system

Abstract

Provide a system. [Solution] a means for collecting metadata for a new file when the user creates the file; means for transmitting the collected metadata to a server; a means for the server to learn the user's past file naming habits and generate recommended file names; means for transmitting the generated suggested file name to a terminal and displaying it to a user; means for saving the file with the file name determined by the user; A system including:

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] In conventional file naming, users are free to choose their own file names, which often results in inconsistent file names even within the same user. This creates the problem of later file search and management taking time and effort, resulting in reduced work efficiency. Furthermore, while it is possible to manually establish uniform file naming rules, enforcing compliance with them is difficult. Given this background, there has been a demand for a system that can automatically learn users' naming habits and recommend appropriately uniform file names. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The system includes a means for collecting metadata about a file when a user creates a new file, a means for sending the collected metadata to a server, and a means for the server to learn the user's past file naming habits and generate a recommended file name, a means for sending the generated recommended file name to a terminal and displaying it to the user, and a means for saving the file name determined by the user.

[0007] Furthermore, when the server analyzes a user's past filenames, it uses a machine learning algorithm to generate more accurate recommended filenames. The collected metadata includes the file type, creation date and time, user ID, and a summary of the initial contents, providing the information needed to generate a filename appropriately.

[0008] "Metadata" is additional information about a file, including, for example, the file type, creation date and time, user ID, and a summary of the initial contents.

[0009] "Server" is a central computing device that receives and sends data over the network, analyzes user naming patterns, and generates recommended filenames.

[0010] "User ID" is a unique identifier used to identify a particular user within the system.

[0011] A "machine learning algorithm" is a computational technique that learns patterns from data and makes future predictions or recommendations based on those patterns.

[0012] A "suggested file name" is a consistent file name that the server generates and suggests to the user based on the user's naming habits.

[0013] A "terminal" is a computing device that is operated by a user, communicates with a server, creates files, and saves names.

[0014] A "new file" is a digital document or data that a user creates using the system.

[0015] A "storage means" is a method or device for permanently storing a file after it has been created or named. [Brief explanation of the drawings]

[0016] [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. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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, a 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), and an APU (Accelerated Processing Unit).

[0020] 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.

[0021] 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.

[0022] 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), Bluetooth (registered trademark), etc.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] 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.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0038] First, when a user performs an operation to create a new file, the device detects the operation. For example, when a user creates a new document in word processing software. The device starts its operation as a trigger.

[0039] The device then collects metadata associated with the new file, including the user ID, the current date and time, the file type, and a summary of the initial contents, and sends the collected metadata to the server in real time.

[0040] The server receives the metadata and then analyzes the user's naming habits by referencing past filenames stored in a database. For example, it learns how users have named files in the past (including dates, using specific keywords, etc.). A machine learning algorithm is used in the analysis to automatically extract appropriate naming patterns.

[0041] The server generates new recommended file names based on the results of its learning. The generated file names are consistent and easy to understand, conforming to the naming patterns used by the user. For example, the format is "2023_10_03_ProjectA_Report.docx."

[0042] The server then sends the generated suggested file name to the terminal. The terminal displays the received suggested file name to the user. The user can check the proposed file name and modify it if necessary. Once the user has finally decided on a file name, the terminal saves the file with that name.

[0043] As a concrete example, consider the case where a user tries to create a new report file. When the user clicks the "Create New" button on the screen, the device detects this and sends the metadata (user ID: 12345, file format: .docx, date: 2023-10-03) to the server. The server references past file names (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and learns the naming pattern ("date + project name + report"). The server generates a suggested file name, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the name, changes it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0044] In this way, our system automates the naming of new files, improving consistency and efficiency when users create them. Furthermore, by utilizing machine learning, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The user performs an operation to create a new file. The device detects this operation. When the user performs an operation such as clicking the "Create New" button, the device detects the trigger for creating a new file.

[0048] Step 2:

[0049] The device collects metadata for the new file. Specifically, it collects the user ID, current date and time, file type, and a summary of the initial contents. For example, the user ID might be "12345," the date and time might be "2023-10-03," the file type might be ".docx," and the initial contents might be "part of the body of a report."

[0050] Step 3:

[0051] The device sends the collected metadata to the server. The metadata is temporarily stored in the device and then sent to the server in real time. At this time, the data format is standardized and reformatted to make it easier for the server to process.

[0052] Step 4:

[0053] The server receives the metadata and retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" is "2023_09_25_ProjectA_Report.docx."

[0054] Step 5:

[0055] The server analyzes past filenames and learns user naming patterns. Machine learning algorithms are used to extract date formats, keywords, and naming conventions from filenames. For example, a pattern like "date + project name + report" might be found.

[0056] Step 6:

[0057] The server generates a new recommended file name based on the learning results. For example, "2023_10_03_ProjectA_Report.docx" is generated. This recommended file name follows the past pattern and is consistent.

[0058] Step 7:

[0059] The server generates a suggested filename and sends it to the device. The device displays the suggested filename received by the device to the user. The device allows the user to view the suggested name on the device screen.

[0060] Step 8:

[0061] The user can review the suggested file name and modify it as needed. For example, the user can change it to "2023_10_03_Project A_Weekly Report.docx." This will be the final file name.

[0062] Step 9:

[0063] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0064] Step 10:

[0065] The device sends the confirmed filename and associated metadata to the server, which adds the data to a learning database, improving the accuracy of future filename recommendations.

[0066] Example 1

[0067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0068] In conventional systems, when users create new files, the naming of files relies on individual habits, resulting in a lack of consistency. Furthermore, since naming is not automated, users must manually choose file names, which reduces efficiency. Furthermore, the system does not adequately incorporate past naming habits, resulting in low accuracy in suggesting optimal file names for users.

[0069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0070] In this invention, the server includes means for using a generative AI model to learn a user's past file naming habits and generate recommended file names, means for collecting and transmitting metadata in real time, and means for presenting the recommended file names to the user for confirmation and modification, thereby enabling consistent and efficient file naming when the user creates a new file.

[0071] "Metadata" is attribute information related to a file, including the user ID, creation date and time, file format, and a summary of the initial contents.

[0072] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new recommended file names based on past data.

[0073] "Machine learning algorithm" refers to mathematical techniques and program processes that analyze a user's past file naming habits and generate appropriate file names.

[0074] "User ID" is identification information that uniquely identifies a user on the system.

[0075] "File format" is information indicating the type of file, such as .docx, .txt, or .pdf.

[0076] The "summary of initial contents" is data that indicates the beginning or summary of a newly created file.

[0077] "Naming habits" refers to patterns and tendencies regarding how users have named files in the past.

[0078] A "recommended file name" is a file name that the server generates based on the user's naming habits and suggests to the user.

[0079] A "terminal" is a device that a user actually operates, and includes PCs, smartphones, etc.

[0080] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0081] First, when a user creates a new file, the device detects the operation. For example, this occurs when a user creates a new document using word processing software. The hardware used can be a user device such as a PC or smartphone, and the software used can be word processing software such as Microsoft® Word.

[0082] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, creation date and time, file format, and a summary of the initial contents. The collected metadata is sent to the server in real time. The server is equipped with a database system (e.g., MySQL®) and machine learning algorithms (e.g., TENSORFLOW®) to analyze the user's naming habits.

[0083] Based on the received metadata, the server analyzes the user's naming habits by referencing past filenames stored in a database. It uses machine learning algorithms to extract patterns. For example, it learns how the user has previously named files (including dates, using specific keywords, etc.). Based on the analyzed information, the server uses a generative AI model to generate recommended filenames. For example, the server might generate a recommended filename such as "2023_10_03_ProjectA_Report.docx."

[0084] The generated suggested file name is sent from the server to the terminal and displayed to the user on the terminal. The user can check the suggested file name and modify it if necessary. Once the final file name is decided, the terminal will save the file with that name.

[0085] As a concrete example, consider a scenario in which a user attempts to create a new report file. When the user clicks the "New" button in Microsoft Word on their PC, the device detects this action, collects the following metadata (user ID: 12345, file format: .docx, date: 2023-10-03), and sends it to the server. The server then learns naming patterns by referencing past filename data (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and extracts the pattern "date + project name + report." The server then generates a suggested filename, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the proposed filename, edits it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0086] Example prompt sentence:

[0087] "User ID: 12345, Create a new file. File format: .docx, Date: 2023-10-03. Please recommend an appropriate file name based on past naming patterns."

[0088] In this way, our system automates file naming when users create new files, improving consistency and efficiency. Furthermore, by utilizing a generative AI model, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0089] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0090] Step 1:

[0091] When a user performs an operation to create a new file, the terminal detects the operation. Specifically, this corresponds to the user clicking the "Create New" button in word processing software. The input to the terminal is the user's "Create New" operation, and the output is a notification that a new file has been created.

[0092] Step 2:

[0093] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, current date and time, file type, and a summary of the initial contents. Specifically, the device obtains the user's profile information and the format information of the created file, and prepares this as structured data. The input is the information about the new file creation event, and the output is the collected metadata.

[0094] Step 3:

[0095] The collected metadata is sent to the server in real time. The device converts the metadata into an appropriate data format, such as JSON, and sends it to the server via an API call. The input is the collected metadata, and the output is a notification of successful transmission to the server.

[0096] Step 4:

[0097] The server receives the metadata sent in real time and stores it in a database. The server then analyzes the user's naming habits based on previously stored filename data. During the analysis, it applies machine learning algorithms to process the data and extract patterns in filenames used by the user in the past. The input is the newly received metadata and existing database contents, and the output is the analyzed naming patterns.

[0098] Step 5:

[0099] Based on the analysis results, the server uses a generative AI model to generate new recommended file names. The generative AI model generates file names based on natural language processing, for example, using GPT-3 (registered trademark). This generation process takes into account the patterns the user has used to name files in the past and generates the most appropriate file name. The input is the analyzed naming pattern and metadata, and the output is a recommended file name.

[0100] Step 6:

[0101] The generated suggested file name is sent from the server to the terminal. The terminal receives this suggested file name and displays it to the user. Specifically, the suggested file name is displayed in a popup window or inline editor so that the user can confirm it. The input is the suggested file name sent from the server, and the output is the name information displayed to the user.

[0102] Step 7:

[0103] The user can check the suggested file name displayed and modify it if necessary. The user then changes the file name through the terminal and confirms the final file name. Specifically, the user enters the suggested file name into an input form and, if necessary, modifies it. The input is the suggested file name and any modifications made by the user, and the output is the final confirmed file name.

[0104] Step 8:

[0105] Once the user has determined the final filename, the terminal saves the file with that name. The word processing software saves the file to disk using the name the user specified. The input is the final filename, and the output is the saved file.

[0106] (Application example 1)

[0107] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0108] Conventionally, it has not been easy to standardize the file names of work reports and inspection reports within a factory and manage them efficiently, and file naming consistency has often been lacking, especially in situations where many workers are involved. Furthermore, the time workers spend individually thinking up file names is also a factor that reduces work efficiency. There is a need to solve these problems and improve work efficiency and file management consistency.

[0109] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0110] In this invention, the server includes means for collecting metadata of a file when a user creates a new file, means for transmitting the collected metadata to the server, means for the server to learn the user's past file naming habits and generate a recommended file name, means for transmitting the generated recommended file name to a terminal and displaying it to the user, means for saving the file name determined by the user as a file, and means for the machine device to work in conjunction with the file naming system and suggest a file name based on the task, thereby reducing the burden on workers when naming new files and making it possible to maintain consistency in file names.

[0111] "User" refers to a person who uses the system to create a new file.

[0112] "New file" refers to a file that is created using the system and has never been saved.

[0113] "Metadata" refers to information related to a file, including the file type, creation date and time, user ID, summary of initial contents, and work content.

[0114] "Server" refers to a computer system that processes collected metadata, learns users' naming habits, and generates recommended filenames.

[0115] "Past file naming habits" refers to information for analyzing patterns of how a user has named files in the past.

[0116] "Suggested file name" refers to a candidate file name generated by the server that is appropriate for the user.

[0117] "Terminal" refers to a computer or smart device used by a user, which receives and displays the recommended filenames.

[0118] "Machinery" refers to machines and robots used in factories and other workplaces, and refers to devices that are linked to the file naming system.

[0119] "Task-based filenames" refer to filenames that contain information related to the specific tasks being performed on-site.

[0120] The present invention provides a system that automates the file naming of work reports and inspection reports in a factory, and realizes efficient and consistent file management. This system operates in cooperation with users, servers, terminals, and machinery used in the field.

[0121] When a user creates a new file, the device first detects the creation and collects relevant metadata, including the file type, creation date and time, user ID, initial content summary, and work details. This metadata is then sent to the server in real time.

[0122] The server receives the metadata and analyzes past file naming habits using a machine learning algorithm. Specifically, it performs feature extraction and learning to understand how users have named files in the past. Specific machine learning algorithms used in this process include the Naive Bayes model.

[0123] The server generates a recommended filename based on the analysis results. This recommended filename takes into account the user's past naming patterns and is both consistent and clear. The generated recommended filename is sent to the terminal and displayed to the user.

[0124] The user can review the proposed filename and modify it if necessary, and then a final filename is determined. The file is then saved with this finalized filename.

[0125] For example, after a quality inspection at a factory, when a worker creates a new report, the smart glasses automatically suggest the file name "2023_10_03_QualityInspection_Report.docx." The worker can then review the file name and change it to, for example, "2023_10_03_QualityInspection_WeeklyReport.docx."

[0126] To help you work with this system, we also provide the following example prompts:

[0127] "Factory quality inspection reports are named in the format YYYY_MM_DD_task_report. The file name to be generated should be YYYY_MM_DD with the current date inserted, and the task should be 'Quality Inspection'. Please generate the file name based on this."

[0128] In this way, the present invention reduces the burden on the user and realizes efficient and consistent file management.

[0129] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0130] Step 1:

[0131] The device detects when a user creates a new file. When a user creates a new work report or inspection report, the device triggers the user's action and starts operation. The metadata collected includes the file type, creation date and time, user ID, summary of the initial contents, and work content.

[0132] Step 2:

[0133] The device sends the collected metadata to the server, which receives the metadata sent from the device as input and forwards the data to the analysis platform, preparing it for analysis.

[0134] Step 3:

[0135] The server receives the submitted metadata and analyzes past file naming habits using machine learning algorithms. The input is past file names and the latest metadata, and feature extraction and data learning are used to identify file name patterns. Specific processing involves vectorization and algorithms such as the Naive Bayes model.

[0136] Step 4:

[0137] The server generates a recommended file name based on the analysis results. Using the analyzed habit data and new metadata as input, it generates a file name that follows specific rules (e.g., "2023_10_03_Quality Inspection_Report.docx"). It is important that the generated recommended file name is in a format that is easy for users to understand.

[0138] Step 5:

[0139] Sends the generated suggested filename to the terminal and displays it to the user. The input is the suggested filename generated by the server and sends it as output to the terminal, which displays it to the user, who reviews the filename.

[0140] Step 6:

[0141] The user checks the suggested file name and corrects it if necessary. The user edits the suggested file name and decides on the final file name. In this step, corrections are made directly via the user interface.

[0142] Step 7:

[0143] The terminal sends the file name confirmed by the user to the server and stores it. The confirmed file name is sent from the terminal to the server as the final input, and the server stores the confirmed name. The process is completed to ensure consistent and efficient file management.

[0144] This series of processes reduces the burden on the user and enables efficient file naming and management.

[0145] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0146] This invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules, and by combining it with an emotion engine that recognizes the user's emotions, it is possible to recommend more appropriate file names.

[0147] First, when a user creates a new file, the device detects the operation. Based on the detected operation, the device collects metadata for the new file. The collected metadata includes the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[0148] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates emotions by analyzing the user's facial recognition technology, typing speed, and typing patterns. For example, it can analyze the user's facial expressions using a camera to determine their stress level and satisfaction. It can also read emotions from the speed and rhythm of keyboard typing.

[0149] The server receives the submitted metadata and emotion information from the emotion engine. The server integrates this information and retrieves the user's past file naming data from the database. A machine learning algorithm is applied to analyze the past file names and learn the user's naming patterns.

[0150] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it can recommend a simple and easy-to-understand filename. On the other hand, if the user is in a positive state, it can suggest a detailed and specific filename. The generated recommended filenames are adapted to the user's emotional state and are more user-friendly.

[0151] The suggested filename is sent to the device, which displays it to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. The saved filename and associated metadata are sent to the server and used for the next analysis.

[0152] As a concrete example, consider the case where a user attempts to create a new presentation. As the user performs an operation, the device detects it and collects metadata and emotional data. Facial recognition technology is used to recognize that the user is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_TechnicalExplanationPresentation.pptx." This name is sent to the device and displayed to the user. The user confirms the name and, satisfied with it, saves it as is.

[0153] In this way, our system recognizes user emotions and generates appropriate recommended filenames based on those emotions, improving file management efficiency and user experience. By combining it with an emotion engine, we can provide more personalized services and increase user satisfaction.

[0154] The processing flow will be explained below.

[0155] Step 1:

[0156] The user performs an operation to create a new file. For example, the user clicks the "New" button in word processing software. The device detects this operation.

[0157] Step 2:

[0158] The device collects metadata for new files, including user ID, creation date and time, file type, and a summary of the initial contents. The device records this information in real time.

[0159] Step 3:

[0160] The device activates an emotion engine to recognize the user's emotions. For example, the device's camera can be used to recognize the user's face and analyze their facial expressions to determine their emotions. Keyboard input speed and patterns can also be analyzed to read emotions.

[0161] Step 4:

[0162] The device sends the collected metadata and emotion data to the server in a unified format.

[0163] Step 5:

[0164] The server receives the metadata and emotion data. It also retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" might be "2023_09_25_ProjectA_Report.docx."

[0165] Step 6:

[0166] The server analyzes past filenames and uses machine learning algorithms to learn user naming patterns. It extracts date formats, keywords, and naming conventions contained in filenames. For example, it might find a pattern like "date + project name + report."

[0167] Step 7:

[0168] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it recommends a simple filename like "2023_10_03_ProjectA_Report.docx." Conversely, if the user is in a positive state, it generates a detailed filename like "2023_10_03_ProjectA_ProgressReport.docx."

[0169] Step 8:

[0170] The server sends the generated suggested file name to the device. The device displays the received suggested file name to the user. The user confirms the proposed name on the device screen.

[0171] Step 9:

[0172] The user checks the suggested file name and modifies it if necessary. For example, they can change it to "2023_10_03_ProjectA_WeeklyReport.docx." Then, they confirm the modified file name.

[0173] Step 10:

[0174] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0175] Step 11:

[0176] The device sends the confirmed filename and associated metadata to the server, which adds the data to a training database that is used in subsequent analyses to improve the accuracy of filename recommendations.

[0177] Example 2

[0178] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0179] Conventional file naming systems make it difficult for users to quickly generate the file names they intended, and the time and effort required to select an appropriate file name can be a significant burden, especially when users are busy or stressed. Furthermore, inconsistent user naming patterns can make file management cumbersome. Furthermore, conventional systems are unable to suggest personalized file names that take into account the user's emotions and circumstances, resulting in a lack of improvement in the user experience.

[0180] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0181] In this invention, the server includes a means for learning a user's past file naming habits and generating recommended file names, a means for analyzing the user's past file names using a machine learning algorithm, and a means for including the file type, creation date and time, user ID, and a summary of the initial contents in the collected metadata. This allows the server to quickly and automatically generate an optimal file name that takes into account both the user's past naming habits and their current emotional state when creating a new file. This also improves file management efficiency and the user experience.

[0182] A "user" is an entity that uses this system to create and manage new files.

[0183] A "file" is a document, image, sound, or other unit of information stored in digital form.

[0184] "Metadata" is additional information that accompanies a file, specifically information that includes the user ID, creation date and time, file type, and a summary of the initial contents.

[0185] A "terminal" is an electronic device such as a computer, tablet, or smartphone that is directly operated by a user.

[0186] A "server" is a computer system that receives metadata and emotion information from terminals via a network and processes this data.

[0187] An "emotion engine" is software or hardware installed on a device that has the ability to recognize and estimate a user's emotions.

[0188] A "machine learning algorithm" is a mathematical technique that learns from past data and makes predictions and classifications for new data.

[0189] A "suggested file name" is a name for a new file that is generated by the server based on the user's past file naming habits and emotional state, and is displayed on the terminal.

[0190] This invention relates to a system that automates the naming of new files when a user creates them. This system is composed of a terminal, a server, and an emotion engine. The specific operation of the system is described below.

[0191] First, when a user creates a new file using a device, the device detects the action. For example, when a user clicks the "Create New" button on a computer, tablet, or other device. When this action is detected, the device collects metadata about the new file. The metadata includes the user ID, creation date and time, file type (e.g., .docx, .pptx), and a summary of the initial contents.

[0192] The collected metadata is sent from the device to the server in real time. At that time, the device is equipped with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine uses facial recognition technology (e.g., OpenCV) and keyboard input information. It analyzes the user's facial expressions using a camera to estimate their stress level and satisfaction. It also reads changes in the user's emotions by analyzing the speed and rhythm of keyboard input. This makes it possible to understand the emotional state of the user when creating a new file.

[0193] Meanwhile, the server receives the metadata and emotional information sent from the device. The server integrates this information and retrieves the user's past file naming data from a database. It then applies a machine learning algorithm (e.g., random forest or deep learning model) to the retrieved past data to learn the user's naming patterns. Based on this learning result, the server generates new recommended file names. The generated recommended file names are adapted to the user's emotional state and support the editing process.

[0194] For example, if a user is concentrating on creating a presentation, the server generates a detailed and specific filename, such as "2023_10_03_TechnicalExplanationPresentation.pptx." The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary.

[0195] The file is then saved with the filename determined by the user. This filename and associated metadata are then sent back to the server and used for the next analysis. This allows the system to continue learning the user's naming patterns with increasing accuracy.

[0196] Prompt Sentence Examples

[0197] "When creating a new presentation, suggest file names. Consider your past naming patterns and your current emotional state."

[0198] This invention enables automatic generation of file names that take into account the user's feelings and past naming patterns, thereby improving the efficiency of file management and the user experience.

[0199] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0200] Step 1:

[0201] The user creates a new file.

[0202] The user creates a new file using the device. The trigger is a user operation such as clicking the "Create New" button. The device detects this operation event.

[0203] Input: Create new user

[0204] Output: Notification of new event occurrence

[0205] Step 2:

[0206] Device collects metadata

[0207] When a new file creation event occurs, the device collects metadata related to the file, including the user ID, creation date and time, file type, and a summary of the initial contents.

[0208] Input: Newly created event

[0209] Output: Collected metadata (user ID, creation date, file type, summary of initial contents)

[0210] Step 3:

[0211] The device sends the metadata to the server.

[0212] The terminal sends the collected metadata to the server, which transmits the metadata to the server in real time.

[0213] Input: Collected metadata

[0214] Output: Metadata sent to the server

[0215] Step 4:

[0216] The device recognizes emotions using an emotion engine

[0217] The device uses an emotion engine to recognize the user's emotions. It analyzes the user's facial expressions with a camera, as well as the typing speed and rhythm of the keyboard, to estimate the user's emotional state (e.g., stress, concentration, satisfaction).

[0218] Input: Real-time facial expression data and keyboard input data of the user

[0219] Output: Estimated user emotion information (stress, concentration, satisfaction, etc.)

[0220] Step 5:

[0221] Send emotional information to the server

[0222] The device sends the recognized emotion information to the server, which receives the emotion information along with the metadata.

[0223] Input: Estimated emotion information

[0224] Output: Send emotional information to the server

[0225] Step 6:

[0226] The server retrieves the user's past naming data.

[0227] The server retrieves the user's past file naming data from the database based on the received metadata and emotion information.

[0228] Input: Metadata, emotional information

[0229] Output: User's past file naming data

[0230] Step 7:

[0231] The server applies machine learning algorithms to learn naming patterns.

[0232] The server applies a machine learning algorithm (e.g., random forest, deep learning model) to the user's past file naming data to learn the user's naming patterns.

[0233] Input: User's previous file naming data

[0234] Output: Learned naming pattern model

[0235] Step 8:

[0236] The server generates a suggested filename

[0237] The server generates recommended filenames based on the learned naming pattern model and current sentiment information, with appropriate format and content.

[0238] Input: Learned naming pattern model, current emotional information

[0239] Output: Suggested file name

[0240] Step 9:

[0241] Send a suggested filename to the device

[0242] The server sends the generated recommended filename to the terminal, which displays the recommended filename in real time.

[0243] Input: Suggested file name

[0244] Output: Suggested filename sent to terminal

[0245] Step 10:

[0246] The device displays a suggested filename to the user.

[0247] The device will display the received suggested filename to the user, who will be given the option to review and modify the suggested filename.

[0248] Input: Suggested file name

[0249] Output: File name displayed to the user

[0250] Step 11:

[0251] The user confirms the file name

[0252] The user reviews the proposed filename, corrects it if necessary, and confirms the final filename.

[0253] Input: The suggested file name shown

[0254] Output: Final file name

[0255] Step 12:

[0256] The device saves the file and sends the metadata to the server.

[0257] The device saves the file with the determined file name, and sends the saved file name and related metadata to the server for the next analysis.

[0258] Input: Final file name

[0259] Output: Saved files and associated metadata sent to the server

[0260] (Application example 2)

[0261] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0262] Conventional file naming systems require users to think of an appropriate file name when creating a new file, which increases the complexity of the work and reduces work efficiency, especially in workplaces that handle large amounts of data. Furthermore, recommending a uniform file name without considering the user's emotional state can lead to a poor user experience and increased stress at work. Furthermore, file management is even more important in workplaces where many files are generated, such as logistics centers, and a more efficient and appropriate file naming system is needed.

[0263] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting metadata of a file when a user creates a new file; means for transmitting the collected metadata to the server; means for the server to learn the user's past file naming habits and generate a recommended file name; means for transmitting the generated recommended file name to the terminal and displaying it to the user; means for saving the file name determined by the user as a file; means for recognizing the user's emotion; and means for generating a recommended file name based on the recognized emotion. This enables automatic recommendation of an optimal file name taking into account the user's emotional state and past naming patterns, which is expected to improve work efficiency and the user experience. Furthermore, file management can be more effectively performed at sites that handle large amounts of data, such as logistics centers.

[0264] "Metadata" is data that includes various attribute information related to a file, specifically the file type, creation date and time, user ID, and an overview of the initial contents.

[0265] The "emotion engine" is a software component that analyzes the user's emotional state, using facial recognition technology, input speed, and input patterns.

[0266] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications.

[0267] A "head-mounted display" is a display device worn by a user on the head to provide visual information, and is used, for example, in logistics centers to improve work efficiency.

[0268] "Emotion recognition" is a technology that estimates a user's emotional state from their facial expressions, movements, input speed, etc., making it possible to grasp the user's current psychological state.

[0269] "File naming habits" refers to the tendency of users to use certain criteria or patterns in naming files in the past.

[0270] A "recommended file name" is a file name that is automatically generated based on collected data and learning results and presented to the user.

[0271] A logistics center is a facility that stores, manages, and distributes goods and materials, and is a site where a large amount of data needs to be generated and managed.

[0272] This invention relates to a system that automates the naming of new files when a user creates them. This system learns the user's naming habits and recommends file names based on unified rules. In addition, it combines an emotion engine that recognizes the user's emotions to recommend more appropriate file names.

[0273] Specifically, when a user creates a new file, the device detects the operation. At this stage, the device collects metadata for the new file, including the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[0274] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates the user's emotions by analyzing facial recognition technology, typing speed, and typing patterns. For example, it uses a camera to analyze the user's facial expressions to determine stress levels and satisfaction. It can also read emotions from keyboard typing speed and typing patterns.

[0275] The server receives the submitted metadata and the emotional information from the emotion engine and integrates these pieces of information. The server then retrieves the user's past file naming data from a database and applies a machine learning algorithm to analyze past file names. Based on this learning result and the recognized emotional information, the server generates new recommended file names. Based on the emotional information, for example, it can suggest simple file names if the user is feeling stressed, and detailed file names if the user is in a positive state.

[0276] The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. This saved filename and associated metadata are sent to the server and used for the next analysis.

[0277] As a concrete example, consider the case where a worker at a logistics center tries to create new shipping data. When the worker wears a head-mounted display (HMD) and performs an operation to create a new file, the HMD detects the operation and collects metadata and emotional data. Using facial recognition technology and input pattern analysis, it is determined that the worker is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_shipment_data.csv." This name is sent to the HMD and displayed to the worker. The worker reviews the name and, satisfied with it, saves it as is.

[0278] Examples of prompts for generative AI models include:

[0279] Design a system that automatically names a new file when the user creates it. The system recommends the best filename by combining an emotion engine that recognizes the user's emotions. Please explain in detail the specific algorithmic process and the technology used.

[0280] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0281] Step 1:

[0282] The terminal detects that the user is performing an operation to create a new file.

[0283] Input: User creates a file

[0284] Output: File creation detection event

[0285] Specific operation: The device's operating system or application software detects that the user has performed a "create new file" operation and triggers an event.

[0286] Step 2:

[0287] The device collects metadata for the new file.

[0288] Input: File creation detection event

[0289] Output: Metadata (user ID, creation date, file type, summary of initial contents)

[0290] Specific operation: The device collects data using APIs and built-in functions to extract user ID, creation date and time, file type, and a summary of the initial contents from system information and file contents.

[0291] Step 3:

[0292] The terminal transmits the collected metadata and operation status to the server.

[0293] Input: Metadata

[0294] Output: A request to send data to the server

[0295] Specific operation: The terminal sends the collected metadata to the server using a network communication protocol (e.g., HTTP or HTTPS).

[0296] Step 4:

[0297] The terminal uses an emotion engine to recognize the user's emotions.

[0298] Input: User's face image, input speed, input pattern

[0299] Output: Emotion data (estimated emotional state)

[0300] Specific operation: The device's camera and sensors are used to analyze the user's facial expressions and input patterns, and the data is input into an emotion engine to estimate emotions. Emotion estimation is performed using a facial recognition library (e.g., OpenCV) and input pattern analysis algorithms.

[0301] Step 5:

[0302] The device transmits the emotion data to the server.

[0303] Input: Emotion data

[0304] Output: A request to send data to the server

[0305] Specific operation: The estimated emotion data is sent to the server using a network communication protocol.

[0306] Step 6:

[0307] The server integrates the metadata and emotion data and retrieves the user's past file naming data from a database.

[0308] Input: Metadata, emotion data

[0309] Output: Past file naming data

[0310] Specific operation: The server issues a database query to retrieve the user's past filename data and integrates it with metadata and emotion data.

[0311] Step 7:

[0312] The server applies machine learning algorithms to analyze past filenames and generate suggested filenames.

[0313] Input: Integrated data (metadata, emotion data, historical file naming data)

[0314] Output: Suggested file name

[0315] Specific operation: The server uses a machine learning model (e.g., a generative AI model) to analyze the collected data and generate optimal file names based on the results of learning the user's naming patterns.

[0316] Step 8:

[0317] The server generates a suggested filename and sends it to the device.

[0318] Input: Suggested file name

[0319] Output: Request to send data to the device

[0320] Specific operation: The generated recommended file name is sent to the terminal using a network communication protocol.

[0321] Step 9:

[0322] The terminal presents the recommended file name to the user and receives the confirmed file name.

[0323] Input: Suggested file name

[0324] Output: The confirmed file name

[0325] Specific operation: The terminal uses a GUI to display a recommended file name to the user, and if the user is satisfied, saves it as is, accepts corrections as necessary, and then confirms the final file name.

[0326] Step 10:

[0327] The device saves the file with the determined file name and sends the associated metadata to the server.

[0328] Input: Confirmed file name

[0329] Output: File save operation, data transmission request to server

[0330] Specific operation: The device saves the file with the determined file name in local storage and sends the file name and associated metadata to the server.

[0331] 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.

[0332] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0333] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0334] [Second embodiment]

[0335] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0336] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0337] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0338] 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.

[0339] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0340] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0341] 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.

[0342] 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.

[0343] 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 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.

[0344] 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.

[0345] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0346] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0347] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0348] First, when a user performs an operation to create a new file, the device detects the operation. For example, when a user creates a new document in word processing software. The device starts its operation as a trigger.

[0349] The device then collects metadata associated with the new file, including the user ID, the current date and time, the file type, and a summary of the initial contents, and sends the collected metadata to the server in real time.

[0350] The server receives the metadata and then analyzes the user's naming habits by referencing past filenames stored in a database. For example, it learns how users have named files in the past (including dates, using specific keywords, etc.). A machine learning algorithm is used in the analysis to automatically extract appropriate naming patterns.

[0351] The server generates new recommended file names based on the results of its learning. The generated file names are consistent and easy to understand, conforming to the naming patterns used by the user. For example, the format is "2023_10_03_ProjectA_Report.docx."

[0352] The server then sends the generated suggested file name to the terminal. The terminal displays the received suggested file name to the user. The user can check the proposed file name and modify it if necessary. Once the user has finally decided on a file name, the terminal saves the file with that name.

[0353] As a concrete example, consider the case where a user tries to create a new report file. When the user clicks the "Create New" button on the screen, the device detects this and sends the metadata (user ID: 12345, file format: .docx, date: 2023-10-03) to the server. The server references past file names (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and learns the naming pattern ("date + project name + report"). The server generates a suggested file name, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the name, changes it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0354] In this way, our system automates the naming of new files, improving consistency and efficiency when users create them. Furthermore, by utilizing machine learning, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0355] The processing flow will be explained below.

[0356] Step 1:

[0357] The user performs an operation to create a new file. The device detects this operation. When the user performs an operation such as clicking the "Create New" button, the device detects the trigger for creating a new file.

[0358] Step 2:

[0359] The device collects metadata for the new file. Specifically, it collects the user ID, current date and time, file type, and a summary of the initial contents. For example, the user ID might be "12345," the date and time might be "2023-10-03," the file type might be ".docx," and the initial contents might be "part of the body of a report."

[0360] Step 3:

[0361] The device sends the collected metadata to the server. The metadata is temporarily stored in the device and then sent to the server in real time. At this time, the data format is standardized and reformatted to make it easier for the server to process.

[0362] Step 4:

[0363] The server receives the metadata and retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" is "2023_09_25_ProjectA_Report.docx."

[0364] Step 5:

[0365] The server analyzes past filenames and learns user naming patterns. Machine learning algorithms are used to extract date formats, keywords, and naming conventions from filenames. For example, a pattern like "date + project name + report" might be found.

[0366] Step 6:

[0367] The server generates a new recommended file name based on the learning results. For example, "2023_10_03_ProjectA_Report.docx" is generated. This recommended file name follows the past pattern and is consistent.

[0368] Step 7:

[0369] The server generates a suggested filename and sends it to the device. The device displays the suggested filename received by the device to the user. The device allows the user to view the suggested name on the device screen.

[0370] Step 8:

[0371] The user can review the suggested file name and modify it as needed. For example, the user can change it to "2023_10_03_Project A_Weekly Report.docx." This will be the final file name.

[0372] Step 9:

[0373] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0374] Step 10:

[0375] The device sends the confirmed filename and associated metadata to the server, which adds the data to a learning database, improving the accuracy of future filename recommendations.

[0376] Example 1

[0377] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0378] In conventional systems, when users create new files, the naming of files relies on individual habits, resulting in a lack of consistency. Furthermore, since naming is not automated, users must manually choose file names, which reduces efficiency. Furthermore, the system does not adequately incorporate past naming habits, resulting in low accuracy in suggesting optimal file names for users.

[0379] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0380] In this invention, the server includes means for using a generative AI model to learn a user's past file naming habits and generate recommended file names, means for collecting and transmitting metadata in real time, and means for presenting the recommended file names to the user for confirmation and modification, thereby enabling consistent and efficient file naming when the user creates a new file.

[0381] "Metadata" is attribute information related to a file, including the user ID, creation date and time, file format, and a summary of the initial contents.

[0382] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new recommended file names based on past data.

[0383] "Machine learning algorithm" refers to mathematical techniques and program processes that analyze a user's past file naming habits and generate appropriate file names.

[0384] "User ID" is identification information that uniquely identifies a user on the system.

[0385] "File format" is information indicating the type of file, such as .docx, .txt, or .pdf.

[0386] The "summary of initial contents" is data that indicates the beginning or summary of a newly created file.

[0387] "Naming habits" refers to patterns and tendencies regarding how users have named files in the past.

[0388] A "recommended file name" is a file name that the server generates based on the user's naming habits and suggests to the user.

[0389] A "terminal" is a device that a user actually operates, and includes PCs, smartphones, etc.

[0390] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0391] First, when a user creates a new file, the device detects the operation. For example, when a user creates a new document using word processing software, the hardware used can be a user device such as a PC or smartphone, and the software used can be word processing software such as Microsoft Word.

[0392] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, creation date and time, file format, and a summary of the initial contents. The collected metadata is sent to a server in real time. The server uses a database system (e.g., MySQL) and machine learning algorithms (e.g., TensorFlow) to analyze the user's naming habits.

[0393] Based on the received metadata, the server analyzes the user's naming habits by referencing past filenames stored in a database. It uses machine learning algorithms to extract patterns. For example, it learns how the user has previously named files (including dates, using specific keywords, etc.). Based on the analyzed information, the server uses a generative AI model to generate recommended filenames. For example, the server might generate a recommended filename such as "2023_10_03_ProjectA_Report.docx."

[0394] The generated suggested file name is sent from the server to the terminal and displayed to the user on the terminal. The user can check the suggested file name and modify it if necessary. Once the final file name is decided, the terminal will save the file with that name.

[0395] As a concrete example, consider a scenario in which a user attempts to create a new report file. When the user clicks the "New" button in Microsoft Word on their PC, the device detects this action, collects the following metadata (user ID: 12345, file format: .docx, date: 2023-10-03), and sends it to the server. The server then learns naming patterns by referencing past filename data (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and extracts the pattern "date + project name + report." The server then generates a suggested filename, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the proposed filename, edits it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0396] Example prompt sentence:

[0397] "User ID: 12345, Create a new file. File format: .docx, Date: 2023-10-03. Please recommend an appropriate file name based on past naming patterns."

[0398] In this way, our system automates file naming when users create new files, improving consistency and efficiency. Furthermore, by utilizing a generative AI model, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0399] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0400] Step 1:

[0401] When a user performs an operation to create a new file, the terminal detects the operation. Specifically, this corresponds to the user clicking the "Create New" button in word processing software. The input to the terminal is the user's "Create New" operation, and the output is a notification that a new file has been created.

[0402] Step 2:

[0403] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, current date and time, file type, and a summary of the initial contents. Specifically, the device obtains the user's profile information and the format information of the created file, and prepares this as structured data. The input is the information about the new file creation event, and the output is the collected metadata.

[0404] Step 3:

[0405] The collected metadata is sent to the server in real time. The device converts the metadata into an appropriate data format, such as JSON, and sends it to the server via an API call. The input is the collected metadata, and the output is a notification of successful transmission to the server.

[0406] Step 4:

[0407] The server receives the metadata sent in real time and stores it in a database. The server then analyzes the user's naming habits based on previously stored filename data. During the analysis, it applies machine learning algorithms to process the data and extract patterns in filenames used by the user in the past. The input is the newly received metadata and existing database contents, and the output is the analyzed naming patterns.

[0408] Step 5:

[0409] Based on the analysis results, the server uses a generative AI model to generate new recommended file names. The generative AI model generates file names based on natural language processing, for example, using GPT-3. This generation process takes into account the patterns the user has used to name files in the past and generates the most appropriate file name. The input is the analyzed naming pattern and metadata, and the output is the recommended file name.

[0410] Step 6:

[0411] The generated suggested file name is sent from the server to the terminal. The terminal receives this suggested file name and displays it to the user. Specifically, the suggested file name is displayed in a popup window or inline editor so that the user can confirm it. The input is the suggested file name sent from the server, and the output is the name information displayed to the user.

[0412] Step 7:

[0413] The user can check the suggested file name displayed and modify it if necessary. The user then changes the file name through the terminal and confirms the final file name. Specifically, the user enters the suggested file name into an input form and, if necessary, modifies it. The input is the suggested file name and any modifications made by the user, and the output is the final confirmed file name.

[0414] Step 8:

[0415] Once the user has determined the final filename, the terminal saves the file with that name. The word processing software saves the file to disk using the name the user specified. The input is the final filename, and the output is the saved file.

[0416] (Application example 1)

[0417] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0418] Conventionally, it has not been easy to standardize the file names of work reports and inspection reports within a factory and manage them efficiently, and file naming consistency has often been lacking, especially in situations where many workers are involved. Furthermore, the time workers spend individually thinking up file names is also a factor that reduces work efficiency. There is a need to solve these problems and improve work efficiency and file management consistency.

[0419] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0420] In this invention, the server includes means for collecting metadata of a file when a user creates a new file, means for transmitting the collected metadata to the server, means for the server to learn the user's past file naming habits and generate a recommended file name, means for transmitting the generated recommended file name to a terminal and displaying it to the user, means for saving the file name determined by the user as a file, and means for the machine device to work in conjunction with the file naming system and suggest a file name based on the task, thereby reducing the burden on workers when naming new files and making it possible to maintain consistency in file names.

[0421] "User" refers to a person who uses the system to create a new file.

[0422] "New file" refers to a file that is created using the system and has never been saved.

[0423] "Metadata" refers to information related to a file, including the file type, creation date and time, user ID, summary of initial contents, and work content.

[0424] "Server" refers to a computer system that processes collected metadata, learns users' naming habits, and generates recommended filenames.

[0425] "Past file naming habits" refers to information for analyzing patterns of how a user has named files in the past.

[0426] "Suggested file name" refers to a candidate file name generated by the server that is appropriate for the user.

[0427] "Terminal" refers to a computer or smart device used by a user, which receives and displays the recommended filenames.

[0428] "Machinery" refers to machines and robots used in factories and other workplaces, and refers to devices that are linked to the file naming system.

[0429] "Task-based filenames" refer to filenames that contain information related to the specific tasks being performed on-site.

[0430] The present invention provides a system that automates the file naming of work reports and inspection reports in a factory, and realizes efficient and consistent file management. This system operates in cooperation with users, servers, terminals, and machinery used in the field.

[0431] When a user creates a new file, the device first detects the creation and collects relevant metadata, including the file type, creation date and time, user ID, initial content summary, and work details. This metadata is then sent to the server in real time.

[0432] The server receives the metadata and analyzes past file naming habits using a machine learning algorithm. Specifically, it performs feature extraction and learning to understand how users have named files in the past. Specific machine learning algorithms used in this process include the Naive Bayes model.

[0433] The server generates a recommended filename based on the analysis results. This recommended filename takes into account the user's past naming patterns and is both consistent and clear. The generated recommended filename is sent to the terminal and displayed to the user.

[0434] The user can review the proposed filename and modify it if necessary, and then a final filename is determined. The file is then saved with this finalized filename.

[0435] For example, after a quality inspection at a factory, when a worker creates a new report, the smart glasses automatically suggest the file name "2023_10_03_QualityInspection_Report.docx." The worker can then review the file name and change it to, for example, "2023_10_03_QualityInspection_WeeklyReport.docx."

[0436] To help you work with this system, we also provide the following example prompts:

[0437] "Factory quality inspection reports are named in the format YYYY_MM_DD_task_report. The file name to be generated should be YYYY_MM_DD with the current date inserted, and the task should be 'Quality Inspection'. Please generate the file name based on this."

[0438] In this way, the present invention reduces the burden on the user and realizes efficient and consistent file management.

[0439] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0440] Step 1:

[0441] The device detects when a user creates a new file. When a user creates a new work report or inspection report, the device triggers the user's action and starts operation. The metadata collected includes the file type, creation date and time, user ID, summary of the initial contents, and work content.

[0442] Step 2:

[0443] The device sends the collected metadata to the server, which receives the metadata sent from the device as input and forwards the data to the analysis platform, preparing it for analysis.

[0444] Step 3:

[0445] The server receives the submitted metadata and analyzes past file naming habits using machine learning algorithms. The input is past file names and the latest metadata, and feature extraction and data learning are used to identify file name patterns. Specific processing involves vectorization and algorithms such as the Naive Bayes model.

[0446] Step 4:

[0447] The server generates a recommended file name based on the analysis results. Using the analyzed habit data and new metadata as input, it generates a file name that follows specific rules (e.g., "2023_10_03_Quality Inspection_Report.docx"). It is important that the generated recommended file name is in a format that is easy for users to understand.

[0448] Step 5:

[0449] Sends the generated suggested filename to the terminal and displays it to the user. The input is the suggested filename generated by the server and sends it as output to the terminal, which displays it to the user, who reviews the filename.

[0450] Step 6:

[0451] The user checks the suggested file name and corrects it if necessary. The user edits the suggested file name and decides on the final file name. In this step, corrections are made directly via the user interface.

[0452] Step 7:

[0453] The terminal sends the file name confirmed by the user to the server and stores it. The confirmed file name is sent from the terminal to the server as the final input, and the server stores the confirmed name. The process is completed to ensure consistent and efficient file management.

[0454] This series of processes reduces the burden on the user and enables efficient file naming and management.

[0455] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0456] This invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules, and by combining it with an emotion engine that recognizes the user's emotions, it is possible to recommend more appropriate file names.

[0457] First, when a user creates a new file, the device detects the operation. Based on the detected operation, the device collects metadata for the new file. The collected metadata includes the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[0458] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates emotions by analyzing the user's facial recognition technology, typing speed, and typing patterns. For example, it can analyze the user's facial expressions using a camera to determine their stress level and satisfaction. It can also read emotions from the speed and rhythm of keyboard typing.

[0459] The server receives the submitted metadata and emotion information from the emotion engine. The server integrates this information and retrieves the user's past file naming data from the database. A machine learning algorithm is applied to analyze the past file names and learn the user's naming patterns.

[0460] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it can recommend a simple and easy-to-understand filename. On the other hand, if the user is in a positive state, it can suggest a detailed and specific filename. The generated recommended filenames are adapted to the user's emotional state and are more user-friendly.

[0461] The suggested filename is sent to the device, which displays it to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. The saved filename and associated metadata are sent to the server and used for the next analysis.

[0462] As a concrete example, consider the case where a user attempts to create a new presentation. As the user performs an operation, the device detects it and collects metadata and emotional data. Facial recognition technology is used to recognize that the user is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_TechnicalExplanationPresentation.pptx." This name is sent to the device and displayed to the user. The user confirms the name and, satisfied with it, saves it as is.

[0463] In this way, our system recognizes user emotions and generates appropriate recommended filenames based on those emotions, improving file management efficiency and user experience. By combining it with an emotion engine, we can provide more personalized services and increase user satisfaction.

[0464] The processing flow will be explained below.

[0465] Step 1:

[0466] The user performs an operation to create a new file. For example, the user clicks the "New" button in word processing software. The device detects this operation.

[0467] Step 2:

[0468] The device collects metadata for new files, including user ID, creation date and time, file type, and a summary of the initial contents. The device records this information in real time.

[0469] Step 3:

[0470] The device activates an emotion engine to recognize the user's emotions. For example, the device's camera can be used to recognize the user's face and analyze their facial expressions to determine their emotions. Keyboard input speed and patterns can also be analyzed to read emotions.

[0471] Step 4:

[0472] The device sends the collected metadata and emotion data to the server in a unified format.

[0473] Step 5:

[0474] The server receives the metadata and emotion data. It also retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" might be "2023_09_25_ProjectA_Report.docx."

[0475] Step 6:

[0476] The server analyzes past filenames and uses machine learning algorithms to learn user naming patterns. It extracts date formats, keywords, and naming conventions contained in filenames. For example, it might find a pattern like "date + project name + report."

[0477] Step 7:

[0478] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it recommends a simple filename like "2023_10_03_ProjectA_Report.docx." Conversely, if the user is in a positive state, it generates a detailed filename like "2023_10_03_ProjectA_ProgressReport.docx."

[0479] Step 8:

[0480] The server sends the generated suggested file name to the device. The device displays the received suggested file name to the user. The user confirms the proposed name on the device screen.

[0481] Step 9:

[0482] The user checks the suggested file name and modifies it if necessary. For example, they can change it to "2023_10_03_ProjectA_WeeklyReport.docx." Then, they confirm the modified file name.

[0483] Step 10:

[0484] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0485] Step 11:

[0486] The device sends the confirmed filename and associated metadata to the server, which adds the data to a training database that is used in subsequent analyses to improve the accuracy of filename recommendations.

[0487] Example 2

[0488] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] Conventional file naming systems make it difficult for users to quickly generate the file names they intended, and the time and effort required to select an appropriate file name can be a significant burden, especially when users are busy or stressed. Furthermore, inconsistent user naming patterns can make file management cumbersome. Furthermore, conventional systems are unable to suggest personalized file names that take into account the user's emotions and circumstances, resulting in a lack of improvement in the user experience.

[0490] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0491] In this invention, the server includes a means for learning a user's past file naming habits and generating recommended file names, a means for analyzing the user's past file names using a machine learning algorithm, and a means for including the file type, creation date and time, user ID, and a summary of the initial contents in the collected metadata. This allows the server to quickly and automatically generate an optimal file name that takes into account both the user's past naming habits and their current emotional state when creating a new file. This also improves file management efficiency and the user experience.

[0492] A "user" is an entity that uses this system to create and manage new files.

[0493] A "file" is a document, image, sound, or other unit of information stored in digital form.

[0494] "Metadata" is additional information that accompanies a file, specifically information that includes the user ID, creation date and time, file type, and a summary of the initial contents.

[0495] A "terminal" is an electronic device such as a computer, tablet, or smartphone that is directly operated by a user.

[0496] A "server" is a computer system that receives metadata and emotion information from terminals via a network and processes this data.

[0497] An "emotion engine" is software or hardware installed on a device that has the ability to recognize and estimate a user's emotions.

[0498] A "machine learning algorithm" is a mathematical technique that learns from past data and makes predictions and classifications for new data.

[0499] A "suggested file name" is a name for a new file that is generated by the server based on the user's past file naming habits and emotional state, and is displayed on the terminal.

[0500] This invention relates to a system that automates the naming of new files when a user creates them. This system is composed of a terminal, a server, and an emotion engine. The specific operation of the system is described below.

[0501] First, when a user creates a new file using a device, the device detects the action. For example, when a user clicks the "Create New" button on a computer, tablet, or other device. When this action is detected, the device collects metadata about the new file. The metadata includes the user ID, creation date and time, file type (e.g., .docx, .pptx), and a summary of the initial contents.

[0502] The collected metadata is sent from the device to the server in real time. At that time, the device is equipped with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine uses facial recognition technology (e.g., OpenCV) and keyboard input information. It analyzes the user's facial expressions using a camera to estimate their stress level and satisfaction. It also reads changes in the user's emotions by analyzing the speed and rhythm of keyboard input. This makes it possible to understand the emotional state of the user when creating a new file.

[0503] Meanwhile, the server receives the metadata and emotional information sent from the device. The server integrates this information and retrieves the user's past file naming data from a database. It then applies a machine learning algorithm (e.g., random forest or deep learning model) to the retrieved past data to learn the user's naming patterns. Based on this learning result, the server generates new recommended file names. The generated recommended file names are adapted to the user's emotional state and support the editing process.

[0504] For example, if a user is concentrating on creating a presentation, the server generates a detailed and specific filename, such as "2023_10_03_TechnicalExplanationPresentation.pptx." The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary.

[0505] The file is then saved with the filename determined by the user. This filename and associated metadata are then sent back to the server and used for the next analysis. This allows the system to continue learning the user's naming patterns with increasing accuracy.

[0506] Prompt Sentence Examples

[0507] "When creating a new presentation, suggest file names. Consider your past naming patterns and your current emotional state."

[0508] This invention enables automatic generation of file names that take into account the user's feelings and past naming patterns, thereby improving the efficiency of file management and the user experience.

[0509] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0510] Step 1:

[0511] The user creates a new file.

[0512] The user creates a new file using the device. The trigger is a user operation such as clicking the "Create New" button. The device detects this operation event.

[0513] Input: Create new user

[0514] Output: Notification of new event occurrence

[0515] Step 2:

[0516] Device collects metadata

[0517] When a new file creation event occurs, the device collects metadata related to the file, including the user ID, creation date and time, file type, and a summary of the initial contents.

[0518] Input: Newly created event

[0519] Output: Collected metadata (user ID, creation date, file type, summary of initial contents)

[0520] Step 3:

[0521] The device sends the metadata to the server.

[0522] The terminal sends the collected metadata to the server, which transmits the metadata to the server in real time.

[0523] Input: Collected metadata

[0524] Output: Metadata sent to the server

[0525] Step 4:

[0526] The device recognizes emotions using an emotion engine

[0527] The device uses an emotion engine to recognize the user's emotions. It analyzes the user's facial expressions with a camera, as well as the typing speed and rhythm of the keyboard, to estimate the user's emotional state (e.g., stress, concentration, satisfaction).

[0528] Input: Real-time facial expression data and keyboard input data of the user

[0529] Output: Estimated user emotion information (stress, concentration, satisfaction, etc.)

[0530] Step 5:

[0531] Send emotional information to the server

[0532] The device sends the recognized emotion information to the server, which receives the emotion information along with the metadata.

[0533] Input: Estimated emotion information

[0534] Output: Send emotional information to the server

[0535] Step 6:

[0536] The server retrieves the user's past naming data.

[0537] The server retrieves the user's past file naming data from the database based on the received metadata and emotion information.

[0538] Input: Metadata, emotional information

[0539] Output: User's past file naming data

[0540] Step 7:

[0541] The server applies machine learning algorithms to learn naming patterns.

[0542] The server applies a machine learning algorithm (e.g., random forest, deep learning model) to the user's past file naming data to learn the user's naming patterns.

[0543] Input: User's previous file naming data

[0544] Output: Learned naming pattern model

[0545] Step 8:

[0546] The server generates a suggested filename

[0547] The server generates recommended filenames based on the learned naming pattern model and current sentiment information, with appropriate format and content.

[0548] Input: Learned naming pattern model, current emotional information

[0549] Output: Suggested file name

[0550] Step 9:

[0551] Send a suggested filename to the device

[0552] The server sends the generated recommended filename to the terminal, which displays the recommended filename in real time.

[0553] Input: Suggested file name

[0554] Output: Suggested filename sent to terminal

[0555] Step 10:

[0556] The device displays a suggested filename to the user.

[0557] The device will display the received suggested filename to the user, who will be given the option to review and modify the suggested filename.

[0558] Input: Suggested file name

[0559] Output: File name displayed to the user

[0560] Step 11:

[0561] The user confirms the file name

[0562] The user reviews the proposed filename, corrects it if necessary, and confirms the final filename.

[0563] Input: The suggested file name shown

[0564] Output: Final file name

[0565] Step 12:

[0566] The device saves the file and sends the metadata to the server.

[0567] The device saves the file with the determined file name, and sends the saved file name and related metadata to the server for the next analysis.

[0568] Input: Final file name

[0569] Output: Saved files and associated metadata sent to the server

[0570] (Application example 2)

[0571] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0572] Conventional file naming systems require users to think of an appropriate file name when creating a new file, which increases the complexity of the work and reduces work efficiency, especially in workplaces that handle large amounts of data. Furthermore, recommending a uniform file name without considering the user's emotional state can lead to a poor user experience and increased stress at work. Furthermore, file management is even more important in workplaces where many files are generated, such as logistics centers, and a more efficient and appropriate file naming system is needed.

[0573] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting metadata of a file when a user creates a new file; means for transmitting the collected metadata to the server; means for the server to learn the user's past file naming habits and generate a recommended file name; means for transmitting the generated recommended file name to the terminal and displaying it to the user; means for saving the file name determined by the user as a file; means for recognizing the user's emotion; and means for generating a recommended file name based on the recognized emotion. This enables automatic recommendation of an optimal file name taking into account the user's emotional state and past naming patterns, which is expected to improve work efficiency and the user experience. Furthermore, file management can be more effectively performed at sites that handle large amounts of data, such as logistics centers.

[0574] "Metadata" is data that includes various attribute information related to a file, specifically the file type, creation date and time, user ID, and an overview of the initial contents.

[0575] The "emotion engine" is a software component that analyzes the user's emotional state, using facial recognition technology, input speed, and input patterns.

[0576] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications.

[0577] A "head-mounted display" is a display device worn by a user on the head to provide visual information, and is used, for example, in logistics centers to improve work efficiency.

[0578] "Emotion recognition" is a technology that estimates a user's emotional state from their facial expressions, movements, input speed, etc., making it possible to grasp the user's current psychological state.

[0579] "File naming habits" refers to the tendency of users to use certain criteria or patterns in naming files in the past.

[0580] A "recommended file name" is a file name that is automatically generated based on collected data and learning results and presented to the user.

[0581] A logistics center is a facility that stores, manages, and distributes goods and materials, and is a site where a large amount of data needs to be generated and managed.

[0582] This invention relates to a system that automates the naming of new files when a user creates them. This system learns the user's naming habits and recommends file names based on unified rules. In addition, it combines an emotion engine that recognizes the user's emotions to recommend more appropriate file names.

[0583] Specifically, when a user creates a new file, the device detects the operation. At this stage, the device collects metadata for the new file, including the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[0584] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates the user's emotions by analyzing facial recognition technology, typing speed, and typing patterns. For example, it uses a camera to analyze the user's facial expressions to determine stress levels and satisfaction. It can also read emotions from keyboard typing speed and typing patterns.

[0585] The server receives the submitted metadata and the emotional information from the emotion engine and integrates these pieces of information. The server then retrieves the user's past file naming data from a database and applies a machine learning algorithm to analyze past file names. Based on this learning result and the recognized emotional information, the server generates new recommended file names. Based on the emotional information, for example, it can suggest simple file names if the user is feeling stressed, and detailed file names if the user is in a positive state.

[0586] The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. This saved filename and associated metadata are sent to the server and used for the next analysis.

[0587] As a concrete example, consider the case where a worker at a logistics center tries to create new shipping data. When the worker wears a head-mounted display (HMD) and performs an operation to create a new file, the HMD detects the operation and collects metadata and emotional data. Using facial recognition technology and input pattern analysis, it is determined that the worker is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_shipment_data.csv." This name is sent to the HMD and displayed to the worker. The worker reviews the name and, satisfied with it, saves it as is.

[0588] Examples of prompts for generative AI models include:

[0589] Design a system that automatically names a new file when the user creates it. The system recommends the best filename by combining an emotion engine that recognizes the user's emotions. Please explain in detail the specific algorithmic process and the technology used.

[0590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0591] Step 1:

[0592] The terminal detects that the user is performing an operation to create a new file.

[0593] Input: User creates a file

[0594] Output: File creation detection event

[0595] Specific operation: The device's operating system or application software detects that the user has performed a "create new file" operation and triggers an event.

[0596] Step 2:

[0597] The device collects metadata for the new file.

[0598] Input: File creation detection event

[0599] Output: Metadata (user ID, creation date, file type, summary of initial contents)

[0600] Specific operation: The device collects data using APIs and built-in functions to extract user ID, creation date and time, file type, and a summary of the initial contents from system information and file contents.

[0601] Step 3:

[0602] The terminal transmits the collected metadata and operation status to the server.

[0603] Input: Metadata

[0604] Output: A request to send data to the server

[0605] Specific operation: The terminal sends the collected metadata to the server using a network communication protocol (e.g., HTTP or HTTPS).

[0606] Step 4:

[0607] The terminal uses an emotion engine to recognize the user's emotions.

[0608] Input: User's face image, input speed, input pattern

[0609] Output: Emotion data (estimated emotional state)

[0610] Specific operation: The device's camera and sensors are used to analyze the user's facial expressions and input patterns, and the data is input into an emotion engine to estimate emotions. Emotion estimation is performed using a facial recognition library (e.g., OpenCV) and input pattern analysis algorithms.

[0611] Step 5:

[0612] The device transmits the emotion data to the server.

[0613] Input: Emotion data

[0614] Output: A request to send data to the server

[0615] Specific operation: The estimated emotion data is sent to the server using a network communication protocol.

[0616] Step 6:

[0617] The server integrates the metadata and emotion data and retrieves the user's past file naming data from a database.

[0618] Input: Metadata, emotion data

[0619] Output: Past file naming data

[0620] Specific operation: The server issues a database query to retrieve the user's past filename data and integrates it with metadata and emotion data.

[0621] Step 7:

[0622] The server applies machine learning algorithms to analyze past filenames and generate suggested filenames.

[0623] Input: Integrated data (metadata, emotion data, historical file naming data)

[0624] Output: Suggested file name

[0625] Specific operation: The server uses a machine learning model (e.g., a generative AI model) to analyze the collected data and generate optimal file names based on the results of learning the user's naming patterns.

[0626] Step 8:

[0627] The server generates a suggested filename and sends it to the device.

[0628] Input: Suggested file name

[0629] Output: Request to send data to the device

[0630] Specific operation: The generated recommended file name is sent to the terminal using a network communication protocol.

[0631] Step 9:

[0632] The terminal presents the recommended file name to the user and receives the confirmed file name.

[0633] Input: Suggested file name

[0634] Output: The confirmed file name

[0635] Specific operation: The terminal uses a GUI to display a recommended file name to the user, and if the user is satisfied, saves it as is, accepts corrections as necessary, and then confirms the final file name.

[0636] Step 10:

[0637] The device saves the file with the determined file name and sends the associated metadata to the server.

[0638] Input: Confirmed file name

[0639] Output: File save operation, data transmission request to server

[0640] Specific operation: The device saves the file with the determined file name in local storage and sends the file name and associated metadata to the server.

[0641] 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.

[0642] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0643] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0644] [Third embodiment]

[0645] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0646] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0647] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0648] 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.

[0649] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0650] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0651] 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.

[0652] 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.

[0653] 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 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.

[0654] 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.

[0655] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0656] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0657] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0658] First, when a user performs an operation to create a new file, the device detects the operation. For example, when a user creates a new document in word processing software. The device starts its operation as a trigger.

[0659] The device then collects metadata associated with the new file, including the user ID, the current date and time, the file type, and a summary of the initial contents, and sends the collected metadata to the server in real time.

[0660] The server receives the metadata and then analyzes the user's naming habits by referencing past filenames stored in a database. For example, it learns how users have named files in the past (including dates, using specific keywords, etc.). A machine learning algorithm is used in the analysis to automatically extract appropriate naming patterns.

[0661] The server generates new recommended file names based on the results of its learning. The generated file names are consistent and easy to understand, conforming to the naming patterns used by the user. For example, the format is "2023_10_03_ProjectA_Report.docx."

[0662] The server then sends the generated suggested file name to the terminal. The terminal displays the received suggested file name to the user. The user can check the proposed file name and modify it if necessary. Once the user has finally decided on a file name, the terminal saves the file with that name.

[0663] As a concrete example, consider the case where a user tries to create a new report file. When the user clicks the "Create New" button on the screen, the device detects this and sends the metadata (user ID: 12345, file format: .docx, date: 2023-10-03) to the server. The server references past file names (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and learns the naming pattern ("date + project name + report"). The server generates a suggested file name, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the name, changes it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0664] In this way, our system automates the naming of new files, improving consistency and efficiency when users create them. Furthermore, by utilizing machine learning, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0665] The processing flow will be explained below.

[0666] Step 1:

[0667] The user performs an operation to create a new file. The device detects this operation. When the user performs an operation such as clicking the "Create New" button, the device detects the trigger for creating a new file.

[0668] Step 2:

[0669] The device collects metadata for the new file. Specifically, it collects the user ID, current date and time, file type, and a summary of the initial contents. For example, the user ID might be "12345," the date and time might be "2023-10-03," the file type might be ".docx," and the initial contents might be "part of the body of a report."

[0670] Step 3:

[0671] The device sends the collected metadata to the server. The metadata is temporarily stored in the device and then sent to the server in real time. At this time, the data format is standardized and reformatted to make it easier for the server to process.

[0672] Step 4:

[0673] The server receives the metadata and retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" is "2023_09_25_ProjectA_Report.docx."

[0674] Step 5:

[0675] The server analyzes past filenames and learns user naming patterns. Machine learning algorithms are used to extract date formats, keywords, and naming conventions from filenames. For example, a pattern like "date + project name + report" might be found.

[0676] Step 6:

[0677] The server generates a new recommended file name based on the learning results. For example, "2023_10_03_ProjectA_Report.docx" is generated. This recommended file name follows the past pattern and is consistent.

[0678] Step 7:

[0679] The server generates a suggested filename and sends it to the device. The device displays the suggested filename received by the device to the user. The device allows the user to view the suggested name on the device screen.

[0680] Step 8:

[0681] The user can review the suggested file name and modify it as needed. For example, the user can change it to "2023_10_03_Project A_Weekly Report.docx." This will be the final file name.

[0682] Step 9:

[0683] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0684] Step 10:

[0685] The device sends the confirmed filename and associated metadata to the server, which adds the data to a learning database, improving the accuracy of future filename recommendations.

[0686] Example 1

[0687] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0688] In conventional systems, when users create new files, the naming of files relies on individual habits, resulting in a lack of consistency. Furthermore, since naming is not automated, users must manually choose file names, which reduces efficiency. Furthermore, the system does not adequately incorporate past naming habits, resulting in low accuracy in suggesting optimal file names for users.

[0689] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0690] In this invention, the server includes means for using a generative AI model to learn a user's past file naming habits and generate recommended file names, means for collecting and transmitting metadata in real time, and means for presenting the recommended file names to the user for confirmation and modification, thereby enabling consistent and efficient file naming when the user creates a new file.

[0691] "Metadata" is attribute information related to a file, including the user ID, creation date and time, file format, and a summary of the initial contents.

[0692] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new recommended file names based on past data.

[0693] "Machine learning algorithm" refers to mathematical techniques and program processes that analyze a user's past file naming habits and generate appropriate file names.

[0694] "User ID" is identification information that uniquely identifies a user on the system.

[0695] "File format" is information indicating the type of file, such as .docx, .txt, or .pdf.

[0696] The "summary of initial contents" is data that indicates the beginning or summary of a newly created file.

[0697] "Naming habits" refers to patterns and tendencies regarding how users have named files in the past.

[0698] A "recommended file name" is a file name that the server generates based on the user's naming habits and suggests to the user.

[0699] A "terminal" is a device that a user actually operates, and includes PCs, smartphones, etc.

[0700] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0701] First, when a user creates a new file, the device detects the operation. For example, when a user creates a new document using word processing software, the hardware used can be a user device such as a PC or smartphone, and the software used can be word processing software such as Microsoft Word.

[0702] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, creation date and time, file format, and a summary of the initial contents. The collected metadata is sent to a server in real time. The server uses a database system (e.g., MySQL) and machine learning algorithms (e.g., TensorFlow) to analyze the user's naming habits.

[0703] Based on the received metadata, the server analyzes the user's naming habits by referencing past filenames stored in a database. It uses machine learning algorithms to extract patterns. For example, it learns how the user has previously named files (including dates, using specific keywords, etc.). Based on the analyzed information, the server uses a generative AI model to generate recommended filenames. For example, the server might generate a recommended filename such as "2023_10_03_ProjectA_Report.docx."

[0704] The generated suggested file name is sent from the server to the terminal and displayed to the user on the terminal. The user can check the suggested file name and modify it if necessary. Once the final file name is decided, the terminal will save the file with that name.

[0705] As a concrete example, consider a scenario in which a user attempts to create a new report file. When the user clicks the "New" button in Microsoft Word on their PC, the device detects this action, collects the following metadata (user ID: 12345, file format: .docx, date: 2023-10-03), and sends it to the server. The server then learns naming patterns by referencing past filename data (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and extracts the pattern "date + project name + report." The server then generates a suggested filename, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the proposed filename, edits it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0706] Example prompt sentence:

[0707] "User ID: 12345, Create a new file. File format: .docx, Date: 2023-10-03. Please recommend an appropriate file name based on past naming patterns."

[0708] In this way, our system automates file naming when users create new files, improving consistency and efficiency. Furthermore, by utilizing a generative AI model, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0709] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0710] Step 1:

[0711] When a user performs an operation to create a new file, the terminal detects the operation. Specifically, this corresponds to the user clicking the "Create New" button in word processing software. The input to the terminal is the user's "Create New" operation, and the output is a notification that a new file has been created.

[0712] Step 2:

[0713] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, current date and time, file type, and a summary of the initial contents. Specifically, the device obtains the user's profile information and the format information of the created file, and prepares this as structured data. The input is the information about the new file creation event, and the output is the collected metadata.

[0714] Step 3:

[0715] The collected metadata is sent to the server in real time. The device converts the metadata into an appropriate data format, such as JSON, and sends it to the server via an API call. The input is the collected metadata, and the output is a notification of successful transmission to the server.

[0716] Step 4:

[0717] The server receives the metadata sent in real time and stores it in a database. The server then analyzes the user's naming habits based on previously stored filename data. During the analysis, it applies machine learning algorithms to process the data and extract patterns in filenames used by the user in the past. The input is the newly received metadata and existing database contents, and the output is the analyzed naming patterns.

[0718] Step 5:

[0719] Based on the analysis results, the server uses a generative AI model to generate new recommended file names. The generative AI model generates file names based on natural language processing, for example, using GPT-3. This generation process takes into account the patterns the user has used to name files in the past and generates the most appropriate file name. The input is the analyzed naming pattern and metadata, and the output is the recommended file name.

[0720] Step 6:

[0721] The generated suggested file name is sent from the server to the terminal. The terminal receives this suggested file name and displays it to the user. Specifically, the suggested file name is displayed in a popup window or inline editor so that the user can confirm it. The input is the suggested file name sent from the server, and the output is the name information displayed to the user.

[0722] Step 7:

[0723] The user can check the suggested file name displayed and modify it if necessary. The user then changes the file name through the terminal and confirms the final file name. Specifically, the user enters the suggested file name into an input form and, if necessary, modifies it. The input is the suggested file name and any modifications made by the user, and the output is the final confirmed file name.

[0724] Step 8:

[0725] Once the user has determined the final filename, the terminal saves the file with that name. The word processing software saves the file to disk using the name the user specified. The input is the final filename, and the output is the saved file.

[0726] (Application example 1)

[0727] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0728] Conventionally, it has not been easy to standardize the file names of work reports and inspection reports within a factory and manage them efficiently, and file naming consistency has often been lacking, especially in situations where many workers are involved. Furthermore, the time workers spend individually thinking up file names is also a factor that reduces work efficiency. There is a need to solve these problems and improve work efficiency and file management consistency.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0730] In this invention, the server includes means for collecting metadata of a file when a user creates a new file, means for transmitting the collected metadata to the server, means for the server to learn the user's past file naming habits and generate a recommended file name, means for transmitting the generated recommended file name to a terminal and displaying it to the user, means for saving the file name determined by the user as a file, and means for the machine device to work in conjunction with the file naming system and suggest a file name based on the task, thereby reducing the burden on workers when naming new files and making it possible to maintain consistency in file names.

[0731] "User" refers to a person who uses the system to create a new file.

[0732] "New file" refers to a file that is created using the system and has never been saved.

[0733] "Metadata" refers to information related to a file, including the file type, creation date and time, user ID, summary of initial contents, and work content.

[0734] "Server" refers to a computer system that processes collected metadata, learns users' naming habits, and generates recommended filenames.

[0735] "Past file naming habits" refers to information for analyzing patterns of how a user has named files in the past.

[0736] "Suggested file name" refers to a candidate file name generated by the server that is appropriate for the user.

[0737] "Terminal" refers to a computer or smart device used by a user, which receives and displays the recommended filenames.

[0738] "Machinery" refers to machines and robots used in factories and other workplaces, and refers to devices that are linked to the file naming system.

[0739] "Task-based filenames" refer to filenames that contain information related to the specific tasks being performed on-site.

[0740] The present invention provides a system that automates the file naming of work reports and inspection reports in a factory, and realizes efficient and consistent file management. This system operates in cooperation with users, servers, terminals, and machinery used in the field.

[0741] When a user creates a new file, the device first detects the creation and collects relevant metadata, including the file type, creation date and time, user ID, initial content summary, and work details. This metadata is then sent to the server in real time.

[0742] The server receives the metadata and analyzes past file naming habits using a machine learning algorithm. Specifically, it performs feature extraction and learning to understand how users have named files in the past. Specific machine learning algorithms used in this process include the Naive Bayes model.

[0743] The server generates a recommended filename based on the analysis results. This recommended filename takes into account the user's past naming patterns and is both consistent and clear. The generated recommended filename is sent to the terminal and displayed to the user.

[0744] The user can review the proposed filename and modify it if necessary, and then a final filename is determined. The file is then saved with this finalized filename.

[0745] For example, after a quality inspection at a factory, when a worker creates a new report, the smart glasses automatically suggest the file name "2023_10_03_QualityInspection_Report.docx." The worker can then review the file name and change it to, for example, "2023_10_03_QualityInspection_WeeklyReport.docx."

[0746] To help you work with this system, we also provide the following example prompts:

[0747] "Factory quality inspection reports are named in the format YYYY_MM_DD_task_report. The file name to be generated should be YYYY_MM_DD with the current date inserted, and the task should be 'Quality Inspection'. Please generate the file name based on this."

[0748] In this way, the present invention reduces the burden on the user and realizes efficient and consistent file management.

[0749] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0750] Step 1:

[0751] The device detects when a user creates a new file. When a user creates a new work report or inspection report, the device triggers the user's action and starts operation. The metadata collected includes the file type, creation date and time, user ID, summary of the initial contents, and work content.

[0752] Step 2:

[0753] The device sends the collected metadata to the server, which receives the metadata sent from the device as input and forwards the data to the analysis platform, preparing it for analysis.

[0754] Step 3:

[0755] The server receives the submitted metadata and analyzes past file naming habits using machine learning algorithms. The input is past file names and the latest metadata, and feature extraction and data learning are used to identify file name patterns. Specific processing involves vectorization and algorithms such as the Naive Bayes model.

[0756] Step 4:

[0757] The server generates a recommended file name based on the analysis results. Using the analyzed habit data and new metadata as input, it generates a file name that follows specific rules (e.g., "2023_10_03_Quality Inspection_Report.docx"). It is important that the generated recommended file name is in a format that is easy for users to understand.

[0758] Step 5:

[0759] Sends the generated suggested filename to the terminal and displays it to the user. The input is the suggested filename generated by the server and sends it as output to the terminal, which displays it to the user, who reviews the filename.

[0760] Step 6:

[0761] The user checks the suggested file name and corrects it if necessary. The user edits the suggested file name and decides on the final file name. In this step, corrections are made directly via the user interface.

[0762] Step 7:

[0763] The terminal sends the file name confirmed by the user to the server and stores it. The confirmed file name is sent from the terminal to the server as the final input, and the server stores the confirmed name. The process is completed to ensure consistent and efficient file management.

[0764] This series of processes reduces the burden on the user and enables efficient file naming and management.

[0765] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0766] This invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules, and by combining it with an emotion engine that recognizes the user's emotions, it is possible to recommend more appropriate file names.

[0767] First, when a user creates a new file, the device detects the operation. Based on the detected operation, the device collects metadata for the new file. The collected metadata includes the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[0768] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates emotions by analyzing the user's facial recognition technology, typing speed, and typing patterns. For example, it can analyze the user's facial expressions using a camera to determine their stress level and satisfaction. It can also read emotions from the speed and rhythm of keyboard typing.

[0769] The server receives the submitted metadata and emotion information from the emotion engine. The server integrates this information and retrieves the user's past file naming data from the database. A machine learning algorithm is applied to analyze the past file names and learn the user's naming patterns.

[0770] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it can recommend a simple and easy-to-understand filename. On the other hand, if the user is in a positive state, it can suggest a detailed and specific filename. The generated recommended filenames are adapted to the user's emotional state and are more user-friendly.

[0771] The suggested filename is sent to the device, which displays it to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. The saved filename and associated metadata are sent to the server and used for the next analysis.

[0772] As a concrete example, consider the case where a user attempts to create a new presentation. As the user performs an operation, the device detects it and collects metadata and emotional data. Facial recognition technology is used to recognize that the user is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_TechnicalExplanationPresentation.pptx." This name is sent to the device and displayed to the user. The user confirms the name and, satisfied with it, saves it as is.

[0773] In this way, our system recognizes user emotions and generates appropriate recommended filenames based on those emotions, improving file management efficiency and user experience. By combining it with an emotion engine, we can provide more personalized services and increase user satisfaction.

[0774] The processing flow will be explained below.

[0775] Step 1:

[0776] The user performs an operation to create a new file. For example, the user clicks the "New" button in word processing software. The device detects this operation.

[0777] Step 2:

[0778] The device collects metadata for new files, including user ID, creation date and time, file type, and a summary of the initial contents. The device records this information in real time.

[0779] Step 3:

[0780] The device activates an emotion engine to recognize the user's emotions. For example, the device's camera can be used to recognize the user's face and analyze their facial expressions to determine their emotions. Keyboard input speed and patterns can also be analyzed to read emotions.

[0781] Step 4:

[0782] The device sends the collected metadata and emotion data to the server in a unified format.

[0783] Step 5:

[0784] The server receives the metadata and emotion data. It also retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" might be "2023_09_25_ProjectA_Report.docx."

[0785] Step 6:

[0786] The server analyzes past filenames and uses machine learning algorithms to learn user naming patterns. It extracts date formats, keywords, and naming conventions contained in filenames. For example, it might find a pattern like "date + project name + report."

[0787] Step 7:

[0788] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it recommends a simple filename like "2023_10_03_ProjectA_Report.docx." Conversely, if the user is in a positive state, it generates a detailed filename like "2023_10_03_ProjectA_ProgressReport.docx."

[0789] Step 8:

[0790] The server sends the generated suggested file name to the device. The device displays the received suggested file name to the user. The user confirms the proposed name on the device screen.

[0791] Step 9:

[0792] The user checks the suggested file name and modifies it if necessary. For example, they can change it to "2023_10_03_ProjectA_WeeklyReport.docx." Then, they confirm the modified file name.

[0793] Step 10:

[0794] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0795] Step 11:

[0796] The device sends the confirmed filename and associated metadata to the server, which adds the data to a training database that is used in subsequent analyses to improve the accuracy of filename recommendations.

[0797] Example 2

[0798] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0799] Conventional file naming systems make it difficult for users to quickly generate the file names they intended, and the time and effort required to select an appropriate file name can be a significant burden, especially when users are busy or stressed. Furthermore, inconsistent user naming patterns can make file management cumbersome. Furthermore, conventional systems are unable to suggest personalized file names that take into account the user's emotions and circumstances, resulting in a lack of improvement in the user experience.

[0800] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0801] In this invention, the server includes a means for learning a user's past file naming habits and generating recommended file names, a means for analyzing the user's past file names using a machine learning algorithm, and a means for including the file type, creation date and time, user ID, and a summary of the initial contents in the collected metadata. This allows the server to quickly and automatically generate an optimal file name that takes into account both the user's past naming habits and their current emotional state when creating a new file. This also improves file management efficiency and the user experience.

[0802] A "user" is an entity that uses this system to create and manage new files.

[0803] A "file" is a document, image, sound, or other unit of information stored in digital form.

[0804] "Metadata" is additional information that accompanies a file, specifically information that includes the user ID, creation date and time, file type, and a summary of the initial contents.

[0805] A "terminal" is an electronic device such as a computer, tablet, or smartphone that is directly operated by a user.

[0806] A "server" is a computer system that receives metadata and emotion information from terminals via a network and processes this data.

[0807] An "emotion engine" is software or hardware installed on a device that has the ability to recognize and estimate a user's emotions.

[0808] A "machine learning algorithm" is a mathematical technique that learns from past data and makes predictions and classifications for new data.

[0809] A "suggested file name" is a name for a new file that is generated by the server based on the user's past file naming habits and emotional state, and is displayed on the terminal.

[0810] This invention relates to a system that automates the naming of new files when a user creates them. This system is composed of a terminal, a server, and an emotion engine. The specific operation of the system is described below.

[0811] First, when a user creates a new file using a device, the device detects the action. For example, when a user clicks the "Create New" button on a computer, tablet, or other device. When this action is detected, the device collects metadata about the new file. The metadata includes the user ID, creation date and time, file type (e.g., .docx, .pptx), and a summary of the initial contents.

[0812] The collected metadata is sent from the device to the server in real time. At that time, the device is equipped with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine uses facial recognition technology (e.g., OpenCV) and keyboard input information. It analyzes the user's facial expressions using a camera to estimate their stress level and satisfaction. It also reads changes in the user's emotions by analyzing the speed and rhythm of keyboard input. This makes it possible to understand the emotional state of the user when creating a new file.

[0813] Meanwhile, the server receives the metadata and emotional information sent from the device. The server integrates this information and retrieves the user's past file naming data from a database. It then applies a machine learning algorithm (e.g., random forest or deep learning model) to the retrieved past data to learn the user's naming patterns. Based on this learning result, the server generates new recommended file names. The generated recommended file names are adapted to the user's emotional state and support the editing process.

[0814] For example, if a user is concentrating on creating a presentation, the server generates a detailed and specific filename, such as "2023_10_03_TechnicalExplanationPresentation.pptx." The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary.

[0815] The file is then saved with the filename determined by the user. This filename and associated metadata are then sent back to the server and used for the next analysis. This allows the system to continue learning the user's naming patterns with increasing accuracy.

[0816] Prompt Sentence Examples

[0817] "When creating a new presentation, suggest file names. Consider your past naming patterns and your current emotional state."

[0818] This invention enables automatic generation of file names that take into account the user's feelings and past naming patterns, thereby improving the efficiency of file management and the user experience.

[0819] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0820] Step 1:

[0821] The user creates a new file.

[0822] The user creates a new file using the device. The trigger is a user operation such as clicking the "Create New" button. The device detects this operation event.

[0823] Input: Create new user

[0824] Output: Notification of new event occurrence

[0825] Step 2:

[0826] Device collects metadata

[0827] When a new file creation event occurs, the device collects metadata related to the file, including the user ID, creation date and time, file type, and a summary of the initial contents.

[0828] Input: Newly created event

[0829] Output: Collected metadata (user ID, creation date, file type, summary of initial contents)

[0830] Step 3:

[0831] The device sends the metadata to the server.

[0832] The terminal sends the collected metadata to the server, which transmits the metadata to the server in real time.

[0833] Input: Collected metadata

[0834] Output: Metadata sent to the server

[0835] Step 4:

[0836] The device recognizes emotions using an emotion engine

[0837] The device uses an emotion engine to recognize the user's emotions. It analyzes the user's facial expressions with a camera, as well as the typing speed and rhythm of the keyboard, to estimate the user's emotional state (e.g., stress, concentration, satisfaction).

[0838] Input: Real-time facial expression data and keyboard input data of the user

[0839] Output: Estimated user emotion information (stress, concentration, satisfaction, etc.)

[0840] Step 5:

[0841] Send emotional information to the server

[0842] The device sends the recognized emotion information to the server, which receives the emotion information along with the metadata.

[0843] Input: Estimated emotion information

[0844] Output: Send emotional information to the server

[0845] Step 6:

[0846] The server retrieves the user's past naming data.

[0847] The server retrieves the user's past file naming data from the database based on the received metadata and emotion information.

[0848] Input: Metadata, emotional information

[0849] Output: User's past file naming data

[0850] Step 7:

[0851] The server applies machine learning algorithms to learn naming patterns.

[0852] The server applies a machine learning algorithm (e.g., random forest, deep learning model) to the user's past file naming data to learn the user's naming patterns.

[0853] Input: User's previous file naming data

[0854] Output: Learned naming pattern model

[0855] Step 8:

[0856] The server generates a suggested filename

[0857] The server generates recommended filenames based on the learned naming pattern model and current sentiment information, with appropriate format and content.

[0858] Input: Learned naming pattern model, current emotional information

[0859] Output: Suggested file name

[0860] Step 9:

[0861] Send a suggested filename to the device

[0862] The server sends the generated recommended filename to the terminal, which displays the recommended filename in real time.

[0863] Input: Suggested file name

[0864] Output: Suggested filename sent to terminal

[0865] Step 10:

[0866] The device displays a suggested filename to the user.

[0867] The device will display the received suggested filename to the user, who will be given the option to review and modify the suggested filename.

[0868] Input: Suggested file name

[0869] Output: File name displayed to the user

[0870] Step 11:

[0871] The user confirms the file name

[0872] The user reviews the proposed filename, corrects it if necessary, and confirms the final filename.

[0873] Input: The suggested file name shown

[0874] Output: Final file name

[0875] Step 12:

[0876] The device saves the file and sends the metadata to the server.

[0877] The device saves the file with the determined file name, and sends the saved file name and related metadata to the server for the next analysis.

[0878] Input: Final file name

[0879] Output: Saved files and associated metadata sent to the server

[0880] (Application example 2)

[0881] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0882] Conventional file naming systems require users to think of an appropriate file name when creating a new file, which increases the complexity of the work and reduces work efficiency, especially in workplaces that handle large amounts of data. Furthermore, recommending a uniform file name without considering the user's emotional state can lead to a poor user experience and increased stress at work. Furthermore, file management is even more important in workplaces where many files are generated, such as logistics centers, and a more efficient and appropriate file naming system is needed.

[0883] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting metadata of a file when a user creates a new file; means for transmitting the collected metadata to the server; means for the server to learn the user's past file naming habits and generate a recommended file name; means for transmitting the generated recommended file name to the terminal and displaying it to the user; means for saving the file name determined by the user as a file; means for recognizing the user's emotion; and means for generating a recommended file name based on the recognized emotion. This enables automatic recommendation of an optimal file name taking into account the user's emotional state and past naming patterns, which is expected to improve work efficiency and the user experience. Furthermore, file management can be more effectively performed at sites that handle large amounts of data, such as logistics centers.

[0884] "Metadata" is data that includes various attribute information related to a file, specifically the file type, creation date and time, user ID, and an overview of the initial contents.

[0885] The "emotion engine" is a software component that analyzes the user's emotional state, using facial recognition technology, input speed, and input patterns.

[0886] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications.

[0887] A "head-mounted display" is a display device worn by a user on the head to provide visual information, and is used, for example, in logistics centers to improve work efficiency.

[0888] "Emotion recognition" is a technology that estimates a user's emotional state from their facial expressions, movements, input speed, etc., making it possible to grasp the user's current psychological state.

[0889] "File naming habits" refers to the tendency of users to use certain criteria or patterns in naming files in the past.

[0890] A "recommended file name" is a file name that is automatically generated based on collected data and learning results and presented to the user.

[0891] A logistics center is a facility that stores, manages, and distributes goods and materials, and is a site where a large amount of data needs to be generated and managed.

[0892] This invention relates to a system that automates the naming of new files when a user creates them. This system learns the user's naming habits and recommends file names based on unified rules. In addition, it combines an emotion engine that recognizes the user's emotions to recommend more appropriate file names.

[0893] Specifically, when a user creates a new file, the device detects the operation. At this stage, the device collects metadata for the new file, including the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[0894] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates the user's emotions by analyzing facial recognition technology, typing speed, and typing patterns. For example, it uses a camera to analyze the user's facial expressions to determine stress levels and satisfaction. It can also read emotions from keyboard typing speed and typing patterns.

[0895] The server receives the submitted metadata and the emotional information from the emotion engine and integrates these pieces of information. The server then retrieves the user's past file naming data from a database and applies a machine learning algorithm to analyze past file names. Based on this learning result and the recognized emotional information, the server generates new recommended file names. Based on the emotional information, for example, it can suggest simple file names if the user is feeling stressed, and detailed file names if the user is in a positive state.

[0896] The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. This saved filename and associated metadata are sent to the server and used for the next analysis.

[0897] As a concrete example, consider the case where a worker at a logistics center tries to create new shipping data. When the worker wears a head-mounted display (HMD) and performs an operation to create a new file, the HMD detects the operation and collects metadata and emotional data. Using facial recognition technology and input pattern analysis, it is determined that the worker is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_shipment_data.csv." This name is sent to the HMD and displayed to the worker. The worker reviews the name and, satisfied with it, saves it as is.

[0898] Examples of prompts for generative AI models include:

[0899] Design a system that automatically names a new file when the user creates it. The system recommends the best filename by combining an emotion engine that recognizes the user's emotions. Please explain in detail the specific algorithmic process and the technology used.

[0900] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0901] Step 1:

[0902] The terminal detects that the user is performing an operation to create a new file.

[0903] Input: User creates a file

[0904] Output: File creation detection event

[0905] Specific operation: The device's operating system or application software detects that the user has performed a "create new file" operation and triggers an event.

[0906] Step 2:

[0907] The device collects metadata for the new file.

[0908] Input: File creation detection event

[0909] Output: Metadata (user ID, creation date, file type, summary of initial contents)

[0910] Specific operation: The device collects data using APIs and built-in functions to extract user ID, creation date and time, file type, and a summary of the initial contents from system information and file contents.

[0911] Step 3:

[0912] The terminal transmits the collected metadata and operation status to the server.

[0913] Input: Metadata

[0914] Output: A request to send data to the server

[0915] Specific operation: The terminal sends the collected metadata to the server using a network communication protocol (e.g., HTTP or HTTPS).

[0916] Step 4:

[0917] The terminal uses an emotion engine to recognize the user's emotions.

[0918] Input: User's face image, input speed, input pattern

[0919] Output: Emotion data (estimated emotional state)

[0920] Specific operation: The device's camera and sensors are used to analyze the user's facial expressions and input patterns, and the data is input into an emotion engine to estimate emotions. Emotion estimation is performed using a facial recognition library (e.g., OpenCV) and input pattern analysis algorithms.

[0921] Step 5:

[0922] The device transmits the emotion data to the server.

[0923] Input: Emotion data

[0924] Output: A request to send data to the server

[0925] Specific operation: The estimated emotion data is sent to the server using a network communication protocol.

[0926] Step 6:

[0927] The server integrates the metadata and emotion data and retrieves the user's past file naming data from a database.

[0928] Input: Metadata, emotion data

[0929] Output: Past file naming data

[0930] Specific operation: The server issues a database query to retrieve the user's past filename data and integrates it with metadata and emotion data.

[0931] Step 7:

[0932] The server applies machine learning algorithms to analyze past filenames and generate suggested filenames.

[0933] Input: Integrated data (metadata, emotion data, historical file naming data)

[0934] Output: Suggested file name

[0935] Specific operation: The server uses a machine learning model (e.g., a generative AI model) to analyze the collected data and generate optimal file names based on the results of learning the user's naming patterns.

[0936] Step 8:

[0937] The server generates a suggested filename and sends it to the device.

[0938] Input: Suggested file name

[0939] Output: Request to send data to the device

[0940] Specific operation: The generated recommended file name is sent to the terminal using a network communication protocol.

[0941] Step 9:

[0942] The terminal presents the recommended file name to the user and receives the confirmed file name.

[0943] Input: Suggested file name

[0944] Output: The confirmed file name

[0945] Specific operation: The terminal uses a GUI to display a recommended file name to the user, and if the user is satisfied, saves it as is, accepts corrections as necessary, and then confirms the final file name.

[0946] Step 10:

[0947] The device saves the file with the determined file name and sends the associated metadata to the server.

[0948] Input: Confirmed file name

[0949] Output: File save operation, data transmission request to server

[0950] Specific operation: The device saves the file with the determined file name in local storage and sends the file name and associated metadata to the server.

[0951] 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.

[0952] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[0953] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0954] [Fourth embodiment]

[0955] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0956] 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.

[0957] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0958] 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.

[0959] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0960] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0961] 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.

[0962] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[0963] 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.

[0964] 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 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.

[0965] 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.

[0966] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0967] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0968] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[0969] First, when a user performs an operation to create a new file, the device detects the operation. For example, when a user creates a new document in word processing software. The device starts its operation as a trigger.

[0970] The device then collects metadata associated with the new file, including the user ID, the current date and time, the file type, and a summary of the initial contents, and sends the collected metadata to the server in real time.

[0971] The server receives the metadata and then analyzes the user's naming habits by referencing past filenames stored in a database. For example, it learns how users have named files in the past (including dates, using specific keywords, etc.). A machine learning algorithm is used in the analysis to automatically extract appropriate naming patterns.

[0972] The server generates new recommended file names based on the results of its learning. The generated file names are consistent and easy to understand, conforming to the naming patterns used by the user. For example, the format is "2023_10_03_ProjectA_Report.docx."

[0973] The server then sends the generated suggested file name to the terminal. The terminal displays the received suggested file name to the user. The user can check the proposed file name and modify it if necessary. Once the user has finally decided on a file name, the terminal saves the file with that name.

[0974] As a concrete example, consider the case where a user tries to create a new report file. When the user clicks the "Create New" button on the screen, the device detects this and sends the metadata (user ID: 12345, file format: .docx, date: 2023-10-03) to the server. The server references past file names (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and learns the naming pattern ("date + project name + report"). The server generates a suggested file name, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the name, changes it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[0975] In this way, our system automates the naming of new files, improving consistency and efficiency when users create them. Furthermore, by utilizing machine learning, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[0976] The processing flow will be explained below.

[0977] Step 1:

[0978] The user performs an operation to create a new file. The device detects this operation. When the user performs an operation such as clicking the "Create New" button, the device detects the trigger for creating a new file.

[0979] Step 2:

[0980] The device collects metadata for the new file. Specifically, it collects the user ID, current date and time, file type, and a summary of the initial contents. For example, the user ID might be "12345," the date and time might be "2023-10-03," the file type might be ".docx," and the initial contents might be "part of the body of a report."

[0981] Step 3:

[0982] The device sends the collected metadata to the server. The metadata is temporarily stored in the device and then sent to the server in real time. At this time, the data format is standardized and reformatted to make it easier for the server to process.

[0983] Step 4:

[0984] The server receives the metadata and retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" is "2023_09_25_ProjectA_Report.docx."

[0985] Step 5:

[0986] The server analyzes past filenames and learns user naming patterns. Machine learning algorithms are used to extract date formats, keywords, and naming conventions from filenames. For example, a pattern like "date + project name + report" might be found.

[0987] Step 6:

[0988] The server generates a new recommended file name based on the learning results. For example, "2023_10_03_ProjectA_Report.docx" is generated. This recommended file name follows the past pattern and is consistent.

[0989] Step 7:

[0990] The server generates a suggested filename and sends it to the device. The device displays the suggested filename received by the device to the user. The device allows the user to view the suggested name on the device screen.

[0991] Step 8:

[0992] The user can review the suggested file name and modify it as needed. For example, the user can change it to "2023_10_03_Project A_Weekly Report.docx." This will be the final file name.

[0993] Step 9:

[0994] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[0995] Step 10:

[0996] The device sends the confirmed filename and associated metadata to the server, which adds the data to a learning database, improving the accuracy of future filename recommendations.

[0997] Example 1

[0998] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0999] In conventional systems, when users create new files, the naming of files relies on individual habits, resulting in a lack of consistency. Furthermore, since naming is not automated, users must manually choose file names, which reduces efficiency. Furthermore, the system does not adequately incorporate past naming habits, resulting in low accuracy in suggesting optimal file names for users.

[1000] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1001] In this invention, the server includes means for using a generative AI model to learn a user's past file naming habits and generate recommended file names, means for collecting and transmitting metadata in real time, and means for presenting the recommended file names to the user for confirmation and modification, thereby enabling consistent and efficient file naming when the user creates a new file.

[1002] "Metadata" is attribute information related to a file, including the user ID, creation date and time, file format, and a summary of the initial contents.

[1003] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new recommended file names based on past data.

[1004] "Machine learning algorithm" refers to mathematical techniques and program processes that analyze a user's past file naming habits and generate appropriate file names.

[1005] "User ID" is identification information that uniquely identifies a user on the system.

[1006] "File format" is information indicating the type of file, such as .docx, .txt, or .pdf.

[1007] The "summary of initial contents" is data that indicates the beginning or summary of a newly created file.

[1008] "Naming habits" refers to patterns and tendencies regarding how users have named files in the past.

[1009] A "recommended file name" is a file name that the server generates based on the user's naming habits and suggests to the user.

[1010] A "terminal" is a device that a user actually operates, and includes PCs, smartphones, etc.

[1011] The present invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules. Specific embodiments of the system are described in detail below.

[1012] First, when a user creates a new file, the device detects the operation. For example, when a user creates a new document using word processing software, the hardware used can be a user device such as a PC or smartphone, and the software used can be word processing software such as Microsoft Word.

[1013] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, creation date and time, file format, and a summary of the initial contents. The collected metadata is sent to a server in real time. The server uses a database system (e.g., MySQL) and machine learning algorithms (e.g., TensorFlow) to analyze the user's naming habits.

[1014] Based on the received metadata, the server analyzes the user's naming habits by referencing past filenames stored in a database. It uses machine learning algorithms to extract patterns. For example, it learns how the user has previously named files (including dates, using specific keywords, etc.). Based on the analyzed information, the server uses a generative AI model to generate recommended filenames. For example, the server might generate a recommended filename such as "2023_10_03_ProjectA_Report.docx."

[1015] The generated suggested file name is sent from the server to the terminal and displayed to the user on the terminal. The user can check the suggested file name and modify it if necessary. Once the final file name is decided, the terminal will save the file with that name.

[1016] As a concrete example, consider a scenario in which a user attempts to create a new report file. When the user clicks the "New" button in Microsoft Word on their PC, the device detects this action, collects the following metadata (user ID: 12345, file format: .docx, date: 2023-10-03), and sends it to the server. The server then learns naming patterns by referencing past filename data (e.g., "2023_09_25_ProjectA_Report.docx," "2023_09_18_ProjectB_Report.docx") and extracts the pattern "date + project name + report." The server then generates a suggested filename, "2023_10_03_ProjectA_Report.docx," and sends it to the device. The user confirms the proposed filename, edits it to "2023_10_03_ProjectA_WeeklyReport.docx," and saves it.

[1017] Example prompt sentence:

[1018] "User ID: 12345, Create a new file. File format: .docx, Date: 2023-10-03. Please recommend an appropriate file name based on past naming patterns."

[1019] In this way, our system automates file naming when users create new files, improving consistency and efficiency. Furthermore, by utilizing a generative AI model, the system adaptively learns users' naming habits, enabling more accurate recommendations.

[1020] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1021] Step 1:

[1022] When a user performs an operation to create a new file, the terminal detects the operation. Specifically, this corresponds to the user clicking the "Create New" button in word processing software. The input to the terminal is the user's "Create New" operation, and the output is a notification that a new file has been created.

[1023] Step 2:

[1024] When a new file is created, the device collects metadata related to the file. This metadata includes the user ID, current date and time, file type, and a summary of the initial contents. Specifically, the device obtains the user's profile information and the format information of the created file, and prepares this as structured data. The input is the information about the new file creation event, and the output is the collected metadata.

[1025] Step 3:

[1026] The collected metadata is sent to the server in real time. The device converts the metadata into an appropriate data format, such as JSON, and sends it to the server via an API call. The input is the collected metadata, and the output is a notification of successful transmission to the server.

[1027] Step 4:

[1028] The server receives the metadata sent in real time and stores it in a database. The server then analyzes the user's naming habits based on previously stored filename data. During the analysis, it applies machine learning algorithms to process the data and extract patterns in filenames used by the user in the past. The input is the newly received metadata and existing database contents, and the output is the analyzed naming patterns.

[1029] Step 5:

[1030] Based on the analysis results, the server uses a generative AI model to generate new recommended file names. The generative AI model generates file names based on natural language processing, for example, using GPT-3. This generation process takes into account the patterns the user has used to name files in the past and generates the most appropriate file name. The input is the analyzed naming pattern and metadata, and the output is the recommended file name.

[1031] Step 6:

[1032] The generated suggested file name is sent from the server to the terminal. The terminal receives this suggested file name and displays it to the user. Specifically, the suggested file name is displayed in a popup window or inline editor so that the user can confirm it. The input is the suggested file name sent from the server, and the output is the name information displayed to the user.

[1033] Step 7:

[1034] The user can check the suggested file name displayed and modify it if necessary. The user then changes the file name through the terminal and confirms the final file name. Specifically, the user enters the suggested file name into an input form and, if necessary, modifies it. The input is the suggested file name and any modifications made by the user, and the output is the final confirmed file name.

[1035] Step 8:

[1036] Once the user has determined the final filename, the terminal saves the file with that name. The word processing software saves the file to disk using the name the user specified. The input is the final filename, and the output is the saved file.

[1037] (Application example 1)

[1038] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1039] Conventionally, it has not been easy to standardize the file names of work reports and inspection reports within a factory and manage them efficiently, and file naming consistency has often been lacking, especially in situations where many workers are involved. Furthermore, the time workers spend individually thinking up file names is also a factor that reduces work efficiency. There is a need to solve these problems and improve work efficiency and file management consistency.

[1040] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1041] In this invention, the server includes means for collecting metadata of a file when a user creates a new file, means for transmitting the collected metadata to the server, means for the server to learn the user's past file naming habits and generate a recommended file name, means for transmitting the generated recommended file name to a terminal and displaying it to the user, means for saving the file name determined by the user as a file, and means for the machine device to work in conjunction with the file naming system and suggest a file name based on the task, thereby reducing the burden on workers when naming new files and making it possible to maintain consistency in file names.

[1042] "User" refers to a person who uses the system to create a new file.

[1043] "New file" refers to a file that is created using the system and has never been saved.

[1044] "Metadata" refers to information related to a file, including the file type, creation date and time, user ID, summary of initial contents, and work content.

[1045] "Server" refers to a computer system that processes collected metadata, learns users' naming habits, and generates recommended filenames.

[1046] "Past file naming habits" refers to information for analyzing patterns of how a user has named files in the past.

[1047] "Suggested file name" refers to a candidate file name generated by the server that is appropriate for the user.

[1048] "Terminal" refers to a computer or smart device used by a user, which receives and displays the recommended filenames.

[1049] "Machinery" refers to machines and robots used in factories and other workplaces, and refers to devices that are linked to the file naming system.

[1050] "Task-based filenames" refer to filenames that contain information related to the specific tasks being performed on-site.

[1051] The present invention provides a system that automates the file naming of work reports and inspection reports in a factory, and realizes efficient and consistent file management. This system operates in cooperation with users, servers, terminals, and machinery used in the field.

[1052] When a user creates a new file, the device first detects the creation and collects relevant metadata, including the file type, creation date and time, user ID, initial content summary, and work details. This metadata is then sent to the server in real time.

[1053] The server receives the metadata and analyzes past file naming habits using a machine learning algorithm. Specifically, it performs feature extraction and learning to understand how users have named files in the past. Specific machine learning algorithms used in this process include the Naive Bayes model.

[1054] The server generates a recommended filename based on the analysis results. This recommended filename takes into account the user's past naming patterns and is both consistent and clear. The generated recommended filename is sent to the terminal and displayed to the user.

[1055] The user can review the proposed filename and modify it if necessary, and then a final filename is determined. The file is then saved with this finalized filename.

[1056] For example, after a quality inspection at a factory, when a worker creates a new report, the smart glasses automatically suggest the file name "2023_10_03_QualityInspection_Report.docx." The worker can then review the file name and change it to, for example, "2023_10_03_QualityInspection_WeeklyReport.docx."

[1057] To help you work with this system, we also provide the following example prompts:

[1058] "Factory quality inspection reports are named in the format YYYY_MM_DD_task_report. The file name to be generated should be YYYY_MM_DD with the current date inserted, and the task should be 'Quality Inspection'. Please generate the file name based on this."

[1059] In this way, the present invention reduces the burden on the user and realizes efficient and consistent file management.

[1060] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1061] Step 1:

[1062] The device detects when a user creates a new file. When a user creates a new work report or inspection report, the device triggers the user's action and starts operation. The metadata collected includes the file type, creation date and time, user ID, summary of the initial contents, and work content.

[1063] Step 2:

[1064] The device sends the collected metadata to the server, which receives the metadata sent from the device as input and forwards the data to the analysis platform, preparing it for analysis.

[1065] Step 3:

[1066] The server receives the submitted metadata and analyzes past file naming habits using machine learning algorithms. The input is past file names and the latest metadata, and feature extraction and data learning are used to identify file name patterns. Specific processing involves vectorization and algorithms such as the Naive Bayes model.

[1067] Step 4:

[1068] The server generates a recommended file name based on the analysis results. Using the analyzed habit data and new metadata as input, it generates a file name that follows specific rules (e.g., "2023_10_03_Quality Inspection_Report.docx"). It is important that the generated recommended file name is in a format that is easy for users to understand.

[1069] Step 5:

[1070] Sends the generated suggested filename to the terminal and displays it to the user. The input is the suggested filename generated by the server and sends it as output to the terminal, which displays it to the user, who reviews the filename.

[1071] Step 6:

[1072] The user checks the suggested file name and corrects it if necessary. The user edits the suggested file name and decides on the final file name. In this step, corrections are made directly via the user interface.

[1073] Step 7:

[1074] The terminal sends the file name confirmed by the user to the server and stores it. The confirmed file name is sent from the terminal to the server as the final input, and the server stores the confirmed name. The process is completed to ensure consistent and efficient file management.

[1075] This series of processes reduces the burden on the user and enables efficient file naming and management.

[1076] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1077] This invention relates to a system that automates the naming of new files when a user creates them. This system has the function of learning each user's naming habits and recommending file names based on unified rules, and by combining it with an emotion engine that recognizes the user's emotions, it is possible to recommend more appropriate file names.

[1078] First, when a user creates a new file, the device detects the operation. Based on the detected operation, the device collects metadata for the new file. The collected metadata includes the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[1079] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates emotions by analyzing the user's facial recognition technology, typing speed, and typing patterns. For example, it can analyze the user's facial expressions using a camera to determine their stress level and satisfaction. It can also read emotions from the speed and rhythm of keyboard typing.

[1080] The server receives the submitted metadata and emotion information from the emotion engine. The server integrates this information and retrieves the user's past file naming data from the database. A machine learning algorithm is applied to analyze the past file names and learn the user's naming patterns.

[1081] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it can recommend a simple and easy-to-understand filename. On the other hand, if the user is in a positive state, it can suggest a detailed and specific filename. The generated recommended filenames are adapted to the user's emotional state and are more user-friendly.

[1082] The suggested filename is sent to the device, which displays it to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. The saved filename and associated metadata are sent to the server and used for the next analysis.

[1083] As a concrete example, consider the case where a user attempts to create a new presentation. As the user performs an operation, the device detects it and collects metadata and emotional data. Facial recognition technology is used to recognize that the user is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_TechnicalExplanationPresentation.pptx." This name is sent to the device and displayed to the user. The user confirms the name and, satisfied with it, saves it as is.

[1084] In this way, our system recognizes user emotions and generates appropriate recommended filenames based on those emotions, improving file management efficiency and user experience. By combining it with an emotion engine, we can provide more personalized services and increase user satisfaction.

[1085] The processing flow will be explained below.

[1086] Step 1:

[1087] The user performs an operation to create a new file. For example, the user clicks the "New" button in word processing software. The device detects this operation.

[1088] Step 2:

[1089] The device collects metadata for new files, including user ID, creation date and time, file type, and a summary of the initial contents. The device records this information in real time.

[1090] Step 3:

[1091] The device activates an emotion engine to recognize the user's emotions. For example, the device's camera can be used to recognize the user's face and analyze their facial expressions to determine their emotions. Keyboard input speed and patterns can also be analyzed to read emotions.

[1092] Step 4:

[1093] The device sends the collected metadata and emotion data to the server in a unified format.

[1094] Step 5:

[1095] The server receives the metadata and emotion data. It also retrieves the user's past file naming data from the database. For example, the past file name of user ID "12345" might be "2023_09_25_ProjectA_Report.docx."

[1096] Step 6:

[1097] The server analyzes past filenames and uses machine learning algorithms to learn user naming patterns. It extracts date formats, keywords, and naming conventions contained in filenames. For example, it might find a pattern like "date + project name + report."

[1098] Step 7:

[1099] The server generates new recommended filenames based on the learning results and the recognized emotional information. For example, if the user is feeling stressed, it recommends a simple filename like "2023_10_03_ProjectA_Report.docx." Conversely, if the user is in a positive state, it generates a detailed filename like "2023_10_03_ProjectA_ProgressReport.docx."

[1100] Step 8:

[1101] The server sends the generated suggested file name to the device. The device displays the received suggested file name to the user. The user confirms the proposed name on the device screen.

[1102] Step 9:

[1103] The user checks the suggested file name and modifies it if necessary. For example, they can change it to "2023_10_03_ProjectA_WeeklyReport.docx." Then, they confirm the modified file name.

[1104] Step 10:

[1105] The device creates and saves a new file with the file name determined by the user, and the file is saved persistently to local or cloud storage.

[1106] Step 11:

[1107] The device sends the confirmed filename and associated metadata to the server, which adds the data to a training database that is used in subsequent analyses to improve the accuracy of filename recommendations.

[1108] Example 2

[1109] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1110] Conventional file naming systems make it difficult for users to quickly generate the file names they intended, and the time and effort required to select an appropriate file name can be a significant burden, especially when users are busy or stressed. Furthermore, inconsistent user naming patterns can make file management cumbersome. Furthermore, conventional systems are unable to suggest personalized file names that take into account the user's emotions and circumstances, resulting in a lack of improvement in the user experience.

[1111] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1112] In this invention, the server includes a means for learning a user's past file naming habits and generating recommended file names, a means for analyzing the user's past file names using a machine learning algorithm, and a means for including the file type, creation date and time, user ID, and a summary of the initial contents in the collected metadata. This allows the server to quickly and automatically generate an optimal file name that takes into account both the user's past naming habits and their current emotional state when creating a new file. This also improves file management efficiency and the user experience.

[1113] A "user" is an entity that uses this system to create and manage new files.

[1114] A "file" is a document, image, sound, or other unit of information stored in digital form.

[1115] "Metadata" is additional information that accompanies a file, specifically information that includes the user ID, creation date and time, file type, and a summary of the initial contents.

[1116] A "terminal" is an electronic device such as a computer, tablet, or smartphone that is directly operated by a user.

[1117] A "server" is a computer system that receives metadata and emotion information from terminals via a network and processes this data.

[1118] An "emotion engine" is software or hardware installed on a device that has the ability to recognize and estimate a user's emotions.

[1119] A "machine learning algorithm" is a mathematical technique that learns from past data and makes predictions and classifications for new data.

[1120] A "suggested file name" is a name for a new file that is generated by the server based on the user's past file naming habits and emotional state, and is displayed on the terminal.

[1121] This invention relates to a system that automates the naming of new files when a user creates them. This system is composed of a terminal, a server, and an emotion engine. The specific operation of the system is described below.

[1122] First, when a user creates a new file using a device, the device detects the action. For example, when a user clicks the "Create New" button on a computer, tablet, or other device. When this action is detected, the device collects metadata about the new file. The metadata includes the user ID, creation date and time, file type (e.g., .docx, .pptx), and a summary of the initial contents.

[1123] The collected metadata is sent from the device to the server in real time. At that time, the device is equipped with an emotion engine that recognizes the user's emotions. Specifically, the emotion engine uses facial recognition technology (e.g., OpenCV) and keyboard input information. It analyzes the user's facial expressions using a camera to estimate their stress level and satisfaction. It also reads changes in the user's emotions by analyzing the speed and rhythm of keyboard input. This makes it possible to understand the emotional state of the user when creating a new file.

[1124] Meanwhile, the server receives the metadata and emotional information sent from the device. The server integrates this information and retrieves the user's past file naming data from a database. It then applies a machine learning algorithm (e.g., random forest or deep learning model) to the retrieved past data to learn the user's naming patterns. Based on this learning result, the server generates new recommended file names. The generated recommended file names are adapted to the user's emotional state and support the editing process.

[1125] For example, if a user is concentrating on creating a presentation, the server generates a detailed and specific filename, such as "2023_10_03_TechnicalExplanationPresentation.pptx." The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary.

[1126] The file is then saved with the filename determined by the user. This filename and associated metadata are then sent back to the server and used for the next analysis. This allows the system to continue learning the user's naming patterns with increasing accuracy.

[1127] Prompt Sentence Examples

[1128] "When creating a new presentation, suggest file names. Consider your past naming patterns and your current emotional state."

[1129] This invention enables automatic generation of file names that take into account the user's feelings and past naming patterns, thereby improving the efficiency of file management and the user experience.

[1130] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1131] Step 1:

[1132] The user creates a new file.

[1133] The user creates a new file using the device. The trigger is a user operation such as clicking the "Create New" button. The device detects this operation event.

[1134] Input: Create new user

[1135] Output: Notification of new event occurrence

[1136] Step 2:

[1137] Device collects metadata

[1138] When a new file creation event occurs, the device collects metadata related to the file, including the user ID, creation date and time, file type, and a summary of the initial contents.

[1139] Input: Newly created event

[1140] Output: Collected metadata (user ID, creation date, file type, summary of initial contents)

[1141] Step 3:

[1142] The device sends the metadata to the server.

[1143] The terminal sends the collected metadata to the server, which transmits the metadata to the server in real time.

[1144] Input: Collected metadata

[1145] Output: Metadata sent to the server

[1146] Step 4:

[1147] The device recognizes emotions using an emotion engine

[1148] The device uses an emotion engine to recognize the user's emotions. It analyzes the user's facial expressions with a camera, as well as the typing speed and rhythm of the keyboard, to estimate the user's emotional state (e.g., stress, concentration, satisfaction).

[1149] Input: Real-time facial expression data and keyboard input data of the user

[1150] Output: Estimated user emotion information (stress, concentration, satisfaction, etc.)

[1151] Step 5:

[1152] Send emotional information to the server

[1153] The device sends the recognized emotion information to the server, which receives the emotion information along with the metadata.

[1154] Input: Estimated emotion information

[1155] Output: Send emotional information to the server

[1156] Step 6:

[1157] The server retrieves the user's past naming data.

[1158] The server retrieves the user's past file naming data from the database based on the received metadata and emotion information.

[1159] Input: Metadata, emotional information

[1160] Output: User's past file naming data

[1161] Step 7:

[1162] The server applies machine learning algorithms to learn naming patterns.

[1163] The server applies a machine learning algorithm (e.g., random forest, deep learning model) to the user's past file naming data to learn the user's naming patterns.

[1164] Input: User's previous file naming data

[1165] Output: Learned naming pattern model

[1166] Step 8:

[1167] The server generates a suggested filename

[1168] The server generates recommended filenames based on the learned naming pattern model and current sentiment information, with appropriate format and content.

[1169] Input: Learned naming pattern model, current emotional information

[1170] Output: Suggested file name

[1171] Step 9:

[1172] Send a suggested filename to the device

[1173] The server sends the generated recommended filename to the terminal, which displays the recommended filename in real time.

[1174] Input: Suggested file name

[1175] Output: Suggested filename sent to terminal

[1176] Step 10:

[1177] The device displays a suggested filename to the user.

[1178] The device will display the received suggested filename to the user, who will be given the option to review and modify the suggested filename.

[1179] Input: Suggested file name

[1180] Output: File name displayed to the user

[1181] Step 11:

[1182] The user confirms the file name

[1183] The user reviews the proposed filename, corrects it if necessary, and confirms the final filename.

[1184] Input: The suggested file name shown

[1185] Output: Final file name

[1186] Step 12:

[1187] The device saves the file and sends the metadata to the server.

[1188] The device saves the file with the determined file name, and sends the saved file name and related metadata to the server for the next analysis.

[1189] Input: Final file name

[1190] Output: Saved files and associated metadata sent to the server

[1191] (Application example 2)

[1192] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1193] Conventional file naming systems require users to think of an appropriate file name when creating a new file, which increases the complexity of the work and reduces work efficiency, especially in workplaces that handle large amounts of data. Furthermore, recommending a uniform file name without considering the user's emotional state can lead to a poor user experience and increased stress at work. Furthermore, file management is even more important in workplaces where many files are generated, such as logistics centers, and a more efficient and appropriate file naming system is needed.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting metadata of a file when a user creates a new file; means for transmitting the collected metadata to the server; means for the server to learn the user's past file naming habits and generate a recommended file name; means for transmitting the generated recommended file name to the terminal and displaying it to the user; means for saving the file name determined by the user as a file; means for recognizing the user's emotion; and means for generating a recommended file name based on the recognized emotion. This enables automatic recommendation of an optimal file name taking into account the user's emotional state and past naming patterns, which is expected to improve work efficiency and the user experience. Furthermore, file management can be more effectively performed at sites that handle large amounts of data, such as logistics centers.

[1195] "Metadata" is data that includes various attribute information related to a file, specifically the file type, creation date and time, user ID, and an overview of the initial contents.

[1196] The "emotion engine" is a software component that analyzes the user's emotional state, using facial recognition technology, input speed, and input patterns.

[1197] A "machine learning algorithm" is an algorithm that learns patterns and rules based on data and makes predictions and classifications.

[1198] A "head-mounted display" is a display device worn by a user on the head to provide visual information, and is used, for example, in logistics centers to improve work efficiency.

[1199] "Emotion recognition" is a technology that estimates a user's emotional state from their facial expressions, movements, input speed, etc., making it possible to grasp the user's current psychological state.

[1200] "File naming habits" refers to the tendency of users to use certain criteria or patterns in naming files in the past.

[1201] A "recommended file name" is a file name that is automatically generated based on collected data and learning results and presented to the user.

[1202] A logistics center is a facility that stores, manages, and distributes goods and materials, and is a site where a large amount of data needs to be generated and managed.

[1203] This invention relates to a system that automates the naming of new files when a user creates them. This system learns the user's naming habits and recommends file names based on unified rules. In addition, it combines an emotion engine that recognizes the user's emotions to recommend more appropriate file names.

[1204] Specifically, when a user creates a new file, the device detects the operation. At this stage, the device collects metadata for the new file, including the user ID, creation date and time, file type, and a summary of the initial contents. This metadata is then sent to the server.

[1205] The device then uses an emotion engine to recognize the user's emotions. The emotion engine estimates the user's emotions by analyzing facial recognition technology, typing speed, and typing patterns. For example, it uses a camera to analyze the user's facial expressions to determine stress levels and satisfaction. It can also read emotions from keyboard typing speed and typing patterns.

[1206] The server receives the submitted metadata and the emotional information from the emotion engine and integrates these pieces of information. The server then retrieves the user's past file naming data from a database and applies a machine learning algorithm to analyze past file names. Based on this learning result and the recognized emotional information, the server generates new recommended file names. Based on the emotional information, for example, it can suggest simple file names if the user is feeling stressed, and detailed file names if the user is in a positive state.

[1207] The generated suggested filename is sent to the device and displayed to the user. The user can review the suggested filename and modify it if necessary. Once the user has finalized the filename, the device saves the file with that name. This saved filename and associated metadata are sent to the server and used for the next analysis.

[1208] As a concrete example, consider the case where a worker at a logistics center tries to create new shipping data. When the worker wears a head-mounted display (HMD) and performs an operation to create a new file, the HMD detects the operation and collects metadata and emotional data. Using facial recognition technology and input pattern analysis, it is determined that the worker is concentrating. Based on this information, the server analyzes past naming patterns and generates a suggested file name: "2023_10_03_shipment_data.csv." This name is sent to the HMD and displayed to the worker. The worker reviews the name and, satisfied with it, saves it as is.

[1209] Examples of prompts for generative AI models include:

[1210] Design a system that automatically names a new file when the user creates it. The system recommends the best filename by combining an emotion engine that recognizes the user's emotions. Please explain in detail the specific algorithmic process and the technology used.

[1211] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1212] Step 1:

[1213] The terminal detects that the user is performing an operation to create a new file.

[1214] Input: User creates a file

[1215] Output: File creation detection event

[1216] Specific operation: The device's operating system or application software detects that the user has performed a "create new file" operation and triggers an event.

[1217] Step 2:

[1218] The device collects metadata for the new file.

[1219] Input: File creation detection event

[1220] Output: Metadata (user ID, creation date, file type, summary of initial contents)

[1221] Specific operation: The device collects data using APIs and built-in functions to extract user ID, creation date and time, file type, and a summary of the initial contents from system information and file contents.

[1222] Step 3:

[1223] The terminal transmits the collected metadata and operation status to the server.

[1224] Input: Metadata

[1225] Output: A request to send data to the server

[1226] Specific operation: The terminal sends the collected metadata to the server using a network communication protocol (e.g., HTTP or HTTPS).

[1227] Step 4:

[1228] The terminal uses an emotion engine to recognize the user's emotions.

[1229] Input: User's face image, input speed, input pattern

[1230] Output: Emotion data (estimated emotional state)

[1231] Specific operation: The device's camera and sensors are used to analyze the user's facial expressions and input patterns, and the data is input into an emotion engine to estimate emotions. Emotion estimation is performed using a facial recognition library (e.g., OpenCV) and input pattern analysis algorithms.

[1232] Step 5:

[1233] The device transmits the emotion data to the server.

[1234] Input: Emotion data

[1235] Output: A request to send data to the server

[1236] Specific operation: The estimated emotion data is sent to the server using a network communication protocol.

[1237] Step 6:

[1238] The server integrates the metadata and emotion data and retrieves the user's past file naming data from a database.

[1239] Input: Metadata, emotion data

[1240] Output: Past file naming data

[1241] Specific operation: The server issues a database query to retrieve the user's past filename data and integrates it with metadata and emotion data.

[1242] Step 7:

[1243] The server applies machine learning algorithms to analyze past filenames and generate suggested filenames.

[1244] Input: Integrated data (metadata, emotion data, historical file naming data)

[1245] Output: Suggested file name

[1246] Specific operation: The server uses a machine learning model (e.g., a generative AI model) to analyze the collected data and generate optimal file names based on the results of learning the user's naming patterns.

[1247] Step 8:

[1248] The server generates a suggested filename and sends it to the device.

[1249] Input: Suggested file name

[1250] Output: Request to send data to the device

[1251] Specific operation: The generated recommended file name is sent to the terminal using a network communication protocol.

[1252] Step 9:

[1253] The terminal presents the recommended file name to the user and receives the confirmed file name.

[1254] Input: Suggested file name

[1255] Output: The confirmed file name

[1256] Specific operation: The terminal uses a GUI to display a recommended file name to the user, and if the user is satisfied, saves it as is, accepts corrections as necessary, and then confirms the final file name.

[1257] Step 10:

[1258] The device saves the file with the determined file name and sends the associated metadata to the server.

[1259] Input: Confirmed file name

[1260] Output: File save operation, data transmission request to server

[1261] Specific operation: The device saves the file with the determined file name in local storage and sends the file name and associated metadata to the server.

[1262] 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.

[1263] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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.

[1264] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1265] 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.

[1266] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1267] 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.

[1268] 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).

[1269] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1270] 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."

[1271] 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.

[1272] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1273] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1278] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] The following is further disclosed regarding the above embodiment.

[1284] (Claim 1)

[1285] a means for collecting metadata for a new file when the user creates the file;

[1286] means for transmitting the collected metadata to a server;

[1287] a means for the server to learn the user's past file naming habits and generate recommended file names;

[1288] means for transmitting the generated suggested file name to a terminal and displaying it to a user;

[1289] means for saving the file with the file name determined by the user;

[1290] A system including:

[1291] (Claim 2)

[1292] The system of claim 1, wherein the server uses a machine learning algorithm when analyzing the user's past file names.

[1293] (Claim 3)

[1294] 2. The system of claim 1, wherein the collected metadata includes file type, creation date and time, user ID, and a summary of the initial contents.

[1295] "Example 1"

[1296] (Claim 1)

[1297] a means for collecting metadata for a new file when the user creates the file;

[1298] means for transmitting the collected metadata to a server;

[1299] a means for the server to use a generative AI model to learn users' past file naming habits and generate recommended file names;

[1300] means for transmitting the generated suggested file name to a terminal and displaying it to a user;

[1301] a means for finally determining the file name confirmed and corrected by the user and saving it as a file;

[1302] A system including:

[1303] (Claim 2)

[1304] The system of claim 1, wherein the server uses a machine learning algorithm when analyzing the user's past file names.

[1305] (Claim 3)

[1306] 2. The system of claim 1, wherein the collected metadata includes file type, creation date and time, user ID, and a summary of the initial contents.

[1307] "Application Example 1"

[1308] (Claim 1)

[1309] a means for collecting metadata for a new file when the user creates the file;

[1310] means for transmitting the collected metadata to a server;

[1311] a means for the server to learn the user's past file naming habits and generate recommended file names;

[1312] means for transmitting the generated suggested file name to a terminal and displaying it to a user;

[1313] means for saving the file with the file name determined by the user;

[1314] a means for the machine to interface with the file naming system and suggest file names based on the task;

[1315] A system including:

[1316] (Claim 2)

[1317] The system of claim 1, wherein the server uses a machine learning algorithm when analyzing the user's past file names.

[1318] (Claim 3)

[1319] 2. The system of claim 1, wherein the collected metadata includes file type, creation date and time, user ID, initial content summary, and work content.

[1320] "Example 2: Combining Emotion Engines"

[1321] (Claim 1)

[1322] a means for collecting metadata for a new file when the user creates the file;

[1323] means for transmitting the collected metadata to a server;

[1324] A means for recognizing user emotions using an emotion engine in the terminal;

[1325] a means for the server to learn the user's past file naming habits and generate recommended file names;

[1326] means for transmitting the generated suggested file name to a terminal and displaying it to a user;

[1327] means for saving the file with the file name determined by the user;

[1328] a means for transmitting the saved file name and associated metadata to a server for subsequent analysis;

[1329] A system including:

[1330] (Claim 2)

[1331] The system of claim 1, wherein the server uses a machine learning algorithm when analyzing the user's past file names.

[1332] (Claim 3)

[1333] 2. The system of claim 1, wherein the collected metadata includes file type, creation date and time, user ID, and a summary of the initial contents.

[1334] "Application example 2 when combining emotion engines"

[1335] (Claim 1)

[1336] a means for collecting metadata for a new file when the user creates the file;

[1337] means for transmitting the collected metadata to a server;

[1338] a means for the server to learn the user's past file naming habits and generate recommended file names;

[1339] means for transmitting the generated suggested file name to a terminal and displaying it to a user;

[1340] means for saving the file with the file name determined by the user;

[1341] means for recognizing a user's emotion;

[1342] means for generating recommended filenames based on the recognized sentiment;

[1343] A system including:

[1344] (Claim 2)

[1345] The system of claim 1, wherein the server uses a machine learning algorithm when analyzing the user's past file names.

[1346] (Claim 3)

[1347] 2. The system of claim 1, wherein the collected metadata includes file type, creation date and time, user ID, and a summary of the initial contents.

[1348] (Claim 4)

[1349] The system according to claim 1, characterized in that it uses an emotion engine that analyzes facial recognition technology, input speed, and input patterns to recognize the user's emotions.

[1350] (Claim 5)

[1351] 2. The system according to claim 1, characterized in that the system is installed in a head-mounted display. [Explanation of symbols]

[1352] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting metadata for a new file when the user creates the file; means for transmitting the collected metadata to a server; a means for the server to learn the user's past file naming habits and generate recommended file names; means for transmitting the generated suggested file name to a terminal and displaying it to a user; means for saving the file with the file name determined by the user; A system including:

2. 2. The system of claim 1, wherein the server uses a machine learning algorithm when analyzing the user's past filenames.

3. 2. The system of claim 1, wherein the collected metadata includes file type, creation date and time, user ID, and a summary of the initial contents.

Images