System

Abstract

A system is provided.SOLUTION: A system comprising: means for periodically collecting data from internal information sources; means for analyzing the collected data and extracting important information; means for generating new content based on the extracted information using a generative model; means for distributing the generated content to employees; and means for searching for and providing the generated content in response to questions from employees.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] There is a lot of information stored within a company, but it is not easy to keep up with it all. Employees also tend to rely on specific information sources, which can lead to new insights and important information getting lost. Furthermore, there are concerns that information can become confused due to company mergers and other events, making efficient information sharing difficult. These issues can lead to a decline in employee efficiency and a situation where the organization's information utilization capabilities are not maximized. To solve this problem, an efficient information sharing system is required. [Means for solving the problem]

[0005] The present invention is a system that includes a means for periodically collecting data from internal information sources, a means for analyzing the collected data and extracting important information, a means for generating new content using a generative model based on the extracted information, a means for distributing the generated content to employees, and a means for searching and providing the generated content in response to questions from employees. This makes it possible to efficiently extract and share important information from the vast amount of information within the company and provide employees with the information they need in a timely manner. This prevents information from being buried, improves employee work efficiency, and maximizes the organization's ability to utilize information.

[0006] "Internal information sources" refer to multiple information sources for accumulating information within the company, such as Wiki, project documents, and meeting minutes.

[0007] "Means for collecting data" refers to a function or tool for periodically acquiring and storing text data from internal information sources.

[0008] "Means for analyzing data" refers to functions or tools for analyzing collected text data using natural language processing technology, etc., and extracting important information.

[0009] "Means for extracting important information" refers to functions or tools that identify keywords and phrases that are useful to employees from the results of data analysis.

[0010] A "generative model" is a generative AI model, such as GPT-4, an algorithm or program that generates content in a format that is easy for humans to understand based on text data.

[0011] "Means for generating content" refers to functions or tools for creating new content such as slides or articles based on the extracted information.

[0012] "Means of content delivery" refers to the functions or tools used to notify and provide generated content to employees, including email, internal portals, Slack channels, etc.

[0013] A "means for responding to questions" is an interface or system for accepting questions from employees and retrieving and providing generated content.

[0014] "Generated content" means slides, articles, or other forms of informational material created by a generative AI model.

[0015] "Employees" refers to company employees who use this system to access information or search for questions. [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] This invention is a system that efficiently collects and analyzes huge amounts of text data accumulated within a company, and generates and distributes new content that is useful to employees. A specific embodiment of the system is described below.

[0038] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). For example, every day at 1:00 AM, the server retrieves new data from these sources and stores it in a central database. This collection process is automated using scheduling software (e.g., a Cron job).

[0039] The server then analyzes the collected data using natural language processing (NLP) techniques, such as the TextRank algorithm, to extract important keywords and phrases from the text data. The information obtained from this analysis is then turned into useful insights and tips that can be shared with employees.

[0040] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate new content, such as slide presentations or article-style reports. The generative AI model takes the extracted key information as input and converts it into a format that employees can easily understand.

[0041] The generated content is then distributed to employees from the server via an internal portal site, email newsletter, Slack channel, etc. For example, a slide show summarizing the progress of a new project is sent to all employees via email.

[0042] Terminals (employee PCs and mobile devices) provide an interface for easy access to generated content. The terminals have a built-in search function, allowing employees to type in a specific question and display relevant content. For example, an employee can search for "progress on new projects" and instantly be served relevant slides and reports.

[0043] As a concrete example, the system might operate as follows: Every day at 1:00 AM, the server collects the latest data from the company's internal wiki, project documents, and meeting minutes. This data is analyzed and important information is extracted. Based on this information, a generative AI model generates a "Project A Progress Report" slide deck, which is shared with all employees via email and Slack. Employees can view the slide deck on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting minutes and suggestions for resolving the problem are displayed.

[0044] In this way, the information accumulated within the company can be efficiently managed and shared, thereby improving the work efficiency of employees.

[0045] The processing flow will be explained below.

[0046] Step 1: Schedule information collection

[0047] The server is scheduled to periodically collect data from internal sources, for example, using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0048] Step 2: Collect data from sources

[0049] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0050] Step 3: Analyze the data

[0051] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process involves analyzing the text data and extracting important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0052] Step 4: Extracting important information

[0053] The server then extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0054] Step 5: Use the generative AI model

[0055] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model, which organizes the information in a form that is easy for humans to understand.

[0056] Step 6: Storing generated content

[0057] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0058] Step 7: Deliver your content

[0059] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0060] Step 8: Answering user questions

[0061] The terminal provides an interface for employees to access generated content. When an employee types a question into the terminal, the terminal searches for related generated content and displays the results. For example, if a user types "latest project status," the terminal displays related slides and articles.

[0062] Step 9: Viewing Generated Content

[0063] Users view the generated content through an interface provided by their device. Users can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to stay up to date on the latest developments.

[0064] Example 1

[0065] 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."

[0066] Efficient management and sharing of internal information is important for improving employee work efficiency. However, many companies today have scattered information and lack systems for properly collecting, analyzing, and sharing it. As a result, necessary information is often not readily available, leading to a decline in work efficiency. Therefore, there is a need for a system that can effectively collect and analyze information accumulated within the company and generate and distribute it as new content that is useful to employees.

[0067] 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.

[0068] In this invention, the server includes a time scheduling means for periodically collecting data from internal information sources, a database means for storing the collected data, a means for analyzing the collected data using natural language processing technology and extracting important information, a means for generating new content using a generative AI model based on the extracted information, a distribution means for distributing the generated content to employees, and a terminal means with a search function for responding to questions from employees and searching for and providing the generated content. This makes it possible to efficiently manage and share information accumulated within the company and improve employee work efficiency.

[0069] "Time scheduling means" is a function that enables the server to periodically collect in-house information at scheduled times.

[0070] "Database means" refers to a system for safely and systematically storing and managing collected data.

[0071] "Natural language processing technology" is a technology for analyzing text data and extracting important information. Specifically, it uses language models and algorithms.

[0072] A "generative AI model" is an artificial intelligence technology that generates new content based on analyzed information.

[0073] "Distribution means" refers to the method or system used to distribute the generated content to employees. Specifically, email, an internal portal site, a messaging app, etc. are used.

[0074] "Terminal means with search functionality" refers to a device and its software that allows employees to easily search and access generated content.

[0075] "Internal documents" are various documents created and managed within a company, including information related to specific tasks or projects.

[0076] "Meeting records" are documents that record the contents of a meeting, and include minutes and memos.

[0077] "Work-related documents" means all documents and materials related to the work, including project documents.

[0078] The "TextRank algorithm" is a type of natural language processing technology, and is an algorithm for extracting important keywords and phrases from text.

[0079] This invention is a system that efficiently collects and analyzes information accumulated within a company, and generates and distributes it as new content. Specific embodiments will be described in detail below.

[0080] Gathering internal information

[0081] The server first collects data from various internal sources (such as the company's internal wiki, project documents, and meeting minutes). This collection process is run periodically using scheduling software (e.g., a Cron job). Every day at 1:00 AM, new data is retrieved from these sources and stored in a central database. Specifically, an HTTP request is sent to each source, the data is retrieved in JSON format, and the data is then inserted into the database using an INSERT query.

[0082] Data analysis

[0083] The server analyzes the collected data using natural language processing (NLP) techniques. A Python script is run to extract important keywords and phrases from the text data using the TextRank algorithm. For example, the Python library gensim can be used. The resulting information is then stored in a central database.

[0084] Content generation

[0085] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The generative AI model generates specific content by inputting the following prompt sentence:

[0086] Prompt statement:

[0087] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0088] Project Objective

[0089] Current progress

[0090] Future plans

[0091] Issues and Solutions"

[0092] The generated content is converted into a format that is easy for employees to understand, such as a slide presentation or an article-style report.

[0093] Content Delivery

[0094] The server distributes the generated content to employees via an internal portal site, email newsletter, Slack channel, etc. Specifically, it sends the generated slides and reports to a list of email addresses of all employees, or posts them to the appropriate channel using Slack's API.

[0095] Access to content

[0096] The terminals provide an interface that allows employees to easily access generated content. The terminals have a built-in search function, allowing employees to input a specific question and instantly display relevant content. For example, if an employee searches for "progress on new projects," relevant slides and reports are instantly displayed. Additionally, the terminals offer interactive features (zoom, commenting, sharing, etc.) to improve the usability of the displayed content.

[0097] Specific examples

[0098] As a concrete example, the system may operate as follows: Every day at 1:00 AM, the server collects the latest data from internal sources and analyzes this data to extract important information. Based on the extracted information, a generative AI model creates slides such as "Project A Progress Report" and shares them with all employees via email and Slack. Employees can view the slides on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting records and suggestions for resolving the problem are displayed.

[0099] In this way, employees can improve their work efficiency by efficiently managing and sharing information accumulated within the company.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The server collects data from internal sources (internal wikis, project documents, meeting minutes, etc.) every day at 1 AM. This process is automated using a Cron job. The server sends an HTTP request to the sources to retrieve the latest data. The retrieved data is sent to the server in JSON format and stored as input data in a central database. The output is the newly collected text data.

[0103] Step 2:

[0104] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it runs a Python script and uses the gensim library. As input, it uses the text data stored in a central database. It applies the TextRank algorithm to extract important keywords and phrases. As output, it generates a list of important keywords and phrases, which are also stored in the database.

[0105] Step 3:

[0106] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The server creates a prompt and incorporates keywords and phrases obtained from the analysis results into this prompt. The following is an example.

[0107] Prompt statement:

[0108] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0109] Project Objective

[0110] Current progress

[0111] Future plans

[0112] Issues and Solutions"

[0113] As input, the prompt and the analysis results are passed to a generative AI model, which processes them and generates specific content (in the form of slides or articles). As output, new content is generated and stored in a database.

[0114] Step 4:

[0115] The server distributes the generated content to employees. To do this, it uses various distribution methods (internal portal site, email newsletter, Slack channel, etc.). As input, it uses the generated content and employee contact information. The server distributes the content using, for example, an email sending script or Slack API. As output, the distributed content reaches the employee, and a record of this is kept.

[0116] Step 5:

[0117] The terminal provides an interface that allows employees to access the generated content. The terminal has a built-in search function that allows employees to input a specific question and display related content. Specifically, the terminal uses the employee's search query as input. The terminal queries the query against a database, searches for relevant content, and displays the results. In addition, the terminal provides interactive functions such as zooming, commenting, and sharing to improve the usability of the content. As an output, related content is provided to the employee.

[0118] (Application example 1)

[0119] 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."

[0120] In order to improve information management and operational efficiency at logistics centers, a system is required that can effectively collect and analyze a huge amount of information, such as incoming and outgoing records, inventory data, and employee shift schedules, and distribute it to staff in a format that is quick and easy to understand. However, currently, information collection and analysis is often done manually, which takes time and effort, and there is a risk of important information being overlooked. Furthermore, there is no system in place to properly distribute the generated information and make it easy for staff to access, which results in a decline in operational efficiency.

[0121] 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.

[0122] In this invention, the server includes means for periodically collecting data from information sources within the logistics center, means for analyzing the collected data and extracting important information, means for generating new content using a generative AI model based on the extracted information, means for distributing the generated content to staff, and means for responding to questions from staff and searching and providing the generated content. This improves the efficiency of information management in the logistics center, prevents overlooking of important information when performing work, and creates an environment in which staff can quickly access the information they need.

[0123] A "logistics center" refers to a facility that carries out logistics activities such as storing, sorting, transporting, and delivering goods.

[0124] "Source" refers to the records, databases, etc. within the distribution center or from which relevant data is collected.

[0125] "Means for periodically collecting data" refers to means that include functions or devices that continuously acquire and store data at regular intervals.

[0126] "Means for analyzing data" refers to means, including software and algorithms, for analyzing collected data and extracting useful information.

[0127] "Means for extracting significant information" refers to techniques and methods for identifying and extracting particularly useful information through data analysis.

[0128] "Generative AI models" refer to models or algorithms that use artificial intelligence technology to automatically generate new content.

[0129] "Content generation means" refers to the systems or technologies that take the extracted information and convert it into useful forms such as reports or notifications.

[0130] "Means of distribution to staff" refers to the communications methods and platforms that allow generated content to be delivered quickly to the relevant personnel.

[0131] "Means of searching and providing" refers to a system that searches for relevant content based on inquiries from staff and provides the necessary information.

[0132] This invention is a system for improving information management and operational efficiency in a logistics center. The system is configured as follows.

[0133] The server periodically collects data from various sources within the distribution center (inventory records, incoming and outgoing records, employee shift schedules, etc.) on a daily basis. This data collection process is automated using scheduling software (e.g., schedule). The data is then stored in a database management system (e.g., SQLite).

[0134] Next, for data analysis, the server analyzes the data using natural language processing technology (e.g., nltk) to extract important keywords and phrases. This analysis process provides useful information about the current status of the logistics center, future challenges, resource status, etc.

[0135] Based on the analysis results, new content is generated using a generative AI model (e.g., GPT-4). This generative AI model receives the extracted key information as a prompt and converts it into a report or notification format. An example of a prompt would be, "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management."

[0136] The generated content is distributed from the server to logistics center staff. This distribution process uses internal email and chat tools (e.g., Slack). Staff can access the generated content using their own devices (smartphones, tablets, etc.) and easily obtain the information they need for their work. The system also includes a search function, which allows them to respond to staff questions and quickly provide relevant information.

[0137] As a concrete example, the server collects the latest data from each information source within the distribution center at 1:00 AM every day. This data is analyzed using natural language processing technology to extract important information. A generative AI model uses this information to create an "inventory status report" that is shared with all staff via email and Slack. Staff can view the report on their own devices to understand the current situation at the distribution center. Additionally, when staff use the search function on their devices to search for information about "resource shortages," related data and suggestions are displayed.

[0138] In this way, the information accumulated within the logistics center can be efficiently managed and shared, leading to improved operational efficiency and streamlined operations.

[0139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0140] Step 1:

[0141] The server periodically collects data from sources within the distribution center. This data collection is scheduled at 1:00 AM every day and specifically covers data such as inventory records, inbound and outbound records, and employee shift schedules. It is automated using scheduling software (e.g., schedule). The collected data is stored in a database management system (e.g., SQLite).

[0142] Input: Information source (inventory records, receipt / dispatch records, employee shift schedules)

[0143] Output: Collected data (stored in a database)

[0144] Step 2:

[0145] The server analyzes the collected data using natural language processing techniques (e.g., nltk). This analysis process involves tokenizing the data and performing word frequency counts to extract important keywords and phrases.

[0146] Input: Collected data (data saved in step 1)

[0147] Output: Important keywords and phrases

[0148] Step 3:

[0149] The server generates new content using a generative AI model (e.g., GPT-4) based on the extracted keywords and phrases. Specifically, the generative AI model is given the following prompt: "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management." The generated content can take the form of a report or notification, for example.

[0150] Input: Important keywords, phrases, and prompts

[0151] Output: New content (reports, notifications)

[0152] Step 4:

[0153] The generated content is distributed from the server to logistics center staff via internal email and chat tools (e.g., Slack), allowing staff to quickly obtain the information they need for their work.

[0154] Input: New content (the content generated in step 3)

[0155] Output: Delivered content (email or chat format)

[0156] Step 5:

[0157] Staff use devices (smartphones and tablets) to view the distributed content. Additionally, they can use the device's search function to search for content generated based on specific questions. For example, searching for information on "resource shortages" will display relevant data and suggestions.

[0158] Input: Published content, search query

[0159] Output: Search results (related data and suggestions)

[0160] The above processing steps improve information management and operational efficiency within the logistics center.

[0161] 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.

[0162] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0163] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process is run daily at 1:00 AM using a cron job, for example. The server uses APIs to retrieve the latest data from each source and stores it in a central database.

[0164] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process uses the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. The server then organizes the results of this analysis and prepares them for the next content generation step.

[0165] The server then uses the extracted key information to generate new content using a generative AI model (e.g., GPT-4). The generative AI model takes the analysis results as input and generates content such as slides and articles based on that information.

[0166] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0167] The server then distributes the generated content to employees, using communication methods such as internal portals, email, and Slack channels. For example, a project progress report slide deck can be shared with all employees via email.

[0168] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's inputs and reactions and evaluates the user's emotional state in real time. For example, the emotion engine recognizes the user's stress level and satisfaction by analyzing the user's keyboard and mouse movements and the language used in chat.

[0169] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0170] As a concrete example, let's consider how the following system works. The server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. A generative AI model is used to generate a "Project A Progress Report" slide deck, which is then distributed to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides information at the appropriate time and in the appropriate format.

[0171] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0172] The processing flow will be explained below.

[0173] Step 1: Schedule information collection

[0174] The server is scheduled to periodically collect data from internal sources, for example using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0175] Step 2: Collect data from sources

[0176] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0177] Step 3: Analyze the data

[0178] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process analyzes the text data and extracts important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0179] Step 4: Extracting important information

[0180] The server identifies and extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0181] Step 5: Use the generative AI model

[0182] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model and organizes the information in a format that is easy for humans to understand.

[0183] Step 6: Storing generated content

[0184] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0185] Step 7: Deliver your content

[0186] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0187] Step 8: Emotion Recognition with the Emotion Engine

[0188] The device analyzes the user's inputs and reactions in real time and recognizes the user's emotional state using an emotion engine that analyzes keyboard typing speed, mouse movements, and chat language to assess the user's stress level and satisfaction.

[0189] Step 9: Providing a Question-Response Interface

[0190] The device provides an interface where users can input questions. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, the emotion engine detects that the user's stress level is high and provides content based on that situation.

[0191] Step 10: Viewing Generated Content

[0192] Users view the generated content through an interface provided by their devices. They can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to keep up with the latest developments. The emotion engine displays content taking the user's emotions into consideration, ensuring users receive information with a high level of satisfaction.

[0193] Example 2

[0194] 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."

[0195] In today's corporate environment, large amounts of internal information are stored in a variety of formats, and there is a need to efficiently collect and analyze this information and provide it as useful content for employees. However, current systems take a long time to collect and analyze information, and the generated content is often not shared appropriately. Furthermore, there are problems such as an inability to quickly provide appropriate content in response to employee questions, and the information provided is not adjusted to the user's emotional state. This can reduce the efficiency of information utilization and potentially worsen employee work efficiency.

[0196] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and retrieving and providing the generated content, means for recognizing the user's emotional state, and means for adjusting the format and order of the content to be provided based on the user's emotional state. This makes it possible to efficiently manage and share information accumulated within the company and provide information in an appropriate manner while taking into consideration the user's emotions.

[0197] "Internal sources" are collections of data generated and stored within a company, including internal documents, meeting minutes, project materials, etc.

[0198] "Periodic data collection methods" refers to mechanisms that automatically collect data at specified times or intervals, including Cron jobs and API calls.

[0199] "Means for analyzing collected data and extracting important information" refers to methods for analyzing acquired data and identifying keywords and phrases that are important to business operations, including natural language processing technology and the TextRank algorithm.

[0200] "Methods for generating new content using generative models" refers to methods for creating new content such as text or slides using machine learning models, particularly generative AI models, based on collected and analyzed data.

[0201] "Means of delivering generated content to employees" refers to the methods by which the generated content is provided to employees via email or internal communication tools (e.g., internal portal sites or Slack channels).

[0202] "Means for searching and providing generated content in response to employee inquiries" refers to a method for searching for and providing related generated content in response to an employee's inquiry to the system.

[0203] "Means for recognizing the user's emotional state" refers to a process for analyzing the user's input and behavior to evaluate their emotional state at that time, such as stress or satisfaction, and includes keyboard operation analysis and chat analysis.

[0204] "Means for adjusting the format and order of content provided based on the user's emotional state" refers to a method for dynamically changing the format and priority of information provided in consideration of the user's emotional state.

[0205] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0206] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process runs every day at 1:00 AM using a cron job. The server uses APIs to retrieve the latest data from each source and stores it in a central database. Specifically, it uses Python scripts and the "requests" library to retrieve the data and the "psycopg2" library to store it in the database.

[0207] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process utilizes the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. Specifically, the text analysis is performed using the "spaCy" library.

[0208] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and generates content such as slides and articles based on that information. Specifically, it uses OpenAI's API to send prompt text and obtain the generated text.

[0209] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0210] The server then distributes the generated content to employees. This distribution process uses communication methods such as an internal portal site, email, and Slack channels. Specifically, notifications are sent using the Slack API, and content is distributed using an email server. For example, a project progress report slide deck is shared with all employees via email.

[0211] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, it recognizes the user's stress level and satisfaction by analyzing keyboard and mouse movements and the language used in chat. "SentiStrength" is used for emotion recognition.

[0212] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0213] For example, the server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. Using a generative AI model, it generates a "Project A Progress Report" slide deck and distributes it to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides the information at the appropriate time and in the appropriate format.

[0214] Examples of prompts include:

[0215] "How's the new project going?"

[0216] "I want to know more about the current situation regarding resource shortages."

[0217] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0218] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0219] Program processing steps

[0220] Step 1: Data collection

[0221] The server periodically collects data from internal information sources. Specifically, a Cron job is run at 1:00 AM every day to retrieve data from each source using APIs. This allows the server to collect the latest information, such as the internal wiki, project documents, and meeting minutes.

[0222] Input: Cron job, API

[0223] Output: Raw data collected

[0224] How it works: A cron job launches a Python script that uses the "requests" library to retrieve data from each source and store it in a central database.

[0225] Step 2: Data analysis

[0226] The server analyzes the collected data using natural language processing (NLP) techniques, specifically the TextRank algorithm, to extract important keywords and phrases.

[0227] Input: Raw data collected

[0228] Output: Analyzed important information

[0229] How it works: It uses the "spaCy" library to analyze text data and extracts keywords and phrases using the TextRank algorithm.

[0230] Step 3: Content generation

[0231] The server generates new content using a generative AI model (e.g., GPT-4) based on the analyzed key information. In the generation process, the server sends a prompt to the generative AI model and receives the generated text.

[0232] Input: Analyzed important information, prompt text

[0233] Output: Generated content

[0234] Specific operation: Using the OpenAI API, the prompt "Generate progress report slides for Project A" is sent to GPT-4, and the generated slide content is saved in the database.

[0235] Step 4: Content Delivery

[0236] The server then distributes the generated content to employees via internal portals, email, Slack channels, and other communication methods.

[0237] Input: Generated content

[0238] Output: Streamed content

[0239] Specific behavior: Sends notifications using the Slack API and emails to employees using a mail server.

[0240] Step 5: Emotion Recognition and User Response

[0241] The device uses an emotion engine to recognize the user's emotions in real time, specifically by analyzing keyboard and mouse operation data and chat language to assess stress and satisfaction.

[0242] Input: User input and behavior data

[0243] Output: User's emotional state rating

[0244] What it does: It uses SentiStrength to analyze the user's keyboard input and assess their emotional state in real time.

[0245] Step 6: Providing content to users

[0246] Users can browse the generated content through their devices, input questions, and the system will provide appropriate content for that question, taking into account the user's emotional state.

[0247] Input: User question, emotional state

[0248] Output: The appropriate content provided

[0249] Specific operation: When a user asks about the "progress of a new project," the device uses an emotion engine to analyze the user's emotional state and provides information in the optimal order according to the situation.

[0250] (Application example 2)

[0251] 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."

[0252] In today's corporate environment, it is important to efficiently collect and analyze internal information and provide it to employees in a timely manner. However, in many cases, the amount of information is so vast that it is difficult for employees to effectively utilize it in response to their own emotions and stress levels. For this reason, there is a need for a method that makes it easy for employees to find information and provides appropriate information according to their emotional state.

[0253] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0254] In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and searching and providing the generated content, means for analyzing the emotional state of a user using an emotion engine that recognizes the user's emotions, and means for prioritizing and providing appropriate information according to the emotional state, thereby enabling employees to quickly obtain appropriate information according to their emotional state.

[0255] 1. "Internal information sources" refers to databases and systems that provide information such as documents, meeting minutes, and project documents that are generated and stored within a company.

[0256] 2. "Data collection means" means the methods and devices by which the required data is periodically obtained from sources and stored in a central database.

[0257] 3. "Means for analyzing data and extracting important information" refers to methods or devices that use natural language processing technology to analyze collected data and identify important information, such as specific keywords or phrases.

[0258] 4. “Generative Model” means an artificial intelligence model, particularly a generative AI model, used to generate new content based on collected and analyzed information.

[0259] 5. "Means for generating content" refers to a method or device for automatically creating content such as new slides or articles using a generative model.

[0260] 6. "Means for distributing content to employees" refers to methods and devices for providing generated content to employees via internal portals, email, chat tools, etc.

[0261] 7. "Means for searching and providing content" refers to methods and devices for effectively searching for and appropriately providing content generated in response to employee questions.

[0262] 8. "Emotion engine" refers to artificial intelligence technology that analyzes user input and operations and evaluates the user's emotional state in real time.

[0263] 9. "Means for analyzing emotional state" means a method or device that uses an emotion engine to determine a user's stress level or satisfaction level.

[0264] 10. "Means for prioritizing and providing appropriate information according to emotional state" means a method or device for providing the most appropriate information on a priority basis based on the user's emotional state.

[0265] A specific embodiment of the present invention will be described. This invention is a system that realizes user emotion recognition and appropriate product recommendations in a virtual store. The detailed operation of the system and the hardware and software used will be described below.

[0266] The server periodically collects data from various internal sources (internal documents, meeting minutes, project documents, etc.). The data collection process is run daily at 1:00 AM using a Cron job, for example. The collected data is stored in a central database, using an API to retrieve the latest data from each source.

[0267] The collected data is then analyzed by the server using natural language processing (NLP) techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases for the next step of content generation.

[0268] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and automatically generates content such as slides and articles based on that information. The generated content is stored in a database by the server and properly indexed.

[0269] Furthermore, this system incorporates an emotion engine that allows the device to recognize the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, when the user is using a smartphone or head-mounted display (HMD), emotion recognition is performed using sensors such as the camera and microphone. This is done using the emotion engine API and TextBlob library.

[0270] Users can browse the generated content and use the interactive interface through their device. When the user inputs a question or request, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. At this time, the following prompt sentence is input into the generative AI model:

[0271] text

[0272] User emotion data: {'happy': 0.8, 'stressed': 0.2}, Sentiment analysis data: {'polarity': -0.5, 'subjectivity': 0.6}

[0273] For example, if a user enters "I'm looking for a new smartphone but I'm having trouble choosing," the application uses the emotion engine to recognize their stress level and inputs the above prompt sentence into the GPT-4 model. The GPT-4 model then outputs recommendations for relaxing products, such as "aroma diffusers" and "massage chairs." The application then retrieves relevant product information from the product database and suggests them to the user.

[0274] This system allows users to quickly find the right product based on their emotional state, improving the shopping experience in virtual stores by enabling effective emotional product selection based on the information provided.

[0275] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0276] Step 1:

[0277] The server collects data from internal sources. Specifically, it uses an API to retrieve the latest data from internal documents, meeting minutes, project documents, etc., and stores it in a central database. This process runs at 1:00 AM every day using a Cron job. The input is data from each source, and the output is the data stored in the central database.

[0278] Step 2:

[0279] The server analyzes the collected data using natural language processing techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases. The input is the data stored in a central database, and the output is the extracted important information.

[0280] Step 3:

[0281] The server generates new content using a generative AI model (such as GPT-4) based on the extracted key information. The generative AI model receives the analysis results as input and generates content such as slides and articles. The input is the extracted key information, and the output is the generated new content.

[0282] Step 4:

[0283] The server stores the generated content in a database and indexes it appropriately, making it easily searchable and accessible later. The input is the new content generated, and the output is an indexed database entry.

[0284] Step 5:

[0285] The server distributes the generated content to employees. The content is shared with employees using communication methods such as internal portal sites, email, and chat tools. The input is the indexed new content, and the output is notifications and links sent to employees.

[0286] Step 6:

[0287] The device uses an emotion engine to recognize the user's emotions. The device collects the user's facial expressions and voice using the camera and microphone of the smartphone or HMD, and analyzes the user's emotional state using the emotion engine API and TextBlob library. The input is the user's facial expression and voice data, and the output is the user's emotional state data (e.g., {'happy': 0.8, 'stressed': 0.2}).

[0288] Step 7:

[0289] The device receives questions or requests entered by the user and uses an emotion engine to analyze their emotional state. Based on the analysis results, the device inputs prompts into a generative AI model to generate optimal content. The input is the user's question or request and emotional state data, and the output is the generated recommended content.

[0290] Step 8:

[0291] The server searches the product database for the generated recommended content and provides it to the user. For example, if a user inputs "I'm looking for a new smartphone, but I'm having trouble choosing one," the server inputs the following prompt sentence to the generative AI model:

[0292] text

[0293] User emotion data: {'happy': 0.1, 'stressed': 0.9}, Sentiment analysis data: {'polarity': -0.7, 'subjectivity': 0.9}

[0294] Based on this prompt, the GPT-4 model recommends the most suitable products, searches for the relevant products in the product database based on the recommendation results, and provides them to the user. The input is the prompt and the generated recommendation content, and the output is a list of products presented to the user.

[0295] 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.

[0296] 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.

[0297] 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.

[0298] [Second embodiment]

[0299] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0300] 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.

[0301] 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).

[0302] 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.

[0303] 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.

[0304] 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).

[0305] 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.

[0306] 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.

[0307] 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.

[0308] 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.

[0309] 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.

[0310] 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."

[0311] This invention is a system that efficiently collects and analyzes huge amounts of text data accumulated within a company, and generates and distributes new content that is useful to employees. A specific embodiment of the system is described below.

[0312] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). For example, every day at 1:00 AM, the server retrieves new data from these sources and stores it in a central database. This collection process is automated using scheduling software (e.g., a Cron job).

[0313] The server then analyzes the collected data using natural language processing (NLP) techniques, such as the TextRank algorithm, to extract important keywords and phrases from the text data. The information obtained from this analysis is then turned into useful insights and tips that can be shared with employees.

[0314] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate new content, such as slide presentations or article-style reports. The generative AI model takes the extracted key information as input and converts it into a format that employees can easily understand.

[0315] The generated content is then distributed to employees from the server via an internal portal site, email newsletter, Slack channel, etc. For example, a slide show summarizing the progress of a new project is sent to all employees via email.

[0316] Terminals (employee PCs and mobile devices) provide an interface for easy access to generated content. The terminals have a built-in search function, allowing employees to type in a specific question and display relevant content. For example, an employee can search for "progress on new projects" and instantly be served relevant slides and reports.

[0317] As a concrete example, the system might operate as follows: Every day at 1:00 AM, the server collects the latest data from the company's internal wiki, project documents, and meeting minutes. This data is analyzed and important information is extracted. Based on this information, a generative AI model generates a "Project A Progress Report" slide deck, which is shared with all employees via email and Slack. Employees can view the slide deck on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting minutes and suggestions for resolving the problem are displayed.

[0318] In this way, the information accumulated within the company can be efficiently managed and shared, thereby improving the work efficiency of employees.

[0319] The processing flow will be explained below.

[0320] Step 1: Schedule information collection

[0321] The server is scheduled to periodically collect data from internal sources, for example, using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0322] Step 2: Collect data from sources

[0323] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0324] Step 3: Analyze the data

[0325] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process involves analyzing the text data and extracting important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0326] Step 4: Extracting important information

[0327] The server then extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0328] Step 5: Use the generative AI model

[0329] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model, which organizes the information in a form that is easy for humans to understand.

[0330] Step 6: Storing generated content

[0331] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0332] Step 7: Deliver your content

[0333] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0334] Step 8: Answering user questions

[0335] The terminal provides an interface for employees to access generated content. When an employee types a question into the terminal, the terminal searches for related generated content and displays the results. For example, if a user types "latest project status," the terminal displays related slides and articles.

[0336] Step 9: Viewing Generated Content

[0337] Users view the generated content through an interface provided by their device. Users can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to stay up to date on the latest developments.

[0338] Example 1

[0339] 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."

[0340] Efficient management and sharing of internal information is important for improving employee work efficiency. However, many companies today have scattered information and lack systems for properly collecting, analyzing, and sharing it. As a result, necessary information is often not readily available, leading to a decline in work efficiency. Therefore, there is a need for a system that can effectively collect and analyze information accumulated within the company and generate and distribute it as new content that is useful to employees.

[0341] 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.

[0342] In this invention, the server includes a time scheduling means for periodically collecting data from internal information sources, a database means for storing the collected data, a means for analyzing the collected data using natural language processing technology and extracting important information, a means for generating new content using a generative AI model based on the extracted information, a distribution means for distributing the generated content to employees, and a terminal means with a search function for responding to questions from employees and searching for and providing the generated content. This makes it possible to efficiently manage and share information accumulated within the company and improve employee work efficiency.

[0343] "Time scheduling means" is a function that enables the server to periodically collect in-house information at scheduled times.

[0344] "Database means" refers to a system for safely and systematically storing and managing collected data.

[0345] "Natural language processing technology" is a technology for analyzing text data and extracting important information. Specifically, it uses language models and algorithms.

[0346] A "generative AI model" is an artificial intelligence technology that generates new content based on analyzed information.

[0347] "Distribution means" refers to the method or system used to distribute the generated content to employees. Specifically, email, an internal portal site, a messaging app, etc. are used.

[0348] "Terminal means with search functionality" refers to a device and its software that allows employees to easily search and access generated content.

[0349] "Internal documents" are various documents created and managed within a company, including information related to specific tasks or projects.

[0350] "Meeting records" are documents that record the contents of a meeting, and include minutes and memos.

[0351] "Work-related documents" means all documents and materials related to the work, including project documents.

[0352] The "TextRank algorithm" is a type of natural language processing technology, and is an algorithm for extracting important keywords and phrases from text.

[0353] This invention is a system that efficiently collects and analyzes information accumulated within a company, and generates and distributes it as new content. Specific embodiments will be described in detail below.

[0354] Gathering internal information

[0355] The server first collects data from various internal sources (such as the company's internal wiki, project documents, and meeting minutes). This collection process is run periodically using scheduling software (e.g., a Cron job). Every day at 1:00 AM, new data is retrieved from these sources and stored in a central database. Specifically, an HTTP request is sent to each source, the data is retrieved in JSON format, and the data is then inserted into the database using an INSERT query.

[0356] Data analysis

[0357] The server analyzes the collected data using natural language processing (NLP) techniques. A Python script is run to extract important keywords and phrases from the text data using the TextRank algorithm. For example, the Python library gensim can be used. The resulting information is then stored in a central database.

[0358] Content generation

[0359] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The generative AI model generates specific content by inputting the following prompt sentence:

[0360] Prompt statement:

[0361] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0362] Project Objective

[0363] Current progress

[0364] Future plans

[0365] Issues and Solutions"

[0366] The generated content is converted into a format that is easy for employees to understand, such as a slide presentation or an article-style report.

[0367] Content Delivery

[0368] The server distributes the generated content to employees via an internal portal site, email newsletter, Slack channel, etc. Specifically, it sends the generated slides and reports to a list of email addresses of all employees, or posts them to the appropriate channel using Slack's API.

[0369] Access to content

[0370] The terminals provide an interface that allows employees to easily access generated content. The terminals have a built-in search function, allowing employees to input a specific question and instantly display relevant content. For example, if an employee searches for "progress on new projects," relevant slides and reports are instantly displayed. Additionally, the terminals offer interactive features (zoom, commenting, sharing, etc.) to improve the usability of the displayed content.

[0371] Specific examples

[0372] As a concrete example, the system may operate as follows: Every day at 1:00 AM, the server collects the latest data from internal sources and analyzes this data to extract important information. Based on the extracted information, a generative AI model creates slides such as "Project A Progress Report" and shares them with all employees via email and Slack. Employees can view the slides on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting records and suggestions for resolving the problem are displayed.

[0373] In this way, employees can improve their work efficiency by efficiently managing and sharing information accumulated within the company.

[0374] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0375] Step 1:

[0376] The server collects data from internal sources (internal wikis, project documents, meeting minutes, etc.) every day at 1 AM. This process is automated using a Cron job. The server sends an HTTP request to the sources to retrieve the latest data. The retrieved data is sent to the server in JSON format and stored as input data in a central database. The output is the newly collected text data.

[0377] Step 2:

[0378] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it runs a Python script and uses the gensim library. As input, it uses the text data stored in a central database. It applies the TextRank algorithm to extract important keywords and phrases. As output, it generates a list of important keywords and phrases, which are also stored in the database.

[0379] Step 3:

[0380] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The server creates a prompt and incorporates keywords and phrases obtained from the analysis results into this prompt. The following is an example.

[0381] Prompt statement:

[0382] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0383] Project Objective

[0384] Current progress

[0385] Future plans

[0386] Issues and Solutions"

[0387] As input, the prompt and the analysis results are passed to a generative AI model, which processes them and generates specific content (in the form of slides or articles). As output, new content is generated and stored in a database.

[0388] Step 4:

[0389] The server distributes the generated content to employees. To do this, it uses various distribution methods (internal portal site, email newsletter, Slack channel, etc.). As input, it uses the generated content and employee contact information. The server distributes the content using, for example, an email sending script or Slack API. As output, the distributed content reaches the employee, and a record of this is kept.

[0390] Step 5:

[0391] The terminal provides an interface that allows employees to access the generated content. The terminal has a built-in search function that allows employees to input a specific question and display related content. Specifically, the terminal uses the employee's search query as input. The terminal queries the query against a database, searches for relevant content, and displays the results. In addition, the terminal provides interactive functions such as zooming, commenting, and sharing to improve the usability of the content. As an output, related content is provided to the employee.

[0392] (Application example 1)

[0393] 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."

[0394] In order to improve information management and operational efficiency at logistics centers, a system is required that can effectively collect and analyze a huge amount of information, such as incoming and outgoing records, inventory data, and employee shift schedules, and distribute it to staff in a format that is quick and easy to understand. However, currently, information collection and analysis is often done manually, which takes time and effort, and there is a risk of important information being overlooked. Furthermore, there is no system in place to properly distribute the generated information and make it easy for staff to access, which results in a decline in operational efficiency.

[0395] 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.

[0396] In this invention, the server includes means for periodically collecting data from information sources within the logistics center, means for analyzing the collected data and extracting important information, means for generating new content using a generative AI model based on the extracted information, means for distributing the generated content to staff, and means for responding to questions from staff and searching and providing the generated content. This improves the efficiency of information management in the logistics center, prevents overlooking of important information when performing work, and creates an environment in which staff can quickly access the information they need.

[0397] A "logistics center" refers to a facility that carries out logistics activities such as storing, sorting, transporting, and delivering goods.

[0398] "Source" refers to the records, databases, etc. within the distribution center or from which relevant data is collected.

[0399] "Means for periodically collecting data" refers to means that include functions or devices that continuously acquire and store data at regular intervals.

[0400] "Means for analyzing data" refers to means, including software and algorithms, for analyzing collected data and extracting useful information.

[0401] "Means for extracting significant information" refers to techniques and methods for identifying and extracting particularly useful information through data analysis.

[0402] "Generative AI models" refer to models or algorithms that use artificial intelligence technology to automatically generate new content.

[0403] "Content generation means" refers to the systems or technologies that take the extracted information and convert it into useful forms such as reports or notifications.

[0404] "Means of distribution to staff" refers to the communications methods and platforms that allow generated content to be delivered quickly to the relevant personnel.

[0405] "Means of searching and providing" refers to a system that searches for relevant content based on inquiries from staff and provides the necessary information.

[0406] This invention is a system for improving information management and operational efficiency in a logistics center. The system is configured as follows.

[0407] The server periodically collects data from various sources within the distribution center (inventory records, incoming and outgoing records, employee shift schedules, etc.) on a daily basis. This data collection process is automated using scheduling software (e.g., schedule). The data is then stored in a database management system (e.g., SQLite).

[0408] Next, for data analysis, the server analyzes the data using natural language processing technology (e.g., nltk) to extract important keywords and phrases. This analysis process provides useful information about the current status of the logistics center, future challenges, resource status, etc.

[0409] Based on the analysis results, new content is generated using a generative AI model (e.g., GPT-4). This generative AI model receives the extracted key information as a prompt and converts it into a report or notification format. An example of a prompt would be, "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management."

[0410] The generated content is distributed from the server to logistics center staff. This distribution process uses internal email and chat tools (e.g., Slack). Staff can access the generated content using their own devices (smartphones, tablets, etc.) and easily obtain the information they need for their work. The system also includes a search function, which allows them to respond to staff questions and quickly provide relevant information.

[0411] As a concrete example, the server collects the latest data from each information source within the distribution center at 1:00 AM every day. This data is analyzed using natural language processing technology to extract important information. A generative AI model uses this information to create an "inventory status report" that is shared with all staff via email and Slack. Staff can view the report on their own devices to understand the current situation at the distribution center. Additionally, when staff use the search function on their devices to search for information about "resource shortages," related data and suggestions are displayed.

[0412] In this way, the information accumulated within the logistics center can be efficiently managed and shared, leading to improved operational efficiency and streamlined operations.

[0413] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0414] Step 1:

[0415] The server periodically collects data from sources within the distribution center. This data collection is scheduled at 1:00 AM every day and specifically covers data such as inventory records, inbound and outbound records, and employee shift schedules. It is automated using scheduling software (e.g., schedule). The collected data is stored in a database management system (e.g., SQLite).

[0416] Input: Information source (inventory records, receipt / dispatch records, employee shift schedules)

[0417] Output: Collected data (stored in a database)

[0418] Step 2:

[0419] The server analyzes the collected data using natural language processing techniques (e.g., nltk). This analysis process involves tokenizing the data and performing word frequency counts to extract important keywords and phrases.

[0420] Input: Collected data (data saved in step 1)

[0421] Output: Important keywords and phrases

[0422] Step 3:

[0423] The server generates new content using a generative AI model (e.g., GPT-4) based on the extracted keywords and phrases. Specifically, the generative AI model is given the following prompt: "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management." The generated content can take the form of a report or notification, for example.

[0424] Input: Important keywords, phrases, and prompts

[0425] Output: New content (reports, notifications)

[0426] Step 4:

[0427] The generated content is distributed from the server to logistics center staff via internal email and chat tools (e.g., Slack), allowing staff to quickly obtain the information they need for their work.

[0428] Input: New content (the content generated in step 3)

[0429] Output: Delivered content (email or chat format)

[0430] Step 5:

[0431] Staff use devices (smartphones and tablets) to view the distributed content. Additionally, they can use the device's search function to search for content generated based on specific questions. For example, searching for information on "resource shortages" will display relevant data and suggestions.

[0432] Input: Published content, search query

[0433] Output: Search results (related data and suggestions)

[0434] The above processing steps improve information management and operational efficiency within the logistics center.

[0435] 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.

[0436] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0437] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process is run daily at 1:00 AM using a cron job, for example. The server uses APIs to retrieve the latest data from each source and stores it in a central database.

[0438] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process uses the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. The server then organizes the results of this analysis and prepares them for the next content generation step.

[0439] The server then uses the extracted key information to generate new content using a generative AI model (e.g., GPT-4). The generative AI model takes the analysis results as input and generates content such as slides and articles based on that information.

[0440] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0441] The server then distributes the generated content to employees, using communication methods such as internal portals, email, and Slack channels. For example, a project progress report slide deck can be shared with all employees via email.

[0442] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's inputs and reactions and evaluates the user's emotional state in real time. For example, the emotion engine recognizes the user's stress level and satisfaction by analyzing the user's keyboard and mouse movements and the language used in chat.

[0443] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0444] As a concrete example, let's consider how the following system works. The server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. A generative AI model is used to generate a "Project A Progress Report" slide deck, which is then distributed to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides information at the appropriate time and in the appropriate format.

[0445] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0446] The processing flow will be explained below.

[0447] Step 1: Schedule information collection

[0448] The server is scheduled to periodically collect data from internal sources, for example using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0449] Step 2: Collect data from sources

[0450] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0451] Step 3: Analyze the data

[0452] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process analyzes the text data and extracts important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0453] Step 4: Extracting important information

[0454] The server identifies and extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0455] Step 5: Use the generative AI model

[0456] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model and organizes the information in a format that is easy for humans to understand.

[0457] Step 6: Storing generated content

[0458] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0459] Step 7: Deliver your content

[0460] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0461] Step 8: Emotion Recognition with the Emotion Engine

[0462] The device analyzes the user's inputs and reactions in real time and recognizes the user's emotional state using an emotion engine that analyzes keyboard typing speed, mouse movements, and chat language to assess the user's stress level and satisfaction.

[0463] Step 9: Providing a Question-Response Interface

[0464] The device provides an interface where users can input questions. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, the emotion engine detects that the user's stress level is high and provides content based on that situation.

[0465] Step 10: Viewing Generated Content

[0466] Users view the generated content through an interface provided by their devices. They can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to keep up with the latest developments. The emotion engine displays content taking the user's emotions into consideration, ensuring users receive information with a high level of satisfaction.

[0467] Example 2

[0468] 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."

[0469] In today's corporate environment, large amounts of internal information are stored in a variety of formats, and there is a need to efficiently collect and analyze this information and provide it as useful content for employees. However, current systems take a long time to collect and analyze information, and the generated content is often not shared appropriately. Furthermore, there are problems such as an inability to quickly provide appropriate content in response to employee questions, and the information provided is not adjusted to the user's emotional state. This can reduce the efficiency of information utilization and potentially worsen employee work efficiency.

[0470] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and retrieving and providing the generated content, means for recognizing the user's emotional state, and means for adjusting the format and order of the content to be provided based on the user's emotional state. This makes it possible to efficiently manage and share information accumulated within the company and provide information in an appropriate manner while taking into consideration the user's emotions.

[0471] "Internal sources" are collections of data generated and stored within a company, including internal documents, meeting minutes, project materials, etc.

[0472] "Periodic data collection methods" refers to mechanisms that automatically collect data at specified times or intervals, including Cron jobs and API calls.

[0473] "Means for analyzing collected data and extracting important information" refers to methods for analyzing acquired data and identifying keywords and phrases that are important to business operations, including natural language processing technology and the TextRank algorithm.

[0474] "Methods for generating new content using generative models" refers to methods for creating new content such as text or slides using machine learning models, particularly generative AI models, based on collected and analyzed data.

[0475] "Means of delivering generated content to employees" refers to the methods by which the generated content is provided to employees via email or internal communication tools (e.g., internal portal sites or Slack channels).

[0476] "Means for searching and providing generated content in response to employee inquiries" refers to a method for searching for and providing related generated content in response to an employee's inquiry to the system.

[0477] "Means for recognizing the user's emotional state" refers to a process for analyzing the user's input and behavior to evaluate their emotional state at that time, such as stress or satisfaction, and includes keyboard operation analysis and chat analysis.

[0478] "Means for adjusting the format and order of content provided based on the user's emotional state" refers to a method for dynamically changing the format and priority of information provided in consideration of the user's emotional state.

[0479] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0480] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process runs every day at 1:00 AM using a cron job. The server uses APIs to retrieve the latest data from each source and stores it in a central database. Specifically, it uses Python scripts and the "requests" library to retrieve the data and the "psycopg2" library to store it in the database.

[0481] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process utilizes the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. Specifically, the text analysis is performed using the "spaCy" library.

[0482] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and generates content such as slides and articles based on that information. Specifically, it uses OpenAI's API to send prompt text and obtain the generated text.

[0483] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0484] The server then distributes the generated content to employees. This distribution process uses communication methods such as an internal portal site, email, and Slack channels. Specifically, notifications are sent using the Slack API, and content is distributed using an email server. For example, a project progress report slide deck is shared with all employees via email.

[0485] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, it recognizes the user's stress level and satisfaction by analyzing keyboard and mouse movements and the language used in chat. "SentiStrength" is used for emotion recognition.

[0486] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0487] For example, the server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. Using a generative AI model, it generates a "Project A Progress Report" slide deck and distributes it to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides the information at the appropriate time and in the appropriate format.

[0488] Examples of prompts include:

[0489] "How's the new project going?"

[0490] "I want to know more about the current situation regarding resource shortages."

[0491] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0492] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0493] Program processing steps

[0494] Step 1: Data collection

[0495] The server periodically collects data from internal information sources. Specifically, a Cron job is run at 1:00 AM every day to retrieve data from each source using APIs. This allows the server to collect the latest information, such as the internal wiki, project documents, and meeting minutes.

[0496] Input: Cron job, API

[0497] Output: Raw data collected

[0498] How it works: A cron job launches a Python script that uses the "requests" library to retrieve data from each source and store it in a central database.

[0499] Step 2: Data analysis

[0500] The server analyzes the collected data using natural language processing (NLP) techniques, specifically the TextRank algorithm, to extract important keywords and phrases.

[0501] Input: Raw data collected

[0502] Output: Analyzed important information

[0503] How it works: It uses the "spaCy" library to analyze text data and extracts keywords and phrases using the TextRank algorithm.

[0504] Step 3: Content generation

[0505] The server generates new content using a generative AI model (e.g., GPT-4) based on the analyzed key information. In the generation process, the server sends a prompt to the generative AI model and receives the generated text.

[0506] Input: Analyzed important information, prompt text

[0507] Output: Generated content

[0508] Specific operation: Using the OpenAI API, the prompt "Generate progress report slides for Project A" is sent to GPT-4, and the generated slide content is saved in the database.

[0509] Step 4: Content Delivery

[0510] The server then distributes the generated content to employees via internal portals, email, Slack channels, and other communication methods.

[0511] Input: Generated content

[0512] Output: Streamed content

[0513] Specific behavior: Sends notifications using the Slack API and emails to employees using a mail server.

[0514] Step 5: Emotion Recognition and User Response

[0515] The device uses an emotion engine to recognize the user's emotions in real time, specifically by analyzing keyboard and mouse operation data and chat language to assess stress and satisfaction.

[0516] Input: User input and behavior data

[0517] Output: User's emotional state rating

[0518] What it does: It uses SentiStrength to analyze the user's keyboard input and assess their emotional state in real time.

[0519] Step 6: Providing content to users

[0520] Users can browse the generated content through their devices, input questions, and the system will provide appropriate content for that question, taking into account the user's emotional state.

[0521] Input: User question, emotional state

[0522] Output: The appropriate content provided

[0523] Specific operation: When a user asks about the "progress of a new project," the device uses an emotion engine to analyze the user's emotional state and provides information in the optimal order according to the situation.

[0524] (Application example 2)

[0525] 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."

[0526] In today's corporate environment, it is important to efficiently collect and analyze internal information and provide it to employees in a timely manner. However, in many cases, the amount of information is so vast that it is difficult for employees to effectively utilize it in response to their own emotions and stress levels. For this reason, there is a need for a method that makes it easy for employees to find information and provides appropriate information according to their emotional state.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0528] In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and searching and providing the generated content, means for analyzing the emotional state of a user using an emotion engine that recognizes the user's emotions, and means for prioritizing and providing appropriate information according to the emotional state, thereby enabling employees to quickly obtain appropriate information according to their emotional state.

[0529] 1. "Internal information sources" refers to databases and systems that provide information such as documents, meeting minutes, and project documents that are generated and stored within a company.

[0530] 2. "Data collection means" means the methods and devices by which the required data is periodically obtained from sources and stored in a central database.

[0531] 3. "Means for analyzing data and extracting important information" refers to methods or devices that use natural language processing technology to analyze collected data and identify important information, such as specific keywords or phrases.

[0532] 4. “Generative Model” means an artificial intelligence model, particularly a generative AI model, used to generate new content based on collected and analyzed information.

[0533] 5. "Means for generating content" refers to a method or device for automatically creating content such as new slides or articles using a generative model.

[0534] 6. "Means for distributing content to employees" refers to methods and devices for providing generated content to employees via internal portals, email, chat tools, etc.

[0535] 7. "Means for searching and providing content" refers to methods and devices for effectively searching for and appropriately providing content generated in response to employee questions.

[0536] 8. "Emotion engine" refers to artificial intelligence technology that analyzes user input and operations and evaluates the user's emotional state in real time.

[0537] 9. "Means for analyzing emotional state" means a method or device that uses an emotion engine to determine a user's stress level or satisfaction level.

[0538] 10. "Means for prioritizing and providing appropriate information according to emotional state" means a method or device for providing the most appropriate information on a priority basis based on the user's emotional state.

[0539] A specific embodiment of the present invention will be described. This invention is a system that realizes user emotion recognition and appropriate product recommendations in a virtual store. The detailed operation of the system and the hardware and software used will be described below.

[0540] The server periodically collects data from various internal sources (internal documents, meeting minutes, project documents, etc.). The data collection process is run daily at 1:00 AM using a Cron job, for example. The collected data is stored in a central database, using an API to retrieve the latest data from each source.

[0541] The collected data is then analyzed by the server using natural language processing (NLP) techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases for the next step of content generation.

[0542] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and automatically generates content such as slides and articles based on that information. The generated content is stored in a database by the server and properly indexed.

[0543] Furthermore, this system incorporates an emotion engine that allows the device to recognize the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, when the user is using a smartphone or head-mounted display (HMD), emotion recognition is performed using sensors such as the camera and microphone. This is done using the emotion engine API and TextBlob library.

[0544] Users can browse the generated content and use the interactive interface through their device. When the user inputs a question or request, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. At this time, the following prompt sentence is input into the generative AI model:

[0545] text

[0546] User emotion data: {'happy': 0.8, 'stressed': 0.2}, Sentiment analysis data: {'polarity': -0.5, 'subjectivity': 0.6}

[0547] For example, if a user enters "I'm looking for a new smartphone but I'm having trouble choosing," the application uses the emotion engine to recognize their stress level and inputs the above prompt sentence into the GPT-4 model. The GPT-4 model then outputs recommendations for relaxing products, such as "aroma diffusers" and "massage chairs." The application then retrieves relevant product information from the product database and suggests them to the user.

[0548] This system allows users to quickly find the right product based on their emotional state, improving the shopping experience in virtual stores by enabling effective emotional product selection based on the information provided.

[0549] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0550] Step 1:

[0551] The server collects data from internal sources. Specifically, it uses an API to retrieve the latest data from internal documents, meeting minutes, project documents, etc., and stores it in a central database. This process runs at 1:00 AM every day using a Cron job. The input is data from each source, and the output is the data stored in the central database.

[0552] Step 2:

[0553] The server analyzes the collected data using natural language processing techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases. The input is the data stored in a central database, and the output is the extracted important information.

[0554] Step 3:

[0555] The server generates new content using a generative AI model (such as GPT-4) based on the extracted key information. The generative AI model receives the analysis results as input and generates content such as slides and articles. The input is the extracted key information, and the output is the generated new content.

[0556] Step 4:

[0557] The server stores the generated content in a database and indexes it appropriately, making it easily searchable and accessible later. The input is the new content generated, and the output is an indexed database entry.

[0558] Step 5:

[0559] The server distributes the generated content to employees. The content is shared with employees using communication methods such as internal portal sites, email, and chat tools. The input is the indexed new content, and the output is notifications and links sent to employees.

[0560] Step 6:

[0561] The device uses an emotion engine to recognize the user's emotions. The device collects the user's facial expressions and voice using the camera and microphone of the smartphone or HMD, and analyzes the user's emotional state using the emotion engine API and TextBlob library. The input is the user's facial expression and voice data, and the output is the user's emotional state data (e.g., {'happy': 0.8, 'stressed': 0.2}).

[0562] Step 7:

[0563] The device receives questions or requests entered by the user and uses an emotion engine to analyze their emotional state. Based on the analysis results, the device inputs prompts into a generative AI model to generate optimal content. The input is the user's question or request and emotional state data, and the output is the generated recommended content.

[0564] Step 8:

[0565] The server searches the product database for the generated recommended content and provides it to the user. For example, if a user inputs "I'm looking for a new smartphone, but I'm having trouble choosing one," the server inputs the following prompt sentence to the generative AI model:

[0566] text

[0567] User emotion data: {'happy': 0.1, 'stressed': 0.9}, Sentiment analysis data: {'polarity': -0.7, 'subjectivity': 0.9}

[0568] Based on this prompt, the GPT-4 model recommends the most suitable products, searches for the relevant products in the product database based on the recommendation results, and provides them to the user. The input is the prompt and the generated recommendation content, and the output is a list of products presented to the user.

[0569] 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.

[0570] 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.

[0571] 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.

[0572] [Third embodiment]

[0573] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0574] 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.

[0575] 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).

[0576] 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.

[0577] 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.

[0578] 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).

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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."

[0585] This invention is a system that efficiently collects and analyzes huge amounts of text data accumulated within a company, and generates and distributes new content that is useful to employees. A specific embodiment of the system is described below.

[0586] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). For example, every day at 1:00 AM, the server retrieves new data from these sources and stores it in a central database. This collection process is automated using scheduling software (e.g., a Cron job).

[0587] The server then analyzes the collected data using natural language processing (NLP) techniques, such as the TextRank algorithm, to extract important keywords and phrases from the text data. The information obtained from this analysis is then turned into useful insights and tips that can be shared with employees.

[0588] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate new content, such as slide presentations or article-style reports. The generative AI model takes the extracted key information as input and converts it into a format that employees can easily understand.

[0589] The generated content is then distributed to employees from the server via an internal portal site, email newsletter, Slack channel, etc. For example, a slide show summarizing the progress of a new project is sent to all employees via email.

[0590] Terminals (employee PCs and mobile devices) provide an interface for easy access to generated content. The terminals have a built-in search function, allowing employees to type in a specific question and display relevant content. For example, an employee can search for "progress on new projects" and instantly be served relevant slides and reports.

[0591] As a concrete example, the system might operate as follows: Every day at 1:00 AM, the server collects the latest data from the company's internal wiki, project documents, and meeting minutes. This data is analyzed and important information is extracted. Based on this information, a generative AI model generates a "Project A Progress Report" slide deck, which is shared with all employees via email and Slack. Employees can view the slide deck on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting minutes and suggestions for resolving the problem are displayed.

[0592] In this way, the information accumulated within the company can be efficiently managed and shared, thereby improving the work efficiency of employees.

[0593] The processing flow will be explained below.

[0594] Step 1: Schedule information collection

[0595] The server is scheduled to periodically collect data from internal sources, for example, using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0596] Step 2: Collect data from sources

[0597] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0598] Step 3: Analyze the data

[0599] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process involves analyzing the text data and extracting important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0600] Step 4: Extracting important information

[0601] The server then extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0602] Step 5: Use the generative AI model

[0603] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model, which organizes the information in a form that is easy for humans to understand.

[0604] Step 6: Storing generated content

[0605] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0606] Step 7: Deliver your content

[0607] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0608] Step 8: Answering user questions

[0609] The terminal provides an interface for employees to access generated content. When an employee types a question into the terminal, the terminal searches for related generated content and displays the results. For example, if a user types "latest project status," the terminal displays related slides and articles.

[0610] Step 9: Viewing Generated Content

[0611] Users view the generated content through an interface provided by their device. Users can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to stay up to date on the latest developments.

[0612] Example 1

[0613] 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."

[0614] Efficient management and sharing of internal information is important for improving employee work efficiency. However, many companies today have scattered information and lack systems for properly collecting, analyzing, and sharing it. As a result, necessary information is often not readily available, leading to a decline in work efficiency. Therefore, there is a need for a system that can effectively collect and analyze information accumulated within the company and generate and distribute it as new content that is useful to employees.

[0615] 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.

[0616] In this invention, the server includes a time scheduling means for periodically collecting data from internal information sources, a database means for storing the collected data, a means for analyzing the collected data using natural language processing technology and extracting important information, a means for generating new content using a generative AI model based on the extracted information, a distribution means for distributing the generated content to employees, and a terminal means with a search function for responding to questions from employees and searching for and providing the generated content. This makes it possible to efficiently manage and share information accumulated within the company and improve employee work efficiency.

[0617] "Time scheduling means" is a function that enables the server to periodically collect in-house information at scheduled times.

[0618] "Database means" refers to a system for safely and orderly storing and managing collected data.

[0619] "Natural language processing technology" is a technology for analyzing text data and extracting important information. Specifically, it uses language models and algorithms.

[0620] A "generative AI model" is an artificial intelligence technology that generates new content based on analyzed information.

[0621] "Distribution means" refers to the method or system used to distribute the generated content to employees. Specifically, email, an internal portal site, a messaging app, etc. are used.

[0622] "Terminal means with search functionality" refers to a device and its software that allows employees to easily search and access generated content.

[0623] "Internal documents" are various documents created and managed within a company, including information related to specific tasks or projects.

[0624] "Meeting records" are documents that record the contents of a meeting, and include minutes and memos.

[0625] "Work-related documents" means all documents and materials related to the work, including project documents.

[0626] The "TextRank algorithm" is a type of natural language processing technology, and is an algorithm for extracting important keywords and phrases from text.

[0627] This invention is a system that efficiently collects and analyzes information accumulated within a company, and generates and distributes it as new content. Specific embodiments will be described in detail below.

[0628] Gathering internal information

[0629] The server first collects data from various internal sources (such as the company's internal wiki, project documents, and meeting minutes). This collection process is run periodically using scheduling software (e.g., a Cron job). Every day at 1:00 AM, new data is retrieved from these sources and stored in a central database. Specifically, an HTTP request is sent to each source, the data is retrieved in JSON format, and the data is then inserted into the database using an INSERT query.

[0630] Data analysis

[0631] The server analyzes the collected data using natural language processing (NLP) techniques. A Python script is run to extract important keywords and phrases from the text data using the TextRank algorithm. For example, the Python library gensim can be used. The resulting information is then stored in a central database.

[0632] Content generation

[0633] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The generative AI model generates specific content by inputting the following prompt sentence:

[0634] Prompt statement:

[0635] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0636] Project Objective

[0637] Current progress

[0638] Future plans

[0639] Issues and Solutions"

[0640] The generated content is converted into a format that is easy for employees to understand, such as a slide presentation or an article-style report.

[0641] Content Delivery

[0642] The server distributes the generated content to employees via an internal portal site, email newsletter, Slack channel, etc. Specifically, it sends the generated slides and reports to a list of email addresses of all employees, or posts them to the appropriate channel using Slack's API.

[0643] Access to content

[0644] The terminals provide an interface that allows employees to easily access generated content. The terminals have a built-in search function, allowing employees to input a specific question and instantly display relevant content. For example, if an employee searches for "progress on new projects," relevant slides and reports are instantly displayed. Additionally, the terminals offer interactive features (zoom, commenting, sharing, etc.) to improve the usability of the displayed content.

[0645] Specific examples

[0646] As a concrete example, the system may operate as follows: Every day at 1:00 AM, the server collects the latest data from internal sources and analyzes this data to extract important information. Based on the extracted information, a generative AI model creates slides such as "Project A Progress Report" and shares them with all employees via email and Slack. Employees can view the slides on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting records and suggestions for resolving the problem are displayed.

[0647] In this way, employees can improve their work efficiency by efficiently managing and sharing information accumulated within the company.

[0648] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0649] Step 1:

[0650] The server collects data from internal sources (internal wikis, project documents, meeting minutes, etc.) every day at 1 AM. This process is automated using a Cron job. The server sends an HTTP request to the sources to retrieve the latest data. The retrieved data is sent to the server in JSON format and stored as input data in a central database. The output is the newly collected text data.

[0651] Step 2:

[0652] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it runs a Python script and uses the gensim library. As input, it uses the text data stored in a central database. It applies the TextRank algorithm to extract important keywords and phrases. As output, it generates a list of important keywords and phrases, which are also stored in the database.

[0653] Step 3:

[0654] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The server creates a prompt and incorporates keywords and phrases obtained from the analysis results into this prompt. The following is an example.

[0655] Prompt statement:

[0656] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0657] Project Objective

[0658] Current progress

[0659] Future plans

[0660] Issues and Solutions"

[0661] As input, this prompt and the analysis results are passed to a generative AI model, which processes them and generates specific content (in the form of slides or articles). As output, new content is generated and stored in a database.

[0662] Step 4:

[0663] The server distributes the generated content to employees. To do this, it uses various distribution methods (internal portal site, email newsletter, Slack channel, etc.). As input, it uses the generated content and employee contact information. The server distributes the content using, for example, an email sending script or Slack API. As output, the distributed content reaches the employee, and a record of this is kept.

[0664] Step 5:

[0665] The terminal provides an interface that allows employees to access the generated content. The terminal has a built-in search function that allows employees to input a specific question and display related content. Specifically, the terminal uses the employee's search query as input. The terminal queries the query against a database, searches for relevant content, and displays the results. In addition, the terminal provides interactive functions such as zooming, commenting, and sharing to improve the usability of the content. As an output, related content is provided to the employee.

[0666] (Application example 1)

[0667] 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."

[0668] In order to improve information management and operational efficiency at logistics centers, a system is required that can effectively collect and analyze a huge amount of information, such as incoming and outgoing records, inventory data, and employee shift schedules, and distribute it to staff in a format that is quick and easy to understand. However, currently, information collection and analysis is often done manually, which takes time and effort, and there is a risk of important information being overlooked. Furthermore, there is no system in place to properly distribute the generated information and make it easy for staff to access, which results in a decline in operational efficiency.

[0669] 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.

[0670] In this invention, the server includes means for periodically collecting data from information sources within the logistics center, means for analyzing the collected data and extracting important information, means for generating new content using a generative AI model based on the extracted information, means for distributing the generated content to staff, and means for responding to questions from staff and searching and providing the generated content. This improves the efficiency of information management in the logistics center, prevents overlooking of important information when performing work, and creates an environment in which staff can quickly access the information they need.

[0671] A "logistics center" refers to a facility that carries out logistics activities such as storing, sorting, transporting, and delivering goods.

[0672] "Source" refers to the records, databases, etc. within the distribution center or from which relevant data is collected.

[0673] "Means for periodically collecting data" refers to means that include functions or devices that continuously acquire and store data at regular intervals.

[0674] "Means for analyzing data" refers to means, including software and algorithms, for analyzing collected data and extracting useful information.

[0675] "Means for extracting significant information" refers to techniques and methods for identifying and extracting particularly useful information through data analysis.

[0676] "Generative AI models" refer to models or algorithms that use artificial intelligence technology to automatically generate new content.

[0677] "Content generation means" refers to the systems or technologies that take the extracted information and convert it into useful forms such as reports or notifications.

[0678] "Means of distribution to staff" refers to the communications methods and platforms that allow generated content to be delivered quickly to the relevant personnel.

[0679] "Means of searching and providing" refers to a system that searches for relevant content based on inquiries from staff and provides the necessary information.

[0680] This invention is a system for improving information management and operational efficiency in a logistics center. The system is configured as follows.

[0681] The server periodically collects data from various sources within the distribution center (inventory records, incoming and outgoing records, employee shift schedules, etc.) on a daily basis. This data collection process is automated using scheduling software (e.g., schedule). The data is then stored in a database management system (e.g., SQLite).

[0682] Next, for data analysis, the server analyzes the data using natural language processing technology (e.g., nltk) to extract important keywords and phrases. This analysis process provides useful information about the current status of the logistics center, future challenges, resource status, etc.

[0683] Based on the analysis results, new content is generated using a generative AI model (e.g., GPT-4). This generative AI model receives the extracted key information as a prompt and converts it into a report or notification format. An example of a prompt would be, "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management."

[0684] The generated content is distributed from the server to logistics center staff. This distribution process uses internal email and chat tools (e.g., Slack). Staff can access the generated content using their own devices (smartphones, tablets, etc.) and easily obtain the information they need for their work. The system also includes a search function, which allows them to respond to staff questions and quickly provide relevant information.

[0685] As a concrete example, the server collects the latest data from each information source within the distribution center at 1:00 AM every day. This data is analyzed using natural language processing technology to extract important information. A generative AI model uses this information to create an "inventory status report" that is shared with all staff via email and Slack. Staff can view the report on their own devices to understand the current situation at the distribution center. Additionally, when staff use the search function on their devices to search for information about "resource shortages," related data and suggestions are displayed.

[0686] In this way, the information accumulated within the logistics center can be efficiently managed and shared, leading to improved operational efficiency and streamlined operations.

[0687] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0688] Step 1:

[0689] The server periodically collects data from sources within the distribution center. This data collection is scheduled at 1:00 AM every day and specifically covers data such as inventory records, inbound and outbound records, and employee shift schedules. It is automated using scheduling software (e.g., schedule). The collected data is stored in a database management system (e.g., SQLite).

[0690] Input: Information source (inventory records, receipt / dispatch records, employee shift schedules)

[0691] Output: Collected data (stored in a database)

[0692] Step 2:

[0693] The server analyzes the collected data using natural language processing techniques (e.g., nltk). This analysis process involves tokenizing the data and performing word frequency counts to extract important keywords and phrases.

[0694] Input: Collected data (data saved in step 1)

[0695] Output: Important keywords and phrases

[0696] Step 3:

[0697] The server generates new content using a generative AI model (e.g., GPT-4) based on the extracted keywords and phrases. Specifically, the generative AI model is given the following prompt: "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management." The generated content can take the form of a report or notification, for example.

[0698] Input: Important keywords, phrases, and prompts

[0699] Output: New content (reports, notifications)

[0700] Step 4:

[0701] The generated content is distributed from the server to logistics center staff via internal email and chat tools (e.g., Slack), allowing staff to quickly obtain the information they need for their work.

[0702] Input: New content (the content generated in step 3)

[0703] Output: Delivered content (email or chat format)

[0704] Step 5:

[0705] Staff use devices (smartphones and tablets) to view the distributed content. Additionally, they can use the device's search function to search for content generated based on specific questions. For example, searching for information on "resource shortages" will display relevant data and suggestions.

[0706] Input: Published content, search query

[0707] Output: Search results (related data and suggestions)

[0708] The above processing steps improve information management and operational efficiency within the logistics center.

[0709] 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.

[0710] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0711] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process is run daily at 1:00 AM using a cron job, for example. The server uses APIs to retrieve the latest data from each source and stores it in a central database.

[0712] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process uses the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. The server then organizes the results of this analysis and prepares them for the next content generation step.

[0713] The server then uses the extracted key information to generate new content using a generative AI model (e.g., GPT-4). The generative AI model takes the analysis results as input and generates content such as slides and articles based on that information.

[0714] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0715] The server then distributes the generated content to employees, using communication methods such as internal portals, email, and Slack channels. For example, a project progress report slide deck can be shared with all employees via email.

[0716] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's inputs and reactions and evaluates the user's emotional state in real time. For example, the emotion engine recognizes the user's stress level and satisfaction by analyzing the user's keyboard and mouse movements and the language used in chat.

[0717] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0718] As a concrete example, let's consider how the following system works. The server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. A generative AI model is used to generate a "Project A Progress Report" slide deck, which is then distributed to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides information at the appropriate time and in the appropriate format.

[0719] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0720] The processing flow will be explained below.

[0721] Step 1: Schedule information collection

[0722] The server is scheduled to periodically collect data from internal sources, for example using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0723] Step 2: Collect data from sources

[0724] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0725] Step 3: Analyze the data

[0726] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process analyzes the text data and extracts important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0727] Step 4: Extracting important information

[0728] The server identifies and extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0729] Step 5: Use the generative AI model

[0730] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model and organizes the information in a format that is easy for humans to understand.

[0731] Step 6: Storing generated content

[0732] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0733] Step 7: Deliver your content

[0734] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0735] Step 8: Emotion Recognition with the Emotion Engine

[0736] The device analyzes the user's inputs and reactions in real time and recognizes the user's emotional state using an emotion engine that analyzes keyboard typing speed, mouse movements, and chat language to assess the user's stress level and satisfaction.

[0737] Step 9: Providing a Question-Response Interface

[0738] The device provides an interface where users can input questions. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, the emotion engine detects that the user's stress level is high and provides content based on that situation.

[0739] Step 10: Viewing Generated Content

[0740] Users view the generated content through an interface provided by their devices. They can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to keep up with the latest developments. The emotion engine displays content taking the user's emotions into consideration, ensuring users receive information with a high level of satisfaction.

[0741] Example 2

[0742] 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."

[0743] In today's corporate environment, large amounts of internal information are stored in a variety of formats, and there is a need to efficiently collect and analyze this information and provide it as useful content for employees. However, current systems take a long time to collect and analyze information, and the generated content is often not shared appropriately. Furthermore, there are problems such as an inability to quickly provide appropriate content in response to employee questions, and the information provided is not adjusted to the user's emotional state. This can reduce the efficiency of information utilization and potentially worsen employee work efficiency.

[0744] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and retrieving and providing the generated content, means for recognizing the user's emotional state, and means for adjusting the format and order of the content to be provided based on the user's emotional state. This makes it possible to efficiently manage and share information accumulated within the company and provide information in an appropriate manner while taking into consideration the user's emotions.

[0745] "Internal sources" are collections of data generated and stored within a company, including internal documents, meeting minutes, project materials, etc.

[0746] "Periodic data collection methods" refers to mechanisms that automatically collect data at specified times or intervals, including Cron jobs and API calls.

[0747] "Means for analyzing collected data and extracting important information" refers to methods for analyzing acquired data and identifying keywords and phrases that are important to business operations, including natural language processing technology and the TextRank algorithm.

[0748] "Methods for generating new content using generative models" refers to methods for creating new content such as text or slides using machine learning models, particularly generative AI models, based on collected and analyzed data.

[0749] "Means of delivering generated content to employees" refers to how the generated content is provided to employees via email or internal communication tools (e.g., internal portal site or Slack channel).

[0750] "Means for searching and providing generated content in response to employee inquiries" refers to a method for searching for and providing related generated content in response to an employee's inquiry to the system.

[0751] "Means for recognizing the user's emotional state" refers to a process for analyzing the user's input and behavior to evaluate their emotional state at that time, such as stress or satisfaction, and includes keyboard operation analysis and chat analysis.

[0752] "Means for adjusting the format and order of content provided based on the user's emotional state" refers to a method for dynamically changing the format and priority of information provided in consideration of the user's emotional state.

[0753] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0754] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process runs every day at 1:00 AM using a cron job. The server uses APIs to retrieve the latest data from each source and stores it in a central database. Specifically, it uses Python scripts and the "requests" library to retrieve the data and the "psycopg2" library to store it in the database.

[0755] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process utilizes the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. Specifically, the text analysis is performed using the "spaCy" library.

[0756] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and generates content such as slides and articles based on that information. Specifically, it uses OpenAI's API to send prompt text and obtain the generated text.

[0757] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0758] The server then distributes the generated content to employees. This distribution process uses communication methods such as an internal portal site, email, and Slack channels. Specifically, notifications are sent using the Slack API, and content is distributed using an email server. For example, a project progress report slide deck is shared with all employees via email.

[0759] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, it recognizes the user's stress level and satisfaction by analyzing keyboard and mouse movements and the language used in chat. "SentiStrength" is used for emotion recognition.

[0760] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0761] For example, the server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. Using a generative AI model, it generates a "Project A Progress Report" slide deck and distributes it to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides the information at the appropriate time and in the appropriate format.

[0762] Examples of prompts include:

[0763] "How's the new project going?"

[0764] "I want to know more about the current situation regarding resource shortages."

[0765] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0766] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0767] Program processing steps

[0768] Step 1: Data collection

[0769] The server periodically collects data from internal information sources. Specifically, a Cron job is run at 1:00 AM every day to retrieve data from each source using APIs. This allows the server to collect the latest information, such as the internal wiki, project documents, and meeting minutes.

[0770] Input: Cron job, API

[0771] Output: Raw data collected

[0772] What it does: A cron job launches a Python script that uses the "requests" library to retrieve data from each source and store it in a central database.

[0773] Step 2: Data analysis

[0774] The server analyzes the collected data using natural language processing (NLP) techniques, specifically the TextRank algorithm, to extract important keywords and phrases.

[0775] Input: Raw data collected

[0776] Output: Analyzed important information

[0777] How it works: It uses the "spaCy" library to analyze text data and extracts keywords and phrases using the TextRank algorithm.

[0778] Step 3: Content generation

[0779] The server generates new content using a generative AI model (e.g., GPT-4) based on the analyzed key information. In the generation process, the server sends a prompt to the generative AI model and receives the generated text.

[0780] Input: Analyzed important information, prompt text

[0781] Output: Generated content

[0782] Specific operation: Using the OpenAI API, the prompt "Generate progress report slides for Project A" is sent to GPT-4, and the generated slide content is saved in the database.

[0783] Step 4: Content Delivery

[0784] The server then distributes the generated content to employees via internal portals, email, Slack channels, and other communication methods.

[0785] Input: Generated content

[0786] Output: Streamed content

[0787] Specific behavior: Sends notifications using the Slack API and emails to employees using a mail server.

[0788] Step 5: Emotion Recognition and User Response

[0789] The device uses an emotion engine to recognize the user's emotions in real time, specifically by analyzing keyboard and mouse operation data and chat language to assess stress and satisfaction.

[0790] Input: User input and behavior data

[0791] Output: User's emotional state rating

[0792] What it does: It uses SentiStrength to analyze the user's keyboard input and assess their emotional state in real time.

[0793] Step 6: Providing content to users

[0794] Users can browse the generated content through their devices, input questions, and the system will provide appropriate content for that question, taking into account the user's emotional state.

[0795] Input: User question, emotional state

[0796] Output: The appropriate content provided

[0797] Specific operation: When a user asks about the "progress of a new project," the device uses an emotion engine to analyze the user's emotional state and provides information in the optimal order according to the situation.

[0798] (Application example 2)

[0799] 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."

[0800] In today's corporate environment, it is important to efficiently collect and analyze internal information and provide it to employees in a timely manner. However, in many cases, the amount of information is so vast that it is difficult for employees to effectively utilize it in response to their own emotions and stress levels. For this reason, there is a need for a method that makes it easy for employees to find information and provides appropriate information according to their emotional state.

[0801] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0802] In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and searching and providing the generated content, means for analyzing the emotional state of a user using an emotion engine that recognizes the user's emotions, and means for prioritizing and providing appropriate information according to the emotional state, thereby enabling employees to quickly obtain appropriate information according to their emotional state.

[0803] 1. "Internal information sources" refers to databases and systems that provide information such as documents, meeting minutes, and project documents that are generated and stored within a company.

[0804] 2. "Data collection means" means the methods and devices by which the required data is periodically obtained from sources and stored in a central database.

[0805] 3. "Means for analyzing data and extracting important information" refers to methods or devices that use natural language processing technology to analyze collected data and identify important information, such as specific keywords or phrases.

[0806] 4. “Generative Model” means an artificial intelligence model, particularly a generative AI model, used to generate new content based on collected and analyzed information.

[0807] 5. "Means for generating content" refers to a method or device for automatically creating content such as new slides or articles using a generative model.

[0808] 6. "Means for distributing content to employees" refers to methods and devices for providing generated content to employees via internal portals, email, chat tools, etc.

[0809] 7. "Means for searching and providing content" refers to methods and devices for effectively searching for and appropriately providing content generated in response to employee questions.

[0810] 8. "Emotion engine" refers to artificial intelligence technology that analyzes user input and operations and evaluates the user's emotional state in real time.

[0811] 9. "Means for analyzing emotional state" means a method or device that uses an emotion engine to determine a user's stress level or satisfaction level.

[0812] 10. "Means for prioritizing and providing appropriate information according to emotional state" means a method or device for providing the most appropriate information on a priority basis based on the user's emotional state.

[0813] A specific embodiment of the present invention will be described. This invention is a system that realizes user emotion recognition and appropriate product recommendations in a virtual store. The detailed operation of the system and the hardware and software used will be described below.

[0814] The server periodically collects data from various internal sources (internal documents, meeting minutes, project documents, etc.). The data collection process is run daily at 1:00 AM using a Cron job, for example. The collected data is stored in a central database, using an API to retrieve the latest data from each source.

[0815] The collected data is then analyzed by the server using natural language processing (NLP) techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases for the next step of content generation.

[0816] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and automatically generates content such as slides and articles based on that information. The generated content is stored in a database by the server and properly indexed.

[0817] Furthermore, this system incorporates an emotion engine that allows the device to recognize the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, when the user is using a smartphone or head-mounted display (HMD), emotion recognition is performed using sensors such as the camera and microphone. This is done using the emotion engine API and TextBlob library.

[0818] Users can browse the generated content and use the interactive interface through their device. When the user inputs a question or request, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. At this time, the following prompt sentence is input into the generative AI model:

[0819] text

[0820] User emotion data: {'happy': 0.8, 'stressed': 0.2}, Sentiment analysis data: {'polarity': -0.5, 'subjectivity': 0.6}

[0821] For example, if a user enters "I'm looking for a new smartphone but I'm having trouble choosing," the application uses the emotion engine to recognize their stress level and inputs the above prompt sentence into the GPT-4 model. The GPT-4 model then outputs recommendations for relaxing products, such as "aroma diffusers" and "massage chairs." The application then retrieves relevant product information from the product database and suggests them to the user.

[0822] This system allows users to quickly find the right product based on their emotional state, improving the shopping experience in virtual stores by enabling effective emotional product selection based on the information provided.

[0823] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0824] Step 1:

[0825] The server collects data from internal sources. Specifically, it uses an API to retrieve the latest data from internal documents, meeting minutes, project documents, etc., and stores it in a central database. This process runs at 1:00 AM every day using a Cron job. The input is data from each source, and the output is the data stored in the central database.

[0826] Step 2:

[0827] The server analyzes the collected data using natural language processing techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases. The input is the data stored in a central database, and the output is the extracted important information.

[0828] Step 3:

[0829] The server generates new content using a generative AI model (such as GPT-4) based on the extracted key information. The generative AI model receives the analysis results as input and generates content such as slides and articles. The input is the extracted key information, and the output is the generated new content.

[0830] Step 4:

[0831] The server stores the generated content in a database and indexes it appropriately, making it easily searchable and accessible later. The input is the new content generated, and the output is an indexed database entry.

[0832] Step 5:

[0833] The server distributes the generated content to employees. The content is shared with employees using communication methods such as internal portal sites, email, and chat tools. The input is the indexed new content, and the output is notifications and links sent to employees.

[0834] Step 6:

[0835] The device uses an emotion engine to recognize the user's emotions. The device collects the user's facial expressions and voice using the camera and microphone of the smartphone or HMD, and analyzes the user's emotional state using the emotion engine API and TextBlob library. The input is the user's facial expression and voice data, and the output is the user's emotional state data (e.g., {'happy': 0.8, 'stressed': 0.2}).

[0836] Step 7:

[0837] The device receives questions or requests entered by the user and uses an emotion engine to analyze their emotional state. Based on the analysis results, the device inputs prompts into a generative AI model to generate optimal content. The input is the user's question or request and emotional state data, and the output is the generated recommended content.

[0838] Step 8:

[0839] The server searches the product database for the generated recommended content and provides it to the user. For example, if a user inputs "I'm looking for a new smartphone, but I'm having trouble choosing one," the server inputs the following prompt sentence to the generative AI model:

[0840] text

[0841] User emotion data: {'happy': 0.1, 'stressed': 0.9}, Sentiment analysis data: {'polarity': -0.7, 'subjectivity': 0.9}

[0842] Based on this prompt, the GPT-4 model recommends the most suitable products, searches for the relevant products in the product database based on the recommendation results, and provides them to the user. The input is the prompt and the generated recommendation content, and the output is a list of products presented to the user.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] [Fourth embodiment]

[0847] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0848] 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.

[0849] 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).

[0850] 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.

[0851] 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.

[0852] 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).

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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."

[0860] This invention is a system that efficiently collects and analyzes huge amounts of text data accumulated within a company, and generates and distributes new content that is useful to employees. A specific embodiment of the system is described below.

[0861] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). For example, every day at 1:00 AM, the server retrieves new data from these sources and stores it in a central database. This collection process is automated using scheduling software (e.g., a Cron job).

[0862] The server then analyzes the collected data using natural language processing (NLP) techniques, such as the TextRank algorithm, to extract important keywords and phrases from the text data. The information obtained from this analysis is then turned into useful insights and tips that can be shared with employees.

[0863] Based on the analysis results, the server uses a generative AI model (e.g., GPT-4) to generate new content, such as slide presentations or article-style reports. The generative AI model takes the extracted key information as input and converts it into a format that employees can easily understand.

[0864] The generated content is then distributed to employees from the server via an internal portal site, email newsletter, Slack channel, etc. For example, a slide show summarizing the progress of a new project is sent to all employees via email.

[0865] Terminals (employee PCs and mobile devices) provide an interface for easy access to generated content. The terminals have a built-in search function, allowing employees to type in a specific question and display relevant content. For example, an employee can search for "progress on new projects" and instantly be served relevant slides and reports.

[0866] As a concrete example, the system might operate as follows: Every day at 1:00 AM, the server collects the latest data from the company's internal wiki, project documents, and meeting minutes. This data is analyzed and important information is extracted. Based on this information, a generative AI model generates a "Project A Progress Report" slide deck, which is shared with all employees via email and Slack. Employees can view the slide deck on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting minutes and suggestions for resolving the problem are displayed.

[0867] In this way, the information accumulated within the company can be efficiently managed and shared, thereby improving the work efficiency of employees.

[0868] The processing flow will be explained below.

[0869] Step 1: Schedule information collection

[0870] The server is scheduled to periodically collect data from internal sources, for example, using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0871] Step 2: Collect data from sources

[0872] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[0873] Step 3: Analyze the data

[0874] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process involves analyzing the text data and extracting important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[0875] Step 4: Extracting important information

[0876] The server then extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[0877] Step 5: Use the generative AI model

[0878] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model, which organizes the information in a form that is easy for humans to understand.

[0879] Step 6: Storing generated content

[0880] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[0881] Step 7: Deliver your content

[0882] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[0883] Step 8: Answering user questions

[0884] The terminal provides an interface for employees to access generated content. When an employee types a question into the terminal, the terminal searches for related generated content and displays the results. For example, if a user types "latest project status," the terminal displays related slides and articles.

[0885] Step 9: Viewing Generated Content

[0886] Users view the generated content through an interface provided by their device. Users can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to stay up to date on the latest developments.

[0887] Example 1

[0888] 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."

[0889] Efficient management and sharing of internal information is important for improving employee work efficiency. However, many companies today have scattered information and lack systems for properly collecting, analyzing, and sharing it. As a result, necessary information is often not readily available, leading to a decline in work efficiency. Therefore, there is a need for a system that can effectively collect and analyze information accumulated within the company and generate and distribute it as new content that is useful to employees.

[0890] 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.

[0891] In this invention, the server includes a time scheduling means for periodically collecting data from internal information sources, a database means for storing the collected data, a means for analyzing the collected data using natural language processing technology and extracting important information, a means for generating new content using a generative AI model based on the extracted information, a distribution means for distributing the generated content to employees, and a terminal means with a search function for responding to questions from employees and searching for and providing the generated content. This makes it possible to efficiently manage and share information accumulated within the company and improve employee work efficiency.

[0892] "Time scheduling means" is a function that enables the server to periodically collect in-house information at scheduled times.

[0893] "Database means" refers to a system for safely and orderly storing and managing collected data.

[0894] "Natural language processing technology" is a technology for analyzing text data and extracting important information. Specifically, it uses language models and algorithms.

[0895] A "generative AI model" is an artificial intelligence technology that generates new content based on analyzed information.

[0896] "Distribution means" refers to the method or system used to distribute the generated content to employees. Specifically, email, an internal portal site, a messaging app, etc. are used.

[0897] "Terminal means with search functionality" refers to a device and its software that allows employees to easily search and access generated content.

[0898] "Internal documents" are various documents created and managed within a company, including information related to specific tasks or projects.

[0899] "Meeting records" are documents that record the contents of a meeting, and include minutes and memos.

[0900] "Work-related documents" means all documents and materials related to the work, including project documents.

[0901] The "TextRank algorithm" is a type of natural language processing technology, and is an algorithm for extracting important keywords and phrases from text.

[0902] This invention is a system that efficiently collects and analyzes information accumulated within a company, and generates and distributes it as new content. Specific embodiments will be described in detail below.

[0903] Gathering internal information

[0904] The server first collects data from various internal sources (such as the company's internal wiki, project documents, and meeting minutes). This collection process is run periodically using scheduling software (e.g., a Cron job). Every day at 1:00 AM, new data is retrieved from these sources and stored in a central database. Specifically, an HTTP request is sent to each source, the data is retrieved in JSON format, and the data is then inserted into the database using an INSERT query.

[0905] Data analysis

[0906] The server analyzes the collected data using natural language processing (NLP) techniques. A Python script is run to extract important keywords and phrases from the text data using the TextRank algorithm. For example, the Python library gensim can be used. The resulting information is then stored in a central database.

[0907] Content generation

[0908] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The generative AI model generates specific content by inputting the following prompt sentence:

[0909] Prompt statement:

[0910] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0911] Project Objective

[0912] Current progress

[0913] Future plans

[0914] Issues and Solutions"

[0915] The generated content is converted into a format that is easy for employees to understand, such as a slide presentation or an article-style report.

[0916] Content Delivery

[0917] The server distributes the generated content to employees via an internal portal site, email newsletter, Slack channel, etc. Specifically, it sends the generated slides and reports to a list of email addresses of all employees, or posts them to the appropriate channel using Slack's API.

[0918] Access to content

[0919] The terminals provide an interface that allows employees to easily access generated content. The terminals have a built-in search function, allowing employees to input a specific question and instantly display relevant content. For example, if an employee searches for "progress on new projects," relevant slides and reports are instantly displayed. Additionally, the terminals offer interactive features (zoom, commenting, sharing, etc.) to improve the usability of the displayed content.

[0920] Specific examples

[0921] As a concrete example, the system may operate as follows: Every day at 1:00 AM, the server collects the latest data from internal sources and analyzes this data to extract important information. Based on the extracted information, a generative AI model creates slides such as "Project A Progress Report" and shares them with all employees via email and Slack. Employees can view the slides on their own devices and understand the current status of the project. Furthermore, when an employee uses the search function on their device to search for information about "resource shortages," related past meeting records and suggestions for resolving the problem are displayed.

[0922] In this way, employees can improve their work efficiency by efficiently managing and sharing information accumulated within the company.

[0923] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0924] Step 1:

[0925] The server collects data from internal sources (internal wikis, project documents, meeting minutes, etc.) every day at 1 AM. This process is automated using a Cron job. The server sends an HTTP request to the sources to retrieve the latest data. The retrieved data is sent to the server in JSON format and stored as input data in a central database. The output is the newly collected text data.

[0926] Step 2:

[0927] The server analyzes the collected text data using natural language processing (NLP) techniques. Specifically, it runs a Python script and uses the gensim library. As input, it uses the text data stored in a central database. It applies the TextRank algorithm to extract important keywords and phrases. As output, it generates a list of important keywords and phrases, which are also stored in the database.

[0928] Step 3:

[0929] The server generates new content using a generative AI model (e.g., GPT-4) based on the analysis results. The server creates a prompt and incorporates keywords and phrases obtained from the analysis results into this prompt. The following is an example.

[0930] Prompt statement:

[0931] "Please create a slide that summarizes the progress of Project A. Include the following information:

[0932] Project Objective

[0933] Current progress

[0934] Future plans

[0935] Issues and Solutions"

[0936] As input, this prompt and the analysis results are passed to a generative AI model, which processes them and generates specific content (in the form of slides or articles). As output, new content is generated and stored in a database.

[0937] Step 4:

[0938] The server distributes the generated content to employees. To do this, it uses various distribution methods (internal portal site, email newsletter, Slack channel, etc.). As input, it uses the generated content and employee contact information. The server distributes the content using, for example, an email sending script or Slack API. As output, the distributed content reaches the employee, and a record of this is kept.

[0939] Step 5:

[0940] The terminal provides an interface that allows employees to access the generated content. The terminal has a built-in search function that allows employees to input a specific question and display related content. Specifically, the terminal uses the employee's search query as input. The terminal queries the query against a database, searches for relevant content, and displays the results. In addition, the terminal provides interactive functions such as zooming, commenting, and sharing to improve the usability of the content. As an output, related content is provided to the employee.

[0941] (Application example 1)

[0942] 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."

[0943] In order to improve information management and operational efficiency at logistics centers, a system is required that can effectively collect and analyze a huge amount of information, such as incoming and outgoing records, inventory data, and employee shift schedules, and distribute it to staff in a format that is quick and easy to understand. However, currently, information collection and analysis is often done manually, which takes time and effort, and there is a risk of important information being overlooked. Furthermore, there is no system in place to properly distribute the generated information and make it easy for staff to access, which results in a decline in operational efficiency.

[0944] 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.

[0945] In this invention, the server includes means for periodically collecting data from information sources within the logistics center, means for analyzing the collected data and extracting important information, means for generating new content using a generative AI model based on the extracted information, means for distributing the generated content to staff, and means for responding to questions from staff and searching and providing the generated content. This improves the efficiency of information management in the logistics center, prevents overlooking of important information when performing work, and creates an environment in which staff can quickly access the information they need.

[0946] A "logistics center" refers to a facility that carries out logistics activities such as storing, sorting, transporting, and delivering goods.

[0947] "Source" refers to the records, databases, etc. within the distribution center or from which relevant data is collected.

[0948] "Means for periodically collecting data" refers to means that include functions or devices that continuously acquire and store data at regular intervals.

[0949] "Means for analyzing data" refers to means, including software and algorithms, for analyzing collected data and extracting useful information.

[0950] "Means for extracting significant information" refers to techniques and methods for identifying and extracting particularly useful information through data analysis.

[0951] "Generative AI models" refer to models or algorithms that use artificial intelligence technology to automatically generate new content.

[0952] "Content generation means" refers to the systems or technologies that take the extracted information and convert it into useful forms such as reports or notifications.

[0953] "Means of distribution to staff" refers to the communications methods and platforms that allow generated content to be delivered quickly to the relevant personnel.

[0954] "Means of searching and providing" refers to a system that searches for relevant content based on inquiries from staff and provides the necessary information.

[0955] This invention is a system for improving information management and operational efficiency in a logistics center. The system is configured as follows.

[0956] The server periodically collects data from various sources within the distribution center (inventory records, incoming and outgoing records, employee shift schedules, etc.) on a daily basis. This data collection process is automated using scheduling software (e.g., schedule). The data is then stored in a database management system (e.g., SQLite).

[0957] Next, for data analysis, the server analyzes the data using natural language processing technology (e.g., nltk) to extract important keywords and phrases. This analysis process provides useful information about the current status of the logistics center, future challenges, resource status, etc.

[0958] Based on the analysis results, new content is generated using a generative AI model (e.g., GPT-4). This generative AI model receives the extracted key information as a prompt and converts it into a report or notification format. An example of a prompt would be, "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management."

[0959] The generated content is distributed from the server to logistics center staff. This distribution process uses internal email and chat tools (e.g., Slack). Staff can access the generated content using their own devices (smartphones, tablets, etc.) and easily obtain the information they need for their work. The system also includes a search function, which allows them to respond to staff questions and quickly provide relevant information.

[0960] As a concrete example, the server collects the latest data from each information source within the distribution center at 1:00 AM every day. This data is analyzed using natural language processing technology to extract important information. A generative AI model uses this information to create an "inventory status report" that is shared with all staff via email and Slack. Staff can view the report on their own devices to understand the current situation at the distribution center. Additionally, when staff use the search function on their devices to search for information about "resource shortages," related data and suggestions are displayed.

[0961] In this way, the information accumulated within the logistics center can be efficiently managed and shared, leading to improved operational efficiency and streamlined operations.

[0962] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0963] Step 1:

[0964] The server periodically collects data from sources within the distribution center. This data collection is scheduled at 1:00 AM every day and specifically covers data such as inventory records, inbound and outbound records, and employee shift schedules. It is automated using scheduling software (e.g., schedule). The collected data is stored in a database management system (e.g., SQLite).

[0965] Input: Information source (inventory records, receipt / dispatch records, employee shift schedules)

[0966] Output: Collected data (stored in a database)

[0967] Step 2:

[0968] The server analyzes the collected data using natural language processing techniques (e.g., nltk). This analysis process involves tokenizing the data and performing word frequency counts to extract important keywords and phrases.

[0969] Input: Collected data (data saved in step 1)

[0970] Output: Important keywords and phrases

[0971] Step 3:

[0972] The server generates new content using a generative AI model (e.g., GPT-4) based on the extracted keywords and phrases. Specifically, the generative AI model is given the following prompt: "Generate a weekly report for the distribution center based on the following keywords: inventory, arrival, shipment, resource shortage, and shift management." The generated content can take the form of a report or notification, for example.

[0973] Input: Important keywords, phrases, and prompts

[0974] Output: New content (reports, notifications)

[0975] Step 4:

[0976] The generated content is distributed from the server to logistics center staff via internal email and chat tools (e.g., Slack), allowing staff to quickly obtain the information they need for their work.

[0977] Input: New content (the content generated in step 3)

[0978] Output: Delivered content (email or chat format)

[0979] Step 5:

[0980] Staff use devices (smartphones and tablets) to view the distributed content. Additionally, they can use the device's search function to search for content generated based on specific questions. For example, searching for information on "resource shortages" will display relevant data and suggestions.

[0981] Input: Published content, search query

[0982] Output: Search results (related data and suggestions)

[0983] The above processing steps improve information management and operational efficiency within the logistics center.

[0984] 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.

[0985] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0986] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process is run daily at 1:00 AM using a cron job, for example. The server uses APIs to retrieve the latest data from each source and stores it in a central database.

[0987] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process uses the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. The server then organizes the results of this analysis and prepares them for the next content generation step.

[0988] The server then uses the extracted key information to generate new content using a generative AI model (e.g., GPT-4). The generative AI model takes the analysis results as input and generates content such as slides and articles based on that information.

[0989] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[0990] The server then distributes the generated content to employees, using communication methods such as internal portals, email, and Slack channels. For example, a project progress report slide deck can be shared with all employees via email.

[0991] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's inputs and reactions and evaluates the user's emotional state in real time. For example, the emotion engine recognizes the user's stress level and satisfaction by analyzing the user's keyboard and mouse movements and the language used in chat.

[0992] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[0993] As a concrete example, let's consider how the following system works. The server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. A generative AI model is used to generate a "Project A Progress Report" slide deck, which is then distributed to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides information at the appropriate time and in the appropriate format.

[0994] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[0995] The processing flow will be explained below.

[0996] Step 1: Schedule information collection

[0997] The server is scheduled to periodically collect data from internal sources, for example using a Cron job to collect data at 1:00 AM every day. The server runs automatically according to the schedule.

[0998] Step 2: Collect data from sources

[0999] The server collects data from sources such as internal wikis, project documents, meeting minutes, etc. This collection process is done through the API of each source. For example, the server calls the API of an internal wiki to get the latest entries and stores them in a database.

[1000] Step 3: Analyze the data

[1001] The server analyzes the collected data using natural language processing (NLP) techniques. This analysis process analyzes the text data and extracts important keywords and phrases using TextRank and other algorithms. The server then organizes the analysis results and prepares them for the next content generation step.

[1002] Step 4: Extracting important information

[1003] The server identifies and extracts information from the analyzed data that will provide employees with useful insights and tips. This extraction process uses specific rules and filtering techniques to remove noise and extract only the necessary information.

[1004] Step 5: Use the generative AI model

[1005] The server uses a generative AI model (e.g., GPT-4) to generate content such as slides and articles based on the extracted important information. The server inputs the analysis results into the generative AI model and organizes the information in a format that is easy for humans to understand.

[1006] Step 6: Storing generated content

[1007] The server stores the generated content in a database, and this storage process ensures that the generated slides, articles, etc. are properly indexed for easy searching and access later.

[1008] Step 7: Deliver your content

[1009] The server distributes the generated content to employees. In this distribution process, the content is sent via communication methods such as an internal portal site, email, or Slack channel. For example, a project progress report slide deck is shared with all employees via email.

[1010] Step 8: Emotion Recognition with the Emotion Engine

[1011] The device analyzes the user's inputs and reactions in real time and recognizes the user's emotional state using an emotion engine that analyzes keyboard typing speed, mouse movements, and chat language to assess the user's stress level and satisfaction.

[1012] Step 9: Providing a Question-Response Interface

[1013] The device provides an interface where users can input questions. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, the emotion engine detects that the user's stress level is high and provides content based on that situation.

[1014] Step 10: Viewing Generated Content

[1015] Users view the generated content through an interface provided by their devices. They can use the search function to find specific information and quickly access the information they need. For example, users can view slides about the progress of a project to keep up with the latest developments. The emotion engine displays content taking the user's emotions into consideration, ensuring users receive information with a high level of satisfaction.

[1016] Example 2

[1017] 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."

[1018] In today's corporate environment, large amounts of internal information are stored in a variety of formats, and there is a need to efficiently collect and analyze this information and provide it as useful content for employees. However, current systems take a long time to collect and analyze information, and the generated content is often not shared appropriately. Furthermore, there are problems such as an inability to quickly provide appropriate content in response to employee questions, and the information provided is not adjusted to the user's emotional state. This can reduce the efficiency of information utilization and potentially worsen employee work efficiency.

[1019] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and retrieving and providing the generated content, means for recognizing the user's emotional state, and means for adjusting the format and order of the content to be provided based on the user's emotional state. This makes it possible to efficiently manage and share information accumulated within the company and provide information in an appropriate manner while taking into consideration the user's emotions.

[1020] "Internal sources" are collections of data generated and stored within a company, including internal documents, meeting minutes, project materials, etc.

[1021] "Periodic data collection methods" refers to mechanisms that automatically collect data at specified times or intervals, including Cron jobs and API calls.

[1022] "Means for analyzing collected data and extracting important information" refers to methods for analyzing acquired data and identifying keywords and phrases that are important to business operations, including natural language processing technology and the TextRank algorithm.

[1023] "Methods for generating new content using generative models" refers to methods for creating new content such as text or slides using machine learning models, particularly generative AI models, based on collected and analyzed data.

[1024] "Means of delivering generated content to employees" refers to how the generated content is provided to employees via email or internal communication tools (e.g., internal portal site or Slack channel).

[1025] "Means for searching and providing generated content in response to employee inquiries" refers to a method for searching for and providing related generated content in response to an employee's inquiry to the system.

[1026] "Means for recognizing the user's emotional state" refers to a process for analyzing the user's input and behavior to evaluate their emotional state at that time, such as stress or satisfaction, and includes keyboard operation analysis and chat analysis.

[1027] "Means for adjusting the format and order of content provided based on the user's emotional state" refers to a method for dynamically changing the format and priority of information provided in consideration of the user's emotional state.

[1028] This invention combines a system that efficiently collects and analyzes in-house information, generates and distributes new content, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1029] The server periodically collects data from various internal sources (such as the company wiki, project documents, and meeting minutes). This data collection process runs every day at 1:00 AM using a cron job. The server uses APIs to retrieve the latest data from each source and stores it in a central database. Specifically, it uses Python scripts and the "requests" library to retrieve the data and the "psycopg2" library to store it in the database.

[1030] The collected data is analyzed by the server using natural language processing (NLP) techniques. This analysis process utilizes the TextRank algorithm and other NLP techniques to analyze the text data and extract important keywords and phrases. Specifically, the text analysis is performed using the "spaCy" library.

[1031] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and generates content such as slides and articles based on that information. Specifically, it uses OpenAI's API to send prompt text and obtain the generated text.

[1032] The generated content is stored in a database by the server and properly indexed, making it easily searchable and accessible later.

[1033] The server then distributes the generated content to employees. This distribution process uses communication methods such as an internal portal site, email, and Slack channels. Specifically, notifications are sent using the Slack API, and content is distributed using an email server. For example, a project progress report slide deck is shared with all employees via email.

[1034] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, it recognizes the user's stress level and satisfaction by analyzing keyboard and mouse movements and the language used in chat. "SentiStrength" is used for emotion recognition.

[1035] Users browse the generated content through their device and use the interactive interface. When a user inputs a question, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. For example, when a user asks about the progress of a new project, if the emotion engine detects that the user's stress level is high, it will provide content in a prioritized order according to the situation.

[1036] For example, the server collects the latest data from various internal sources at 1:00 AM every day, analyzes this data, and extracts important information. Using a generative AI model, it generates a "Project A Progress Report" slide deck and distributes it to all employees via email and Slack. Users can view the slide deck on their own devices to understand the current status of the project. Furthermore, when a user uses the device's search function to search for information about "resource shortages," the emotion engine recognizes the user's stress and provides the information at the appropriate time and in the appropriate format.

[1037] Examples of prompts include:

[1038] "How's the new project going?"

[1039] "I want to know more about the current situation regarding resource shortages."

[1040] This system allows for efficient management and sharing of information accumulated within the company, and provides information while taking into consideration the feelings of users, thereby improving employee work efficiency and maximizing the organization's ability to utilize information.

[1041] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1042] Program processing steps

[1043] Step 1: Data collection

[1044] The server periodically collects data from internal information sources. Specifically, a Cron job is run at 1:00 AM every day to retrieve data from each source using APIs. This allows the server to collect the latest information, such as the internal wiki, project documents, and meeting minutes.

[1045] Input: Cron job, API

[1046] Output: Raw data collected

[1047] What it does: A cron job launches a Python script that uses the "requests" library to retrieve data from each source and store it in a central database.

[1048] Step 2: Data analysis

[1049] The server analyzes the collected data using natural language processing (NLP) techniques, specifically the TextRank algorithm, to extract important keywords and phrases.

[1050] Input: Raw data collected

[1051] Output: Analyzed important information

[1052] How it works: It uses the "spaCy" library to analyze text data and extracts keywords and phrases using the TextRank algorithm.

[1053] Step 3: Content generation

[1054] The server generates new content using a generative AI model (e.g., GPT-4) based on the analyzed key information. In the generation process, the server sends a prompt to the generative AI model and receives the generated text.

[1055] Input: Analyzed important information, prompt text

[1056] Output: Generated content

[1057] Specific operation: Using the OpenAI API, the prompt "Generate progress report slides for Project A" is sent to GPT-4, and the generated slide content is saved in the database.

[1058] Step 4: Content Delivery

[1059] The server then distributes the generated content to employees via internal portals, email, Slack channels, and other communication methods.

[1060] Input: Generated content

[1061] Output: Streamed content

[1062] What it does: Sends notifications using the Slack API and emails employees using a mail server.

[1063] Step 5: Emotion Recognition and User Response

[1064] The device uses an emotion engine to recognize the user's emotions in real time, specifically by analyzing keyboard and mouse operation data and chat language to assess stress and satisfaction.

[1065] Input: User input and behavior data

[1066] Output: User's emotional state rating

[1067] What it does: It uses SentiStrength to analyze the user's keyboard input and assess their emotional state in real time.

[1068] Step 6: Providing content to users

[1069] Users can browse the generated content through their devices, and by entering a question, the system will provide appropriate content for that question, taking into account the user's emotional state.

[1070] Input: User question, emotional state

[1071] Output: The appropriate content provided

[1072] Specific operation: When a user asks about the "progress of a new project," the device uses an emotion engine to analyze the user's emotional state and provides information in the optimal order according to the situation.

[1073] (Application example 2)

[1074] 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."

[1075] In today's corporate environment, it is important to efficiently collect and analyze internal information and provide it to employees in a timely manner. However, in many cases, the amount of information is so vast that it is difficult for employees to effectively utilize it in response to their own emotions and stress levels. For this reason, there is a need for a method that makes it easy for employees to find information and provides appropriate information according to their emotional state.

[1076] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1077] In this invention, the server includes means for periodically collecting data from internal information sources, means for analyzing the collected data and extracting important information, means for generating new content using a generative model based on the extracted information, means for distributing the generated content to employees, means for responding to questions from employees and searching and providing the generated content, means for analyzing the emotional state of a user using an emotion engine that recognizes the user's emotions, and means for prioritizing and providing appropriate information according to the emotional state, thereby enabling employees to quickly obtain appropriate information according to their emotional state.

[1078] 1. "Internal information sources" refers to databases and systems that provide information such as documents, meeting minutes, and project documents that are generated and stored within a company.

[1079] 2. "Data collection means" means the methods and devices by which the required data is periodically obtained from sources and stored in a central database.

[1080] 3. "Means for analyzing data and extracting important information" refers to methods or devices that use natural language processing technology to analyze collected data and identify important information, such as specific keywords or phrases.

[1081] 4. “Generative Model” means an artificial intelligence model, particularly a generative AI model, used to generate new content based on collected and analyzed information.

[1082] 5. "Means for generating content" refers to a method or device for automatically creating content such as new slides or articles using a generative model.

[1083] 6. "Means for distributing content to employees" refers to methods and devices for providing generated content to employees via internal portals, email, chat tools, etc.

[1084] 7. "Means for searching and providing content" refers to methods and devices for effectively searching for and appropriately providing content generated in response to employee questions.

[1085] 8. "Emotion engine" refers to artificial intelligence technology that analyzes user input and operations and evaluates the user's emotional state in real time.

[1086] 9. "Means for analyzing emotional state" means a method or device that uses an emotion engine to determine a user's stress level or satisfaction level.

[1087] 10. "Means for prioritizing and providing appropriate information according to emotional state" means a method or device for providing the most appropriate information on a priority basis based on the user's emotional state.

[1088] A specific embodiment of the present invention will be described. This invention is a system that realizes user emotion recognition and appropriate product recommendations in a virtual store. The detailed operation of the system and the hardware and software used will be described below.

[1089] The server periodically collects data from various internal sources (internal documents, meeting minutes, project documents, etc.). The data collection process is run daily at 1:00 AM using a Cron job, for example. The collected data is stored in a central database, using an API to retrieve the latest data from each source.

[1090] The collected data is then analyzed by the server using natural language processing (NLP) techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases for the next step of content generation.

[1091] Next, the server generates new content using a generative AI model (e.g., GPT-4) based on the extracted important information. The generative AI model receives the analysis results as input and automatically generates content such as slides and articles based on that information. The generated content is stored in a database by the server and properly indexed.

[1092] Furthermore, this system incorporates an emotion engine that allows the device to recognize the user's emotions. This emotion engine analyzes the user's input and reactions and evaluates the user's emotional state in real time. Specifically, when the user is using a smartphone or head-mounted display (HMD), emotion recognition is performed using sensors such as the camera and microphone. This is done using the emotion engine API and TextBlob library.

[1093] Users can browse the generated content and use the interactive interface through their device. When the user inputs a question or request, the device uses an emotion engine to analyze the user's emotional state and search for and provide appropriate content. At this time, the following prompt sentence is input into the generative AI model:

[1094] text

[1095] User emotion data: {'happy': 0.8, 'stressed': 0.2}, Sentiment analysis data: {'polarity': -0.5, 'subjectivity': 0.6}

[1096] For example, if a user enters "I'm looking for a new smartphone but I'm having trouble choosing," the application uses the emotion engine to recognize their stress level and inputs the above prompt sentence into the GPT-4 model. The GPT-4 model then outputs recommendations for relaxing products, such as "aroma diffusers" and "massage chairs." The application then retrieves relevant product information from the product database and suggests them to the user.

[1097] This system allows users to quickly find the right product based on their emotional state, improving the shopping experience in virtual stores by enabling effective emotional product selection based on the information provided.

[1098] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1099] Step 1:

[1100] The server collects data from internal sources, specifically from internal documents, meeting minutes, project documents, etc., using an API to retrieve the latest data and store it in a central database. This process runs at 1:00 AM every day using a Cron job. The input is data from each source, and the output is the data stored in the central database.

[1101] Step 2:

[1102] The server analyzes the collected data using natural language processing techniques, such as the TextRank algorithm and other NLP techniques, to extract important keywords and phrases. The input is the data stored in a central database, and the output is the extracted important information.

[1103] Step 3:

[1104] The server generates new content using a generative AI model (such as GPT-4) based on the extracted key information. The generative AI model receives the analysis results as input and generates content such as slides and articles. The input is the extracted key information, and the output is the generated new content.

[1105] Step 4:

[1106] The server stores the generated content in a database and indexes it appropriately, making it easily searchable and accessible later. The input is the new content generated, and the output is an indexed database entry.

[1107] Step 5:

[1108] The server distributes the generated content to employees. The content is shared with employees using communication methods such as internal portal sites, email, and chat tools. The input is the indexed new content, and the output is notifications and links sent to employees.

[1109] Step 6:

[1110] The device uses an emotion engine to recognize the user's emotions. The device collects the user's facial expressions and voice using the camera and microphone of the smartphone or HMD, and analyzes the user's emotional state using the emotion engine API and TextBlob library. The input is the user's facial expression and voice data, and the output is the user's emotional state data (e.g., {'happy': 0.8, 'stressed': 0.2}).

[1111] Step 7:

[1112] The device receives questions or requests entered by the user and uses an emotion engine to analyze their emotional state. Based on the analysis results, the device inputs prompts into a generative AI model to generate optimal content. The input is the user's question or request and emotional state data, and the output is the generated recommended content.

[1113] Step 8:

[1114] The server searches the product database for the generated recommended content and provides it to the user. For example, if a user inputs "I'm looking for a new smartphone, but I'm having trouble choosing one," the server inputs the following prompt sentence to the generative AI model:

[1115] text

[1116] User emotion data: {'happy': 0.1, 'stressed': 0.9}, Sentiment analysis data: {'polarity': -0.7, 'subjectivity': 0.9}

[1117] Based on this prompt, the GPT-4 model recommends the most suitable products, searches for the relevant products in the product database based on the recommendation results, and provides them to the user. The input is the prompt and the generated recommendation content, and the output is a list of products presented to the user.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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).

[1125] 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.

[1126] 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."

[1127] 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.

[1128] 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).

[1129] 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.

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] The following is further disclosed regarding the above embodiment.

[1140] (Claim 1)

[1141] a means of collecting data periodically from internal sources;

[1142] A means of analyzing the collected data and extracting key information;

[1143] a means for generating new content using a generative model based on the extracted information;

[1144] a means of distributing the generated content to employees;

[1145] A way to respond to employee questions and search and provide generated content,

[1146] A system including:

[1147] (Claim 2)

[1148] 10. The system of claim 1, wherein the system collects data from internal company documents, meeting minutes, and project documents.

[1149] (Claim 3)

[1150] 10. The system of claim 1, wherein natural language processing techniques are used to analyze the data and extract important information.

[1151] "Example 1"

[1152] (Claim 1)

[1153] time-scheduling measures for collecting data periodically from internal sources;

[1154] database means for storing the collected data;

[1155] A means for analyzing the collected data using natural language processing technology and extracting important information;

[1156] a means for generating new content using a generative AI model based on the extracted information; and

[1157] a distribution means for distributing the generated content to employees;

[1158] A terminal means having a search function for responding to questions from employees and searching and providing generated content;

[1159] A system including:

[1160] (Claim 2)

[1161] 10. The system of claim 1, wherein data is collected from internal company documents, meeting notes, and business-related documents.

[1162] (Claim 3)

[1163] 10. The system of claim 1, wherein the system analyzes the data using the TextRank algorithm to extract important information.

[1164] "Application Example 1"

[1165] (Claim 1)

[1166] a means for periodically collecting data from sources within the distribution center;

[1167] A means of analyzing the collected data and extracting key information;

[1168] a means for generating new content using a generative AI model based on the extracted information; and

[1169] a means for distributing the generated content to staff;

[1170] A means to respond to staff inquiries and search and provide generated content;

[1171] A system including:

[1172] (Claim 2)

[1173] 10. The system of claim 1, wherein data is collected from inventory records, inventory records, and employee shift schedules.

[1174] (Claim 3)

[1175] 10. The system of claim 1, wherein natural language processing techniques are used to analyze the data and extract important information.

[1176] "Example 2: Combining Emotion Engines"

[1177] (Claim 1)

[1178] a means of collecting data periodically from internal sources;

[1179] A means of analyzing the collected data and extracting key information;

[1180] a means for generating new content using a generative model based on the extracted information;

[1181] a means of distributing the generated content to employees;

[1182] A way to respond to employee questions and search and provide generated content,

[1183] means for recognizing the emotional state of a user;

[1184] means for adjusting the format and sequence of content provided based on the user's emotional state;

[1185] A system including:

[1186] (Claim 2)

[1187] 10. The system of claim 1, wherein the system collects data from internal company documents, meeting minutes, and project materials.

[1188] (Claim 3)

[1189] 10. The system of claim 1, wherein natural language processing techniques are used to analyze the data and extract important information.

[1190] "Application example 2 when combining emotion engines"

[1191] (Claim 1)

[1192] a means of collecting data periodically from internal sources;

[1193] A means of analyzing the collected data and extracting key information;

[1194] a means for generating new content using a generative model based on the extracted information;

[1195] a means of distributing the generated content to employees;

[1196] A way to respond to employee questions and search and provide generated content,

[1197] means for analyzing the emotional state of the user using an emotion engine that recognizes the user's emotions;

[1198] A system including a means for prioritizing and providing appropriate information depending on emotional state.

[1199] (Claim 2)

[1200] 10. The system of claim 1, wherein the system collects data from internal company documents, meeting minutes, and project documents.

[1201] (Claim 3)

[1202] 10. The system of claim 1, wherein natural language processing techniques are used to analyze the data and extract important information. [Explanation of symbols]

[1203] 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 of collecting data periodically from internal sources; A means of analyzing the collected data and extracting key information; a means for generating new content using a generative model based on the extracted information; a means of distributing the generated content to employees; A way to respond to employee questions and search and provide generated content, A system including:

2. The system of claim 1 , wherein the system collects data from internal company documents, meeting minutes, and project documents.

3. 10. The system of claim 1, wherein natural language processing techniques are used to analyze the data and extract important information.

Images