System

Abstract

An object of the system according to the embodiment is to efficiently learn a slide in a PowerPoint format or a document in a Word format and automatically generate a template.SOLUTION: A system according to an embodiment includes a collection unit, a conversion unit, a learning unit, and a generation unit. The collection unit collects a file. The conversion unit analyzes the file collected by the collection unit and converts the file into an xml format. The learning unit learns the data converted by the conversion unit. The generation unit automatically generates a template based on the data learned by the learning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to efficiently learn PowerPoint slides or Word documents and automatically generate templates.

[0005] The system according to the embodiment aims to efficiently learn PowerPoint slides and Word documents and automatically generate templates. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a conversion unit, a learning unit, and a generation unit. The collection unit collects files. The conversion unit analyzes the files collected by the collection unit and converts them into XML format. The learning unit learns from the data converted by the conversion unit. The generation unit automatically generates a template based on the data learned by the learning unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently learn PowerPoint slides and Word documents and automatically generate templates. [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 system according to an embodiment of the present invention uses a generation AI to extract all PowerPoint slides and Word documents from .pptx and .docx files in a company into XML format and convert them into a learnable format. This system collects files, and the generation AI analyzes and converts them into XML format. The generation AI then learns from the converted XML data and automatically creates templates for PowerPoint slides and Word documents. For example, the system collects all .pptx and .docx files in a company. The generation AI then analyzes and converts these files into XML format. The content of each file is analyzed in detail, and elements such as text, images, and tables are represented in XML format. For example, slide titles, main text, image positions, and sizes are represented using XML tags. The generation AI then learns from the converted XML data and automatically creates templates for PowerPoint slides and Word documents. For example, the system automatically generates slide layouts and document structures based on a specific theme. The generation AI then suggests optimal layouts and structures based on past slide and document data. This allows the system to streamline in-house document creation work, significantly reducing the time and effort required. For example, when creating a proposal for a new project, a template automatically generated by the generative AI can be used to quickly create high-quality documents. In addition, the generative AI learns from past data, improving the consistency and quality of documents.

[0029] The document generation system according to the embodiment includes a collection unit, a conversion unit, a learning unit, and a generation unit. The collection unit collects files. Examples of files include, but are not limited to, text files, image files, and audio files. For example, the collection unit collects all .pptx and .docx files within a company. The collection unit can also collect files from a remote server via a network. The conversion unit analyzes the files collected by the collection unit and converts them into XML format. For example, the conversion unit analyzes the contents of the files using text analysis technology and expresses them in XML format. The conversion unit can also analyze image files using image analysis technology and express them in XML format. The conversion unit can also analyze audio files using audio analysis technology and express them in XML format. For example, the conversion unit analyzes the contents of text files in detail and expresses elements such as text, images, and tables using XML tags. The learning unit learns from the data converted by the conversion unit. For example, the learning unit learns from the data using a machine learning algorithm and proposes optimal layouts and structures. The learning unit can also learn from past slide and document data. For example, the learning unit proposes a layout and structure based on a specific theme based on data of past slides and documents. The generation unit automatically generates a template based on the data learned by the learning unit. The generation unit automatically generates, for example, a slide layout and document structure based on a specific theme. The generation unit can also generate a customized template based on a user's instructions. For example, the generation unit proposes an optimal layout and structure based on a theme specified by the user. This allows the document generation system according to the embodiment to efficiently perform processes from file collection to automatic template generation.

[0030] The document generation system further includes a customization unit that provides a user-customizable interface. The customization unit provides a means for the user to customize the interface. For example, the customization unit provides options for changing the layout and color scheme of the interface. The customization unit can also provide options for the user to select functions to be used. For example, the customization unit provides an option to prioritize displaying functions frequently used by the user. The customization unit can also suggest optimal customization options based on the user's operation history. For example, the customization unit suggests optimal options based on customization options used by the user in the past. This allows the user to customize the interface, improving usability.

[0031] The document generation system further includes an evaluation unit that evaluates the quality of the generated template. The evaluation unit provides a means for evaluating the quality of the generated template. The evaluation unit evaluates, for example, the accuracy and ease of use of the template. The evaluation unit can also evaluate the aesthetic appeal of the template. For example, the evaluation unit evaluates the aesthetic appeal based on the layout and color scheme of the template. The evaluation unit can also evaluate the quality of the template based on user feedback. For example, the evaluation unit evaluates the quality of the template based on feedback provided by the user. In this way, by evaluating the quality of the generated template, it is possible to provide a high-quality template.

[0032] The conversion unit can analyze the contents of each file and represent elements such as text, images, and tables in XML format. The conversion unit can, for example, use text analysis technology to analyze the contents of the file and represent them in XML format. For example, the conversion unit can analyze the contents of a text file in detail and represent elements such as text, images, and tables using XML tags. The conversion unit can also analyze image files using image analysis technology and represent them in XML format. For example, the conversion unit can analyze the contents of an image file and represent the position and size of the image using XML tags. The conversion unit can also analyze audio files using audio analysis technology and represent them in XML format. For example, the conversion unit can analyze the contents of an audio file and represent the start and end times of the audio using XML tags. In this way, by analyzing the contents of the file in detail and representing them in XML format, data reusability is improved.

[0033] The generation unit can automatically generate a slide layout and a document structure based on a theme. The generation unit automatically generates, for example, a slide layout and a document structure based on a specific theme. For example, the generation unit automatically generates a slide layout based on the theme of a business presentation. The generation unit can also automatically generate a document structure based on the theme of an academic paper. For example, the generation unit automatically generates a document layout based on the theme of marketing materials. This allows documents to be created efficiently by automatically generating a layout and structure based on a specific theme.

[0034] The learning unit can propose layouts and structures based on data from past slides and documents. For example, the learning unit proposes optimal layouts and structures based on data from past slides and documents. For example, the learning unit proposes optimal slide layouts based on data from past business presentations. The learning unit can also propose optimal document structures based on data from past academic papers. For example, the learning unit proposes optimal document layouts based on data from past marketing materials. In this way, by proposing optimal layouts and structures based on past data, the consistency and quality of documents are improved.

[0035] The collection unit can analyze the user's past file collection history and select a collection method. For example, the collection unit prioritizes collection of file formats that the user has frequently collected in the past. The collection unit can also suggest the optimal method by referring to the collection methods (manual, scheduled, etc.) used by the user in the past. For example, the collection unit can set collection to be performed during a specific time period based on the user's past collection history. This allows the optimal collection method to be selected by analyzing the past collection history.

[0036] When collecting files, the collection unit can filter the files based on the user's current project or area of ​​interest. For example, the collection unit collects only files related to the user's current project. The collection unit can also preferentially collect highly relevant files based on the user's area of ​​interest. For example, the collection unit filters and collects relevant files based on keywords specified by the user. This allows highly relevant files to be collected efficiently by filtering based on the user's current project or area of ​​interest.

[0037] When collecting files, the collection unit can select a collection means according to the user's input method. For example, when the user uses voice input, the collection unit collects files using voice recognition technology. Also, when the user uses text input, the collection unit can collect files using text analysis technology. For example, when the user uses image input, the collection unit collects files using image recognition technology. This allows files to be collected efficiently by selecting the optimal collection means according to the user's input method.

[0038] When collecting files, the collection unit can prioritize collecting highly relevant files based on the user's geographical location information. For example, when the user is in a particular office, the collection unit prioritizes collecting files related to the office. Furthermore, when the user is on a business trip, the collection unit can also prioritize collecting files related to the business trip destination. For example, when the user is at home, the collection unit prioritizes collecting files related to work at home. In this way, highly relevant files can be collected efficiently by taking geographical location information into consideration.

[0039] When collecting files, the collection unit can analyze the user's social media activities and collect related files. For example, the collection unit collects files shared by the user on social media. The collection unit can also analyze the content posted by the user on social media to collect related files. For example, the collection unit collects related files by referring to the activities of the user's friends on social media. This makes it possible to efficiently collect highly related files by analyzing social media activities.

[0040] When collecting files, the collection unit can customize the collection method based on the user's past feedback. For example, the collection unit optimizes the collection method based on feedback provided by the user in the past. The collection unit can also preferentially use a specific collection method based on the user's past feedback. For example, the collection unit adjusts the collection frequency and timing by reflecting the user's feedback. In this way, the collection method can be optimized by reflecting the past feedback.

[0041] During conversion, the conversion unit can adjust the level of detail of the conversion based on the priority of the file. For example, the conversion unit converts files of high importance into a detailed XML format. The conversion unit can also convert files of low importance into a simplified XML format. For example, the conversion unit gradually adjusts the level of detail of the conversion depending on the importance of the file. This allows for efficient conversion by adjusting the level of detail of the conversion depending on the importance of the file.

[0042] The conversion unit can apply different conversion algorithms depending on the file type during conversion. For example, the conversion unit applies a text analysis algorithm to a text file for conversion. The conversion unit can also apply an image recognition algorithm to an image file for conversion. For example, the conversion unit applies a spreadsheet analysis algorithm to convert a spreadsheet file. This improves conversion accuracy by applying the optimal conversion algorithm depending on the file category.

[0043] During conversion, the conversion unit can improve the accuracy of the conversion based on the user's past conversion results. For example, the conversion unit optimizes the conversion algorithm based on the results of files the user has converted in the past. The conversion unit can also learn specific conversion patterns from the user's past conversion results to improve accuracy. For example, the conversion unit adjusts the conversion algorithm by reflecting user feedback. This improves the accuracy of the conversion by referring to past conversion results.

[0044] During conversion, the conversion unit can determine the conversion priority based on the submission date and time of the file. For example, the conversion unit prioritizes the conversion of files with an upcoming submission deadline. The conversion unit can also postpone files with a distant submission deadline. For example, the conversion unit gradually adjusts the conversion priority according to the submission time. This allows conversion to be performed efficiently by determining the conversion priority based on the submission time.

[0045] During conversion, the conversion unit can adjust the conversion order based on the relevance of the files. For example, the conversion unit preferentially converts highly relevant files. The conversion unit can also postpone files with low relevance. For example, the conversion unit adjusts the conversion order in stages according to the relevance of the files. This allows for efficient conversion by adjusting the conversion order based on the relevance of the files.

[0046] During conversion, the conversion unit can adjust the use of technical terminology in the conversion depending on the user's level of knowledge. For example, if the user has specialized knowledge, the conversion unit converts the data into an XML format that uses a lot of technical terminology. Alternatively, if the user does not have specialized knowledge, the conversion unit can convert the data into an XML format that uses simpler terminology. For example, the conversion unit gradually adjusts the use of technical terminology in the conversion depending on the user's level of expertise. This allows for easy-to-understand conversion by adjusting the use of technical terminology depending on the user's level of expertise.

[0047] During learning, the learning unit can optimize the learning algorithm based on past learning data. For example, the learning unit adjusts the parameters of the learning algorithm based on past learning data. The learning unit can also analyze past learning results and select the optimal learning algorithm. For example, the learning unit learns specific patterns from past learning data and optimizes the algorithm. In this way, the accuracy of the learning algorithm is improved by referring to past learning data.

[0048] During learning, the learning unit can update the learning data based on user feedback. For example, the learning unit updates the learning data based on feedback provided by the user. The learning unit can also perform learning by adding a specific data set based on the user feedback. For example, the learning unit reflects the user feedback to improve the quality of the learning data. In this way, the quality of the learning data is improved by reflecting the user feedback.

[0049] During training, the learning unit can integrate information from different data sources to enrich the training data. For example, the learning unit collects information from an internal database and integrates it into the training data. The learning unit can also collect information from external public data sources and integrate it into the training data. For example, the learning unit integrates data provided by a user into the training data to enrich the dataset. This increases the diversity of the training data by integrating information from different data sources.

[0050] During learning, the learning unit can weight the learning data based on the submission date and time of the file. For example, the learning unit prioritizes learning of data of files with an upcoming submission deadline. The learning unit can also lower the weighting of data of files with a distant submission deadline. For example, the learning unit gradually adjusts the weighting of the learning data depending on the submission date. This allows for efficient learning by weighting the learning data based on the submission date.

[0051] During learning, the learning unit can analyze fluctuations in the user's purchasing history and adjust the update frequency of the learning data. For example, if the user's purchasing history fluctuates frequently, the learning unit can increase the update frequency of the learning data. Also, if the user's purchasing history is stable, the learning unit can decrease the update frequency of the learning data. For example, the learning unit gradually adjusts the update frequency of the learning data according to fluctuations in the user's purchasing history. This enables efficient learning by adjusting the update frequency of the learning data according to fluctuations in the purchasing history.

[0052] During learning, the learning unit can adjust the learning algorithm based on the user's past feedback. For example, the learning unit adjusts the parameters of the learning algorithm based on the user's past feedback. The learning unit can also select and optimize a specific algorithm based on the user's past feedback. For example, the learning unit reflects the user's feedback to improve the accuracy of the learning algorithm. In this way, the accuracy of the learning algorithm is improved by reflecting the past feedback.

[0053] The generation unit can adjust the level of detail of the generation based on the priority of the file at the time of generation. For example, the generation unit generates a detailed template for a file with high importance. The generation unit can also generate a simplified template for a file with low importance. For example, the generation unit adjusts the level of detail of the generation in stages according to the importance of the file. In this way, templates can be generated efficiently by adjusting the level of detail of the generation according to the importance of the file.

[0054] The generation unit can apply different generation algorithms depending on the type of file during generation. For example, the generation unit applies a generation algorithm for presentations to slides for presentations. The generation unit can also apply a generation algorithm for reports to documents for reports. For example, the generation unit applies a generation algorithm for notes to documents for notes. This improves the accuracy of generation by applying the optimal generation algorithm depending on the file category.

[0055] During generation, the generation unit can improve the accuracy of generation based on the user's past generation results. For example, the generation unit optimizes the generation algorithm based on the results of templates generated by the user in the past. The generation unit can also learn specific generation patterns from the user's past generation results to improve accuracy. For example, the generation unit adjusts the generation algorithm by reflecting user feedback. This improves the accuracy of generation by referring to past generation results.

[0056] The generation unit can determine the generation priority based on the submission date and time of the file at the time of generation. For example, the generation unit generates a template with priority for a file whose submission deadline is approaching. The generation unit can also postpone the generation of a template for a file whose submission deadline is far away. For example, the generation unit adjusts the generation priority in stages depending on the submission time. In this way, templates can be generated efficiently by determining the generation priority based on the submission time.

[0057] The generation unit can adjust the order of generation based on the relevance of the files during generation. For example, the generation unit generates templates for highly related files with priority. The generation unit can also postpone the generation of templates for less related files. For example, the generation unit adjusts the order of generation in stages according to the relevance of the files. In this way, templates can be generated efficiently by adjusting the order of generation based on the relevance of the files.

[0058] The generation unit can adjust the use of technical terminology in the generation process according to the user's level of knowledge at the time of generation. For example, if the user has specialized knowledge, the generation unit generates a template that uses a lot of technical terminology. Furthermore, if the user does not have specialized knowledge, the generation unit can also generate a template that uses simple terminology. For example, the generation unit gradually adjusts the use of technical terminology in the generation process according to the user's level of expertise. In this way, by adjusting the use of technical terminology according to the user's level of expertise, a template that is easy to understand is generated.

[0059] During customization, the customization unit can select a customization method based on the user's past customization history. For example, the customization unit preferentially suggests customization options that the user has used in the past. The customization unit can also learn specific patterns from the user's past customization history and suggest the optimal method. For example, the customization unit optimizes the customization options based on user feedback. This allows the optimal customization method to be selected by referring to the past customization history.

[0060] During customization, the customization unit can customize the customization means based on the user's project. For example, the customization unit provides customization options related to the user's current project. The customization unit can also suggest the optimal customization method depending on the progress of the user's project. For example, the customization unit adjusts the customization options based on the content of the user's project. This allows optimal customization for the project by adjusting the customization means based on the current project.

[0061] During customization, the customization unit can select a customization method based on the user's geographic location information. For example, if the user is in a particular office, the customization unit provides customization options related to the office. Furthermore, if the user is on a business trip, the customization unit can provide customization options related to the destination of the business trip. For example, if the user is at home, the customization unit provides customization options related to working from home. This allows the optimal customization method to be selected by taking the geographic location information into consideration.

[0062] During customization, the customization unit can analyze the user's social media activity to suggest customization methods. For example, the customization unit can suggest customization options based on information shared by the user on social media. The customization unit can also analyze the content of the user's social media posts to suggest related customization options. For example, the customization unit can suggest customization options based on the activity of the user's friends on social media. In this way, highly relevant customization methods can be suggested by analyzing social media activity.

[0063] When performing an evaluation, the evaluation unit can select an evaluation method based on the user's past evaluation history. For example, the evaluation unit preferentially suggests evaluation methods that the user has used in the past. The evaluation unit can also learn specific patterns from the user's past evaluation history and suggest the optimal method. For example, the evaluation unit optimizes the evaluation method based on user feedback. This allows the optimal evaluation method to be selected by referring to the past evaluation history.

[0064] The evaluation unit can customize the evaluation method based on the user's project during evaluation. For example, the evaluation unit provides an evaluation method related to the user's current project. The evaluation unit can also suggest an optimal evaluation method depending on the progress of the user's project. For example, the evaluation unit adjusts the evaluation method based on the content of the user's project. This allows for optimal evaluation of the project by adjusting the evaluation method based on the current project.

[0065] The evaluation unit can select an evaluation method based on the user's geographical location information during evaluation. For example, if the user is in a particular office, the evaluation unit provides an evaluation method related to the office. Furthermore, if the user is on a business trip, the evaluation unit can also provide an evaluation method related to the business trip destination. For example, if the user is at home, the evaluation unit provides an evaluation method related to working from home. This allows the optimal evaluation method to be selected by taking the geographical location information into consideration.

[0066] The evaluation unit can analyze the user's social media activity and provide relevant information when evaluating. For example, the evaluation unit can suggest an evaluation method based on information shared by the user on social media. The evaluation unit can also analyze the content of the user's social media posts and suggest a relevant evaluation method. For example, the evaluation unit can suggest an evaluation method based on the activity of the user's friends on social media. In this way, by analyzing social media activity, it is possible to suggest a highly relevant evaluation method.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The collection unit can analyze the user's past file collection history and select a collection method. For example, it can prioritize collection of file types that the user has frequently collected in the past. The collection unit can also suggest the optimal method by referring to the collection methods (manual, scheduled, etc.) that the user has used in the past. For example, it can set collection to occur during a specific time period based on the user's past collection history. This allows the optimal collection method to be selected by analyzing the past collection history.

[0069] When collecting files, the collection unit can filter the files based on the user's current project or area of ​​interest. For example, it can collect only files related to the project the user is currently working on. It can also preferentially collect highly relevant files based on the user's area of ​​interest. For example, it can filter and collect relevant files based on keywords specified by the user. This allows highly relevant files to be collected efficiently by filtering based on the current project or area of ​​interest.

[0070] When collecting files, the collection unit can select a collection means according to the user's input method. For example, if the user uses voice input, file collection can be performed using voice recognition technology. Also, if the user uses text input, file collection can be performed using text analysis technology. For example, if the user uses image input, file collection can be performed using image recognition technology. This allows files to be collected efficiently by selecting the optimal collection means according to the user's input method.

[0071] During conversion, the conversion unit can adjust the level of detail of the conversion based on the priority of the file. For example, a file with high importance can be converted in a detailed XML format. On the other hand, a file with low importance can be converted in a simplified XML format. For example, the level of detail of the conversion can be adjusted in stages depending on the importance of the file. This allows for efficient conversion by adjusting the level of detail of the conversion depending on the importance of the file.

[0072] The conversion unit can apply different conversion algorithms depending on the file type during conversion. For example, a text analysis algorithm can be applied to a text file for conversion. An image recognition algorithm can also be applied to an image file for conversion. For example, a spreadsheet file can be converted by applying a table analysis algorithm. This improves the accuracy of conversion by applying the most appropriate conversion algorithm depending on the file category.

[0073] During conversion, the conversion unit can improve the accuracy of the conversion based on the user's past conversion results. For example, the conversion algorithm can be optimized based on the results of files the user has converted in the past. It can also learn specific conversion patterns from the user's past conversion results to improve accuracy. For example, the conversion algorithm can be adjusted based on user feedback. This improves the accuracy of the conversion by referring to past conversion results.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The collection department collects files. Files include text files, image files, audio files, etc. The collection department collects all .pptx and .docx files within the company. It can also collect files from remote servers via the network. Step 2: The conversion unit analyzes the files collected by the collection unit and converts them into XML format. The conversion unit analyzes the contents of the files using text analysis technology and expresses them in XML format. It can also analyze image files using image analysis technology and express them in XML format. It can also analyze audio files using audio analysis technology and express them in XML format. Step 3: The learning unit learns from the data converted by the conversion unit. The learning unit uses machine learning algorithms to learn from the data and propose optimal layouts and structures. It can also learn from data on past slides and documents. Step 4: The generator automatically generates templates based on the data learned by the learning unit. The generator automatically generates slide layouts and document structures based on specific themes. It can also generate customized templates based on user instructions.

[0076] (Example 2) A system according to an embodiment of the present invention uses a generation AI to extract all PowerPoint slides and Word documents from .pptx and .docx files in a company into XML format and convert them into a learnable format. This system collects files, and the generation AI analyzes and converts them into XML format. The generation AI then learns from the converted XML data and automatically creates templates for PowerPoint slides and Word documents. For example, the system collects all .pptx and .docx files in a company. The generation AI then analyzes and converts these files into XML format. The content of each file is analyzed in detail, and elements such as text, images, and tables are represented in XML format. For example, slide titles, main text, image positions, and sizes are represented using XML tags. The generation AI then learns from the converted XML data and automatically creates templates for PowerPoint slides and Word documents. For example, the system automatically generates slide layouts and document structures based on a specific theme. The generation AI then suggests optimal layouts and structures based on past slide and document data. This allows the system to streamline in-house document creation work, significantly reducing the time and effort required. For example, when creating a proposal for a new project, a template automatically generated by the generative AI can be used to quickly create high-quality documents. In addition, the generative AI learns from past data, improving the consistency and quality of documents.

[0077] The document generation system according to the embodiment includes a collection unit, a conversion unit, a learning unit, and a generation unit. The collection unit collects files. Examples of files include, but are not limited to, text files, image files, and audio files. For example, the collection unit collects all .pptx and .docx files within a company. The collection unit can also collect files from a remote server via a network. The conversion unit analyzes the files collected by the collection unit and converts them into XML format. For example, the conversion unit analyzes the contents of the files using text analysis technology and expresses them in XML format. The conversion unit can also analyze image files using image analysis technology and express them in XML format. The conversion unit can also analyze audio files using audio analysis technology and express them in XML format. For example, the conversion unit analyzes the contents of text files in detail and expresses elements such as text, images, and tables using XML tags. The learning unit learns from the data converted by the conversion unit. For example, the learning unit learns from the data using a machine learning algorithm and proposes optimal layouts and structures. The learning unit can also learn from past slide and document data. For example, the learning unit proposes a layout and structure based on a specific theme based on data of past slides and documents. The generation unit automatically generates a template based on the data learned by the learning unit. The generation unit automatically generates, for example, a slide layout and document structure based on a specific theme. The generation unit can also generate a customized template based on a user's instructions. For example, the generation unit proposes an optimal layout and structure based on a theme specified by the user. This allows the document generation system according to the embodiment to efficiently perform processes from file collection to automatic template generation.

[0078] The document generation system further includes a customization unit that provides a user-customizable interface. The customization unit provides a means for the user to customize the interface. For example, the customization unit provides options for changing the layout and color scheme of the interface. The customization unit can also provide options for the user to select functions to be used. For example, the customization unit provides an option to prioritize displaying functions frequently used by the user. The customization unit can also suggest optimal customization options based on the user's operation history. For example, the customization unit suggests optimal options based on customization options used by the user in the past. This allows the user to customize the interface, improving usability.

[0079] The document generation system further includes an evaluation unit that evaluates the quality of the generated template. The evaluation unit provides a means for evaluating the quality of the generated template. The evaluation unit evaluates, for example, the accuracy and ease of use of the template. The evaluation unit can also evaluate the aesthetic appeal of the template. For example, the evaluation unit evaluates the aesthetic appeal based on the layout and color scheme of the template. The evaluation unit can also evaluate the quality of the template based on user feedback. For example, the evaluation unit evaluates the quality of the template based on feedback provided by the user. In this way, by evaluating the quality of the generated template, it is possible to provide a high-quality template.

[0080] The conversion unit can analyze the contents of each file and represent elements such as text, images, and tables in XML format. The conversion unit can, for example, use text analysis technology to analyze the contents of the file and represent them in XML format. For example, the conversion unit can analyze the contents of a text file in detail and represent elements such as text, images, and tables using XML tags. The conversion unit can also analyze image files using image analysis technology and represent them in XML format. For example, the conversion unit can analyze the contents of an image file and represent the position and size of the image using XML tags. The conversion unit can also analyze audio files using audio analysis technology and represent them in XML format. For example, the conversion unit can analyze the contents of an audio file and represent the start and end times of the audio using XML tags. In this way, by analyzing the contents of the file in detail and representing them in XML format, data reusability is improved.

[0081] The generation unit can automatically generate a slide layout and a document structure based on a theme. The generation unit automatically generates, for example, a slide layout and a document structure based on a specific theme. For example, the generation unit automatically generates a slide layout based on the theme of a business presentation. The generation unit can also automatically generate a document structure based on the theme of an academic paper. For example, the generation unit automatically generates a document layout based on the theme of marketing materials. This allows documents to be created efficiently by automatically generating a layout and structure based on a specific theme.

[0082] The learning unit can propose layouts and structures based on data from past slides and documents. For example, the learning unit proposes optimal layouts and structures based on data from past slides and documents. For example, the learning unit proposes optimal slide layouts based on data from past business presentations. The learning unit can also propose optimal document structures based on data from past academic papers. For example, the learning unit proposes optimal document layouts based on data from past marketing materials. In this way, by proposing optimal layouts and structures based on past data, the consistency and quality of documents are improved.

[0083] The collection unit can analyze the user's emotions and adjust the timing of file collection based on the analyzed user's emotions. For example, if the user is feeling stressed, the collection unit reduces the frequency of file collection to reduce the user's burden. The collection unit can also increase the frequency of file collection to efficiently collect data if the user is relaxed. For example, if the user is in a hurry, the collection unit can immediately start file collection and quickly collect data. This reduces the user's burden by adjusting the timing of file collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0084] The collection unit can analyze the user's past file collection history and select a collection method. For example, the collection unit prioritizes collection of file formats that the user has frequently collected in the past. The collection unit can also suggest the optimal method by referring to the collection methods (manual, scheduled, etc.) used by the user in the past. For example, the collection unit can set collection to be performed during a specific time period based on the user's past collection history. This allows the optimal collection method to be selected by analyzing the past collection history.

[0085] When collecting files, the collection unit can filter the files based on the user's current project or area of ​​interest. For example, the collection unit collects only files related to the user's current project. The collection unit can also preferentially collect highly relevant files based on the user's area of ​​interest. For example, the collection unit filters and collects relevant files based on keywords specified by the user. This allows highly relevant files to be collected efficiently by filtering based on the user's current project or area of ​​interest.

[0086] When collecting files, the collection unit can select a collection means according to the user's input method. For example, when the user uses voice input, the collection unit collects files using voice recognition technology. Also, when the user uses text input, the collection unit can collect files using text analysis technology. For example, when the user uses image input, the collection unit collects files using image recognition technology. This allows files to be collected efficiently by selecting the optimal collection means according to the user's input method.

[0087] The collection unit can analyze the user's emotions and determine the priority of files to be collected based on the analyzed user's emotions. For example, if the user is feeling stressed, the collection unit postpones files of low importance. The collection unit can also prioritize collecting files of high importance when the user is relaxed. For example, if the user is in a hurry, the collection unit immediately collects the most important files. In this way, by determining the priority of files to be collected according to the user's emotions, important files can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or 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.

[0088] When collecting files, the collection unit can prioritize collecting highly relevant files based on the user's geographical location information. For example, when the user is in a particular office, the collection unit prioritizes collecting files related to the office. Furthermore, when the user is on a business trip, the collection unit can also prioritize collecting files related to the business trip destination. For example, when the user is at home, the collection unit prioritizes collecting files related to work at home. In this way, highly relevant files can be collected efficiently by taking geographical location information into consideration.

[0089] When collecting files, the collection unit can analyze the user's social media activities and collect related files. For example, the collection unit collects files shared by the user on social media. The collection unit can also analyze the content posted by the user on social media to collect related files. For example, the collection unit collects related files by referring to the activities of the user's friends on social media. This makes it possible to efficiently collect highly related files by analyzing social media activities.

[0090] When collecting files, the collection unit can customize the collection method based on the user's past feedback. For example, the collection unit optimizes the collection method based on feedback provided by the user in the past. The collection unit can also preferentially use a specific collection method based on the user's past feedback. For example, the collection unit adjusts the collection frequency and timing by reflecting the user's feedback. In this way, the collection method can be optimized by reflecting the past feedback.

[0091] The conversion unit can analyze the user's emotions and adjust the way the conversion is expressed based on the analyzed user's emotions. For example, if the user is feeling stressed, the conversion unit can perform the conversion in a simple XML format. Alternatively, if the user is relaxed, the conversion unit can perform the conversion in a detailed XML format. For example, if the user is in a hurry, the conversion unit can quickly perform the conversion and provide the minimum necessary information in XML format. This allows the conversion to meet the user's needs by adjusting the way the conversion is expressed depending on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0092] During conversion, the conversion unit can adjust the level of detail of the conversion based on the priority of the file. For example, the conversion unit converts files of high importance into a detailed XML format. The conversion unit can also convert files of low importance into a simplified XML format. For example, the conversion unit gradually adjusts the level of detail of the conversion depending on the importance of the file. This allows for efficient conversion by adjusting the level of detail of the conversion depending on the importance of the file.

[0093] The conversion unit can apply different conversion algorithms depending on the file type during conversion. For example, the conversion unit applies a text analysis algorithm to a text file for conversion. The conversion unit can also apply an image recognition algorithm to an image file for conversion. For example, the conversion unit applies a spreadsheet analysis algorithm to convert a spreadsheet file. This improves conversion accuracy by applying the optimal conversion algorithm depending on the file category.

[0094] During conversion, the conversion unit can improve the accuracy of the conversion based on the user's past conversion results. For example, the conversion unit optimizes the conversion algorithm based on the results of files the user has converted in the past. The conversion unit can also learn specific conversion patterns from the user's past conversion results to improve accuracy. For example, the conversion unit adjusts the conversion algorithm by reflecting user feedback. This improves the accuracy of the conversion by referring to past conversion results.

[0095] The conversion unit can analyze the user's emotions and adjust the length of the conversion based on the analyzed user's emotions. For example, if the user is in a hurry, the conversion unit converts the text into a short, to-the-point XML format. Alternatively, if the user is relaxed, the conversion unit can convert the text into a longer XML format that includes detailed explanations. For example, if the user is excited, the conversion unit converts the text into an XML format that adds visually stimulating effects. This allows the conversion to be tailored to the user's needs by adjusting the length of the conversion according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] During conversion, the conversion unit can determine the conversion priority based on the submission date and time of the file. For example, the conversion unit prioritizes the conversion of files with an upcoming submission deadline. The conversion unit can also postpone files with a distant submission deadline. For example, the conversion unit gradually adjusts the conversion priority according to the submission time. This allows conversion to be performed efficiently by determining the conversion priority based on the submission time.

[0097] During conversion, the conversion unit can adjust the conversion order based on the relevance of the files. For example, the conversion unit preferentially converts highly relevant files. The conversion unit can also postpone files with low relevance. For example, the conversion unit adjusts the conversion order in stages according to the relevance of the files. This allows for efficient conversion by adjusting the conversion order based on the relevance of the files.

[0098] During conversion, the conversion unit can adjust the use of technical terminology in the conversion depending on the user's level of knowledge. For example, if the user has specialized knowledge, the conversion unit converts the data into an XML format that uses a lot of technical terminology. Alternatively, if the user does not have specialized knowledge, the conversion unit can convert the data into an XML format that uses simpler terminology. For example, the conversion unit gradually adjusts the use of technical terminology in the conversion depending on the user's level of expertise. This allows for easy-to-understand conversion by adjusting the use of technical terminology depending on the user's level of expertise.

[0099] The learning unit can analyze the user's emotions and select training data based on the analyzed user's emotions. For example, if the user is feeling stressed, the learning unit can perform training using a simple data set. Also, if the user is relaxed, the learning unit can perform training using a detailed data set. For example, if the user is in a hurry, the learning unit selects a data set that allows for quick completion of training. This enables efficient training by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0100] During learning, the learning unit can optimize the learning algorithm based on past learning data. For example, the learning unit adjusts the parameters of the learning algorithm based on past learning data. The learning unit can also analyze past learning results and select the optimal learning algorithm. For example, the learning unit learns specific patterns from past learning data and optimizes the algorithm. In this way, the accuracy of the learning algorithm is improved by referring to past learning data.

[0101] During learning, the learning unit can update the learning data based on user feedback. For example, the learning unit updates the learning data based on feedback provided by the user. The learning unit can also perform learning by adding a specific data set based on the user feedback. For example, the learning unit reflects the user feedback to improve the quality of the learning data. In this way, the quality of the learning data is improved by reflecting the user feedback.

[0102] During training, the learning unit can integrate information from different data sources to enrich the training data. For example, the learning unit collects information from an internal database and integrates it into the training data. The learning unit can also collect information from external public data sources and integrate it into the training data. For example, the learning unit integrates data provided by a user into the training data to enrich the dataset. This increases the diversity of the training data by integrating information from different data sources.

[0103] The learning unit can analyze the user's emotions and adjust the frequency of learning based on the analyzed user emotions. For example, if the user is feeling stressed, the learning unit reduces the frequency of learning to reduce the burden. The learning unit can also increase the frequency of learning to efficiently learn data if the user is relaxed. For example, if the user is in a hurry, the learning unit temporarily increases the frequency of learning to quickly complete the learning. This enables efficient learning by adjusting the frequency of learning according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0104] During learning, the learning unit can weight the learning data based on the submission date and time of the file. For example, the learning unit prioritizes learning of data of files with an upcoming submission deadline. The learning unit can also lower the weighting of data of files with a distant submission deadline. For example, the learning unit gradually adjusts the weighting of the learning data depending on the submission date. This allows for efficient learning by weighting the learning data based on the submission date.

[0105] During learning, the learning unit can analyze fluctuations in the user's purchasing history and adjust the update frequency of the learning data. For example, if the user's purchasing history fluctuates frequently, the learning unit can increase the update frequency of the learning data. Also, if the user's purchasing history is stable, the learning unit can decrease the update frequency of the learning data. For example, the learning unit gradually adjusts the update frequency of the learning data according to fluctuations in the user's purchasing history. This enables efficient learning by adjusting the update frequency of the learning data according to fluctuations in the purchasing history.

[0106] During learning, the learning unit can adjust the learning algorithm based on the user's past feedback. For example, the learning unit adjusts the parameters of the learning algorithm based on the user's past feedback. The learning unit can also select and optimize a specific algorithm based on the user's past feedback. For example, the learning unit reflects the user's feedback to improve the accuracy of the learning algorithm. In this way, the accuracy of the learning algorithm is improved by reflecting the past feedback.

[0107] The generation unit can analyze the user's emotions and adjust the expression method of the generated template based on the analyzed user's emotions. For example, if the user is feeling stressed, the generation unit generates a simple template. The generation unit can also generate a detailed template if the user is relaxed. For example, if the user is in a hurry, the generation unit provides a template that can be generated quickly. In this way, by adjusting the expression method of the template according to the user's emotions, a template that meets the user's needs is generated. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0108] The generation unit can adjust the level of detail of the generation based on the priority of the file at the time of generation. For example, the generation unit generates a detailed template for a file with high importance. The generation unit can also generate a simplified template for a file with low importance. For example, the generation unit adjusts the level of detail of the generation in stages according to the importance of the file. In this way, templates can be generated efficiently by adjusting the level of detail of the generation according to the importance of the file.

[0109] The generation unit can apply different generation algorithms depending on the type of file during generation. For example, the generation unit applies a generation algorithm for presentations to slides for presentations. The generation unit can also apply a generation algorithm for reports to documents for reports. For example, the generation unit applies a generation algorithm for notes to documents for notes. This improves the accuracy of generation by applying the optimal generation algorithm depending on the file category.

[0110] During generation, the generation unit can improve the accuracy of generation based on the user's past generation results. For example, the generation unit optimizes the generation algorithm based on the results of templates generated by the user in the past. The generation unit can also learn specific generation patterns from the user's past generation results to improve accuracy. For example, the generation unit adjusts the generation algorithm by reflecting user feedback. This improves the accuracy of generation by referring to past generation results.

[0111] The generation unit can analyze the user's emotions and adjust the length of the template to be generated based on the analyzed user's emotions. For example, if the user is in a hurry, the generation unit generates a short, to-the-point template. Alternatively, if the user is relaxed, the generation unit can generate a longer template with detailed explanations. For example, if the user is excited, the generation unit generates a template with a visually stimulating effect. In this way, by adjusting the length of the template according to the user's emotions, a template that meets the user's needs is generated. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0112] The generation unit can determine the generation priority based on the submission date and time of the file at the time of generation. For example, the generation unit generates a template with priority for a file whose submission deadline is approaching. The generation unit can also postpone the generation of a template for a file whose submission deadline is far away. For example, the generation unit adjusts the generation priority in stages depending on the submission time. In this way, templates can be generated efficiently by determining the generation priority based on the submission time.

[0113] The generation unit can adjust the order of generation based on the relevance of the files during generation. For example, the generation unit generates templates for highly related files with priority. The generation unit can also postpone the generation of templates for less related files. For example, the generation unit adjusts the order of generation in stages according to the relevance of the files. In this way, templates can be generated efficiently by adjusting the order of generation based on the relevance of the files.

[0114] The generation unit can adjust the use of technical terminology in the generation process according to the user's level of knowledge at the time of generation. For example, if the user has specialized knowledge, the generation unit generates a template that uses a lot of technical terminology. Furthermore, if the user does not have specialized knowledge, the generation unit can also generate a template that uses simple terminology. For example, the generation unit gradually adjusts the use of technical terminology in the generation process according to the user's level of expertise. In this way, by adjusting the use of technical terminology according to the user's level of expertise, a template that is easy to understand is generated.

[0115] The customization unit can analyze the user's emotions and adjust the customization method based on the analyzed user's emotions. For example, the customization unit can provide simple customization options when the user is stressed. The customization unit can also provide detailed customization options when the user is relaxed. For example, the customization unit can provide a quick customization option when the user is in a hurry. This allows customization that meets the user's needs by adjusting the customization method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0116] During customization, the customization unit can select a customization method based on the user's past customization history. For example, the customization unit preferentially suggests customization options that the user has used in the past. The customization unit can also learn specific patterns from the user's past customization history and suggest the optimal method. For example, the customization unit optimizes the customization options based on user feedback. This allows the optimal customization method to be selected by referring to the past customization history.

[0117] During customization, the customization unit can customize the customization means based on the user's project. For example, the customization unit provides customization options related to the user's current project. The customization unit can also suggest the optimal customization method depending on the progress of the user's project. For example, the customization unit adjusts the customization options based on the content of the user's project. This allows optimal customization for the project by adjusting the customization means based on the current project.

[0118] The customization unit can analyze the user's emotions and determine the priority of customization based on the analyzed user's emotions. For example, if the user is feeling stressed, the customization unit postpones customization of less importance. Furthermore, if the user is relaxed, the customization unit can also prioritize customization of greater importance. For example, if the user is in a hurry, the customization unit immediately performs the most important customization. In this way, by determining the priority of customization according to the user's emotions, it is possible to prioritize important customization. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0119] During customization, the customization unit can select a customization method based on the user's geographic location information. For example, if the user is in a particular office, the customization unit provides customization options related to the office. Furthermore, if the user is on a business trip, the customization unit can provide customization options related to the destination of the business trip. For example, if the user is at home, the customization unit provides customization options related to working from home. This allows the optimal customization method to be selected by taking the geographic location information into consideration.

[0120] During customization, the customization unit can analyze the user's social media activity to suggest customization methods. For example, the customization unit can suggest customization options based on information shared by the user on social media. The customization unit can also analyze the content of the user's social media posts to suggest related customization options. For example, the customization unit can suggest customization options based on the activity of the user's friends on social media. In this way, highly relevant customization methods can be suggested by analyzing social media activity.

[0121] The evaluation unit can analyze the user's emotions and adjust the evaluation method based on the analyzed user's emotions. For example, if the user is feeling stressed, the evaluation unit can provide a simple evaluation method. The evaluation unit can also provide a detailed evaluation method if the user is relaxed. For example, if the user is in a hurry, the evaluation unit can provide a method that allows for quick evaluation. This allows the evaluation method to be adjusted according to the user's emotions, making it possible to provide an evaluation that meets the user's needs. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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.

[0122] When performing an evaluation, the evaluation unit can select an evaluation method based on the user's past evaluation history. For example, the evaluation unit preferentially suggests evaluation methods that the user has used in the past. The evaluation unit can also learn specific patterns from the user's past evaluation history and suggest the optimal method. For example, the evaluation unit optimizes the evaluation method based on user feedback. This allows the optimal evaluation method to be selected by referring to the past evaluation history.

[0123] The evaluation unit can customize the evaluation method based on the user's project during evaluation. For example, the evaluation unit provides an evaluation method related to the user's current project. The evaluation unit can also suggest an optimal evaluation method depending on the progress of the user's project. For example, the evaluation unit adjusts the evaluation method based on the content of the user's project. This allows for optimal evaluation of the project by adjusting the evaluation method based on the current project.

[0124] The evaluation unit can analyze the user's emotions and determine the priority of evaluations based on the analyzed user's emotions. For example, if the user is feeling stressed, the evaluation unit postpones evaluations with low importance. Furthermore, if the user is relaxed, the evaluation unit can also prioritize evaluations with high importance. For example, if the user is in a hurry, the evaluation unit immediately performs the most important evaluation. In this way, by determining the priority of evaluations according to the user's emotions, important evaluations can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0125] The evaluation unit can select an evaluation method based on the user's geographical location information during evaluation. For example, if the user is in a particular office, the evaluation unit provides an evaluation method related to the office. Furthermore, if the user is on a business trip, the evaluation unit can also provide an evaluation method related to the business trip destination. For example, if the user is at home, the evaluation unit provides an evaluation method related to working from home. This allows the optimal evaluation method to be selected by taking the geographical location information into consideration.

[0126] The evaluation unit can analyze the user's social media activity and provide relevant information when evaluating. For example, the evaluation unit can suggest an evaluation method based on information shared by the user on social media. The evaluation unit can also analyze the content of the user's social media posts and suggest a relevant evaluation method. For example, the evaluation unit can suggest an evaluation method based on the activity of the user's friends on social media. In this way, by analyzing social media activity, it is possible to suggest a highly relevant evaluation method. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, conversion unit, learning unit, generation unit, and customization unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects all .pptx and .docx files within the company. The conversion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected files and converts them to XML format. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and learns the converted data. The generation unit is implemented, for example, by the control unit 46A of the smart device 14 and automatically generates templates based on the learned data. The customization unit is implemented, for example, by the control unit 46A of the smart device 14 and provides a means for the user to customize the interface. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of the generated templates. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, conversion unit, learning unit, generation unit, and customization unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects all .pptx and .docx files within the company. The conversion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected files and converts them to XML format. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and learns the converted data. The generation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and automatically generates templates based on the learned data. The customization unit is implemented, for example, by the control unit 46A of the smart glasses 214 and provides a means for the user to customize the interface. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of the generated templates. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, conversion unit, learning unit, generation unit, and customization unit, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the headset-type terminal 314 and collects all .pptx and .docx files within the company. The conversion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected files and converts them to XML format. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and learns the converted data. The generation unit is implemented, for example, by the control unit 46A of the headset-type terminal 314 and automatically generates templates based on the learned data. The customization unit is implemented, for example, by the control unit 46A of the headset-type terminal 314 and provides a means for the user to customize the interface. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of the generated templates. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, conversion unit, learning unit, generation unit, and customization unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects all .pptx and .docx files within the company. The conversion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected files and converts them to XML format. The learning unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and learns the converted data. The generation unit is implemented, for example, by the control unit 46A of the robot 414 and automatically generates templates based on the learned data. The customization unit is implemented, for example, by the control unit 46A of the robot 414 and provides a means for the user to customize the interface. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and evaluates the quality of the generated templates.

[0127] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0128] The collection unit can analyze the user's emotions and adjust the timing of file collection based on the analyzed user emotions. For example, if the user is feeling stressed, the frequency of file collection can be reduced to reduce the user's burden. Also, if the user is relaxed, the frequency of file collection can be increased to efficiently collect data. For example, if the user is in a hurry, file collection can be started immediately to quickly collect data. This reduces the user's burden by adjusting the timing of file collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0129] The collection unit can analyze the user's past file collection history and select a collection method. For example, it can prioritize collection of file types that the user has frequently collected in the past. The collection unit can also suggest the optimal method by referring to the collection methods (manual, scheduled, etc.) that the user has used in the past. For example, it can set collection to occur during a specific time period based on the user's past collection history. This allows the optimal collection method to be selected by analyzing the past collection history.

[0130] When collecting files, the collection unit can filter the files based on the user's current project or area of ​​interest. For example, it can collect only files related to the project the user is currently working on. It can also preferentially collect highly relevant files based on the user's area of ​​interest. For example, it can filter and collect relevant files based on keywords specified by the user. This allows highly relevant files to be collected efficiently by filtering based on the current project or area of ​​interest.

[0131] When collecting files, the collection unit can select a collection means according to the user's input method. For example, if the user uses voice input, file collection can be performed using voice recognition technology. Also, if the user uses text input, file collection can be performed using text analysis technology. For example, if the user uses image input, file collection can be performed using image recognition technology. This allows files to be collected efficiently by selecting the optimal collection means according to the user's input method.

[0132] The collection unit can analyze the user's emotions and determine the priority of files to be collected based on the analyzed user's emotions. For example, if the user is feeling stressed, less important files can be put off until later. Also, if the user is relaxed, more important files can be collected first. For example, if the user is in a hurry, the most important files can be collected immediately. In this way, by determining the priority of files to be collected according to the user's emotions, important files can be collected first. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or 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.

[0133] The conversion unit can analyze the user's emotions and adjust the way the conversion is expressed based on the analyzed user's emotions. For example, if the user is feeling stressed, the conversion can be performed in a simple XML format. On the other hand, if the user is relaxed, the conversion can be performed in a detailed XML format. For example, if the user is in a hurry, the conversion can be performed quickly and the minimum necessary information can be provided in XML format. This allows the conversion to meet the user's needs by adjusting the way the conversion is expressed depending on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0134] During conversion, the conversion unit can adjust the level of detail of the conversion based on the priority of the file. For example, a file with high importance can be converted in a detailed XML format. On the other hand, a file with low importance can be converted in a simplified XML format. For example, the level of detail of the conversion can be adjusted in stages depending on the importance of the file. This allows for efficient conversion by adjusting the level of detail of the conversion depending on the importance of the file.

[0135] The conversion unit can apply different conversion algorithms depending on the file type during conversion. For example, a text analysis algorithm can be applied to a text file for conversion. An image recognition algorithm can also be applied to an image file for conversion. For example, a spreadsheet file can be converted by applying a table analysis algorithm. This improves the accuracy of conversion by applying the most appropriate conversion algorithm depending on the file category.

[0136] During conversion, the conversion unit can improve the accuracy of the conversion based on the user's past conversion results. For example, the conversion algorithm can be optimized based on the results of files the user has converted in the past. It can also learn specific conversion patterns from the user's past conversion results to improve accuracy. For example, the conversion algorithm can be adjusted based on user feedback. This improves the accuracy of the conversion by referring to past conversion results.

[0137] The conversion unit can analyze the user's emotions and adjust the length of the conversion based on the analyzed user's emotions. For example, if the user is in a hurry, the conversion can be in a short, to-the-point XML format. Alternatively, if the user is relaxed, the conversion can be in a longer XML format with detailed explanations. For example, if the user is excited, the conversion can be in an XML format with visually stimulating effects. This allows the conversion to meet the user's needs by adjusting the length of the conversion according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0138] The processing flow of the second embodiment will be briefly explained below.

[0139] Step 1: The collection department collects files. Files include text files, image files, audio files, etc. The collection department collects all .pptx and .docx files within the company. It can also collect files from remote servers via the network. Step 2: The conversion unit analyzes the files collected by the collection unit and converts them into XML format. The conversion unit analyzes the contents of the files using text analysis technology and expresses them in XML format. It can also analyze image files using image analysis technology and express them in XML format. It can also analyze audio files using audio analysis technology and express them in XML format. Step 3: The learning unit learns from the data converted by the conversion unit. The learning unit uses machine learning algorithms to learn from the data and propose optimal layouts and structures. It can also learn from data on past slides and documents. Step 4: The generator automatically generates templates based on the data learned by the learning unit. The generator automatically generates slide layouts and document structures based on specific themes. It can also generate customized templates based on user instructions.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0145] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0176] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0177] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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."

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] [Explanation of symbols]

[0212] 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 collection unit that collects files; a conversion unit that analyzes the files collected by the collection unit and converts them into an XML format; a learning unit that learns the data converted by the conversion unit; a generation unit that automatically generates a template based on the data learned by the learning unit; Equipped with A system characterized by:

2. A customization section is provided that provides a user-customizable interface.

2. The system of claim 1.

3. Equipped with an evaluation unit that evaluates the quality of the generated template 2. The system of claim 1.

4. The conversion unit The contents of each file are analyzed and elements such as text, images, and tables are represented in XML format.

2. The system of claim 1.

5. The generation unit Automatically generate slide layouts and document structures based on themes 2. The system of claim 1.

6. The learning unit Propose layouts and structures based on past slides and document data 2. The system of claim 1.

7. The collecting unit Analyze user sentiment and adjust file collection timing based on the analyzed user sentiment.

2. The system of claim 1.

8. The collecting unit Analyze the user's past file collection history and select the collection method 2. The system of claim 1.

9. The collecting unit Filter files as they are collected based on your current project or area of ​​interest 2. The system of claim 1.

10. The collecting unit When collecting files, select the collection method according to the user's input method 2. The system of claim 1.

Images