System

Abstract

An object of the system according to the embodiment is to efficiently summarize a long sentence.SOLUTION: A system according to an embodiment includes a reception unit, a division unit, a generation unit, and an integration unit. The receiving unit receives an input of a long sentence from a user. The division unit divides the long sentence received by the reception unit into a number of characters that can be processed by the generation AI. The generation unit inputs each part divided by the division unit to the generation AI and generates a summary. The integration unit integrates the partial summaries 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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] With conventional technology, there was a problem that summarizing long texts was time-consuming due to the character limit of the generation AI.

[0005] The system according to the embodiment aims to efficiently summarize long texts. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a division unit, a generation unit, and an integration unit. The reception unit receives input of a long sentence from a user. The division unit divides the long sentence received by the reception unit into a number of characters that can be processed by the generation AI. The generation unit inputs each part divided by the division unit to the generation AI to generate a summary. The integration unit integrates the partial summaries generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently summarize long texts. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A summarization system according to an embodiment of the present invention overcomes the character limit imposed by a generation AI and enables a user to summarize a long text with a single operation. The summarization system operates as follows: a user inputs a long text to be summarized; an external processing system divides the text into a number of characters that the generation AI can process; each divided portion is sequentially input to the generation AI to generate a summary; and finally, the external processing system combines these partial summaries to generate a final summary. For example, if a user wants to summarize a 10,000-character text, the summarization system inputs the text into the system. The external processing system then divides the input long text into a number of characters that the generation AI can process. For example, if the generation AI can process 2,000 characters at a time, the 10,000-character text is divided into five portions. The summarization system then sequentially inputs each divided portion into the generation AI to generate a partial summary for each portion. For example, the first 2,000 characters are input to the generation AI, and a summary is generated for that portion. The next 2,000 characters are input to the generation AI, and a summary is generated in the same manner. This process is repeated until all portions are summarized. Finally, the summarization system uses an external processing system to integrate these partial summaries and generate a final summary. For example, if five partial summaries are generated, they are combined into one final summary. This mechanism allows users to obtain a long summary with a single operation. This allows the summarization system to overcome the character limit imposed by the generation AI and efficiently summarize long texts. For example, when summarizing long texts such as research papers or novels, this eliminates the need to manually divide the text, allowing for more efficient summarization.

[0029] A summarization system according to an embodiment includes a reception unit, a division unit, a generation unit, and an integration unit. The reception unit receives a long sentence from a user. The long sentence from a user may be, for example, a text input, a voice input, or an image input, but is not limited to these examples. The reception unit may directly receive a text input. The reception unit may also receive a voice input and convert it into text data using voice recognition technology. The reception unit may also receive an image input and convert it into text data using OCR technology. For example, the reception unit may input voice data input by a user to a generation AI and cause the generation AI to convert the voice data into text data. The division unit divides the long sentence received by the reception unit into a number of characters that the generation AI can process. The division is performed based on, for example, the maximum number of characters that the generation AI can process at one time, but is not limited to these examples. For example, the division unit may divide the long sentence into paragraphs. The division unit may also select natural division points based on the context. For example, the division unit may analyze the content of the long sentence and select appropriate division points. The generation unit uses a generation AI to summarize each part divided by the division unit. The generation AI generates a summary using, for example, a text generation AI (e.g., LLM). The generation unit can also use a multimodal generation AI to handle multiple modalities, such as images and audio, in addition to text. For example, the generation unit inputs a prompt such as "Please summarize the main points of this passage" to the generation AI and generates a summary. The integration unit integrates the partial summaries generated by the generation unit. The integration is performed, for example, based on the order and content of the partial summaries, but is not limited to such an example. For example, the integration unit analyzes the content of the partial summaries and integrates them in a natural flow. The integration unit can also prioritize important parts based on the importance of the partial summaries. This allows the summarization system according to the embodiment to efficiently summarize a long text provided by a user and provide a final summary. Some or all of the above-described processes in the generation unit and integration unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs each part divided by the division unit to the generation AI and generates a summary.The synthesizer synthesizes the partial summaries generated by the generators to generate a final summary.

[0030] The reception unit can analyze the user's past input history and select the optimal input method. For example, the reception unit can prioritize and suggest input methods (such as voice and text) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used during a specific time period based on the user's past input history. The reception unit can also complete input by referring to content that the user has previously input. This makes it possible to provide the optimal input method based on the user's past input history. Some or all of the above-described processing in the reception unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the reception unit can input the user's past input history data into the generation AI and have the generation AI select the optimal input method.

[0031] When a long sentence is input, the reception unit can filter the input based on the user's current project or area of ​​interest. For example, the reception unit prioritizes input of keywords related to the project the user is currently working on. The reception unit can also automatically complete related information based on the user's area of ​​interest. The reception unit can also suggest related information by referring to the user's past project history. This makes it possible to provide related information based on the user's project or area of ​​interest. Some or all of the above-mentioned processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's project data into the generation AI and have the generation AI filter the related information.

[0032] When inputting a long sentence, the reception unit can select the optimal input means depending on the user's input method. For example, if the user desires voice input, the reception unit can prioritize providing a voice recognition function. Furthermore, if the user desires text input, the reception unit can also prioritize providing a keyboard input. Furthermore, if the user desires image input, the reception unit can also prioritize providing an image recognition function. This makes it possible to provide the optimal means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's input method data into the generation AI and have the generation AI select the optimal input means.

[0033] When inputting a long sentence, the reception unit can prioritize inputting a highly relevant long sentence taking into consideration the user's geographical location information. For example, when the user is in a specific area, the reception unit can prioritize inputting information related to that area. Furthermore, when the user is traveling, the reception unit can prioritize inputting information related to the travel destination. Furthermore, when the user is at home, the reception unit can prioritize inputting information related to the home. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's geographical location information data to the generation AI and cause the generation AI to select highly relevant information.

[0034] When a long text is input, the reception unit can analyze the user's social media activity and input a related long text. The reception unit can, for example, input the related long text based on information shared by the user on social media. The reception unit can also analyze the content of the user's social media posts and input the related long text. The reception unit can also input the related long text with reference to the activity of the user's friends on social media. This makes it possible to provide related information based on the user's social media activity. Some or all of the above-described processing in the reception unit can be performed using, or without, a generation AI. For example, the reception unit can input the user's social media data into the generation AI and cause the generation AI to select the related long text.

[0035] The reception unit can customize the input method by reflecting the user's past feedback when inputting a long sentence. The reception unit can improve the input method, for example, based on feedback provided by the user in the past. The reception unit can also preferentially provide a specific input method based on the user's past feedback. The reception unit can also customize the input interface by referring to the user's feedback. This allows the input method to be customized based on the user's past feedback. Some or all of the above-mentioned processing in the reception unit can be performed using, or without, the generation AI. For example, the reception unit can input the user's feedback data into the generation AI and have the generation AI customize the input method.

[0036] When dividing the long text, the division unit can select optimal division points based on the content of the long text. The division unit, for example, sets division points for each paragraph of the long text. The division unit can also select natural division points based on the context of the long text. The division unit can also select optimal division points based on keywords in the long text. This makes it possible to select optimal division points based on the content of the long text. Some or all of the above-mentioned processing in the division unit may be performed using, or without, a generation AI. For example, the division unit can input content data of the long text into the generation AI and have the generation AI select optimal division points.

[0037] The segmentation unit can apply different segmentation algorithms depending on the category of the long text during segmentation. For example, in the case of a technical document, the segmentation unit can apply a segmentation algorithm based on technical terms. In the case of a novel, the segmentation unit can also apply a segmentation algorithm based on the development of the story. In the case of a news article, the segmentation unit can also apply a segmentation algorithm based on the section of the article. This makes it possible to apply the optimal segmentation algorithm depending on the category of the long text. Some or all of the above-mentioned processing in the segmentation unit may be performed using, or without, a generation AI, for example. For example, the segmentation unit can input category data of the long text into the generation AI and have the generation AI apply the segmentation algorithm.

[0038] The division unit can improve the accuracy of division by referring to the user's past division results. For example, the division unit selects the optimal division point based on the user's past division results. The division unit can also analyze the user's past division history and improve the division algorithm. The division unit can also improve the accuracy of division by referring to user feedback. This improves the accuracy of division based on the user's past division results. Some or all of the above-mentioned processing in the division unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the division unit can input the user's past division result data into the generation AI and have the generation AI improve the accuracy of division.

[0039] When dividing, the dividing unit can determine the division priority based on the submission time of the long text. For example, the dividing unit prioritizes dividing long texts with an upcoming submission deadline. The dividing unit can also postpone dividing long texts with a distant submission deadline. The dividing unit can also adjust the division schedule based on the submission deadline. This makes it possible to determine the division priority based on the submission time of the long text. Some or all of the above-mentioned processing in the dividing unit may be performed using, or without, the generation AI. For example, the dividing unit can input submission time data into the generation AI and have the generation AI determine the division priority.

[0040] The division unit can adjust the order of division based on the relevance of the long sentence when dividing. For example, the division unit divides highly relevant parts with priority. The division unit can also postpone dividing less relevant parts. The division unit can also adjust the order of division based on the relevance. This makes it possible to adjust the order of division based on the relevance of the long sentence. Some or all of the above-mentioned processing in the division unit may be performed using, or without, the generation AI. For example, the division unit can input relevance data of the long sentence into the generation AI and have the generation AI adjust the order of division.

[0041] The division unit can adjust the division method according to the user's level of expertise during division. For example, the division unit can provide a detailed division method to a user with high expertise. The division unit can also provide a simple division method to a user with low expertise. The division unit can also customize the division method based on the user's level of expertise. This allows the division method to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the division unit can be performed using, or without, a generation AI. For example, the division unit can input the user's expertise level data into the generation AI and cause the generation AI to adjust the division method.

[0042] When generating a summary, the generation unit can adjust the level of detail of the summary based on the importance of the long text. For example, the generation unit summarizes parts of high importance in detail. The generation unit can also summarize parts of low importance in brief. The generation unit can also adjust the level of detail of the summary based on the importance of the long text. This allows the level of detail of the summary to be adjusted based on the importance of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input importance data of the long text into the generation AI and have the generation AI adjust the level of detail of the summary.

[0043] When generating a summary, the generation unit can apply different summarization algorithms depending on the category of the long text. For example, in the case of a technical document, the generation unit can apply a summarization algorithm that includes technical terms. In the case of a novel, the generation unit can also apply a summarization algorithm that emphasizes the development of the story. In the case of a news article, the generation unit can also apply a summarization algorithm based on the section of the article. This allows the application of the optimal summarization algorithm depending on the category of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input category data of the long text into the generation AI and have the generation AI apply the summarization algorithm.

[0044] When generating a summary, the generation unit can improve the accuracy of the summary by referring to the user's past summarization results. The generation unit, for example, improves the summarization algorithm based on the user's past summarization results. The generation unit can also analyze the user's past summarization history to improve the accuracy of the summary. The generation unit can also improve the accuracy of the summary by referring to the user's feedback. In this way, the accuracy of the summary is improved based on the user's past summarization results. Some 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 input the user's past summary result data into the generation AI and have the generation AI improve the accuracy of the summary.

[0045] When generating summaries, the generation unit can determine the priority of summaries based on the submission time of the long text. For example, the generation unit prioritizes summarizing long texts with upcoming submission deadlines. The generation unit can also postpone long texts with distant submission deadlines. The generation unit can also adjust the summary schedule based on the submission deadlines. This makes it possible to determine the priority of summaries based on the submission time of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input submission time data into the generation AI and have the generation AI determine the priority of summaries.

[0046] When generating summaries, the generation unit can adjust the order of summaries based on the relevance of the long text. For example, the generation unit prioritizes summarizing highly relevant parts. The generation unit can also postpone summarizing less relevant parts. The generation unit can also adjust the order of summaries based on relevance. This makes it possible to adjust the order of summaries based on the relevance of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input relevance data of the long text into the generation AI and have the generation AI adjust the order of the summaries.

[0047] When generating a summary, the generation unit can adjust the use of technical terms in the summary according to the user's level of expertise. For example, the generation unit can provide a summary that uses a lot of technical terms to a user with high level of expertise. The generation unit can also provide a concise and easy-to-understand summary to a user with low level of expertise. The generation unit can also adjust the use of technical terms in the summary based on the user's level of expertise. This allows the use of technical terms in the summary to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms in the summary.

[0048] During integration, the integration unit can select the optimal integration method based on the content of the partial summaries. For example, the integration unit prioritizes integration of highly relevant parts based on the theme of the partial summaries. The integration unit can also prioritize integration of important parts based on the importance of the partial summaries. The integration unit can also integrate in a natural flow based on the context of the partial summaries. This makes it possible to select the optimal integration method based on the content of the partial summaries. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, a generation AI. For example, the integration unit can input content data of the partial summaries to the generation AI and have the generation AI select the optimal integration method.

[0049] During integration, the integration unit can apply different integration algorithms depending on the category of the partial summary. For example, in the case of a technical document, the integration unit can apply an integration algorithm that includes technical terms. In the case of a novel, the integration unit can also apply an integration algorithm that emphasizes the development of the story. In the case of a news article, the integration unit can also apply an integration algorithm based on the section of the article. This makes it possible to apply the optimal integration algorithm depending on the category of the partial summary. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, the generation AI, for example. For example, the integration unit can input category data of the partial summary to the generation AI and have the generation AI apply the integration algorithm.

[0050] During integration, the integration unit can improve the accuracy of integration by referring to the user's past integration results. The integration unit, for example, improves the integration algorithm based on the user's past integration results. The integration unit can also analyze the user's past integration history to improve the accuracy of integration. The integration unit can also improve the accuracy of integration by referring to the user's feedback. This improves the accuracy of integration based on the user's past integration results. Some or all of the above-mentioned processing in the integration unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the integration unit can input the user's past integration result data into the generation AI and cause the generation AI to improve the accuracy of integration.

[0051] The integration unit can determine the priority of integration based on the submission dates of the partial summaries when integrating them. For example, the integration unit prioritizes integrating partial summaries with upcoming submission deadlines. The integration unit can also postpone partial summaries with distant submission deadlines. The integration unit can also adjust the integration schedule based on the submission deadlines. This makes it possible to determine the priority of integration based on the submission dates of the partial summaries. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, the generation AI. For example, the integration unit can input submission date data into the generation AI and have the generation AI determine the priority of integration.

[0052] The integration unit can adjust the order of integration based on the relevance of the partial summaries when integrating them. For example, the integration unit prioritizes integration of highly relevant parts. The integration unit can also postpone integration of less relevant parts. The integration unit can also adjust the order of integration based on the relevance. This makes it possible to adjust the order of integration based on the relevance of the partial summaries. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, the generation AI. For example, the integration unit can input relevance data of the partial summaries to the generation AI and have the generation AI adjust the order of integration.

[0053] The integration unit can adjust the integration method according to the user's level of expertise during integration. For example, the integration unit can provide a detailed integration method to a user with high expertise. The integration unit can also provide a simple integration method to a user with low expertise. The integration unit can also customize the integration method based on the user's level of expertise. This allows the integration method to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the integration unit can be performed using, or without, the generation AI. For example, the integration unit can input the user's expertise level data into the generation AI and cause the generation AI to adjust the integration method.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The reception unit can detect the user's posture when inputting and adjust the input method based on the posture. For example, if the user is sitting, keyboard input can be given priority. Also, if the user is standing, voice input can be given priority. Also, if the user is walking, voice input can be given priority, and adjustments can be made to make input easier even while walking. This makes it possible to provide the optimal input method according to the user's posture.

[0056] The reception unit can analyze the user's past input history and predict input. For example, it can automatically suggest phrases that the user has frequently used in the past. It can also predict what the user will input during a specific time period and complete the input. It can also suggest what the user is likely to input next, taking into account what the user has input in the past. This makes it possible to support efficient input based on the user's past input history.

[0057] The reception unit can automatically collect relevant information based on the user's current project or area of ​​interest and complete the input. For example, it can automatically collect the latest research papers related to the project the user is currently working on and provide them as reference information when the user is entering information. It can also collect related news articles and blog articles based on the user's area of ​​interest and complete the input. This supports efficient input based on the user's project or area of ​​interest.

[0058] The reception unit can provide feedback to improve input accuracy depending on the user's input method. For example, in the case of voice input, feedback on pronunciation improvements can be provided. In the case of text input, feedback on typing speed and accuracy can be provided. In the case of image input, feedback on image resolution and quality can be provided. This makes it possible to improve input accuracy depending on the user's input method.

[0059] The reception unit can provide relevant local information at the time of input, taking into account the user's geographical location information. For example, if the user is in a specific area, news and event information related to that area can be provided. If the user is traveling, tourist information and traffic information for the travel destination can be provided. If the user is at home, information on nearby stores and services can be provided. This makes it possible to provide relevant information based on the user's geographical location information.

[0060] The reception unit can analyze the user's social media activity and suggest related topics when the user is typing. For example, the reception unit can suggest related input content based on topics that the user frequently mentions on social media. The reception unit can also suggest related topics based on the activities of the user's friends on social media. The reception unit can also suggest related input content based on information shared by the user on social media. This can support efficient input based on the user's social media activity.

[0061] The receiving unit can customize the input interface by reflecting the user's past feedback. For example, the input interface layout can be changed based on the user's past feedback. Also, specific functions can be provided with priority based on the user's past feedback. The input interface design can also be improved by referring to the user's feedback. This makes it possible to provide an optimal input interface based on the user's past feedback.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The reception unit receives a long-form input from the user. The long-form input from the user includes text input, voice input, image input, and the like. In addition to directly receiving text input, the reception unit can also convert voice input into text data using voice recognition technology and convert image input into text data using OCR technology. Step 2: The division unit divides the long text received by the reception unit into a number of characters that the generation AI can process. The division is based on the maximum number of characters that the generation AI can process at one time, but it can also select natural division points based on paragraphs or context. Step 3: The generator uses a generation AI to summarize each part divided by the segmentation unit. The generator uses a text generation AI (e.g., LLM) to generate a summary. The generator also uses a multimodal generation AI to handle multiple modalities, such as images and audio, in addition to text. Step 4: The integrator integrates the partial summaries generated by the generator. Integration is based on the order and content of the partial summaries, but it can also analyze the content of the partial summaries and integrate them in a natural flow. It can also prioritize the integration of important parts based on the importance of the partial summaries.

[0064] (Example 2) A summarization system according to an embodiment of the present invention overcomes the character limit imposed by a generation AI and enables a user to summarize a long text with a single operation. The summarization system operates as follows: a user inputs a long text to be summarized; an external processing system divides the text into a number of characters that the generation AI can process; each divided portion is sequentially input to the generation AI to generate a summary; and finally, the external processing system combines these partial summaries to generate a final summary. For example, if a user wants to summarize a 10,000-character text, the summarization system inputs the text into the system. The external processing system then divides the input long text into a number of characters that the generation AI can process. For example, if the generation AI can process 2,000 characters at a time, the 10,000-character text is divided into five portions. The summarization system then sequentially inputs each divided portion into the generation AI to generate a partial summary for each portion. For example, the first 2,000 characters are input to the generation AI, and a summary is generated for that portion. The next 2,000 characters are input to the generation AI, and a summary is generated in the same manner. This process is repeated until all portions are summarized. Finally, the summarization system uses an external processing system to integrate these partial summaries and generate a final summary. For example, if five partial summaries are generated, they are combined into one final summary. This mechanism allows users to obtain a long summary with a single operation. This allows the summarization system to overcome the character limit imposed by the generation AI and efficiently summarize long texts. For example, when summarizing long texts such as research papers or novels, this eliminates the need to manually divide the text, allowing for more efficient summarization.

[0065] A summarization system according to an embodiment includes a reception unit, a division unit, a generation unit, and an integration unit. The reception unit receives a long sentence from a user. The long sentence from a user may be, for example, a text input, a voice input, or an image input, but is not limited to these examples. The reception unit may directly receive a text input. The reception unit may also receive a voice input and convert it into text data using voice recognition technology. The reception unit may also receive an image input and convert it into text data using OCR technology. For example, the reception unit may input voice data input by a user to a generation AI and cause the generation AI to convert the voice data into text data. The division unit divides the long sentence received by the reception unit into a number of characters that the generation AI can process. The division is performed based on, for example, the maximum number of characters that the generation AI can process at one time, but is not limited to these examples. For example, the division unit may divide the long sentence into paragraphs. The division unit may also select natural division points based on the context. For example, the division unit may analyze the content of the long sentence and select appropriate division points. The generation unit uses a generation AI to summarize each part divided by the division unit. The generation AI generates a summary using, for example, a text generation AI (e.g., LLM). The generation unit can also use a multimodal generation AI to handle multiple modalities, such as images and audio, in addition to text. For example, the generation unit inputs a prompt such as "Please summarize the main points of this passage" to the generation AI and generates a summary. The integration unit integrates the partial summaries generated by the generation unit. The integration is performed, for example, based on the order and content of the partial summaries, but is not limited to such an example. For example, the integration unit analyzes the content of the partial summaries and integrates them in a natural flow. The integration unit can also prioritize important parts based on the importance of the partial summaries. This allows the summarization system according to the embodiment to efficiently summarize a long text provided by a user and provide a final summary. Some or all of the above-described processes in the generation unit and integration unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit inputs each part divided by the division unit to the generation AI and generates a summary.The synthesizer synthesizes the partial summaries generated by the generators to generate a final summary.

[0066] The reception unit can estimate the user's emotions and adjust the timing of inputting long sentences based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can delay the timing of input to provide a relaxing environment. Furthermore, if the user is concentrating, the reception unit can also speed up the timing of input, allowing the user to input long sentences efficiently. Furthermore, if the user is tired, the reception unit can adjust the timing of input and display a message encouraging the user to take a break. This enables the user to input long sentences at the optimal timing depending on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using, for example, the generation AI. For example, the reception unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0067] The reception unit can analyze the user's past input history and select the optimal input method. For example, the reception unit can prioritize and suggest input methods (such as voice and text) that the user has frequently used in the past. The reception unit can also predict and suggest an input method to be used during a specific time period based on the user's past input history. The reception unit can also complete input by referring to content that the user has previously input. This makes it possible to provide the optimal input method based on the user's past input history. Some or all of the above-described processing in the reception unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the reception unit can input the user's past input history data into the generation AI and have the generation AI select the optimal input method.

[0068] When a long sentence is input, the reception unit can filter the input based on the user's current project or area of ​​interest. For example, the reception unit prioritizes input of keywords related to the project the user is currently working on. The reception unit can also automatically complete related information based on the user's area of ​​interest. The reception unit can also suggest related information by referring to the user's past project history. This makes it possible to provide related information based on the user's project or area of ​​interest. Some or all of the above-mentioned processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's project data into the generation AI and have the generation AI filter the related information.

[0069] When inputting a long sentence, the reception unit can select the optimal input means depending on the user's input method. For example, if the user desires voice input, the reception unit can prioritize providing a voice recognition function. Furthermore, if the user desires text input, the reception unit can also prioritize providing a keyboard input. Furthermore, if the user desires image input, the reception unit can also prioritize providing an image recognition function. This makes it possible to provide the optimal means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's input method data into the generation AI and have the generation AI select the optimal input means.

[0070] The reception unit can estimate the user's emotions and determine the priority of long sentences to be input based on the estimated user emotions. For example, if the user is nervous, the reception unit postpones input of long sentences of less importance. Furthermore, if the user is relaxed, the reception unit can prioritize input of long sentences of greater importance. Furthermore, if the user is in a hurry, the reception unit can prioritize input of long sentences that can be input in a shorter time. This allows the priority of long sentences to be determined according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0071] When inputting a long sentence, the reception unit can prioritize inputting a highly relevant long sentence taking into consideration the user's geographical location information. For example, when the user is in a specific area, the reception unit can prioritize inputting information related to that area. Furthermore, when the user is traveling, the reception unit can prioritize inputting information related to the travel destination. Furthermore, when the user is at home, the reception unit can prioritize inputting information related to the home. This makes it possible to provide highly relevant information based on the user's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can input the user's geographical location information data to the generation AI and cause the generation AI to select highly relevant information.

[0072] When a long text is input, the reception unit can analyze the user's social media activity and input a related long text. The reception unit can, for example, input the related long text based on information shared by the user on social media. The reception unit can also analyze the content of the user's social media posts and input the related long text. The reception unit can also input the related long text with reference to the activity of the user's friends on social media. This makes it possible to provide related information based on the user's social media activity. Some or all of the above-described processing in the reception unit can be performed using, or without, a generation AI. For example, the reception unit can input the user's social media data into the generation AI and cause the generation AI to select the related long text.

[0073] The reception unit can customize the input method by reflecting the user's past feedback when inputting a long sentence. The reception unit can improve the input method, for example, based on feedback provided by the user in the past. The reception unit can also preferentially provide a specific input method based on the user's past feedback. The reception unit can also customize the input interface by referring to the user's feedback. This allows the input method to be customized based on the user's past feedback. Some or all of the above-mentioned processing in the reception unit can be performed using, or without, the generation AI. For example, the reception unit can input the user's feedback data into the generation AI and have the generation AI customize the input method.

[0074] The segmentation unit can estimate the user's emotion and adjust the timing of segmentation based on the estimated user emotion. For example, if the user is feeling stressed, the segmentation unit can delay the timing of segmentation to provide a relaxing environment. Furthermore, if the user is concentrating, the segmentation unit can also advance the timing of segmentation to perform segmentation efficiently. Furthermore, if the user is tired, the segmentation unit can adjust the timing of segmentation and display a message encouraging the user to take a break. This enables segmentation at the optimal timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the segmentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the segmentation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0075] When dividing the long text, the division unit can select optimal division points based on the content of the long text. The division unit, for example, sets division points for each paragraph of the long text. The division unit can also select natural division points based on the context of the long text. The division unit can also select optimal division points based on keywords in the long text. This makes it possible to select optimal division points based on the content of the long text. Some or all of the above-mentioned processing in the division unit may be performed using, or without, a generation AI. For example, the division unit can input content data of the long text into the generation AI and have the generation AI select optimal division points.

[0076] The segmentation unit can apply different segmentation algorithms depending on the category of the long text during segmentation. For example, in the case of a technical document, the segmentation unit can apply a segmentation algorithm based on technical terms. In the case of a novel, the segmentation unit can also apply a segmentation algorithm based on the development of the story. In the case of a news article, the segmentation unit can also apply a segmentation algorithm based on the section of the article. This makes it possible to apply the optimal segmentation algorithm depending on the category of the long text. Some or all of the above-mentioned processing in the segmentation unit may be performed using, or without, a generation AI, for example. For example, the segmentation unit can input category data of the long text into the generation AI and have the generation AI apply the segmentation algorithm.

[0077] The division unit can improve the accuracy of division by referring to the user's past division results. For example, the division unit selects the optimal division point based on the user's past division results. The division unit can also analyze the user's past division history and improve the division algorithm. The division unit can also improve the accuracy of division by referring to user feedback. This improves the accuracy of division based on the user's past division results. Some or all of the above-mentioned processing in the division unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the division unit can input the user's past division result data into the generation AI and have the generation AI improve the accuracy of division.

[0078] The segmentation unit can estimate the user's emotions and determine segmentation priorities based on the estimated user emotions. For example, if the user is nervous, the segmentation unit postpones segments of lower importance. Furthermore, if the user is relaxed, the segmentation unit can prioritize segmenting segments of higher importance. Furthermore, if the user is in a hurry, the segmentation unit can prioritize segmenting segments that can be segmented in a short time. This allows segmentation priorities to be determined according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the segmentation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the segmentation unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0079] When dividing, the dividing unit can determine the division priority based on the submission time of the long text. For example, the dividing unit prioritizes dividing long texts with an upcoming submission deadline. The dividing unit can also postpone dividing long texts with a distant submission deadline. The dividing unit can also adjust the division schedule based on the submission deadline. This makes it possible to determine the division priority based on the submission time of the long text. Some or all of the above-mentioned processing in the dividing unit may be performed using, or without, the generation AI. For example, the dividing unit can input submission time data into the generation AI and have the generation AI determine the division priority.

[0080] The division unit can adjust the order of division based on the relevance of the long sentence when dividing. For example, the division unit divides highly relevant parts with priority. The division unit can also postpone dividing less relevant parts. The division unit can also adjust the order of division based on the relevance. This makes it possible to adjust the order of division based on the relevance of the long sentence. Some or all of the above-mentioned processing in the division unit may be performed using, or without, the generation AI. For example, the division unit can input relevance data of the long sentence into the generation AI and have the generation AI adjust the order of division.

[0081] The division unit can adjust the division method according to the user's level of expertise during division. For example, the division unit can provide a detailed division method to a user with high expertise. The division unit can also provide a simple division method to a user with low expertise. The division unit can also customize the division method based on the user's level of expertise. This allows the division method to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the division unit can be performed using, or without, a generation AI. For example, the division unit can input the user's expertise level data into the generation AI and cause the generation AI to adjust the division method.

[0082] The generation unit can estimate the user's emotions and adjust the summary presentation style based on the estimated user emotions. For example, if the user is relaxed, the generation unit can use a relaxed presentation style. If the user is in a hurry, the generation unit can use a concise and to-the-point presentation style. If the user is excited, the generation unit can use a visually stimulating presentation style. This allows the summary presentation style to be adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0083] When generating a summary, the generation unit can adjust the level of detail of the summary based on the importance of the long text. For example, the generation unit summarizes parts of high importance in detail. The generation unit can also summarize parts of low importance in brief. The generation unit can also adjust the level of detail of the summary based on the importance of the long text. This allows the level of detail of the summary to be adjusted based on the importance of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input importance data of the long text into the generation AI and have the generation AI adjust the level of detail of the summary.

[0084] When generating a summary, the generation unit can apply different summarization algorithms depending on the category of the long text. For example, in the case of a technical document, the generation unit can apply a summarization algorithm that includes technical terms. In the case of a novel, the generation unit can also apply a summarization algorithm that emphasizes the development of the story. In the case of a news article, the generation unit can also apply a summarization algorithm based on the section of the article. This allows the application of the optimal summarization algorithm depending on the category of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input category data of the long text into the generation AI and have the generation AI apply the summarization algorithm.

[0085] When generating a summary, the generation unit can improve the accuracy of the summary by referring to the user's past summarization results. The generation unit, for example, improves the summarization algorithm based on the user's past summarization results. The generation unit can also analyze the user's past summarization history to improve the accuracy of the summary. The generation unit can also improve the accuracy of the summary by referring to the user's feedback. In this way, the accuracy of the summary is improved based on the user's past summarization results. Some 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 input the user's past summary result data into the generation AI and have the generation AI improve the accuracy of the summary.

[0086] The generation unit can estimate the user's emotions and adjust the length of the summary based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate a short, concise summary. If the user is relaxed, the generation unit can generate a longer summary with detailed explanations. If the user is excited, the generation unit can generate a summary with visually stimulating effects. This allows the length of the summary to be adjusted according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0087] When generating summaries, the generation unit can determine the priority of summaries based on the submission time of the long text. For example, the generation unit prioritizes summarizing long texts with upcoming submission deadlines. The generation unit can also postpone long texts with distant submission deadlines. The generation unit can also adjust the summary schedule based on the submission deadlines. This makes it possible to determine the priority of summaries based on the submission time of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input submission time data into the generation AI and have the generation AI determine the priority of summaries.

[0088] When generating summaries, the generation unit can adjust the order of summaries based on the relevance of the long text. For example, the generation unit prioritizes summarizing highly relevant parts. The generation unit can also postpone summarizing less relevant parts. The generation unit can also adjust the order of summaries based on relevance. This makes it possible to adjust the order of summaries based on the relevance of the long text. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input relevance data of the long text into the generation AI and have the generation AI adjust the order of the summaries.

[0089] When generating a summary, the generation unit can adjust the use of technical terms in the summary according to the user's level of expertise. For example, the generation unit can provide a summary that uses a lot of technical terms to a user with high level of expertise. The generation unit can also provide a concise and easy-to-understand summary to a user with low level of expertise. The generation unit can also adjust the use of technical terms in the summary based on the user's level of expertise. This allows the use of technical terms in the summary to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms in the summary.

[0090] The integration unit can estimate the user's emotion and adjust the integration method based on the estimated user's emotion. For example, if the user is relaxed, the integration unit can perform integration at a leisurely pace. Furthermore, if the user is in a hurry, the integration unit can perform integration quickly. Furthermore, if the user is excited, the integration unit can perform integration with a visually stimulating effect. This allows the integration method to be adjusted according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the integration unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the integration unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0091] During integration, the integration unit can select the optimal integration method based on the content of the partial summaries. For example, the integration unit prioritizes integration of highly relevant parts based on the theme of the partial summaries. The integration unit can also prioritize integration of important parts based on the importance of the partial summaries. The integration unit can also integrate in a natural flow based on the context of the partial summaries. This makes it possible to select the optimal integration method based on the content of the partial summaries. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, a generation AI. For example, the integration unit can input content data of the partial summaries to the generation AI and have the generation AI select the optimal integration method.

[0092] During integration, the integration unit can apply different integration algorithms depending on the category of the partial summary. For example, in the case of a technical document, the integration unit can apply an integration algorithm that includes technical terms. In the case of a novel, the integration unit can also apply an integration algorithm that emphasizes the development of the story. In the case of a news article, the integration unit can also apply an integration algorithm based on the section of the article. This makes it possible to apply the optimal integration algorithm depending on the category of the partial summary. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, the generation AI, for example. For example, the integration unit can input category data of the partial summary to the generation AI and have the generation AI apply the integration algorithm.

[0093] During integration, the integration unit can improve the accuracy of integration by referring to the user's past integration results. The integration unit, for example, improves the integration algorithm based on the user's past integration results. The integration unit can also analyze the user's past integration history to improve the accuracy of integration. The integration unit can also improve the accuracy of integration by referring to the user's feedback. This improves the accuracy of integration based on the user's past integration results. Some or all of the above-mentioned processing in the integration unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the integration unit can input the user's past integration result data into the generation AI and cause the generation AI to improve the accuracy of integration.

[0094] The integration unit can estimate the user's emotions and determine integration priorities based on the estimated user emotions. For example, if the user is nervous, the integration unit postpones parts of lower importance. Furthermore, if the user is relaxed, the integration unit can prioritize integration of parts of higher importance. Furthermore, if the user is in a hurry, the integration unit can prioritize integration of parts that can be integrated in a short time. This allows integration priorities to be determined according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the integration unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the integration unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0095] The integration unit can determine the priority of integration based on the submission dates of the partial summaries when integrating them. For example, the integration unit prioritizes integrating partial summaries with upcoming submission deadlines. The integration unit can also postpone partial summaries with distant submission deadlines. The integration unit can also adjust the integration schedule based on the submission deadlines. This makes it possible to determine the priority of integration based on the submission dates of the partial summaries. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, the generation AI. For example, the integration unit can input submission date data into the generation AI and have the generation AI determine the priority of integration.

[0096] The integration unit can adjust the order of integration based on the relevance of the partial summaries when integrating them. For example, the integration unit prioritizes integration of highly relevant parts. The integration unit can also postpone integration of less relevant parts. The integration unit can also adjust the order of integration based on the relevance. This makes it possible to adjust the order of integration based on the relevance of the partial summaries. Some or all of the above-mentioned processing in the integration unit may be performed using, or without, the generation AI. For example, the integration unit can input relevance data of the partial summaries to the generation AI and have the generation AI adjust the order of integration.

[0097] The integration unit can adjust the integration method according to the user's level of expertise during integration. For example, the integration unit can provide a detailed integration method to a user with high expertise. The integration unit can also provide a simple integration method to a user with low expertise. The integration unit can also customize the integration method based on the user's level of expertise. This allows the integration method to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the integration unit can be performed using, or without, the generation AI. For example, the integration unit can input the user's expertise level data into the generation AI and cause the generation AI to adjust the integration method. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, division unit, generation unit, and integration unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives input of a long sentence from a user. The division unit is realized by the specific processing unit 290 of the data processing device 12 and divides the long sentence into a number of characters that can be processed by the generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and inputs each divided part to the generation AI to generate a summary. The integration unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the generated partial summaries to generate a final summary. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, division unit, generation unit, and integration unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives voice input from the user. The division unit is realized by the specific processing unit 290 of the data processing device 12 and divides a long sentence into a number of characters that can be processed by the generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and inputs each divided part to the generation AI to generate a summary. The integration unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the generated partial summaries to generate a final summary. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, division unit, generation unit, and integration unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives voice input from the user. The division unit is realized by the specific processing unit 290 of the data processing device 12 and divides a long sentence into a number of characters that can be processed by the generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and inputs each divided part to the generation AI to generate a summary. The integration unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the generated partial summaries to generate a final summary. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, division unit, generation unit, and integration unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives voice input from the user. The division unit is realized by the specific processing unit 290 of the data processing device 12 and divides a long sentence into a number of characters that can be processed by the generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and inputs each divided part to the generation AI to generate a summary. The integration unit is realized by the specific processing unit 290 of the data processing device 12 and integrates the generated partial summaries to generate a final summary.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The reception unit can detect the user's posture when inputting and adjust the input method based on the posture. For example, if the user is sitting, keyboard input can be given priority. Also, if the user is standing, voice input can be given priority. Also, if the user is walking, voice input can be given priority, and adjustments can be made to make input easier even while walking. This makes it possible to provide the optimal input method according to the user's posture.

[0100] The reception unit can estimate the user's emotion and change the design of the input interface based on the estimated user's emotion. For example, if the user is feeling stressed, an interface with calm colors can be provided. If the user is relaxed, an interface with bright colors can be provided. If the user is concentrating, a simple and unobtrusive interface can be provided. In this way, an optimal input interface can be provided according to the user's emotion.

[0101] The reception unit can analyze the user's past input history and predict input. For example, it can automatically suggest phrases that the user has frequently used in the past. It can also predict what the user will input during a specific time period and complete the input. It can also suggest what the user is likely to input next, taking into account what the user has input in the past. This makes it possible to support efficient input based on the user's past input history.

[0102] The reception unit can automatically collect relevant information based on the user's current project or area of ​​interest and complete the input. For example, it can automatically collect the latest research papers related to the project the user is currently working on and provide them as reference information when the user is entering information. It can also collect related news articles and blog articles based on the user's area of ​​interest and complete the input. This supports efficient input based on the user's project or area of ​​interest.

[0103] The reception unit can provide feedback to improve input accuracy depending on the user's input method. For example, in the case of voice input, feedback on pronunciation improvements can be provided. In the case of text input, feedback on typing speed and accuracy can be provided. In the case of image input, feedback on image resolution and quality can be provided. This makes it possible to improve input accuracy depending on the user's input method.

[0104] The reception unit can estimate the user's emotions and adjust the difficulty of input based on the estimated user's emotions. For example, if the user is nervous, an easy input task can be preferentially provided. Also, if the user is relaxed, an input task with a high level of difficulty can be provided. Also, if the user is concentrating, an input task with a moderate level of difficulty can be provided. In this way, the optimum input task can be provided according to the user's emotions.

[0105] The reception unit can provide relevant local information at the time of input, taking into account the user's geographical location information. For example, if the user is in a specific area, news and event information related to that area can be provided. If the user is traveling, tourist information and traffic information for the travel destination can be provided. If the user is at home, information on nearby stores and services can be provided. This makes it possible to provide relevant information based on the user's geographical location information.

[0106] The reception unit can analyze the user's social media activity and suggest related topics when the user is typing. For example, the reception unit can suggest related input content based on topics that the user frequently mentions on social media. The reception unit can also suggest related topics based on the activities of the user's friends on social media. The reception unit can also suggest related input content based on information shared by the user on social media. This can support efficient input based on the user's social media activity.

[0107] The receiving unit can customize the input interface by reflecting the user's past feedback. For example, the input interface layout can be changed based on the user's past feedback. Also, specific functions can be provided with priority based on the user's past feedback. The input interface design can also be improved by referring to the user's feedback. This makes it possible to provide an optimal input interface based on the user's past feedback.

[0108] The division unit can estimate the user's emotion and adjust the division method based on the estimated user's emotion. For example, if the user is feeling stressed, the division method can be simplified to reduce the burden of division. Also, if the user is relaxed, a detailed division method can be provided. Also, if the user is concentrating, an efficient division method can be provided. In this way, the optimum division method can be provided according to the user's emotion.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The reception unit receives a long-form input from the user. The long-form input from the user includes text input, voice input, image input, and the like. In addition to directly receiving text input, the reception unit can also convert voice input into text data using voice recognition technology and convert image input into text data using OCR technology. Step 2: The division unit divides the long text received by the reception unit into a number of characters that the generation AI can process. The division is based on the maximum number of characters that the generation AI can process at one time, but it can also select natural division points based on paragraphs or context. Step 3: The generator uses a generation AI to summarize each part divided by the segmentation unit. The generator uses a text generation AI (e.g., LLM) to generate a summary. The generator also uses a multimodal generation AI to handle multiple modalities, such as images and audio, in addition to text. Step 4: The integrator integrates the partial summaries generated by the generator. Integration is based on the order and content of the partial summaries, but it can also analyze the content of the partial summaries and integrate them in a natural flow. It can also prioritize the integration of important parts based on the importance of the partial summaries.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] 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.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0122] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] 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.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] 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.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] 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.

[0139] 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.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0141] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] 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.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] 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.

[0156] 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.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0171] 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.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0174] 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.

[0175] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0176] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0180] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0182] [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives input of a long sentence from a user; a division unit that divides the long sentence received by the reception unit into a number of characters that can be processed by the generation AI; a generation unit that inputs each of the parts divided by the division unit into a generation AI to generate a summary; an integration unit that integrates the partial summaries generated by the generation unit; A system characterized by:

2. The reception unit Estimates the user's emotions and adjusts the timing of long sentence input based on the estimated user emotions.

2. The system of claim 1.

3. The reception unit Analyze the user's past input history and select the optimal input method 2. The system of claim 1.

4. The reception unit Filter long-form input based on the user's current projects and interests 2. The system of claim 1.

5. The reception unit When inputting long sentences, select the most appropriate input method according to the user's input method.

2. The system of claim 1.

6. The reception unit Estimate the user's emotions and prioritize long sentences to be input based on the estimated user emotions.

2. The system of claim 1.

7. The reception unit When entering long sentences, the system prioritizes the most relevant sentences by taking into account the user's geographical location information.

2. The system of claim 1.

8. The reception unit When a user enters a long sentence, the app analyzes the user's social media activity and inputs related long sentences.

2. The system of claim 1.

Images