interactions related to an event specified by the user when specifying the information to be provided. For example, interactions on anniversaries or special days are included in the summary. This makes it possible to provide interactions related to an event specified by the user as a summary.

[0071] The providing unit can use the emotion estimation function to select an interaction that is most relaxing for the user and provide a summary for stress relief. The providing unit, for example, uses the emotion estimation function to build a system that selects an interaction that is most relaxing for the user and provides a summary for stress relief. For example, the providing unit includes a relaxing conversation in the summary. The providing unit also extracts the most relaxing interaction based on the user's emotion estimation data and provides a summary for stress relief. For example, the providing unit includes a relaxing moment in the summary. The providing unit also uses the emotion estimation function to select an interaction that is most relaxing for the user and provide a summary for stress relief. For example, the providing unit includes a relaxing conversation in the summary. This makes it possible to select an interaction that is most relaxing for the user and provide a summary for stress relief.

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

[0073] The chat history analysis unit can analyze a user's chat history and extract activity patterns during specific time periods. For example, it can identify the time periods when a user is most active in chatting and include the exchanges during those time periods in the summary. The chat history analysis unit can also extract important exchanges during specific time periods based on the user's activity patterns. For example, it can include important conversations that took place at night in the summary. The chat history analysis unit can also analyze a user's activity patterns and track changes in emotions during specific time periods. For example, it can include exchanges that caused emotional excitement late at night in the summary. This makes it possible to reflect important exchanges during specific time periods in the summary based on the user's activity patterns.

[0074] The summary generation unit can analyze a user's chat history and generate a summary based on a specific theme. For example, it can extract interactions related to travel and generate a summary like a travelogue. The summary generation unit can also extract interactions related to a specific event from the user's chat history and generate a summary focused on that event. For example, it can include interactions about a birthday party in the summary. The summary generation unit can also analyze a user's chat history and extract interactions related to a specific topic and generate a summary based on that topic. For example, it can include interactions related to work in the summary. This makes it possible to generate a summary based on a specific theme or topic.

[0075] The story generation unit can analyze a user's chat history and generate a story centered on a specific character. For example, a person frequently mentioned by the user can appear in the story as a character. The story generation unit can also extract the actions and statements of a specific character from the user's chat history and generate a story centered on that character. For example, it can generate a story based on interactions with friends. The story generation unit can also analyze a user's chat history and generate a story that reflects the changes in the emotions of a specific character. For example, it can generate a story centered on a moving exchange. This makes it possible to generate a story centered on a specific character.

[0076] The providing unit can analyze a user's chat history and provide a summary based on a specific emotion. For example, the exchange that made the user happiest can be included in the summary. The providing unit can also provide a summary based on a specific emotion based on the user's emotion estimation data. For example, the summary can include a touching exchange. The providing unit can also build a system that analyzes a user's chat history and provides a summary based on a specific emotion. For example, the summary can include a transaction that made the user saddest. This makes it possible to provide a summary based on a specific emotion.

[0077] The providing unit can analyze the user's chat history and provide summaries of interactions over a specific period. For example, interactions over the past week can be included in the summary. The providing unit can also provide summaries of interactions over a specific period based on a period specified by the user. For example, important interactions over the past month can be included in the summary. The providing unit can also analyze the user's chat history and provide summaries that reflect changes in emotions over a specific period. For example, moving interactions over a specific period can be included in the summary. In this way, summaries of interactions over a specific period can be provided.

[0078] The chat history analysis unit can analyze a user's chat history and extract interactions related to a specific location. For example, interactions at a travel destination can be included in the summary. The chat history analysis unit can also extract interactions related to a specific location from the user's chat history and generate a summary focused on that location. For example, interactions at a restaurant can be included in the summary. The chat history analysis unit can also analyze a user's chat history and provide a summary that reflects changes in emotions related to a specific location. For example, moving interactions at a travel destination can be included in the summary. This makes it possible to provide a summary of interactions related to a specific location.

[0079] The summary generation unit can analyze a user's chat history and extract interactions related to a specific event. For example, interactions from a birthday party can be included in the summary. The summary generation unit can also extract interactions related to a specific event from a user's chat history and generate a summary that focuses on that event. For example, interactions from a wedding can be included in the summary. The summary generation unit can also analyze a user's chat history and provide a summary that reflects changes in emotions related to a specific event. For example, interactions from an emotional event can be included in the summary. This makes it possible to provide a summary of interactions related to a specific event.

[0080] The story generation unit can analyze a user's chat history and generate a story based on a specific theme. For example, it can extract exchanges related to love and generate a story like a romance novel. The story generation unit can also extract exchanges related to a specific theme from the user's chat history and generate a story based on that theme. For example, it can include exchanges related to adventure in the story. The story generation unit can also analyze a user's chat history and provide a story that reflects changes in emotions related to a specific theme. For example, it can include exchanges on a moving theme in the story. This makes it possible to generate a story based on a specific theme.

[0081] The providing unit can analyze the user's chat history and provide a summary based on a specific emotion. For example, the exchange that moved the user the most can be included in the summary. The providing unit can also provide a summary based on a specific emotion based on the user's emotion estimation data. For example, the exchange that moved the user the most can be included in the summary. The providing unit can also build a system that analyzes the user's chat history and provides a summary based on a specific emotion. For example, the exchange that moved the user the most can be included in the summary. This makes it possible to provide a summary based on a specific emotion.

[0082] The providing unit can analyze the user's chat history and provide summaries of interactions over a specific period. For example, interactions over the past week can be included in the summary. The providing unit can also provide summaries of interactions over a specific period based on a period specified by the user. For example, important interactions over the past month can be included in the summary. The providing unit can also analyze the user's chat history and provide summaries that reflect changes in emotions over a specific period. For example, moving interactions over a specific period can be included in the summary. In this way, summaries of interactions over a specific period can be provided.

[0083] The processing flow of the second embodiment will be briefly explained below.

[0084] Step 1: The chat history analysis unit analyzes the chat history. For example, the chat history analysis unit analyzes text messages between users and extracts important exchanges. The chat history analysis unit can also analyze the frequency of use of images and stamps. Step 2: The summary generator summarizes the chat history analyzed by the chat history analyzer. For example, the summary generator uses a generation AI to concisely summarize important exchanges. The summary generator can also use an emotion estimation function to reflect emotional peaks in the summary. Step 3: The story generation unit converts the summary generated by the summary generation unit into a story-like text. For example, the story generation unit uses a generation AI to write the summary in a story-like format. The story generation unit can also learn the user's past chat style and language usage and generate story-like text that reflects that. Step 4: The providing unit randomly or specifically provides the story-style text generated by the story generation unit. For example, the providing unit summarizes a randomly selected chat history and provides it as a story-style text. The providing unit can also generate a summary based on a person or period specified by the user and provide it as a story-style text.

[0085] 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.

[0086] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0087] 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.

[0088] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0089] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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).

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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 AI 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.

[0102] 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.

[0103] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0104] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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 AI 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.

[0117] 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.

[0118] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0119] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0139] 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."

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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]

[0152] 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 chat history analysis unit that analyzes the chat history; a summary generation unit that summarizes the chat history analyzed by the chat history analysis unit; a story generation unit that converts the summary generated by the summary generation unit into a story-format sentence; a providing unit that randomly or specifically provides the story-style text generated by the story generating unit; A system characterized by:

2. The chat history analysis unit Tracking changes in the user's emotions and reflecting peaks of the emotions in the summary 2. The system of claim 1.

3. The chat history analysis unit Calculate the frequency of specific keywords and phrases and extract important interactions based on that 2. The system of claim 1.

4. The chat history analysis unit Identify the moment when the user's emotions were the strongest and generate the summary centered around that moment.

2. The system of claim 1.

5. The chat history analysis unit Generate a summary that includes visual elements, taking into account the frequency of use of images and stamps.

2. The system of claim 1.

6. The chat history analysis unit Analyzing the chat history in different languages ​​and generating a multilingual summary 2. The system of claim 1.

Images