System

Abstract

To provide a system that efficiently summarizes conversations in a messenger application and provide them to users.SOLUTION: A system according to the embodiment comprises an extraction unit, a generation unit, and a provision unit. The extraction unit analyzes conversions in a messenger application, and extracts important points using emotion analysis technology and topic modeling technology. The generation unit creates a summary based on the points extracted by the extraction unit. The provision unit randomly provides the summary generated by the 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to efficiently extract important points from the large amount of conversations within a messenger app and provide summaries.

[0005] The system according to the embodiment aims to efficiently summarize conversations within a messenger app and provide the summary to a user. [Means for solving the problem]

[0006] The system according to the embodiment includes an extraction unit, a generation unit, and a provision unit. The extraction unit analyzes interactions within a messenger app and extracts important points using sentiment analysis technology and topic modeling technology. The generation unit creates a summary based on the points extracted by the extraction unit. The provision unit randomly provides the summaries generated by the generation unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently summarize interactions within a messenger app and provide the summary to a user. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The messenger app summary system according to the embodiment of the present invention is a system that automatically summarizes interactions within a messenger app and provides chats as a single story (text). This system analyzes interactions within a messenger app and extracts important points using emotion analysis and topic modeling techniques. Next, a generation AI creates a summary based on the extracted points and provides it to the user. For example, the generation AI analyzes interactions within a messenger app, collects information such as the content, sender, and sending time of each message, and extracts important points using emotion analysis and topic modeling techniques. Next, a generation AI creates a summary based on the extracted points. This summary is provided randomly regardless of the most recent interaction, past interactions, or the person involved. Furthermore, in the paid version, the user can create a summary by specifying the person or period. For example, a summary can be created by specifying interactions with a specific friend or interactions over a specific period. This allows the user to obtain a more detailed summary when he or she wants to look back on a specific interaction. This allows the messenger app summary system to allow the user to look back on past interactions and re-experience emotions.

[0029] A messenger app summary system according to an embodiment includes an extraction unit, a generation unit, and a provision unit. The extraction unit analyzes interactions within the messenger app and extracts important points using sentiment analysis technology and topic modeling technology. The extraction unit collects information such as the content, sender, and sending time of each message, and analyzes the emotional nuances of the message using sentiment analysis technology. The extraction unit also identifies the topic of the message using topic modeling technology and extracts important points. For example, the extraction unit analyzes the emotion of the message using a sentiment dictionary-based method and identifies positive emotions and negative emotions. The extraction unit also identifies the topic of the message using LDA (Latent Dirichlet Allocation) and extracts important points. The generation unit creates a summary based on the points extracted by the extraction unit. The generation unit uses, for example, a generation AI to summarize the extracted points into one story (sentence). The generation unit uses, for example, a text generation AI (for example, LLM) to create a summary based on the extracted points. In addition, the generation unit can also create a summary including not only text but also information such as images and audio using a multimodal generation AI. The provision unit randomly provides the summary generated by the generation unit. For example, the provision unit notifies the user of the summary at random timing. In addition, the provision unit can also display the summary on a dedicated screen. For example, the provision unit displays the summary using a pop-up notification. In addition, the provision unit can also display the summary using a push notification. Thereby, the messenger app summary system according to the embodiment allows the user to look back on past interactions and re-experience emotions. A part or all of the above-mentioned processing in the provision unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the provision unit can provide the summary using a generation AI model that inputs the summary generated by the generation unit and randomly provides a summary.

[0030] The extraction unit analyzes the interactions within the messenger app and extracts important points using sentiment analysis and topic modeling techniques. Specifically, it collects information such as the content, sender, and time of sending of each message, and analyzes the emotional nuances of the message using sentiment analysis techniques. Sentiment dictionary-based techniques and machine learning models are used for sentiment analysis. In sentiment dictionary-based techniques, a predefined sentiment dictionary is used to analyze words and phrases in a message and identify emotions such as positive, negative, and neutral. When using a machine learning model, a pre-labeled dataset is used to train the model and predict emotions for new messages. Topic modeling techniques include LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization). When using LDA, a set of messages is expressed as a distribution of topics, and it is determined which topic each message is related to. When using NMF, the message matrix is ​​decomposed to obtain the basis vectors of the topics and the coefficient vectors of the messages. This allows the extraction unit to analyze the emotional nuances and topics of messages and extract important points. Furthermore, the extraction unit can prioritize the extracted points based on the frequency and importance of the messages. For example, if there are many messages related to a particular topic, the topic is extracted as an important point. Emotionally strong messages and messages sent in a concentrated manner during a particular time period are also extracted as important points. This allows the extraction unit to efficiently extract information that is important to the user and use it in the next step, which is summary generation.

[0031] The generation unit creates a summary based on the points extracted by the extraction unit. Specifically, the generation AI is used to summarize the extracted points into one story (sentence). For example, an LLM (large-scale language model) is used for the generation AI. The LLM is trained based on a large amount of text data and has the ability to generate natural sentences. The generation unit gives the extracted points as input to the LLM and generates a summary. For example, if the extracted points are "date and time of the meeting," "agenda," "opinions of participants," etc., the generation unit creates a summary of the meeting based on this information. The generation unit can also use a multimodal generation AI to create a summary that includes not only text but also information such as images and audio. For example, including images and audio clips related to the summary of the meeting provides a richer summary. The generation unit evaluates the quality of the generated summary and makes corrections as necessary. For example, if the generated summary is redundant or missing important information, the generation unit uses the generation AI again to correct the summary. In addition, the generation unit can continuously improve the quality of the summary based on user feedback. For example, the user evaluates the provided summary and adjusts the parameters of the generation AI based on the evaluation results. This enables the generator to provide a high-quality summary that is useful to the user.

[0032] The providing unit randomly provides the summaries generated by the generating unit. Specifically, the summaries are notified to the user at random timing. The providing unit displays the summaries using, for example, a pop-up notification or a push notification. The pop-up notification is displayed on the screen when the user is using the app, and the user can immediately check the summaries. The push notification is displayed in the notification bar of the smartphone even when the user is not using the app, and the user can check the summaries. The providing unit can also display the summaries on a dedicated screen. For example, a tab dedicated to summaries is provided in the app, and the user can check past summaries in a list. The providing unit can optimize the method of providing the summaries based on the user's usage status and feedback. For example, if a user wants to receive a summary at a specific time period, the notification is provided according to that time period. In addition, if the user is interested in a specific topic, summaries related to that topic are preferentially provided. Furthermore, the providing unit can also provide the summaries using a generating AI. For example, the summaries generated by the generating unit are input, and the summaries are provided using a generating AI model that randomly provides summaries. This allows the providing unit to provide summaries at the optimal time for the user, thereby improving user convenience.

[0033] The providing unit can display the summary as a notification. The providing unit displays the summary using, for example, a pop-up notification. For example, when the user is using a messenger app, the providing unit displays a pop-up notification on the screen and provides the summary. The providing unit can also display the summary using a push notification. For example, when the user is not using a messenger app, the providing unit provides the summary using a notification function of the smartphone. This allows the user to immediately check the summary by displaying the summary as a notification. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that receives the summary generated by the generation unit as an input and displays the summary as a notification.

[0034] The providing unit can display the summary on a dedicated screen. The providing unit, for example, displays the summary using a dedicated screen. For example, the providing unit provides a dedicated screen in a messenger app and displays the summary. The providing unit can also provide a dedicated application for displaying the summary. For example, the providing unit provides a dedicated application for displaying the summary to the user and displays the summary through the application. In this way, by displaying the summary on a dedicated screen, the user can concentrate on viewing the summary. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that receives the summary generated by the generating unit as input and displays the summary on a dedicated screen.

[0035] The generation unit can have a filtering function that creates a summary by a user specifying a person and a period. The generation unit has a filtering function that creates a summary by a user specifying, for example, a specific person and a period. For example, the generation unit can create a summary by a user specifying interactions with a specific friend or interactions during a specific period. The generation unit can also create a summary by a user specifying interactions on a specific topic. For example, the generation unit can create a summary by a user specifying interactions related to travel. This allows a user to obtain a more detailed summary when looking back on a specific interaction. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can create a summary using a generation AI model that creates a summary using information on a person and a period specified by the user as input.

[0036] The generation unit can summarize the chat flow as one story. The generation unit, for example, summarizes the chat flow as one story (sentence). For example, the generation unit analyzes the exchanges in the messenger app, extracts important points, and creates a summary as one story based on the analysis. The generation unit can also summarize the chat flow as a story using a storytelling technique. For example, the generation unit summarizes the flow from the start to the end of the chat as one story. By summarizing the chat flow as one story, the user can easily grasp the overall picture of the exchanges. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can create a summary using a generation AI model that uses the extracted points as input and creates a summary as a story.

[0037] The extraction unit can collect information on the content, sender, and sending time of each message, and extract important points using sentiment analysis technology and topic modeling technology. The extraction unit, for example, collects information such as the content, sender, and sending time of each message, and analyzes the emotional nuances of the message using sentiment analysis technology. For example, the extraction unit uses a sentiment dictionary-based method to analyze the emotions of the message and identify positive emotions and negative emotions. The extraction unit also uses topic modeling technology to identify the topic of the message and extract important points. For example, the extraction unit uses LDA (Latent Dirichlet Allocation) to identify the topic of the message and extract important points. This allows for more accurate summarization by collecting information such as the content, sender, and sending time of each message, and extracting important points using sentiment analysis and topic modeling technology. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes the information of each message as input and extracts important points.

[0038] The extraction unit can extract important points by considering the length and frequency of each message in addition to the content, sender, and sending time of each message. The extraction unit extracts important points by considering the length and frequency of each message in addition to the content, sender, and sending time of each message. For example, the extraction unit preferentially extracts long messages and reflects detailed exchanges in the summary. The extraction unit can also preferentially extract frequently sent messages and highlight important topics. The extraction unit can also preferentially extract messages from a specific sender and highlight specific relationships. In this way, more detailed and important points can be extracted by considering the length and frequency of the messages. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes information of each message as input and extracts important points.

[0039] The extraction unit can extract important points based on specific keywords and phrases. The extraction unit extracts important points based on, for example, specific keywords and phrases. For example, the extraction unit preferentially extracts messages including words of gratitude or apology such as "thank you" or "sorry". The extraction unit can also preferentially extract messages including business-related keywords such as "meeting" or "project". The extraction unit can also preferentially extract messages including keywords related to events such as "birthday" or "celebration". In this way, a summary related to a specific topic is generated by extracting important points based on specific keywords and phrases. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes specific keywords and phrases as input and extracts important points.

[0040] The extraction unit can extract important points by considering the location where the message was sent in addition to the content, sender, and sending time of the message. The extraction unit extracts important points by considering the location where the message was sent in addition to the content, sender, and sending time of the message. For example, the extraction unit preferentially extracts messages sent from a specific location and emphasizes interactions related to the location. The extraction unit can also preferentially extract messages sent by the user while traveling and emphasize memories of the trip. The extraction unit can also preferentially extract messages from a location where an important event was held and emphasize interactions related to the event. In this way, interactions related to a specific location can be emphasized by considering the location where the message was sent. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes information on the location where the message was sent as input and extracts important points.

[0041] The extraction unit can extract important points by considering the message transmission device in addition to the message content, sender, and transmission time. The extraction unit extracts important points by considering the message transmission device in addition to the message content, sender, and transmission time. For example, the extraction unit preferentially extracts messages sent from smartphones to emphasize mobile interactions. The extraction unit can also preferentially extract messages sent from personal computers to emphasize business-related interactions. The extraction unit can also preferentially extract messages sent from tablets to emphasize interactions on a specific device. In this way, interactions on a specific device can be emphasized by considering the message transmission device. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that uses information on the message transmission device as input and extracts important points.

[0042] The generating unit can adjust the level of detail of the summary based on the importance of the extracted points when generating the summary. The generating unit, for example, adjusts the level of detail of the summary based on the importance of the extracted points when generating the summary. For example, the generating unit describes points of high importance in detail and summarizes points of low importance briefly. The generating unit can also emphasize points of high importance and place them at the beginning of the summary. The generating unit can also omit points of low importance to shorten the overall length of the summary. In this way, a summary in which important points are emphasized is generated by adjusting the level of detail of the summary based on the importance of the extracted points. Part or all of the above-mentioned processing in the generating unit may be performed, for example, using a generating AI or may be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that uses the importance of the extracted points as input and adjusts the level of detail of the summary.

[0043] The generating unit can apply different summarization algorithms depending on the category of the extracted points when generating a summary. The generating unit can apply different summarization algorithms depending on the category of the extracted points when generating a summary. For example, the generating unit can apply a summarization algorithm that emphasizes emotions to emotional points. The generating unit can also apply a summarization algorithm that emphasizes facts to business-related points. The generating unit can also apply a summarization algorithm that emphasizes the flow of events to event-related points. In this way, a more appropriate summary is generated by applying different summarization algorithms depending on the category of the extracted points. Part or all of the above-mentioned processing in the generating unit can be performed, for example, using a generating AI or can be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that uses the category of the extracted points as input and applies different summarization algorithms.

[0044] The generation unit can determine the priority of the summaries based on the submission time of the extracted points when generating the summaries. The generation unit, for example, determines the priority of the summaries based on the submission time of the extracted points when generating the summaries. For example, the generation unit prioritizes the most recent points and places them at the beginning of the summary. The generation unit can also place important points from the past in the middle of the summary. The generation unit can also place points that were submitted earlier at the end of the summary. In this way, a more appropriate summary is generated by determining the priority of the summaries based on the submission time of the extracted points. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the submission time of the extracted points and determines the priority of the summaries.

[0045] The generation unit can adjust the order of the summaries based on the relevance of the extracted points when generating the summaries. The generation unit, for example, adjusts the order of the summaries based on the relevance of the extracted points when generating the summaries. For example, the generation unit arranges highly relevant points consecutively to smooth the flow of the summary. The generation unit can also distribute and arrange less relevant points to balance the summary. The generation unit can also arrange highly relevant points at the beginning of the summary to attract the reader's interest. In this way, a more appropriate summary is generated by adjusting the order of the summaries based on the relevance of the extracted points. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the relevance of the extracted points as input and adjusts the order of the summaries.

[0046] The providing unit can select the optimal providing method by referring to the user's past summary browsing history when providing a summary. For example, the providing unit selects the optimal providing method by referring to the user's past summary browsing history when providing a summary. For example, the providing unit provides a summary in a format that the user has preferred to browse in the past. The providing unit can also provide a summary topic that the user has frequently browsed in the past with priority. The providing unit can also select the optimal providing timing from the user's past browsing history. In this way, a more appropriate summary is provided by referring to the user's past summary browsing history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide a summary using a generation AI model that inputs the user's past summary browsing history and selects the optimal providing method.

[0047] The providing unit can adjust the timing of providing the summary based on the user's current activity status when providing the summary. For example, the providing unit adjusts the timing of providing the summary based on the user's current activity status when providing the summary. For example, when the user is at work, the providing unit provides the summary during a break. Also, when the user is traveling, the providing unit can provide the summary after the user arrives. Also, when the user is relaxing, the providing unit can provide the summary during the time period when the user is relaxing. In this way, the summary is provided at a more appropriate timing by adjusting the timing of providing based on the user's current activity status. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generating AI, or may be performed without using a generating AI. For example, the providing unit can provide the summary using a generating AI model that inputs the user's current activity status and adjusts the timing of providing.

[0048] The providing unit can select the optimal providing method in consideration of the geographical location information of the user when providing a summary. For example, the providing unit selects the optimal providing method in consideration of the geographical location information of the user when providing a summary. For example, when the user is at home, the providing unit provides a relaxing summary. In addition, when the user is out, the providing unit can also provide a concise and highly visible summary. In addition, when the user is traveling, the providing unit can also provide a summary related to travel. In this way, a more appropriate summary is provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generating AI, or may be performed without using a generating AI. For example, the providing unit can provide a summary using a generating AI model that inputs the geographical location information of the user and selects the optimal providing method.

[0049] The providing unit can select the optimal providing method in consideration of the device information of the user when providing a summary. For example, the providing unit selects the optimal providing method in consideration of the device information of the user when providing a summary. For example, when the user is using a smartphone, the providing unit provides a summary that matches the screen size. In addition, when the user is using a tablet, the providing unit can also provide a summary optimized for a large screen. In addition, when the user is using a smartwatch, the providing unit can also provide a concise summary with high visibility. In this way, a more appropriate summary is provided by taking into account the device information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide a summary using a generation AI model that inputs the device information of the user and selects the optimal providing method.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The extraction unit can extract important points by considering the message sending location in addition to the message content, sender, and sending time. For example, the extraction unit can preferentially extract messages sent from a specific location and emphasize interactions related to the location. The extraction unit can also preferentially extract messages sent by the user while traveling and emphasize memories of the trip. The extraction unit can also preferentially extract messages from a location where an important event took place and emphasize interactions related to the event. In this way, interactions related to a specific location can be emphasized by considering the message sending location. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes information on the message sending location as input and extracts important points.

[0052] The generating unit can adjust the level of detail of the summary based on the importance of the extracted points when generating the summary. For example, the generating unit describes points of high importance in detail and summarizes points of low importance briefly. The generating unit can also emphasize points of high importance and place them at the beginning of the summary. The generating unit can also omit points of low importance to shorten the overall length of the summary. In this way, a summary in which important points are emphasized is generated by adjusting the level of detail of the summary based on the importance of the extracted points. Part or all of the above-mentioned processing in the generating unit may be performed, for example, using a generating AI or may be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that uses the importance of the extracted points as input and adjusts the level of detail of the summary.

[0053] The providing unit can select the optimal providing method by referring to the user's past summary browsing history when providing a summary. For example, the providing unit can provide a summary in a format that the user has preferred in the past. The providing unit can also provide a summary topic that the user has frequently browsed in the past by giving priority. The providing unit can also select the optimal providing timing from the user's past browsing history. In this way, a more appropriate summary is provided by referring to the user's past summary browsing history. A part or all of the above-mentioned processing in the providing unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the providing unit can provide a summary by using a generation AI model that inputs the user's past summary browsing history and selects the optimal providing method.

[0054] The extraction unit can extract important points based on specific keywords and phrases. For example, the extraction unit preferentially extracts messages containing words of gratitude or apology such as "thank you" or "sorry". The extraction unit can also preferentially extract messages containing business-related keywords such as "meeting" or "project". The extraction unit can also preferentially extract messages containing keywords related to events such as "birthday" or "celebration". In this way, a summary related to a specific topic is generated by extracting important points based on specific keywords and phrases. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes specific keywords and phrases as input and extracts important points.

[0055] The providing unit can adjust the timing of providing the summary based on the user's current activity status when providing the summary. For example, when the user is at work, the providing unit provides the summary during a break. Also, when the user is traveling, the providing unit can provide the summary after the user arrives. Also, when the user is relaxing, the providing unit can provide the summary during the time period when the user is relaxing. In this way, the summary is provided at a more appropriate timing by adjusting the timing of providing based on the user's current activity status. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that inputs the user's current activity status and adjusts the timing of providing.

[0056] The process flow of the first embodiment will be briefly described below.

[0057] Step 1: The extraction unit analyzes the conversations in the messenger app and extracts important points using sentiment analysis and topic modeling technologies. Specifically, it collects information such as the content, sender, and sending time of each message, analyzes the sentiment of the message using a sentiment dictionary-based method, and identifies positive and negative sentiment. It also uses LDA (Latent Dirichlet Allocation) to identify the topic of the message and extract important points. Step 2: The generation unit creates a summary based on the points extracted by the extraction unit. Specifically, a generation AI is used to compile the extracted points into a single story (sentence). For example, a text generation AI (e.g., LLM) can be used to create a summary, and in some cases, a multimodal generation AI can be used to create a summary that includes not only text, but also information such as images and audio. Step 3: The providing unit randomly provides the summaries generated by the generating unit. Specifically, the summaries are notified to the user at random times. The summaries can also be displayed on a dedicated screen, or can be displayed using pop-up notifications or push notifications. Furthermore, the providing unit can also randomly provide summaries using a generative AI model.

[0058] (Example 2) The messenger app summary system according to the embodiment of the present invention is a system that automatically summarizes interactions within a messenger app and provides chats as a single story (text). This system analyzes interactions within a messenger app and extracts important points using emotion analysis and topic modeling techniques. Next, a generation AI creates a summary based on the extracted points and provides it to the user. For example, the generation AI analyzes interactions within a messenger app, collects information such as the content, sender, and sending time of each message, and extracts important points using emotion analysis and topic modeling techniques. Next, a generation AI creates a summary based on the extracted points. This summary is provided randomly regardless of the most recent interaction, past interactions, or the person involved. Furthermore, in the paid version, the user can create a summary by specifying the person or period. For example, a summary can be created by specifying interactions with a specific friend or interactions over a specific period. This allows the user to obtain a more detailed summary when he or she wants to look back on a specific interaction. This allows the messenger app summary system to allow the user to look back on past interactions and re-experience emotions.

[0059] A messenger app summary system according to an embodiment includes an extraction unit, a generation unit, and a provision unit. The extraction unit analyzes interactions within the messenger app and extracts important points using sentiment analysis technology and topic modeling technology. The extraction unit collects information such as the content, sender, and sending time of each message, and analyzes the emotional nuances of the message using sentiment analysis technology. The extraction unit also identifies the topic of the message using topic modeling technology and extracts important points. For example, the extraction unit analyzes the emotion of the message using a sentiment dictionary-based method and identifies positive emotions and negative emotions. The extraction unit also identifies the topic of the message using LDA (Latent Dirichlet Allocation) and extracts important points. The generation unit creates a summary based on the points extracted by the extraction unit. The generation unit uses, for example, a generation AI to summarize the extracted points into one story (sentence). The generation unit uses, for example, a text generation AI (for example, LLM) to create a summary based on the extracted points. In addition, the generation unit can also create a summary including not only text but also information such as images and audio using a multimodal generation AI. The provision unit randomly provides the summary generated by the generation unit. For example, the provision unit notifies the user of the summary at random timing. In addition, the provision unit can also display the summary on a dedicated screen. For example, the provision unit displays the summary using a pop-up notification. In addition, the provision unit can also display the summary using a push notification. Thereby, the messenger app summary system according to the embodiment allows the user to look back on past interactions and re-experience emotions. A part or all of the above-mentioned processing in the provision unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the provision unit can provide the summary using a generation AI model that inputs the summary generated by the generation unit and randomly provides a summary.

[0060] The extraction unit analyzes the interactions within the messenger app and extracts important points using sentiment analysis and topic modeling techniques. Specifically, it collects information such as the content, sender, and time of sending of each message, and analyzes the emotional nuances of the message using sentiment analysis techniques. Sentiment dictionary-based techniques and machine learning models are used for sentiment analysis. In sentiment dictionary-based techniques, a predefined sentiment dictionary is used to analyze words and phrases in a message and identify emotions such as positive, negative, and neutral. When using a machine learning model, a pre-labeled dataset is used to train the model and predict emotions for new messages. Topic modeling techniques include LDA (Latent Dirichlet Allocation) and NMF (Non-negative Matrix Factorization). When using LDA, a set of messages is expressed as a distribution of topics, and it is determined which topic each message is related to. When using NMF, the message matrix is ​​decomposed to obtain the basis vectors of the topics and the coefficient vectors of the messages. This allows the extraction unit to analyze the emotional nuances and topics of messages and extract important points. Furthermore, the extraction unit can prioritize the extracted points based on the frequency and importance of the messages. For example, if there are many messages related to a particular topic, the topic is extracted as an important point. Emotionally strong messages and messages sent in a concentrated manner during a particular time period are also extracted as important points. This allows the extraction unit to efficiently extract information that is important to the user and use it in the next step, which is summary generation.

[0061] The generation unit creates a summary based on the points extracted by the extraction unit. Specifically, the generation AI is used to summarize the extracted points into one story (sentence). For example, an LLM (large-scale language model) is used for the generation AI. The LLM is trained based on a large amount of text data and has the ability to generate natural sentences. The generation unit gives the extracted points as input to the LLM and generates a summary. For example, if the extracted points are "date and time of the meeting," "agenda," "opinions of participants," etc., the generation unit creates a summary of the meeting based on this information. The generation unit can also use a multimodal generation AI to create a summary that includes not only text but also information such as images and audio. For example, including images and audio clips related to the summary of the meeting provides a richer summary. The generation unit evaluates the quality of the generated summary and makes corrections as necessary. For example, if the generated summary is redundant or missing important information, the generation unit uses the generation AI again to correct the summary. In addition, the generation unit can continuously improve the quality of the summary based on user feedback. For example, the user evaluates the provided summary and adjusts the parameters of the generation AI based on the evaluation results. This enables the generator to provide a high-quality summary that is useful to the user.

[0062] The providing unit randomly provides the summaries generated by the generating unit. Specifically, the summaries are notified to the user at random timing. The providing unit displays the summaries using, for example, a pop-up notification or a push notification. The pop-up notification is displayed on the screen when the user is using the app, and the user can immediately check the summaries. The push notification is displayed in the notification bar of the smartphone even when the user is not using the app, and the user can check the summaries. The providing unit can also display the summaries on a dedicated screen. For example, a tab dedicated to summaries is provided in the app, and the user can check past summaries in a list. The providing unit can optimize the method of providing the summaries based on the user's usage status and feedback. For example, if a user wants to receive a summary at a specific time period, the notification is provided according to that time period. In addition, if the user is interested in a specific topic, summaries related to that topic are preferentially provided. Furthermore, the providing unit can also provide the summaries using a generating AI. For example, the summaries generated by the generating unit are input, and the summaries are provided using a generating AI model that randomly provides summaries. This allows the providing unit to provide summaries at the optimal time for the user, thereby improving user convenience.

[0063] The providing unit can display the summary as a notification. The providing unit displays the summary using, for example, a pop-up notification. For example, when the user is using a messenger app, the providing unit displays a pop-up notification on the screen and provides the summary. The providing unit can also display the summary using a push notification. For example, when the user is not using a messenger app, the providing unit provides the summary using a notification function of the smartphone. This allows the user to immediately check the summary by displaying the summary as a notification. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that receives the summary generated by the generation unit as an input and displays the summary as a notification.

[0064] The providing unit can display the summary on a dedicated screen. The providing unit, for example, displays the summary using a dedicated screen. For example, the providing unit provides a dedicated screen in a messenger app and displays the summary. The providing unit can also provide a dedicated application for displaying the summary. For example, the providing unit provides a dedicated application for displaying the summary to the user and displays the summary through the application. In this way, by displaying the summary on a dedicated screen, the user can concentrate on viewing the summary. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that receives the summary generated by the generating unit as input and displays the summary on a dedicated screen.

[0065] The generation unit can have a filtering function that creates a summary by a user specifying a person and a period. The generation unit has a filtering function that creates a summary by a user specifying, for example, a specific person and a period. For example, the generation unit can create a summary by a user specifying interactions with a specific friend or interactions during a specific period. The generation unit can also create a summary by a user specifying interactions on a specific topic. For example, the generation unit can create a summary by a user specifying interactions related to travel. This allows a user to obtain a more detailed summary when looking back on a specific interaction. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can create a summary using a generation AI model that creates a summary using information on a person and a period specified by the user as input.

[0066] The generation unit can summarize the chat flow as one story. The generation unit, for example, summarizes the chat flow as one story (sentence). For example, the generation unit analyzes the exchanges in the messenger app, extracts important points, and creates a summary as one story based on the analysis. The generation unit can also summarize the chat flow as a story using a storytelling technique. For example, the generation unit summarizes the flow from the start to the end of the chat as one story. By summarizing the chat flow as one story, the user can easily grasp the overall picture of the exchanges. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can create a summary using a generation AI model that uses the extracted points as input and creates a summary as a story.

[0067] The extraction unit can collect information on the content, sender, and sending time of each message, and extract important points using sentiment analysis technology and topic modeling technology. The extraction unit, for example, collects information such as the content, sender, and sending time of each message, and analyzes the emotional nuances of the message using sentiment analysis technology. For example, the extraction unit uses a sentiment dictionary-based method to analyze the emotions of the message and identify positive emotions and negative emotions. The extraction unit also uses topic modeling technology to identify the topic of the message and extract important points. For example, the extraction unit uses LDA (Latent Dirichlet Allocation) to identify the topic of the message and extract important points. This allows for more accurate summarization by collecting information such as the content, sender, and sending time of each message, and extracting important points using sentiment analysis and topic modeling technology. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes the information of each message as input and extracts important points.

[0068] The extraction unit can estimate the user's emotion and adjust the extraction criteria of the important points based on the estimated user's emotion. The extraction unit, for example, estimates the user's emotion and adjusts the extraction criteria of the important points based on the estimated user's emotion. For example, when the user is happy, the extraction unit preferentially extracts messages containing positive emotions. In addition, when the user is sad, the extraction unit can also preferentially extract messages containing emotional support. In addition, when the user is excited, the extraction unit can also preferentially extract messages related to exciting topics. In this way, by adjusting the extraction criteria of the important points based on the user's emotion, a more appropriate summary is generated. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that inputs the user's emotion data and adjusts the extraction criteria of the important points.

[0069] The extraction unit can extract important points by considering the length and frequency of each message in addition to the content, sender, and sending time of each message. The extraction unit extracts important points by considering the length and frequency of each message in addition to the content, sender, and sending time of each message. For example, the extraction unit preferentially extracts long messages and reflects detailed exchanges in the summary. The extraction unit can also preferentially extract frequently sent messages and highlight important topics. The extraction unit can also preferentially extract messages from a specific sender and highlight specific relationships. In this way, more detailed and important points can be extracted by considering the length and frequency of the messages. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes information of each message as input and extracts important points.

[0070] The extraction unit can extract important points based on specific keywords and phrases. The extraction unit extracts important points based on, for example, specific keywords and phrases. For example, the extraction unit preferentially extracts messages including words of gratitude or apology such as "thank you" or "sorry". The extraction unit can also preferentially extract messages including business-related keywords such as "meeting" or "project". The extraction unit can also preferentially extract messages including keywords related to events such as "birthday" or "celebration". In this way, a summary related to a specific topic is generated by extracting important points based on specific keywords and phrases. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes specific keywords and phrases as input and extracts important points.

[0071] The extraction unit can estimate the user's emotion and determine the priority of the extracted points based on the estimated user's emotion. The extraction unit, for example, estimates the user's emotion and determines the priority of the extracted points based on the estimated user's emotion. For example, when the user is relaxed, the extraction unit can preferentially display messages related to relaxing topics. In addition, when the user is stressed, the extraction unit can also preferentially display messages that are useful for stress reduction. In addition, when the user is excited, the extraction unit can also preferentially display messages related to exciting topics. In this way, a more appropriate summary is generated by determining the priority of the extracted points based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that inputs the user's emotion data and determines the priority of the extracted points.

[0072] The extraction unit can extract important points by considering the location where the message was sent in addition to the content, sender, and sending time of the message. The extraction unit extracts important points by considering the location where the message was sent in addition to the content, sender, and sending time of the message. For example, the extraction unit preferentially extracts messages sent from a specific location and emphasizes interactions related to the location. The extraction unit can also preferentially extract messages sent by the user while traveling and emphasize memories of the trip. The extraction unit can also preferentially extract messages from a location where an important event was held and emphasize interactions related to the event. In this way, interactions related to a specific location can be emphasized by considering the location where the message was sent. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes information on the location where the message was sent as input and extracts important points.

[0073] The extraction unit can extract important points by considering the message transmission device in addition to the message content, sender, and transmission time. The extraction unit extracts important points by considering the message transmission device in addition to the message content, sender, and transmission time. For example, the extraction unit preferentially extracts messages sent from smartphones to emphasize mobile interactions. The extraction unit can also preferentially extract messages sent from personal computers to emphasize business-related interactions. The extraction unit can also preferentially extract messages sent from tablets to emphasize interactions on a specific device. In this way, interactions on a specific device can be emphasized by considering the message transmission device. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that uses information on the message transmission device as input and extracts important points.

[0074] The generation unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the expression method of the summary based on the estimated user's emotion. For example, when the user is happy, the generation unit generates a summary that uses a lot of positive expressions. In addition, when the user is sad, the generation unit can also generate a summary that includes emotional support. In addition, when the user is excited, the generation unit can also generate a summary that uses a lot of exciting expressions. In this way, a more appropriate summary is generated by adjusting the expression method of the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the user's emotion data and adjusts the expression method of the summary.

[0075] The generating unit can adjust the level of detail of the summary based on the importance of the extracted points when generating the summary. The generating unit, for example, adjusts the level of detail of the summary based on the importance of the extracted points when generating the summary. For example, the generating unit describes points of high importance in detail and summarizes points of low importance briefly. The generating unit can also emphasize points of high importance and place them at the beginning of the summary. The generating unit can also omit points of low importance to shorten the overall length of the summary. In this way, a summary in which important points are emphasized is generated by adjusting the level of detail of the summary based on the importance of the extracted points. Part or all of the above-mentioned processing in the generating unit may be performed, for example, using a generating AI or may be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that uses the importance of the extracted points as input and adjusts the level of detail of the summary.

[0076] The generating unit can apply different summarization algorithms depending on the category of the extracted points when generating a summary. The generating unit can apply different summarization algorithms depending on the category of the extracted points when generating a summary. For example, the generating unit can apply a summarization algorithm that emphasizes emotions to emotional points. The generating unit can also apply a summarization algorithm that emphasizes facts to business-related points. The generating unit can also apply a summarization algorithm that emphasizes the flow of events to event-related points. In this way, a more appropriate summary is generated by applying different summarization algorithms depending on the category of the extracted points. Part or all of the above-mentioned processing in the generating unit can be performed, for example, using a generating AI or can be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that uses the category of the extracted points as input and applies different summarization algorithms.

[0077] The generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the length of the summary based on the estimated user's emotion. For example, when the user is in a hurry, the generation unit generates a short summary that covers the main points. In addition, when the user is relaxed, the generation unit can also generate a longer summary including detailed explanations. In addition, when the user is excited, the generation unit can also generate a summary with a visually stimulating effect. In this way, a more appropriate summary is generated by adjusting the length of the summary based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs user's emotion data and adjusts the length of the summary.

[0078] The generation unit can determine the priority of the summaries based on the submission time of the extracted points when generating the summaries. The generation unit, for example, determines the priority of the summaries based on the submission time of the extracted points when generating the summaries. For example, the generation unit prioritizes the most recent points and places them at the beginning of the summary. The generation unit can also place important points from the past in the middle of the summary. The generation unit can also place points that were submitted earlier at the end of the summary. In this way, a more appropriate summary is generated by determining the priority of the summaries based on the submission time of the extracted points. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the submission time of the extracted points and determines the priority of the summaries.

[0079] The generation unit can adjust the order of the summaries based on the relevance of the extracted points when generating the summaries. The generation unit, for example, adjusts the order of the summaries based on the relevance of the extracted points when generating the summaries. For example, the generation unit arranges highly relevant points consecutively to smooth the flow of the summary. The generation unit can also distribute and arrange less relevant points to balance the summary. The generation unit can also arrange highly relevant points at the beginning of the summary to attract the reader's interest. In this way, a more appropriate summary is generated by adjusting the order of the summaries based on the relevance of the extracted points. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the relevance of the extracted points as input and adjusts the order of the summaries.

[0080] The providing unit can estimate the user's emotion and adjust the method of providing the summary based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the method of providing the summary based on the estimated user's emotion. For example, when the user is relaxed, the providing unit provides the summary in a visually relaxing design. Also, when the user is in a hurry, the providing unit can provide the summary in a concise and highly visible design. Also, when the user is excited, the providing unit can provide the summary in a visually stimulating design. In this way, a more appropriate summary is provided by adjusting the method of providing the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that inputs the user's emotion data and adjusts the method of providing the summary.

[0081] The providing unit can select the optimal providing method by referring to the user's past summary browsing history when providing a summary. For example, the providing unit selects the optimal providing method by referring to the user's past summary browsing history when providing a summary. For example, the providing unit provides a summary in a format that the user has preferred to browse in the past. The providing unit can also provide a summary topic that the user has frequently browsed in the past with priority. The providing unit can also select the optimal providing timing from the user's past browsing history. In this way, a more appropriate summary is provided by referring to the user's past summary browsing history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide a summary using a generation AI model that inputs the user's past summary browsing history and selects the optimal providing method.

[0082] The providing unit can adjust the timing of providing the summary based on the user's current activity status when providing the summary. For example, the providing unit adjusts the timing of providing the summary based on the user's current activity status when providing the summary. For example, when the user is at work, the providing unit provides the summary during a break. Also, when the user is traveling, the providing unit can provide the summary after the user arrives. Also, when the user is relaxing, the providing unit can provide the summary during the time period when the user is relaxing. In this way, the summary is provided at a more appropriate timing by adjusting the timing of providing based on the user's current activity status. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generating AI, or may be performed without using a generating AI. For example, the providing unit can provide the summary using a generating AI model that inputs the user's current activity status and adjusts the timing of providing.

[0083] The providing unit can estimate the user's emotion and determine the order of providing the summaries based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and determines the order of providing the summaries based on the estimated user's emotion. For example, when the user is relaxed, the providing unit provides a relaxing summary with priority. In addition, when the user is in a hurry, the providing unit can also provide a concise summary with priority and to the main points with priority. In addition, when the user is excited, the providing unit can also provide an exciting summary with priority. In this way, by determining the order of providing the summaries based on the user's emotion, a more appropriate summary is provided. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the providing unit can provide the summaries using a generation AI model that inputs the user's emotion data and determines the order of providing the summaries.

[0084] The providing unit can select the optimal providing method in consideration of the geographical location information of the user when providing a summary. For example, the providing unit selects the optimal providing method in consideration of the geographical location information of the user when providing a summary. For example, when the user is at home, the providing unit provides a relaxing summary. In addition, when the user is out, the providing unit can also provide a concise and highly visible summary. In addition, when the user is traveling, the providing unit can also provide a summary related to travel. In this way, a more appropriate summary is provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generating AI, or may be performed without using a generating AI. For example, the providing unit can provide a summary using a generating AI model that inputs the geographical location information of the user and selects the optimal providing method.

[0085] The providing unit can select the optimal providing method in consideration of the device information of the user when providing a summary. For example, the providing unit selects the optimal providing method in consideration of the device information of the user when providing a summary. For example, when the user is using a smartphone, the providing unit provides a summary that matches the screen size. In addition, when the user is using a tablet, the providing unit can also provide a summary optimized for a large screen. In addition, when the user is using a smartwatch, the providing unit can also provide a concise summary with high visibility. In this way, a more appropriate summary is provided by taking into account the device information of the user. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide a summary using a generation AI model that inputs the device information of the user and selects the optimal providing method.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The extraction unit can extract important points by considering the message sending location in addition to the message content, sender, and sending time. For example, the extraction unit can preferentially extract messages sent from a specific location and emphasize interactions related to the location. The extraction unit can also preferentially extract messages sent by the user while traveling and emphasize memories of the trip. The extraction unit can also preferentially extract messages from a location where an important event took place and emphasize interactions related to the event. In this way, interactions related to a specific location can be emphasized by considering the message sending location. Part or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes information on the message sending location as input and extracts important points.

[0088] The generating unit can adjust the level of detail of the summary based on the importance of the extracted points when generating the summary. For example, the generating unit describes points of high importance in detail and summarizes points of low importance briefly. The generating unit can also emphasize points of high importance and place them at the beginning of the summary. The generating unit can also omit points of low importance to shorten the overall length of the summary. In this way, a summary in which important points are emphasized is generated by adjusting the level of detail of the summary based on the importance of the extracted points. Part or all of the above-mentioned processing in the generating unit may be performed, for example, using a generating AI or may be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that uses the importance of the extracted points as input and adjusts the level of detail of the summary.

[0089] The providing unit can select the optimal providing method by referring to the user's past summary browsing history when providing a summary. For example, the providing unit can provide a summary in a format that the user has preferred in the past. The providing unit can also provide a summary topic that the user has frequently browsed in the past by giving priority. The providing unit can also select the optimal providing timing from the user's past browsing history. In this way, a more appropriate summary is provided by referring to the user's past summary browsing history. A part or all of the above-mentioned processing in the providing unit can be performed, for example, using a generation AI or can be performed without using a generation AI. For example, the providing unit can provide a summary by using a generation AI model that inputs the user's past summary browsing history and selects the optimal providing method.

[0090] The extraction unit can extract important points based on specific keywords and phrases. For example, the extraction unit preferentially extracts messages containing words of gratitude or apology such as "thank you" or "sorry". The extraction unit can also preferentially extract messages containing business-related keywords such as "meeting" or "project". The extraction unit can also preferentially extract messages containing keywords related to events such as "birthday" or "celebration". In this way, a summary related to a specific topic is generated by extracting important points based on specific keywords and phrases. Some or all of the above-mentioned processing in the extraction unit may be performed, for example, using a generation AI or may be performed without using a generation AI. For example, the extraction unit can extract points using a generation AI model that takes specific keywords and phrases as input and extracts important points.

[0091] The providing unit can adjust the timing of providing the summary based on the user's current activity status when providing the summary. For example, when the user is at work, the providing unit provides the summary during a break. Also, when the user is traveling, the providing unit can provide the summary after the user arrives. Also, when the user is relaxing, the providing unit can provide the summary during the time period when the user is relaxing. In this way, the summary is provided at a more appropriate timing by adjusting the timing of providing based on the user's current activity status. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the summary using a generation AI model that inputs the user's current activity status and adjusts the timing of providing.

[0092] The extraction unit can estimate the user's emotion and adjust the extraction criteria of the important points based on the estimated user's emotion. For example, when the user is happy, the extraction unit preferentially extracts messages containing positive emotions. Also, when the user is sad, the extraction unit can preferentially extract messages containing emotional support. Also, when the user is excited, the extraction unit can preferentially extract messages related to exciting topics. In this way, by adjusting the extraction criteria of the important points based on the user's emotion, a more appropriate summary is generated. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the extraction unit can extract points using a generation AI model that inputs the user's emotion data and adjusts the extraction criteria of the important points.

[0093] The generation unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. For example, when the user is happy, the generation unit generates a summary that uses a lot of positive expressions. Also, when the user is sad, the generation unit can generate a summary that includes emotional support. Also, when the user is excited, the generation unit can generate a summary that uses a lot of exciting expressions. In this way, a more appropriate summary is generated by adjusting the expression method of the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the user's emotion data and adjusts the expression method of the summary.

[0094] The providing unit can estimate the user's emotion and adjust the method of providing the summary based on the estimated user's emotion. For example, when the user is relaxed, the providing unit provides the summary in a visually relaxing design. Also, when the user is in a hurry, the providing unit can provide the summary in a concise and highly visible design. Also, when the user is excited, the providing unit can provide the summary in a visually stimulating design. In this way, a more appropriate summary is provided by adjusting the method of providing the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the providing unit can provide the summary using a generation AI model that inputs the user's emotion data and adjusts the method of providing the summary.

[0095] The extraction unit can estimate the user's emotion and determine the priority of the extracted points based on the estimated user's emotion. For example, when the user is relaxed, the extraction unit can preferentially display messages related to relaxing topics. Also, when the user is stressed, the extraction unit can preferentially display messages that are useful for stress reduction. Also, when the user is excited, the extraction unit can preferentially display messages related to exciting topics. In this way, a more appropriate summary is generated by determining the priority of the extracted points based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the extraction unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the extraction unit can extract points using a generation AI model that inputs the user's emotion data and determines the priority of the extracted points.

[0096] The generating unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. For example, when the user is in a hurry, the generating unit generates a short summary that covers the main points. When the user is relaxed, the generating unit can also generate a longer summary that includes detailed explanations. When the user is excited, the generating unit can also generate a summary with a visually stimulating effect. In this way, a more appropriate summary is generated by adjusting the length of the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generating AI. The generating AI is, for example, a text generating AI (for example, LLM) or a multimodal generating AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generating unit may be performed using, for example, a generating AI, or may be performed without using a generating AI. For example, the generating unit can generate a summary using a generating AI model that inputs the user's emotion data and adjusts the length of the summary.

[0097] The process flow of the second embodiment will be briefly described below.

[0098] Step 1: The extraction unit analyzes the conversations in the messenger app and extracts important points using sentiment analysis and topic modeling technologies. Specifically, it collects information such as the content, sender, and sending time of each message, analyzes the sentiment of the message using a sentiment dictionary-based method, and identifies positive and negative sentiment. It also uses LDA (Latent Dirichlet Allocation) to identify the topic of the message and extract important points. Step 2: The generation unit creates a summary based on the points extracted by the extraction unit. Specifically, a generation AI is used to compile the extracted points into a single story (sentence). For example, a text generation AI (e.g., LLM) can be used to create a summary, and in some cases, a multimodal generation AI can be used to create a summary that includes not only text, but also information such as images and audio. Step 3: The providing unit randomly provides the summaries generated by the generating unit. Specifically, the summaries are notified to the user at random times. The summaries can also be displayed on a dedicated screen, or can be displayed using pop-up notifications or push notifications. Furthermore, the providing unit can also randomly provide summaries using a generative AI model.

[0099] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0100] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0101] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0102] Each of the multiple elements including the above-mentioned extraction unit, generation unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the extraction unit is realized by the processor 46 of the smart device 14, analyzes interactions in a messenger app, and extracts important points using sentiment analysis technology and topic modeling technology. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a summary based on the extracted points. The provision unit is realized, for example, by the control unit 46A of the smart device 14, and randomly provides the generated summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 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.

[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, the RAM 30, and the 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 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.

[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 the voice according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average 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 performed in a secure state.

[0110] Fig. 4 shows an example of 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.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0115] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0117] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements including the above-mentioned extraction unit, generation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the extraction unit is realized by the processor 46 of the smart glasses 214, analyzes interactions in a messenger app, and extracts important points using sentiment analysis technology and topic modeling technology. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a summary based on the extracted points. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214, and randomly provides the generated summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] 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, the RAM 30, and the 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.

[0122] 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.

[0123] 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 the voice according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0125] 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 performed in a secure state.

[0126] 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.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0129] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0131] 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 a voice indicating a user input for 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0133] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements including the above-mentioned extraction unit, generation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the extraction unit is realized by the processor 46 of the headset type terminal 314, analyzes the exchange in the messenger app, and extracts important points using sentiment analysis technology and topic modeling technology. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a summary based on the extracted points. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and randomly provides the generated summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 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.

[0137] 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, the RAM 30, and the 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.

[0138] 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.

[0139] 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 the voice according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0141] 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 performed in a secure state.

[0142] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0143] 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.

[0144] 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.

[0145] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0146] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0147] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0148] 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 a voice indicating a user input for 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.

[0149] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0150] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0151] Each of the multiple elements including the above-mentioned extraction unit, generation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the extraction unit is realized by the processor 46 of the robot 414, analyzes the exchange in the messenger app, and extracts important points using sentiment analysis technology and topic modeling technology. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a summary based on the extracted points. The provision unit is realized, for example, by the control unit 46A of the robot 414, and randomly provides the generated summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0152] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0153] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0155] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0157] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0159] 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.

[0160] 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 Universal Serial Bus (USB) 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.

[0161] In addition, 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 upon request from the data processing device 12.

[0162] 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.

[0163] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0164] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0165] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0166] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0168] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0170] (Appendix 1) An extraction part that analyzes conversations within the messenger app and extracts important points using sentiment analysis and topic modeling technologies; a generation unit for generating a summary based on the points extracted by the extraction unit; A providing unit that randomly provides the summaries generated by the generating unit. A system characterized by: (Appendix 2) The providing unit is Display the summary as a notification 2. The system of claim 1, (Appendix 3) The providing unit is Display the summary on a dedicated screen 2. The system of claim 1, (Appendix 4) The generation unit is Equipped with a filtering function that allows users to create summaries by specifying the recipient and period. 2. The system of claim 1, (Appendix 5) The generation unit is Synthesize chat history into a story 2. The system of claim 1, (Appendix 6) The extraction unit is Collect information about the content, sender and time of each message, and use sentiment analysis and topic modeling techniques to extract key points. 2. The system of claim 1, (Appendix 7) The extraction unit is Estimate the user's emotions and adjust the extraction criteria for important points based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The extraction unit is Extract key points by considering the content, sender, and time of each message, as well as the length and frequency of messages 2. The system of claim 1, (Appendix 9) The extraction unit is Extract key takeaways based on specific keywords or phrases 2. The system of claim 1, (Appendix 10) The extraction unit is Estimate the user's emotions and prioritize the extracted points based on the estimated user's emotions. 2. The system of claim 1, (Appendix 11) The extraction unit is Extract key points by considering the content, sender, time, and where the message was sent 2. The system of claim 1, (Appendix 12) The extraction unit is Extract key points by considering the content, sender, time of message, and device used to send the message 2. The system of claim 1, (Appendix 13) The generation unit is Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions. 2. The system of claim 1, (Appendix 14) The generation unit is When generating summaries, adjust the level of detail in the summary based on the importance of the extracted points 2. The system of claim 1, (Appendix 15) The generation unit is When generating summaries, different summarization algorithms are applied depending on the category of the extracted points. 2. The system of claim 1, (Appendix 16) The generation unit is Estimating user sentiment and adjusting the length of a summary based on the estimated user sentiment 2. The system of claim 1, (Appendix 17) The generation unit is During summary generation, prioritize summaries based on the submission age of extracted points 2. The system of claim 1, (Appendix 18) The generation unit is During summary generation, adjust the order of the summary based on the relevance of the extracted points 2. The system of claim 1, (Appendix 19) The providing unit is A method for predicting a user's emotions and adjusting a method for providing a summary based on the predicted user's emotions 2. The system of claim 1, (Appendix 20) The providing unit is When providing a summary, the system selects the optimal method of providing the summary by referring to the user's past summary viewing history. 2. The system of claim 1, (Appendix 21) The providing unit is When providing summaries, adjust the timing of delivery based on the user's current activity 2. The system of claim 1, (Appendix 22) The providing unit is A method for estimating a user's emotions and determining the order in which summaries are provided based on the estimated user's emotions 2. The system of claim 1, (Appendix 23) The providing unit is When providing a summary, the optimal method of providing the summary is selected taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 24) The providing unit is When providing a summary, the optimal method of providing the summary is selected taking into account the user's device information. 2. The system of claim 1, [Explanation of symbols]

[0171] 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. An extraction part that analyzes conversations within the messenger app and extracts important points using sentiment analysis and topic modeling technologies; a generation unit for generating a summary based on the points extracted by the extraction unit; A providing unit that randomly provides the summaries generated by the generating unit. A system characterized by:

2. The extraction unit is Extract key takeaways based on specific keywords or phrases 2. The system of claim 1 .

3. The generation unit is Adjusting the order of summaries based on the relevance of the points extracted by the extractor 2. The system of claim 1 .

4. The generation unit is Equipped with a filtering function that allows users to create summaries by specifying the recipient and period.

2. The system of claim 1 .

5. The generation unit is Synthesize chat history into a story 2. The system of claim 1 .

6. The extraction unit is Collect information about the content, sender and time of each message, and use sentiment analysis and topic modeling techniques to extract key points.

2. The system of claim 1 .

7. The extraction unit is Estimate the user's emotions and adjust the extraction criteria for important points based on the estimated user emotions.

2. The system of claim 1 .

8. The extraction unit is Extract key points by considering the content, sender, and time of each message, as well as the length and frequency of messages 2. The system of claim 1 .

Images