system

Abstract

We provide the system. [Solution] A means for obtaining messages from the manager or business administrator, A means of analyzing the acquired message, A means for storing the analysis results, A system that includes means for providing stored analysis results to users.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In current corporate operations, messages from business operators and management are extremely important as a means of communicating corporate policies and strategies to employees. However, there is a lack of a mechanism for effectively transmitting these messages to all employees and reflecting them in actual actions. As a result, the consistency of the entire company is lost, and it becomes difficult to execute effective management policies. Therefore, an object of the present invention is to solve this problem by providing a system that effectively collects, analyzes, and provides messages from business operators and management.

Means for Solving the Problems

[0005] The present invention solves the above-mentioned problems with a system that includes means for acquiring messages from managers or executives, means for analyzing the acquired messages using natural language processing technology, means for storing the analysis results, and means for providing the stored analysis results to users. Specifically, a server first collects messages from managers and executives from specified information sources and analyzes these messages in the form of summaries and action guidelines using natural language processing technology. The analyzed information is stored in a database and provided to employees (users) through terminals they access. This system enables the efficient communication of the intentions and policies of managers and executives to employees, thereby maintaining consistency throughout the company.

[0006] "Manager or executive" refers to a person who is involved in the management of a company and is in a position to formulate and direct policies and strategies.

[0007] "Message" refers to information, including company policies, strategies, instructions, and announcements, issued by executives or managers.

[0008] "Means of acquisition" refers to the technical methods and devices used to collect messages from specified information sources.

[0009] "Means of analysis" refers to technical methods and devices used to analyze collected messages and extract important information and guidelines for action.

[0010] "Means of storage" refers to databases and storage systems used to store analyzed data.

[0011] "Means of providing" refers to technical methods or devices for displaying or transmitting stored data to users.

[0012] "Natural language processing technology" refers to the technology used to analyze human language with computers and understand and process its meaning and structure.

[0013] A "system" refers to a collection of components that work together to perform a series of processes and provide a specific function.

[0014] "Users" refers to employees of a company who receive messages from managers and executives and utilize the analysis results.

[0015] A "terminal" refers to electronic devices such as computers and smartphones that users access to obtain data. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the 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 processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0037] This invention provides a system for enabling employees to take consistent actions based on messages from managers and executives, and will provide a specific description of its embodiments.

[0038] overview

[0039] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[0040] Data collection

[0041] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. The retrieved messages are in HTML or text format, and the text portion is extracted using libraries such as BeautifulSoup.

[0042] Data Analysis

[0043] The server analyzes the collected messages using natural language processing techniques (e.g., the Transformers library's pipeline). The purpose of the analysis is to extract message summaries and action guidelines. This allows employees to quickly understand the important points from redundant information.

[0044] Data Gateway

[0045] The server stores the analyzed summaries and action plans in a database. This database serves as a centralized source of information accessible to employees. SQLite is used for the database to enhance data reliability and availability.

[0046] Data distribution

[0047] Users can access the database using dedicated terminals or applications to obtain the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information.

[0048] Specific example

[0049] 1. Example of data collection

[0050] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0051] The server sends an HTTP request and receives an HTML response.

[0052] We will use BeautifulSoup to extract the main text of the article.

[0053] 2. Examples of data analysis

[0054] The server analyzes the collected blog posts using pipeline("summarization").

[0055] The analysis results extract the summary: "Prioritize customer satisfaction."

[0056] 3. Examples of data storage

[0057] The server saves the extracted summary to an SQLite database.

[0058] Each summary is saved as a table row, making it easy to search and refer to.

[0059] 4. Examples of data distribution

[0060] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0061] The device displays the acquired summary to the user, who then uses it to create an action plan.

[0062] As described above, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). The server sends an HTTP request and uses BeautifulSoup to parse the HTML or text received as a response and extract the body.

[0066] Step 2:

[0067] The server analyzes the acquired messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[0068] Step 3:

[0069] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. During storage, the data format is standardized and structured to enable efficient searching and retrieval.

[0070] Step 4:

[0071] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[0072] Step 5:

[0073] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[0074] Step 6:

[0075] The terminal displays the analysis results received from the server to the user. Based on the displayed information, the user formulates a direction for their work and an action plan.

[0076] Through the steps outlined above, this system enables effective communication of messages from managers and executives to employees, allowing for the implementation of management policies while maintaining consistency across the entire company.

[0077] (Example 1)

[0078] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0079] In today's business environment, it is crucial to quickly and accurately communicate messages from company executives and managers to all employees. However, the lack of efficient systems for achieving this often leads to communication gaps and undermines consistency and uniformity of behavior across the entire company. Furthermore, extracting and understanding key points from vast amounts of information requires considerable time and effort, highlighting the need for efficient systems to address this challenge.

[0080] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0081] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages using natural language processing technology, means for sending HTTP requests to collect data, means for processing the extracted text data, means for storing the analyzed messages in a database, and means for querying the database in response to user requests to provide necessary information. This makes it possible to efficiently collect, analyze, and store important messages from managers and executives, and to quickly and accurately communicate them to all employees.

[0082] A "manager" is a person who, as the highest-ranking officer of a company or organization, is responsible for determining the overall strategy and policies.

[0083] A "management officer" is a person who oversees practical management activities within a company or organization and manages departments or areas based on the instructions of management.

[0084] "Means of obtaining messages" refers to the technologies and methods used to collect messages from executives and managers from specific sources on the internet.

[0085] "Means of analysis" refers to the techniques and methods used to analyze collected messages and extract their gist and important information.

[0086] "Means of memory" refers to the technologies and methods used to store summaries of analyzed messages and action guidelines in storage such as databases.

[0087] "Means of providing" refers to the technologies and methods used to appropriately display and make available the stored analysis results to the user.

[0088] "Natural language processing technology" refers to artificial intelligence technology used to process and understand human language using computers.

[0089] "Means of sending HTTP requests to collect data" refers to the techniques and methods of sending requests using the HTTP protocol to obtain information from a web server.

[0090] "Means for processing extracted text data" refers to the techniques and methods used to extract necessary information from acquired raw text data and to format it.

[0091] "Means of saving to a database" refers to the technologies and methods used to organize and store analyzed summaries and action plans in a database.

[0092] "Means of querying and providing necessary information" refers to the technologies and methods used to search a database in response to a user's request, retrieve the necessary information, and provide it to them.

[0093] A "generative AI model" refers to a machine learning model that is generated by artificial intelligence and trained to perform a specific task.

[0094] This invention is a system designed to ensure that employees take consistent actions based on messages from managers and executives. A specific description of its embodiments follows.

[0095] overview

[0096] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[0097] Data collection

[0098] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. Specifically, the server uses a pre-configured list of URLs or RSS feeds to access web-based sources and retrieve messages in HTML or text format. This process utilizes the BeautifulSoup library to extract the text portion, allowing for efficient collection of necessary messages.

[0099] Data Analysis

[0100] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes, for example, the pipeline function of the transformers library. Specifically, the server inputs the collected messages into pipeline("summarization") to generate a summary. This summary helps users quickly understand the key points and eliminates redundant parts of the message.

[0101] Data Gateway

[0102] The server stores the analyzed summaries and action plans in a database. SQLite is used as the database to structure and store the analysis results. For example, summaries and action plans can be stored as rows in a table. This ensures data reliability and availability.

[0103] Data distribution

[0104] Users can access the analyzed data using a dedicated terminal or application. Upon receiving a request from a user, the server queries the database to retrieve the necessary information. This information is then sent back to the user's terminal in JSON format. The terminal displays this data, allowing the user to develop an action plan based on it.

[0105] Specific example

[0106] 1. Example of data collection

[0107] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog. For example, the server sends an HTTP GET request and receives an HTML response.

[0108] Next, BeautifulSoup is used to extract the main text of the article.

[0109] 2. Examples of data analysis

[0110] The server generates summaries by analyzing the collected blog posts using the transformers library's pipeline("summarization") function. For example, it might extract the summary "Prioritize customer satisfaction."

[0111] 3. Examples of data storage

[0112] The server saves the analysis results, which are summaries, to an SQLite database. Each summary is stored as a row in the table.

[0113] 4. Examples of data distribution

[0114] The user accesses a database through a dedicated application and retrieves a summary, such as "Prioritize customer satisfaction." The terminal displays the retrieved summary to the user, who then develops an action plan based on it.

[0115] Thus, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[0116] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0117] Step 1:

[0118] The server retrieves messages from the executive or management from the specified source.

[0119] Input: A pre-configured list of URLs or RSS feeds.

[0120] Data processing: The server sends an HTTP request to each URL and receives an HTML response.

[0121] Output: Message data in HTML or text format.

[0122] Specific operation: The server uses the requests library to send an HTTP GET request, and the HTML response is parsed using the BeautifulSoup library to extract text.

[0123] Step 2:

[0124] The server analyzes the collected messages using natural language processing techniques.

[0125] Input: Extracted text data.

[0126] Data processing: Use the pipeline function of the transformers library to summarize the text data.

[0127] Output: Summarized message and action plan.

[0128] Specific operation: The server passes the extracted text data to pipeline("summarization") to generate a summary. For example, it extracts the summary "Prioritize customer satisfaction."

[0129] Step 3:

[0130] The server saves the analyzed summary and action plan to a database.

[0131] Input: Summarized message and action plan.

[0132] Data processing: Structure this data and store it in an SQLite database.

[0133] Output: Analysis results stored in the database.

[0134] Specific operation: The server connects to the SQLite database and inserts the summary and action plan into the table using an INSERT INTO query.

[0135] Step 4:

[0136] Users access the analyzed data using dedicated terminals or applications.

[0137] Input: Information request from the user.

[0138] Data processing: The server queries the database to retrieve the necessary information.

[0139] Output: Analysis results sent back to the user's terminal.

[0140] Specific operation: When a user accesses the API endpoint through a dedicated application, the server executes a SELECT query to retrieve the necessary analysis results from the database and sends them back to the terminal in JSON format.

[0141] Step 5:

[0142] The device displays the information it has acquired to the user.

[0143] Input: Analysis results (in JSON format) returned from the server.

[0144] Data processing: Convert the analysis results to an appropriate format and display them on the device.

[0145] Output: A summary and action plan displayed to the user.

[0146] Specific operation: The user's device interprets the analysis results received from the server and displays a summary and action plan on the application interface. The user then uses this information to create an action plan.

[0147] Through the processing steps described above, the server can efficiently collect, analyze, and store messages from executives and managers, and provide users with appropriate information. This makes it possible to quickly communicate message content to employees while maintaining consistency across the entire company.

[0148] (Application Example 1)

[0149] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0150] Traditional methods for efficiently communicating messages from managers and executives to employees were time-consuming and often lacked consistency. This made it difficult to quickly and accurately convey key messages and action guidelines to employees, ultimately hindering the achievement of overall company goals and the implementation of management policies.

[0151] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0152] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages and extracting action guidelines, means for storing the analyzed summaries and action guidelines in a centrally managed database, and means for searching and notifying users of the analysis results via their terminals. This enables managers' and executives' policies and guidelines to be communicated to employees quickly and accurately, allowing for consistent action throughout the entire company.

[0153] A "manager" is a person or position in which a company or organization makes major decisions.

[0154] A "management officer" is a person who has the responsibility of managing, planning strategies for, and overseeing the operations of a company or organization.

[0155] A "message" refers to documents or communications containing information, instructions, policies, and goals issued by a manager or executive.

[0156] "Means of acquisition" refers to the methods and techniques used to extract data from a specified source.

[0157] "Means of analysis" refer to methods and techniques for processing acquired messages, summarizing their content, and extracting actionable guidelines.

[0158] "Means of storage" refers to methods and technologies for saving analyzed information in a database or similar format.

[0159] "Means of providing information to users" refers to methods and technologies that enable users to access stored information.

[0160] A "centralized database" is a data management system that centrally manages analyzed information and is designed to allow efficient access to it.

[0161] A "user's device" is a device that a user uses to view or manipulate information.

[0162] "Means of searching and notifying" refers to functions that allow users to find specific information, or technologies that inform users of the latest information.

[0163] A "summary" is a concise compilation of the main points and important aspects of a message.

[0164] A "guideline of action" is a set of specific actions that should be taken based on the analyzed message.

[0165] This invention is a system that enables messages from managers and executives to be conveyed to employees quickly and accurately. The following describes a specific method for implementing this invention.

[0166] Data collection

[0167] The server collects messages from executives or managers from specified sources. Specifically, it sends HTTP requests to sources such as blogs, press releases, and internal emails to retrieve messages in text format. The BeautifulSoup library is used to extract the text portion.

[0168] Data Analysis

[0169] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and action guidelines. The summaries are concise summaries of the main points of the message, while the action guidelines indicate specific actions that employees should take.

[0170] Data Gateway

[0171] The analyzed summaries and action plans are stored in a centrally managed database. This database utilizes SQLite, enabling rapid storage and retrieval of analysis results.

[0172] Data distribution

[0173] Users access the database using devices such as smartphones to retrieve the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information. Furthermore, important information is pushed to enable employees to take immediate action.

[0174] Specific example

[0175] 1. Example of data collection

[0176] The server retrieves blog posts from the company's CEO at https: / / example.com / ceo-blog. The HTML of the article obtained via HTTP request is then used with BeautifulSoup to extract the article's body text.

[0177] 2. Examples of data analysis

[0178] The server analyzes the collected blog posts using pipeline("summarization"). This analysis extracts the summary, "Prioritize customer satisfaction." Based on this summary, the action plan, "Take the following action: Prioritize customer satisfaction," is also generated.

[0179] 3. Examples of data storage

[0180] The server extracts the summary "Prioritize customer satisfaction" and the action plan "Take the following action: Prioritize customer satisfaction" and saves them to an SQLite database.

[0181] 4. Examples of data distribution

[0182] The user accesses the database through a smartphone application and retrieves a summary titled "Prioritize customer satisfaction" and action guidelines titled "Take the next step: Prioritize customer satisfaction." The device then pushes this information to the user.

[0183] Example of a prompt

[0184] Message sample: "Our company plans to double its sales in the next five years..."

[0185] Prompt: summarizer("We plan to double our sales in the next five years...")

[0186] Expected output: "Plan to double sales"

[0187] In this way, this invention efficiently analyzes and distributes important messages within a company, enabling employees to take swift and coordinated action.

[0188] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0189] Step 1:

[0190] The server retrieves messages from the executive or management from the specified source.

[0191] Input: URL of the source (e.g., https: / / example.com / ceo-blog)

[0192] Data processing: Use the requests library to send an HTTP request and retrieve an HTML response.

[0193] Output: Message in HTML format

[0194] Step 2:

[0195] Extract text from the HTML message received by the server.

[0196] Input: HTML message

[0197] Data processing: Extract text from HTML using the BeautifulSoup library.

[0198] Output: Message in text format

[0199] Step 3:

[0200] The server analyzes text-based messages using natural language processing techniques to generate summaries and action plans.

[0201] Input: Text message

[0202] Data processing: Summarize the message using the transformers library's pipeline("summarization") and extract action guidelines.

[0203] Output: Summary and action plan (Example: "Summary: Prioritize customer satisfaction," "Action plan: Take the following action: Prioritize customer satisfaction")

[0204] Step 4:

[0205] The server stores the analyzed summary and action plan in a centrally managed database.

[0206] Input: Summary and action plan

[0207] Data storage: Summaries and action plans are stored in an SQLite database.

[0208] Output: Summaries and action plans stored in the database

[0209] Step 5:

[0210] Users access the database through their devices to obtain the latest summaries and action plans.

[0211] Input: Data request from user

[0212] Data processing: Query databases to retrieve relevant summaries and action plans.

[0213] Output: Summary and action plan displayed on the user's terminal.

[0214] Step 6:

[0215] The device will push notifications to the user with important action guidelines based on specific conditions.

[0216] Input: New analysis results or important messages

[0217] Data manipulation: Determine the trigger conditions for push notifications and generate notifications.

[0218] Output: Action guidelines displayed as push notifications on the user's device.

[0219] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0220] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. This embodiment will be described in detail.

[0221] overview

[0222] The system begins with a server receiving messages from executives or managers and analyzing them using natural language processing technology. The analysis results are stored in a database and provided to employees (users) through their terminals. The system also incorporates an emotion engine that recognizes user emotions, and the information provided is customized based on the user's emotional data.

[0223] Data collection

[0224] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). The server sends HTTP requests and uses the BeautifulSoup library to parse the HTML or text received as responses and extract the body.

[0225] Data Analysis

[0226] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines.

[0227] Data Gateway

[0228] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. The data is structured to allow for efficient searching and retrieval.

[0229] Data distribution

[0230] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[0231] Emotional Engine

[0232] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones, acquiring emotional data such as joy, anger, sadness, and happiness. This emotional data is used to customize how the analysis results are delivered.

[0233] Data customization

[0234] The server adjusts the content and format of information provided to the user based on emotional data received from the emotion engine. For example, if a user is experiencing stress, it will provide only the most important information in a concise manner, providing optimal information tailored to the user's state.

[0235] Specific example

[0236] 1. Example of data collection

[0237] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0238] The server sends an HTTP request and receives an HTML response.

[0239] We will use BeautifulSoup to extract the main text of the article.

[0240] 2. Examples of data analysis

[0241] The server analyzes the collected blog posts using pipeline("summarization").

[0242] The analysis results extract the summary: "Prioritize customer satisfaction."

[0243] 3. Examples of data storage

[0244] The server saves the extracted summary to an SQLite database.

[0245] Each summary is saved as a table row, making it easy to search and refer to.

[0246] 4. Examples of emotional engines

[0247] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user's state is "tension."

[0248] Based on this sentiment data, the server concisely organizes and provides important information to the user.

[0249] 5. Examples of data distribution

[0250] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0251] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[0252] Through these steps, the system effectively communicates messages from managers and executives to employees, and further improves overall consistency and efficiency within the company by customizing information according to the user's emotions.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). Specifically, the server sends an HTTP request, parses the HTML or text received as a response using the BeautifulSoup library, and extracts the body text.

[0256] Step 2:

[0257] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[0258] Step 3:

[0259] The server saves the analysis results to a database. The analyzed summaries and action plans are structured and stored in an SQLite database, allowing for efficient searching and retrieval.

[0260] Step 4:

[0261] The terminal receives a request from the user. The user uses a dedicated terminal or application to send a request to access the analyzed data.

[0262] Step 5:

[0263] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[0264] Step 6:

[0265] The emotion engine recognizes the user's emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones connected to the device, and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[0266] Step 7:

[0267] The server customizes the information it provides based on emotional data obtained from the emotion engine. For example, if a user is feeling anxious, it adjusts how information is presented in the most optimal format depending on the user's state, such as providing information in a concise manner.

[0268] Step 8:

[0269] The terminal displays the analysis results and customized information received from the server to the user. The user views the displayed information and develops an action plan based on it.

[0270] (Example 2)

[0271] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0272] Traditional systems have struggled to effectively communicate messages from management or executives to employees, leading to inconsistent employee behavior. Furthermore, they lack the ability to customize information based on user sentiment, often resulting in ineffective communication. Solving this problem is essential.

[0273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0274] In this invention, the server includes means for acquiring messages from managers or executives from a data source, means for using a natural language processing model to analyze the acquired messages, and means for storing the analysis results in a database. This makes it possible to accurately and effectively analyze messages from managers and executives and provide them to employees. The server further includes application means for providing the stored analysis results to users, emotion recognition engine means for recognizing the user's emotions, and means for adjusting the content and format of the information provided based on emotion data acquired from the emotion recognition engine. This allows information to be customized according to the user's emotions, resulting in more effective information transmission.

[0275] A "data source" refers to an external or internal information provider that a user or system uses to collect information.

[0276] "Manager or executive" refers to a person in a position to make major decisions within a company or organization.

[0277] A "message" refers to information or instructions that a manager or executive communicates to employees or stakeholders.

[0278] "To acquire" refers to collecting information from a specified data source and incorporating it into the system.

[0279] "Analyzing" refers to the process of converting an acquired message into an easily understandable form using natural language processing techniques and other methods.

[0280] A "natural language processing model" refers to artificial intelligence technology that analyzes and interprets text data, and includes models that perform tasks such as summarization and semantic extraction.

[0281] A "database" refers to a system or collection of structured data used to manage and store analysis results and other information.

[0282] "To'memorize'" refers to storing the analyzed information in a storage such as a database so that it can be accessed later.

[0283] "Application means" refers to software or an interface for presenting analysis results and other information to the user.

[0284] "Emotion recognition engine" refers to a technology that analyzes data such as the user's facial expressions and voice to detect emotions.

[0285] "Emotion data" refers to information obtained by the emotion recognition engine analyzing the user's emotions.

[0286] "To adjust the content and form of information provision" refers to appropriately changing the type of information provided and its display method according to the user's needs and status.

[0287] This invention combines an emotion engine that recognizes the user's emotions with a system for enabling employees to take the same actions based on messages from managers and management administrators. This system is implemented in the following steps.

[0288] Data collection

[0289] The server obtains messages from managers and management administrators from a specified information source (e.g., blog, press release, internal company email). For this, the requests library or the BeautifulSoup web scraping tool is used. The server sends an HTTP request and parses the HTML or text received as a response to extract the text.

[0290] Specific example:

[0291] The server obtains a CEO's blog article from https: / / example.com / ceo-blog.

[0292] The server sends an HTTP request and receives an HTML response.

[0293] We will use BeautifulSoup to extract the main text of the article.

[0294] Data Analysis

[0295] The server analyzes the collected messages using natural language processing (NLP) techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and key action guidelines.

[0296] Specific example:

[0297] The server analyzes the collected blog posts using pipeline("summarization").

[0298] The analysis results extract the summary: "Prioritize customer satisfaction."

[0299] Data Gateway

[0300] The server stores the analysis results in a database. A lightweight database such as SQLite is used, and the analysis results are structured to allow for efficient searching and retrieval.

[0301] Specific example:

[0302] The server saves the extracted summary to an SQLite database.

[0303] Each summary is saved as a table row, making it easy to search and refer to.

[0304] Data distribution

[0305] Users access the database and retrieve necessary information using dedicated terminals or applications. The terminal receives requests from users and queries the server for the required information.

[0306] Specific example:

[0307] The user accesses the database through the application and obtains the summary of "giving top priority to customer satisfaction".

[0308] Emotion engine

[0309] The emotion engine includes technologies for recognizing the user's emotions. The user's expressions and voice are analyzed through sensors such as cameras and microphones to obtain emotion data. This data is used to customize the information provided to the user.

[0310] Specific example:

[0311] The emotion engine analyzes the user's expressions and voice and recognizes that the user's state is "nervous".

[0312] The server provides the user with important information in a concise and organized manner.

[0313] Customization of information provision

[0314] The server adjusts the content and format of the information provided to the user based on the emotion data obtained from the emotion engine. For example, when the user is feeling stressed, particularly important information is provided in a concise summary.

[0315] Specific example:

[0316] ]> Based on the results of the emotion engine, the information is displayed to the user in an appropriate format.

[0317] According to this invention, the consistency and efficiency of the entire enterprise can be improved.

[0318] Examples of prompt sentences:

[0319] "Summarize the latest blog posts of the executives."

[0320] "Identify key behavioral guidelines for employees."

[0321] "Adjust the information you provide according to the user's emotions."

[0322] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0323] Step 1:

[0324] The server retrieves messages from executives or managers from a specified data source. Specifically, the server uses the requests library to send HTTP requests and receive HTML responses. For example, the server executes requests.get("https: / / example.com / ceo-blog") to retrieve blog posts. A specified URL is given as input, and an HTML document is obtained as output.

[0325] Step 2:

[0326] The server parses the received HTML document using the BeautifulSoup library and extracts the message body. Specifically, it extracts text from paragraph tags, like soup.find_all("p"). An HTML document is given as input, and the output is the text of the message body.

[0327] Step 3:

[0328] The server analyzes the extracted message body using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines. For example, it uses pipeline("summarization") to summarize the text. The message body is given as input, and the summarized text is obtained as output.

[0329] Step 4:

[0330] The server saves the analysis results to an SQLite database. Specifically, it establishes a database connection using the sqlite3 library and inserts the analysis results using an SQL query like INSERT INTO summaries (summary_text, date) VALUES (?, ?). The input is the summary text and date and time, and the output is a record inserted into the database.

[0331] Step 5:

[0332] The server receives a request from the user and retrieves the necessary information from the database. Specifically, it receives an HTTP request and extracts data using an SQL query such as SELECT FROM summaries WHERE date = ?. The request parameters are given as input, and the output is the summary text extracted from the database.

[0333] Step 6:

[0334] The device displays the retrieved summary text to the user. Specifically, the user accesses the information through the application, and it is displayed on the screen. The retrieved summary text is given as input, and the output is displayed on the user's screen.

[0335] Step 7:

[0336] The emotion engine uses the camera and microphone to analyze the user's facial expressions and voice in order to recognize the user's emotions. Specifically, it analyzes audio using the librosa library and detects facial expressions using the OpenCV library. Camera video and audio data are given as input, and user emotion data is obtained as output.

[0337] Step 8:

[0338] The server adjusts the content and format of the information provided based on sentiment data obtained from the sentiment engine. Specifically, if the user is experiencing stress, the information is presented in a concise summary. Sentiment data and a summary text are provided as input, and customized information is provided to the user as output.

[0339] (Application Example 2)

[0340] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0341] In conventional systems, messages from managers and executives were not effectively communicated to employees, making it difficult for everyone to act in a unified manner. Furthermore, because employees' emotions and psychological states were not considered, messages were sometimes not effectively received. In addition, employees experiencing specific situations or stress levels were not provided with appropriate information, raising concerns about decreased work efficiency and motivation.

[0342] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing the acquired messages, means for storing the analysis results, means for providing the stored analysis results to the user, means for recognizing the user's emotions, and means for customizing the information provided based on the recognized emotions. This enables effective communication of messages from managers and executives to employees, and allows for the provision of information that takes into account the emotions and psychological state of employees. This is expected to improve work efficiency and maintain employee motivation.

[0343] "Management" refers to a manager or leader who makes important decisions regarding the operation of a company or organization.

[0344] A "message" refers to instructions, policies, information, etc., that a manager or executive communicates to employees of a company or organization.

[0345] "Analysis" refers to the process of analyzing the content of acquired messages and extracting important information and guidelines for action.

[0346] "Memory" refers to saving analysis results to a database or storage device, making them easily searchable and retrievable.

[0347] "Providing" refers to presenting the stored analysis results to the user through a device or application.

[0348] "Users" refer to employees of companies or organizations who use the system and receive the stored analysis results.

[0349] "Emotion recognition" refers to technology that detects and analyzes a user's emotions and psychological state using cameras, microphones, sensors, etc.

[0350] "Customization" refers to the process of individually adjusting the content and format of information provided based on recognized sentiment data.

[0351] Modes for carrying out the invention

[0352] This invention is a system that enables employees to effectively receive messages from managers and supervisors and to act consistently based on that content. Furthermore, it aims to reduce employee stress and improve work efficiency by understanding employees' emotional states and customizing the information delivery method accordingly.

[0353] System program generation

[0354] The system consists of the following main components:

[0355] 1. Message acquisition method

[0356] 2. Data Analysis Methods

[0357] 3. Storage means

[0358] 4. Means of provision

[0359] 5. Emotion recognition means

[0360] 6. Customization methods

[0361] Detailed explanation of the process

[0362] Message creation method

[0363] The server sends HTTP requests to retrieve messages from managers and administrators. For example, it uses the requests library to retrieve messages from a specified web page or mail server.

[0364] Data analysis means

[0365] The acquired messages are analyzed using natural language processing techniques with the transformers library. Specifically, message summaries and key action guidelines are extracted. To achieve this, generative AI models such as BERT are utilized to perform the summarization function.

[0366] storage means

[0367] The analyzed results are stored in a database such as SQLite and structured for efficient searching and retrieval. This database is accessible to employees via a smartphone application.

[0368] Providing means

[0369] The server retrieves analysis results from the database based on employee requests and provides them in an appropriate format. Delivery methods include smartphone applications and digital signage.

[0370] emotion recognition means

[0371] The system analyzes employees' facial expressions and voices through sensors such as cameras and microphones installed in smartphones and dedicated devices, and acquires emotional data. Libraries such as mediapipe and cv2 (OpenCV) are used for facial recognition and voice analysis.

[0372] Customization methods

[0373] Based on recognized emotion data, the server adjusts the content and format of the information provided. For example, if an employee is stressed, it provides only essential information in a concise format, while if they are relaxed, it also provides detailed information. This customization can reduce the psychological burden on employees.

[0374] Specific example

[0375] For example, this could be applied when an employee in a physical store is assisting a customer and receives the latest instructions from their manager via an app. If the employee is under stress, the app will display only the essential, summarized instructions concisely, keeping them in a state where they can act quickly. Conversely, if the employee is calm, the app will also provide detailed instructions and supplementary information.

[0376] Example of a prompt

[0377] "Create a system to receive new instructions from management and deliver them to employees in the most appropriate format. This system should recognize employees' emotions and provide only summarized, essential information if they are feeling stressed, and also provide detailed information if they are calm."

[0378] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0379] Step 1:

[0380] The server retrieves messages from managers or administrators. Specifically, the server uses the requests library to send HTTP requests from a specified URL to retrieve messages. The input data is the URL of the message, and the output data is the retrieved HTML content.

[0381] Step 2:

[0382] The server parses the retrieved HTML content and extracts the message body. Specifically, it uses the BeautifulSoup library to parse the HTML and extract the text portion containing the message. The input data is the retrieved HTML content, and the output data is the extracted message body.

[0383] Step 3:

[0384] The server analyzes the extracted messages using natural language processing techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines. A generative AI model is used to generate the summaries. The input data is the extracted message text, and the output data is the summary result.

[0385] Step 4:

[0386] The server stores the analysis results in a database. Specifically, it stores the summarized results in an SQLite database and structures them to facilitate future searching and retrieval. The input data is the summarized results, and the output data is the analysis results stored in the database.

[0387] Step 5:

[0388] The device recognizes the user's emotions through the camera and microphone. Specifically, it uses the cv2 and mediapipe libraries to analyze the user's facial expressions and voice using an emotion recognition algorithm. The input data is real-time video and audio obtained from the camera and microphone, and the output data is the recognized emotion data.

[0389] Step 6:

[0390] The server customizes the information it provides based on the recognized emotion data. Specifically, if the emotion is recognized as "stress," it provides only essential summary information; if the emotion is recognized as "relaxed," it also provides detailed information. The input data consists of the recognized emotion data and the results of database analysis, while the output data is the customized information.

[0391] Step 7:

[0392] The server sends customized information to the terminal, which then displays it to the user. Specifically, the display method is adjusted through the application interface to ensure the user receives the information in the most optimal format. The input data is customized information, and the output data is the information best displayed on the user's terminal.

[0393] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0394] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0395] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0396] [Second Embodiment]

[0397] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0398] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0399] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0400] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0401] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0402] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0403] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0404] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0405] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0406] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0407] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0408] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0409] This invention provides a system for enabling employees to take consistent actions based on messages from managers and executives, and will provide a specific description of its embodiments.

[0410] overview

[0411] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[0412] Data collection

[0413] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. The retrieved messages are in HTML or text format, and the text portion is extracted using libraries such as BeautifulSoup.

[0414] Data Analysis

[0415] The server analyzes the collected messages using natural language processing techniques (e.g., the Transformers library's pipeline). The purpose of the analysis is to extract message summaries and action guidelines. This allows employees to quickly understand the important points from redundant information.

[0416] Data Gateway

[0417] The server stores the analyzed summaries and action plans in a database. This database serves as a centralized source of information accessible to employees. SQLite is used for the database to enhance data reliability and availability.

[0418] Data distribution

[0419] Users can access the database using dedicated terminals or applications to obtain the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information.

[0420] Specific example

[0421] 1. Example of data collection

[0422] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0423] The server sends an HTTP request and receives an HTML response.

[0424] We will use BeautifulSoup to extract the main text of the article.

[0425] 2. Examples of data analysis

[0426] The server analyzes the collected blog posts using pipeline("summarization").

[0427] The analysis results extract the summary: "Prioritize customer satisfaction."

[0428] 3. Examples of data storage

[0429] The server saves the extracted summary to an SQLite database.

[0430] Each summary is saved as a table row, making it easy to search and refer to.

[0431] 4. Examples of data distribution

[0432] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0433] The device displays the acquired summary to the user, who then uses it to create an action plan.

[0434] As described above, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[0435] The following describes the processing flow.

[0436] Step 1:

[0437] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). The server sends an HTTP request and uses BeautifulSoup to parse the HTML or text received as a response and extract the body.

[0438] Step 2:

[0439] The server analyzes the acquired messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[0440] Step 3:

[0441] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. During storage, the data format is standardized and structured to enable efficient searching and retrieval.

[0442] Step 4:

[0443] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[0444] Step 5:

[0445] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[0446] Step 6:

[0447] The terminal displays the analysis results received from the server to the user. Based on the displayed information, the user formulates a direction for their work and an action plan.

[0448] Through the steps outlined above, this system enables effective communication of messages from managers and executives to employees, allowing for the implementation of management policies while maintaining consistency across the entire company.

[0449] (Example 1)

[0450] Next, we will describe Example 1. 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".

[0451] In today's business environment, it is crucial to quickly and accurately communicate messages from company executives and managers to all employees. However, the lack of efficient systems for achieving this often leads to communication gaps and undermines consistency and uniformity of behavior across the entire company. Furthermore, extracting and understanding key points from vast amounts of information requires considerable time and effort, highlighting the need for efficient systems to address this challenge.

[0452] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0453] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages using natural language processing technology, means for sending HTTP requests to collect data, means for processing the extracted text data, means for storing the analyzed messages in a database, and means for querying the database in response to user requests to provide necessary information. This makes it possible to efficiently collect, analyze, and store important messages from managers and executives, and to quickly and accurately communicate them to all employees.

[0454] A "manager" is a person who, as the highest-ranking officer of a company or organization, is responsible for determining the overall strategy and policies.

[0455] A "management officer" is a person who oversees practical management activities within a company or organization and manages departments or areas based on the instructions of management.

[0456] "Means of obtaining messages" refers to the technologies and methods used to collect messages from executives and managers from specific sources on the internet.

[0457] "Means of analysis" refers to the techniques and methods used to analyze collected messages and extract their gist and important information.

[0458] "Means of memory" refers to the technologies and methods used to store summaries of analyzed messages and action guidelines in storage such as databases.

[0459] "Means of providing" refers to the technologies and methods used to appropriately display and make available the stored analysis results to the user.

[0460] "Natural language processing technology" refers to artificial intelligence technology used to process and understand human language using computers.

[0461] "Means of sending HTTP requests to collect data" refers to the techniques and methods of sending requests using the HTTP protocol to obtain information from a web server.

[0462] "Means for processing extracted text data" refers to the techniques and methods used to extract necessary information from acquired raw text data and to format it.

[0463] "Means of saving to a database" refers to the technologies and methods used to organize and store analyzed summaries and action plans in a database.

[0464] "Means of querying and providing necessary information" refers to the technologies and methods used to search a database in response to a user's request, retrieve the necessary information, and provide it to them.

[0465] A "generative AI model" refers to a machine learning model that is generated by artificial intelligence and trained to perform a specific task.

[0466] This invention is a system designed to ensure that employees take consistent actions based on messages from managers and executives. A specific description of its embodiments follows.

[0467] overview

[0468] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[0469] Data collection

[0470] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. Specifically, the server uses a pre-configured list of URLs or RSS feeds to access web-based sources and retrieve messages in HTML or text format. This process utilizes the BeautifulSoup library to extract the text portion, allowing for efficient collection of necessary messages.

[0471] Data Analysis

[0472] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes, for example, the pipeline function of the transformers library. Specifically, the server inputs the collected messages into pipeline("summarization") to generate a summary. This summary helps users quickly understand the key points and eliminates redundant parts of the message.

[0473] Data Gateway

[0474] The server stores the analyzed summaries and action plans in a database. SQLite is used as the database to structure and store the analysis results. For example, summaries and action plans can be stored as rows in a table. This ensures data reliability and availability.

[0475] Data distribution

[0476] Users can access the analyzed data using a dedicated terminal or application. Upon receiving a request from a user, the server queries the database to retrieve the necessary information. This information is then sent back to the user's terminal in JSON format. The terminal displays this data, allowing the user to develop an action plan based on it.

[0477] Specific example

[0478] 1. Example of data collection

[0479] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog. For example, the server sends an HTTP GET request and receives an HTML response.

[0480] Next, BeautifulSoup is used to extract the main text of the article.

[0481] 2. Examples of data analysis

[0482] The server generates summaries by analyzing the collected blog posts using the transformers library's pipeline("summarization") function. For example, it might extract the summary "Prioritize customer satisfaction."

[0483] 3. Examples of data storage

[0484] The server saves the analysis results, which are summaries, to an SQLite database. Each summary is stored as a row in the table.

[0485] 4. Examples of data distribution

[0486] The user accesses a database through a dedicated application and retrieves a summary, such as "Prioritize customer satisfaction." The terminal displays the retrieved summary to the user, who then develops an action plan based on it.

[0487] Thus, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] The server retrieves messages from the executive or management from the specified source.

[0491] Input: A pre-configured list of URLs or RSS feeds.

[0492] Data processing: The server sends an HTTP request to each URL and receives an HTML response.

[0493] Output: Message data in HTML or text format.

[0494] Specific operation: The server uses the requests library to send an HTTP GET request, and the HTML response is parsed using the BeautifulSoup library to extract text.

[0495] Step 2:

[0496] The server analyzes the collected messages using natural language processing techniques.

[0497] Input: Extracted text data.

[0498] Data processing: Use the pipeline function of the transformers library to summarize the text data.

[0499] Output: Summarized message and action plan.

[0500] Specific operation: The server passes the extracted text data to pipeline("summarization") to generate a summary. For example, it extracts the summary "Prioritize customer satisfaction."

[0501] Step 3:

[0502] The server saves the analyzed summary and action plan to a database.

[0503] Input: Summarized message and action plan.

[0504] Data processing: Structure this data and store it in an SQLite database.

[0505] Output: Analysis results stored in the database.

[0506] Specific operation: The server connects to the SQLite database and inserts the summary and action plan into the table using an INSERT INTO query.

[0507] Step 4:

[0508] Users access the analyzed data using dedicated terminals or applications.

[0509] Input: Information request from the user.

[0510] Data processing: The server queries the database to retrieve the necessary information.

[0511] Output: Analysis results sent back to the user's terminal.

[0512] Specific operation: When a user accesses the API endpoint through a dedicated application, the server executes a SELECT query to retrieve the necessary analysis results from the database and sends them back to the terminal in JSON format.

[0513] Step 5:

[0514] The device displays the information it has acquired to the user.

[0515] Input: Analysis results (in JSON format) returned from the server.

[0516] Data processing: Convert the analysis results to an appropriate format and display them on the device.

[0517] Output: A summary and action plan displayed to the user.

[0518] Specific operation: The user's device interprets the analysis results received from the server and displays a summary and action plan on the application interface. The user then uses this information to create an action plan.

[0519] Through the processing steps described above, the server can efficiently collect, analyze, and store messages from executives and managers, and provide users with appropriate information. This makes it possible to quickly communicate message content to employees while maintaining consistency across the entire company.

[0520] (Application Example 1)

[0521] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0522] Traditional methods for efficiently communicating messages from managers and executives to employees were time-consuming and often lacked consistency. This made it difficult to quickly and accurately convey key messages and action guidelines to employees, ultimately hindering the achievement of overall company goals and the implementation of management policies.

[0523] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0524] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages and extracting action guidelines, means for storing the analyzed summaries and action guidelines in a centrally managed database, and means for searching and notifying users of the analysis results via their terminals. This enables managers' and executives' policies and guidelines to be communicated to employees quickly and accurately, allowing for consistent action throughout the entire company.

[0525] A "manager" is a person or position in which a company or organization makes major decisions.

[0526] A "management officer" is a person who has the responsibility of managing, planning strategies for, and overseeing the operations of a company or organization.

[0527] A "message" refers to documents or communications containing information, instructions, policies, and goals issued by a manager or executive.

[0528] "Means of acquisition" refers to the methods and techniques used to extract data from a specified source.

[0529] "Means of analysis" refer to methods and techniques for processing acquired messages, summarizing their content, and extracting actionable guidelines.

[0530] "Means of storage" refers to methods and technologies for saving analyzed information in a database or similar format.

[0531] "Means of providing information to users" refers to methods and technologies that enable users to access stored information.

[0532] A "centralized database" is a data management system that centrally manages analyzed information and is designed to allow efficient access to it.

[0533] A "user's device" is a device that a user uses to view or manipulate information.

[0534] "Means of searching and notifying" refers to functions that allow users to find specific information, or technologies that inform users of the latest information.

[0535] A "summary" is a concise compilation of the main points and important aspects of a message.

[0536] A "guideline of action" is a set of specific actions that should be taken based on the analyzed message.

[0537] This invention is a system that enables messages from managers and executives to be conveyed to employees quickly and accurately. The following describes a specific method for implementing this invention.

[0538] Data collection

[0539] The server collects messages from executives or managers from specified sources. Specifically, it sends HTTP requests to sources such as blogs, press releases, and internal emails to retrieve messages in text format. The BeautifulSoup library is used to extract the text portion.

[0540] Data Analysis

[0541] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and action guidelines. The summaries are concise summaries of the main points of the message, while the action guidelines indicate specific actions that employees should take.

[0542] Data Gateway

[0543] The analyzed summaries and action plans are stored in a centrally managed database. This database utilizes SQLite, enabling rapid storage and retrieval of analysis results.

[0544] Data distribution

[0545] Users access the database using devices such as smartphones to retrieve the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information. Furthermore, important information is pushed to enable employees to take immediate action.

[0546] Specific example

[0547] 1. Example of data collection

[0548] The server retrieves blog posts from the company's CEO at https: / / example.com / ceo-blog. The HTML of the article obtained via HTTP request is then used with BeautifulSoup to extract the article's body text.

[0549] 2. Examples of data analysis

[0550] The server analyzes the collected blog posts using pipeline("summarization"). This analysis extracts the summary, "Prioritize customer satisfaction." Based on this summary, the action plan, "Take the following action: Prioritize customer satisfaction," is also generated.

[0551] 3. Examples of data storage

[0552] The server extracts the summary "Prioritize customer satisfaction" and the action plan "Take the following action: Prioritize customer satisfaction" and saves them to an SQLite database.

[0553] 4. Examples of data distribution

[0554] The user accesses the database through a smartphone application and retrieves a summary titled "Prioritize customer satisfaction" and action guidelines titled "Take the next step: Prioritize customer satisfaction." The device then pushes this information to the user.

[0555] Example of a prompt

[0556] Message sample: "Our company plans to double its sales in the next five years..."

[0557] Prompt: summarizer("We plan to double our sales in the next five years...")

[0558] Expected output: "Plan to double sales"

[0559] In this way, this invention efficiently analyzes and distributes important messages within a company, enabling employees to take swift and coordinated action.

[0560] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0561] Step 1:

[0562] The server retrieves messages from the executive or management from the specified source.

[0563] Input: URL of the source (e.g., https: / / example.com / ceo-blog)

[0564] Data processing: Use the requests library to send an HTTP request and retrieve an HTML response.

[0565] Output: Message in HTML format

[0566] Step 2:

[0567] Extract text from the HTML message received by the server.

[0568] Input: HTML message

[0569] Data processing: Extract text from HTML using the BeautifulSoup library.

[0570] Output: Message in text format

[0571] Step 3:

[0572] The server analyzes text-based messages using natural language processing techniques to generate summaries and action plans.

[0573] Input: Text message

[0574] Data processing: Summarize the message using the transformers library's pipeline("summarization") and extract action guidelines.

[0575] Output: Summary and action plan (Example: "Summary: Prioritize customer satisfaction," "Action plan: Take the following action: Prioritize customer satisfaction")

[0576] Step 4:

[0577] The server stores the analyzed summary and action plan in a centrally managed database.

[0578] Input: Summary and action plan

[0579] Data storage: Summaries and action plans are stored in an SQLite database.

[0580] Output: Summaries and action plans stored in the database

[0581] Step 5:

[0582] Users access the database through their devices to obtain the latest summaries and action plans.

[0583] Input: Data request from user

[0584] Data processing: Query databases to retrieve relevant summaries and action plans.

[0585] Output: Summary and action plan displayed on the user's terminal.

[0586] Step 6:

[0587] The device will push notifications to the user with important action guidelines based on specific conditions.

[0588] Input: New analysis results or important messages

[0589] Data manipulation: Determine the trigger conditions for push notifications and generate notifications.

[0590] Output: Action guidelines displayed as push notifications on the user's device.

[0591] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0592] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. This embodiment will be described in detail.

[0593] overview

[0594] The system begins with a server receiving messages from executives or managers and analyzing them using natural language processing technology. The analysis results are stored in a database and provided to employees (users) through their terminals. The system also incorporates an emotion engine that recognizes user emotions, and the information provided is customized based on the user's emotional data.

[0595] Data collection

[0596] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). The server sends HTTP requests and uses the BeautifulSoup library to parse the HTML or text received as responses and extract the body.

[0597] Data Analysis

[0598] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines.

[0599] Data Gateway

[0600] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. The data is structured to allow for efficient searching and retrieval.

[0601] Data distribution

[0602] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[0603] Emotional Engine

[0604] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones, acquiring emotional data such as joy, anger, sadness, and happiness. This emotional data is used to customize how the analysis results are delivered.

[0605] Data customization

[0606] The server adjusts the content and format of information provided to the user based on emotional data received from the emotion engine. For example, if a user is experiencing stress, it will provide only the most important information in a concise manner, providing optimal information tailored to the user's state.

[0607] Specific example

[0608] 1. Example of data collection

[0609] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0610] The server sends an HTTP request and receives an HTML response.

[0611] We will use BeautifulSoup to extract the main text of the article.

[0612] 2. Examples of data analysis

[0613] The server analyzes the collected blog posts using pipeline("summarization").

[0614] The analysis results extract the summary: "Prioritize customer satisfaction."

[0615] 3. Examples of data storage

[0616] The server saves the extracted summary to an SQLite database.

[0617] Each summary is saved as a table row, making it easy to search and refer to.

[0618] 4. Examples of emotional engines

[0619] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user's state is "tension."

[0620] Based on this sentiment data, the server concisely organizes and provides important information to the user.

[0621] 5. Examples of data distribution

[0622] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0623] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[0624] Through these steps, the system effectively communicates messages from managers and executives to employees, and further improves overall consistency and efficiency within the company by customizing information according to the user's emotions.

[0625] The following describes the processing flow.

[0626] Step 1:

[0627] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). Specifically, the server sends an HTTP request, parses the HTML or text received as a response using the BeautifulSoup library, and extracts the body text.

[0628] Step 2:

[0629] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[0630] Step 3:

[0631] The server saves the analysis results to a database. The analyzed summaries and action plans are structured and stored in an SQLite database, allowing for efficient searching and retrieval.

[0632] Step 4:

[0633] The terminal receives a request from the user. The user uses a dedicated terminal or application to send a request to access the analyzed data.

[0634] Step 5:

[0635] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[0636] Step 6:

[0637] The emotion engine recognizes the user's emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones connected to the device, and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[0638] Step 7:

[0639] The server customizes the information it provides based on emotional data obtained from the emotion engine. For example, if a user is feeling anxious, it adjusts how information is presented in the most optimal format depending on the user's state, such as providing information in a concise manner.

[0640] Step 8:

[0641] The terminal displays the analysis results and customized information received from the server to the user. The user views the displayed information and develops an action plan based on it.

[0642] (Example 2)

[0643] Next, we will describe Example 2. 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".

[0644] Traditional systems have struggled to effectively communicate messages from management or executives to employees, leading to inconsistent employee behavior. Furthermore, they lack the ability to customize information based on user sentiment, often resulting in ineffective communication. Solving this problem is essential.

[0645] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0646] In this invention, the server includes means for acquiring messages from managers or executives from a data source, means for using a natural language processing model to analyze the acquired messages, and means for storing the analysis results in a database. This makes it possible to accurately and effectively analyze messages from managers and executives and provide them to employees. The server further includes application means for providing the stored analysis results to users, emotion recognition engine means for recognizing the user's emotions, and means for adjusting the content and format of the information provided based on emotion data acquired from the emotion recognition engine. This allows information to be customized according to the user's emotions, resulting in more effective information transmission.

[0647] A "data source" refers to an external or internal information provider that a user or system uses to collect information.

[0648] "Manager or executive" refers to a person in a position to make major decisions within a company or organization.

[0649] A "message" refers to information or instructions that a manager or executive communicates to employees or stakeholders.

[0650] "To acquire" refers to collecting information from a specified data source and incorporating it into the system.

[0651] "Analyzing" refers to the process of converting an acquired message into an easily understandable form using natural language processing techniques and other methods.

[0652] A "natural language processing model" refers to artificial intelligence technology that analyzes and interprets text data, and includes models that perform tasks such as summarization and semantic extraction.

[0653] A "database" refers to a system or collection of structured data used to manage and store analysis results and other information.

[0654] "To remember" refers to saving the analyzed information to a storage device such as a database, making it accessible later.

[0655] "Application means" refers to software or an interface used to present analysis results and other information to the user.

[0656] An "emotion recognition engine" refers to a technology that detects emotions by analyzing data such as the user's facial expressions and voice.

[0657] "Emotional data" refers to information obtained by an emotion recognition engine analyzing the user's emotions.

[0658] "Adjusting the content and format of information provision" refers to appropriately changing the type of information provided and how it is displayed according to the user's needs and circumstances.

[0659] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. The system is implemented in the following steps:

[0660] Data collection

[0661] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). This is done using libraries like requests and web scraping tools like BeautifulSoup. The server sends HTTP requests and parses the HTML or text received as responses to extract the message body.

[0662] Specific example:

[0663] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0664] The server sends an HTTP request and receives an HTML response.

[0665] We will use BeautifulSoup to extract the main text of the article.

[0666] Data Analysis

[0667] The server analyzes the collected messages using natural language processing (NLP) techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and key action guidelines.

[0668] Specific example:

[0669] The server analyzes the collected blog posts using pipeline("summarization").

[0670] The analysis results extract the summary: "Prioritize customer satisfaction."

[0671] Data Gateway

[0672] The server stores the analysis results in a database. A lightweight database such as SQLite is used, and the analysis results are structured to allow for efficient searching and retrieval.

[0673] Specific example:

[0674] The server saves the extracted summary to an SQLite database.

[0675] Each summary is saved as a table row, making it easy to search and refer to.

[0676] Data distribution

[0677] Users access the database and retrieve necessary information using dedicated terminals or applications. The terminal receives requests from users and queries the server for the required information.

[0678] Specific example:

[0679] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0680] Emotional Engine

[0681] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones to acquire emotional data. This data is used to customize the information provided to the user.

[0682] Specific example:

[0683] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user is "stressed."

[0684] The server provides users with important information in a concise and organized manner.

[0685] Customization of information provision

[0686] The server adjusts the content and format of the information it provides to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it will provide particularly important information in a concise format.

[0687] Specific example:

[0688] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[0689] This invention can improve the overall consistency and efficiency of a company.

[0690] Example of a prompt:

[0691] "Summarize the latest blog post by a CEO."

[0692] "Identify key behavioral guidelines for employees."

[0693] "Adjust the information you provide according to the user's emotions."

[0694] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0695] Step 1:

[0696] The server retrieves messages from executives or managers from a specified data source. Specifically, the server uses the requests library to send HTTP requests and receive HTML responses. For example, the server executes requests.get("https: / / example.com / ceo-blog") to retrieve blog posts. A specified URL is given as input, and an HTML document is obtained as output.

[0697] Step 2:

[0698] The server parses the received HTML document using the BeautifulSoup library and extracts the message body. Specifically, it extracts text from paragraph tags, like soup.find_all("p"). An HTML document is given as input, and the output is the text of the message body.

[0699] Step 3:

[0700] The server analyzes the extracted message body using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines. For example, it uses pipeline("summarization") to summarize the text. The message body is given as input, and the summarized text is obtained as output.

[0701] Step 4:

[0702] The server saves the analysis results to an SQLite database. Specifically, it establishes a database connection using the sqlite3 library and inserts the analysis results using an SQL query like INSERT INTO summaries (summary_text, date) VALUES (?, ?). The input is the summary text and date and time, and the output is a record inserted into the database.

[0703] Step 5:

[0704] The server receives a request from the user and retrieves the necessary information from the database. Specifically, it receives an HTTP request and extracts data using an SQL query such as SELECT FROM summaries WHERE date = ?. The request parameters are given as input, and the output is the summary text extracted from the database.

[0705] Step 6:

[0706] The device displays the retrieved summary text to the user. Specifically, the user accesses the information through the application, and it is displayed on the screen. The retrieved summary text is given as input, and the output is displayed on the user's screen.

[0707] Step 7:

[0708] The emotion engine uses the camera and microphone to analyze the user's facial expressions and voice in order to recognize the user's emotions. Specifically, it analyzes audio using the librosa library and detects facial expressions using the OpenCV library. Camera video and audio data are given as input, and user emotion data is obtained as output.

[0709] Step 8:

[0710] The server adjusts the content and format of the information provided based on sentiment data obtained from the sentiment engine. Specifically, if the user is experiencing stress, the information is presented in a concise summary. Sentiment data and a summary text are provided as input, and customized information is provided to the user as output.

[0711] (Application Example 2)

[0712] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0713] In conventional systems, messages from managers and executives were not effectively communicated to employees, making it difficult for everyone to act in a unified manner. Furthermore, because employees' emotions and psychological states were not considered, messages were sometimes not effectively received. In addition, employees experiencing specific situations or stress levels were not provided with appropriate information, raising concerns about decreased work efficiency and motivation.

[0714] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing the acquired messages, means for storing the analysis results, means for providing the stored analysis results to the user, means for recognizing the user's emotions, and means for customizing the information provided based on the recognized emotions. This enables effective communication of messages from managers and executives to employees, and allows for the provision of information that takes into account the emotions and psychological state of employees. This is expected to improve work efficiency and maintain employee motivation.

[0715] "Management" refers to a manager or leader who makes important decisions regarding the operation of a company or organization.

[0716] A "message" refers to instructions, policies, information, etc., that a manager or executive communicates to employees of a company or organization.

[0717] "Analysis" refers to the process of analyzing the content of acquired messages and extracting important information and guidelines for action.

[0718] "Memory" refers to saving analysis results to a database or storage device, making them easily searchable and retrievable.

[0719] "Providing" refers to presenting the stored analysis results to the user through a device or application.

[0720] "Users" refer to employees of companies or organizations who use the system and receive the stored analysis results.

[0721] "Emotion recognition" refers to technology that detects and analyzes a user's emotions and psychological state using cameras, microphones, sensors, etc.

[0722] "Customization" refers to the process of individually adjusting the content and format of information provided based on recognized emotional data.

[0723] Modes for carrying out the invention

[0724] This invention is a system that enables employees to effectively receive messages from managers and supervisors and to act consistently based on that content. Furthermore, it aims to reduce employee stress and improve work efficiency by understanding employees' emotional states and customizing the information delivery method accordingly.

[0725] System program generation

[0726] The system consists of the following main components:

[0727] 1. Message acquisition method

[0728] 2. Data Analysis Methods

[0729] 3. Storage means

[0730] 4. Means of provision

[0731] 5. Emotion recognition means

[0732] 6. Customization methods

[0733] Detailed explanation of the process

[0734] Message creation method

[0735] The server sends HTTP requests to retrieve messages from managers and administrators. For example, it uses the requests library to retrieve messages from a specified web page or mail server.

[0736] Data analysis means

[0737] The acquired messages are analyzed using natural language processing techniques with the transformers library. Specifically, message summaries and key action guidelines are extracted. To achieve this, generative AI models such as BERT are utilized to perform the summarization function.

[0738] storage means

[0739] The analyzed results are stored in a database such as SQLite and structured for efficient searching and retrieval. This database is accessible to employees via a smartphone application.

[0740] Providing means

[0741] The server retrieves analysis results from the database based on employee requests and provides them in an appropriate format. Delivery methods include smartphone applications and digital signage.

[0742] emotion recognition means

[0743] The system analyzes employees' facial expressions and voices through sensors such as cameras and microphones installed in smartphones and dedicated devices, and acquires emotional data. Libraries such as mediapipe and cv2 (OpenCV) are used for facial recognition and voice analysis.

[0744] Customization methods

[0745] Based on recognized emotion data, the server adjusts the content and format of the information provided. For example, if an employee is stressed, it provides only essential information in a concise format, while if they are relaxed, it also provides detailed information. This customization can reduce the psychological burden on employees.

[0746] Specific example

[0747] For example, this could be applied when an employee in a physical store is assisting a customer and receives the latest instructions from their manager via an app. If the employee is under stress, the app will display only the essential, summarized instructions concisely, keeping them in a state where they can act quickly. Conversely, if the employee is calm, the app will also provide detailed instructions and supplementary information.

[0748] Example of a prompt

[0749] "Create a system to receive new instructions from management and deliver them to employees in the most appropriate format. This system should recognize employees' emotions and provide only summarized, essential information if they are feeling stressed, and also provide detailed information if they are calm."

[0750] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0751] Step 1:

[0752] The server retrieves messages from managers or administrators. Specifically, the server uses the requests library to send HTTP requests from a specified URL to retrieve messages. The input data is the URL of the message, and the output data is the retrieved HTML content.

[0753] Step 2:

[0754] The server parses the retrieved HTML content and extracts the message body. Specifically, it uses the BeautifulSoup library to parse the HTML and extract the text portion containing the message. The input data is the retrieved HTML content, and the output data is the extracted message body.

[0755] Step 3:

[0756] The server analyzes the extracted messages using natural language processing techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines. A generative AI model is used to generate the summaries. The input data is the extracted message text, and the output data is the summary result.

[0757] Step 4:

[0758] The server stores the analysis results in a database. Specifically, it stores the summarized results in an SQLite database and structures them to facilitate future searching and retrieval. The input data is the summarized results, and the output data is the analysis results stored in the database.

[0759] Step 5:

[0760] The device recognizes the user's emotions through the camera and microphone. Specifically, it uses the cv2 and mediapipe libraries to analyze the user's facial expressions and voice using an emotion recognition algorithm. The input data is real-time video and audio obtained from the camera and microphone, and the output data is the recognized emotion data.

[0761] Step 6:

[0762] The server customizes the information it provides based on the recognized emotion data. Specifically, if the emotion is recognized as "stress," it provides only essential summary information; if the emotion is recognized as "relaxed," it also provides detailed information. The input data consists of the recognized emotion data and the results of database analysis, while the output data is the customized information.

[0763] Step 7:

[0764] The server sends customized information to the terminal, which then displays it to the user. Specifically, the display method is adjusted through the application interface to ensure the user receives the information in the most optimal format. The input data is customized information, and the output data is the information best displayed on the user's terminal.

[0765] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0766] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0767] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0768] [Third Embodiment]

[0769] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0770] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0771] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0772] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0773] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0774] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0775] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0776] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0777] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0778] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0779] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0780] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0781] This invention provides a system for enabling employees to take consistent actions based on messages from managers and executives, and will provide a specific description of its embodiments.

[0782] overview

[0783] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[0784] Data collection

[0785] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. The retrieved messages are in HTML or text format, and the text portion is extracted using libraries such as BeautifulSoup.

[0786] Data Analysis

[0787] The server analyzes the collected messages using natural language processing techniques (e.g., the Transformers library's pipeline). The purpose of the analysis is to extract message summaries and action guidelines. This allows employees to quickly understand the important points from redundant information.

[0788] Data Gateway

[0789] The server stores the analyzed summaries and action plans in a database. This database serves as a centralized source of information accessible to employees. SQLite is used for the database to enhance data reliability and availability.

[0790] Data distribution

[0791] Users can access the database using dedicated terminals or applications to obtain the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information.

[0792] Specific example

[0793] 1. Example of data collection

[0794] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0795] The server sends an HTTP request and receives an HTML response.

[0796] We will use BeautifulSoup to extract the main text of the article.

[0797] 2. Examples of data analysis

[0798] The server analyzes the collected blog posts using pipeline("summarization").

[0799] The analysis results extract the summary: "Prioritize customer satisfaction."

[0800] 3. Examples of data storage

[0801] The server saves the extracted summary to an SQLite database.

[0802] Each summary is saved as a table row, making it easy to search and refer to.

[0803] 4. Examples of data distribution

[0804] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0805] The device displays the acquired summary to the user, who then uses it to create an action plan.

[0806] As described above, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[0807] The following describes the processing flow.

[0808] Step 1:

[0809] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). The server sends an HTTP request and uses BeautifulSoup to parse the HTML or text received as a response and extract the body.

[0810] Step 2:

[0811] The server analyzes the acquired messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[0812] Step 3:

[0813] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. During storage, the data format is standardized and structured to enable efficient searching and retrieval.

[0814] Step 4:

[0815] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[0816] Step 5:

[0817] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[0818] Step 6:

[0819] The terminal displays the analysis results received from the server to the user. Based on the displayed information, the user formulates a direction for their work and an action plan.

[0820] Through the steps outlined above, this system enables effective communication of messages from managers and executives to employees, allowing for the implementation of management policies while maintaining consistency across the entire company.

[0821] (Example 1)

[0822] Next, we will describe Example 1. 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."

[0823] In today's business environment, it is crucial to quickly and accurately communicate messages from company executives and managers to all employees. However, the lack of efficient systems for achieving this often leads to communication gaps and undermines consistency and uniformity of behavior across the entire company. Furthermore, extracting and understanding key points from vast amounts of information requires considerable time and effort, highlighting the need for efficient systems to address this challenge.

[0824] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0825] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages using natural language processing technology, means for sending HTTP requests to collect data, means for processing the extracted text data, means for storing the analyzed messages in a database, and means for querying the database in response to user requests to provide necessary information. This makes it possible to efficiently collect, analyze, and store important messages from managers and executives, and to quickly and accurately communicate them to all employees.

[0826] A "manager" is a person who, as the highest-ranking officer of a company or organization, is responsible for determining the overall strategy and policies.

[0827] A "management officer" is a person who oversees practical management activities within a company or organization and manages departments or areas based on the instructions of management.

[0828] "Means of obtaining messages" refers to the technologies and methods used to collect messages from executives and managers from specific sources on the internet.

[0829] "Means of analysis" refers to the techniques and methods used to analyze collected messages and extract their gist and important information.

[0830] "Means of memory" refers to the technologies and methods used to store summaries of analyzed messages and action guidelines in storage such as databases.

[0831] "Means of providing" refers to the technologies and methods used to appropriately display and make available the stored analysis results to the user.

[0832] "Natural language processing technology" refers to artificial intelligence technology used to process and understand human language using computers.

[0833] "Means of sending HTTP requests to collect data" refers to the techniques and methods of sending requests using the HTTP protocol to obtain information from a web server.

[0834] "Means for processing extracted text data" refers to the techniques and methods used to extract necessary information from acquired raw text data and to format it.

[0835] "Means of saving to a database" refers to the technologies and methods used to organize and store analyzed summaries and action plans in a database.

[0836] "Means of querying and providing necessary information" refers to the technologies and methods used to search a database in response to a user's request, retrieve the necessary information, and provide it to them.

[0837] A "generative AI model" refers to a machine learning model that is generated by artificial intelligence and trained to perform a specific task.

[0838] This invention is a system designed to ensure that employees take consistent actions based on messages from managers and executives. A specific description of its embodiments follows.

[0839] overview

[0840] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[0841] Data collection

[0842] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. Specifically, the server uses a pre-configured list of URLs or RSS feeds to access web-based sources and retrieve messages in HTML or text format. This process utilizes the BeautifulSoup library to extract the text portion, allowing for efficient collection of necessary messages.

[0843] Data Analysis

[0844] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes, for example, the pipeline function of the transformers library. Specifically, the server inputs the collected messages into pipeline("summarization") to generate a summary. This summary helps users quickly understand the key points and eliminates redundant parts of the message.

[0845] Data Gateway

[0846] The server stores the analyzed summaries and action plans in a database. SQLite is used as the database to structure and store the analysis results. For example, summaries and action plans can be stored as rows in a table. This ensures data reliability and availability.

[0847] Data distribution

[0848] Users can access the analyzed data using a dedicated terminal or application. Upon receiving a request from a user, the server queries the database to retrieve the necessary information. This information is then sent back to the user's terminal in JSON format. The terminal displays this data, allowing the user to develop an action plan based on it.

[0849] Specific example

[0850] 1. Example of data collection

[0851] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog. For example, the server sends an HTTP GET request and receives an HTML response.

[0852] Next, BeautifulSoup is used to extract the main text of the article.

[0853] 2. Examples of data analysis

[0854] The server generates summaries by analyzing the collected blog posts using the transformers library's pipeline("summarization") function. For example, it might extract the summary "Prioritize customer satisfaction."

[0855] 3. Examples of data storage

[0856] The server saves the analysis results, which are summaries, to an SQLite database. Each summary is stored as a row in the table.

[0857] 4. Examples of data distribution

[0858] The user accesses a database through a dedicated application and retrieves a summary, such as "Prioritize customer satisfaction." The terminal displays the retrieved summary to the user, who then develops an action plan based on it.

[0859] Thus, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[0860] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0861] Step 1:

[0862] The server retrieves messages from the executive or management from the specified source.

[0863] Input: A pre-configured list of URLs or RSS feeds.

[0864] Data processing: The server sends an HTTP request to each URL and receives an HTML response.

[0865] Output: Message data in HTML or text format.

[0866] Specific operation: The server uses the requests library to send an HTTP GET request, and the HTML response is parsed using the BeautifulSoup library to extract text.

[0867] Step 2:

[0868] The server analyzes the collected messages using natural language processing techniques.

[0869] Input: Extracted text data.

[0870] Data processing: Use the pipeline function of the transformers library to summarize the text data.

[0871] Output: Summarized message and action plan.

[0872] Specific operation: The server passes the extracted text data to pipeline("summarization") to generate a summary. For example, it extracts the summary "Prioritize customer satisfaction."

[0873] Step 3:

[0874] The server saves the analyzed summary and action plan to a database.

[0875] Input: Summarized message and action plan.

[0876] Data processing: Structure this data and store it in an SQLite database.

[0877] Output: Analysis results stored in the database.

[0878] Specific operation: The server connects to the SQLite database and inserts the summary and action plan into the table using an INSERT INTO query.

[0879] Step 4:

[0880] Users access the analyzed data using dedicated terminals or applications.

[0881] Input: Information request from the user.

[0882] Data processing: The server queries the database to retrieve the necessary information.

[0883] Output: Analysis results sent back to the user's terminal.

[0884] Specific operation: When a user accesses the API endpoint through a dedicated application, the server executes a SELECT query to retrieve the necessary analysis results from the database and sends them back to the terminal in JSON format.

[0885] Step 5:

[0886] The device displays the information it has acquired to the user.

[0887] Input: Analysis results (in JSON format) returned from the server.

[0888] Data processing: Convert the analysis results to an appropriate format and display them on the device.

[0889] Output: A summary and action plan displayed to the user.

[0890] Specific operation: The user's device interprets the analysis results received from the server and displays a summary and action plan on the application interface. The user then uses this information to create an action plan.

[0891] Through the processing steps described above, the server can efficiently collect, analyze, and store messages from executives and managers, and provide users with appropriate information. This makes it possible to quickly communicate message content to employees while maintaining consistency across the entire company.

[0892] (Application Example 1)

[0893] Next, we will explain Application Example 1. In the following explanation, 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."

[0894] Traditional methods for efficiently communicating messages from managers and executives to employees were time-consuming and often lacked consistency. This made it difficult to quickly and accurately convey key messages and action guidelines to employees, ultimately hindering the achievement of overall company goals and the implementation of management policies.

[0895] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0896] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages and extracting action guidelines, means for storing the analyzed summaries and action guidelines in a centrally managed database, and means for searching and notifying users of the analysis results via their terminals. This enables managers' and executives' policies and guidelines to be communicated to employees quickly and accurately, allowing for consistent action throughout the entire company.

[0897] A "manager" is a person or position in which a company or organization makes major decisions.

[0898] A "management officer" is a person who has the responsibility of managing, planning strategies for, and overseeing the operations of a company or organization.

[0899] A "message" refers to documents or communications containing information, instructions, policies, and goals issued by a manager or executive.

[0900] "Means of acquisition" refers to the methods and techniques used to extract data from a specified source.

[0901] "Means of analysis" refer to methods and techniques for processing acquired messages, summarizing their content, and extracting actionable guidelines.

[0902] "Means of storage" refers to methods and technologies for saving analyzed information in a database or similar format.

[0903] "Means of providing information to users" refers to methods and technologies that enable users to access stored information.

[0904] A "centralized database" is a data management system that centrally manages analyzed information and is designed to allow efficient access to it.

[0905] A "user's device" is a device that a user uses to view or manipulate information.

[0906] "Means of searching and notifying" refers to functions that allow users to find specific information, or technologies that inform users of the latest information.

[0907] A "summary" is a concise compilation of the main points and important aspects of a message.

[0908] A "guideline of action" is a set of specific actions that should be taken based on the analyzed message.

[0909] This invention is a system that enables messages from managers and executives to be conveyed to employees quickly and accurately. The following describes a specific method for implementing this invention.

[0910] Data collection

[0911] The server collects messages from executives or managers from specified sources. Specifically, it sends HTTP requests to sources such as blogs, press releases, and internal emails to retrieve messages in text format. The BeautifulSoup library is used to extract the text portion.

[0912] Data Analysis

[0913] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and action guidelines. The summaries are concise summaries of the main points of the message, while the action guidelines indicate specific actions that employees should take.

[0914] Data Gateway

[0915] The analyzed summaries and action plans are stored in a centrally managed database. This database utilizes SQLite, enabling rapid storage and retrieval of analysis results.

[0916] Data distribution

[0917] Users access the database using devices such as smartphones to retrieve the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information. Furthermore, important information is pushed to enable employees to take immediate action.

[0918] Specific example

[0919] 1. Example of data collection

[0920] The server retrieves blog posts from the company's CEO at https: / / example.com / ceo-blog. The HTML of the article obtained via HTTP request is then used with BeautifulSoup to extract the article's body text.

[0921] 2. Examples of data analysis

[0922] The server analyzes the collected blog posts using pipeline("summarization"). This analysis extracts the summary, "Prioritize customer satisfaction." Based on this summary, the action plan, "Take the following action: Prioritize customer satisfaction," is also generated.

[0923] 3. Examples of data storage

[0924] The server extracts the summary "Prioritize customer satisfaction" and the action plan "Take the following action: Prioritize customer satisfaction" and saves them to an SQLite database.

[0925] 4. Examples of data distribution

[0926] The user accesses the database through a smartphone application and retrieves a summary titled "Prioritize customer satisfaction" and action guidelines titled "Take the next step: Prioritize customer satisfaction." The device then pushes this information to the user.

[0927] Example of a prompt

[0928] Message sample: "Our company plans to double its sales in the next five years..."

[0929] Prompt: summarizer("We plan to double our sales in the next five years...")

[0930] Expected output: "Plan to double sales"

[0931] In this way, this invention efficiently analyzes and distributes important messages within a company, enabling employees to take swift and coordinated action.

[0932] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0933] Step 1:

[0934] The server retrieves messages from the executive or management from the specified source.

[0935] Input: URL of the source (e.g., https: / / example.com / ceo-blog)

[0936] Data processing: Use the requests library to send an HTTP request and retrieve an HTML response.

[0937] Output: Message in HTML format

[0938] Step 2:

[0939] Extract text from the HTML message received by the server.

[0940] Input: HTML message

[0941] Data processing: Extract text from HTML using the BeautifulSoup library.

[0942] Output: Message in text format

[0943] Step 3:

[0944] The server analyzes text-based messages using natural language processing techniques to generate summaries and action plans.

[0945] Input: Text message

[0946] Data processing: Summarize the message using the transformers library's pipeline("summarization") and extract action guidelines.

[0947] Output: Summary and action plan (Example: "Summary: Prioritize customer satisfaction," "Action plan: Take the following action: Prioritize customer satisfaction")

[0948] Step 4:

[0949] The server stores the analyzed summary and action plan in a centrally managed database.

[0950] Input: Summary and action plan

[0951] Data storage: Summaries and action plans are stored in an SQLite database.

[0952] Output: Summaries and action plans stored in the database

[0953] Step 5:

[0954] Users access the database through their devices to obtain the latest summaries and action plans.

[0955] Input: Data request from user

[0956] Data processing: Query databases to retrieve relevant summaries and action plans.

[0957] Output: Summary and action plan displayed on the user's terminal.

[0958] Step 6:

[0959] The device will push notifications to the user with important action guidelines based on specific conditions.

[0960] Input: New analysis results or important messages

[0961] Data manipulation: Determine the trigger conditions for push notifications and generate notifications.

[0962] Output: Action guidelines displayed as push notifications on the user's device.

[0963] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0964] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. This embodiment will be described in detail.

[0965] overview

[0966] The system begins with a server receiving messages from executives or managers and analyzing them using natural language processing technology. The analysis results are stored in a database and provided to employees (users) through their terminals. The system also incorporates an emotion engine that recognizes user emotions, and the information provided is customized based on the user's emotional data.

[0967] Data collection

[0968] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). The server sends HTTP requests and uses the BeautifulSoup library to parse the HTML or text received as responses and extract the body.

[0969] Data Analysis

[0970] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines.

[0971] Data Gateway

[0972] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. The data is structured to allow for efficient searching and retrieval.

[0973] Data distribution

[0974] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[0975] Emotional Engine

[0976] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones, acquiring emotional data such as joy, anger, sadness, and happiness. This emotional data is used to customize how the analysis results are delivered.

[0977] Data customization

[0978] The server adjusts the content and format of information provided to the user based on emotional data received from the emotion engine. For example, if a user is experiencing stress, it will provide only the most important information in a concise manner, providing optimal information tailored to the user's state.

[0979] Specific example

[0980] 1. Example of data collection

[0981] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[0982] The server sends an HTTP request and receives an HTML response.

[0983] We will use BeautifulSoup to extract the main text of the article.

[0984] 2. Examples of data analysis

[0985] The server analyzes the collected blog posts using pipeline("summarization").

[0986] The analysis results extract the summary: "Prioritize customer satisfaction."

[0987] 3. Examples of data storage

[0988] The server saves the extracted summary to an SQLite database.

[0989] Each summary is saved as a table row, making it easy to search and refer to.

[0990] 4. Examples of emotional engines

[0991] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user's state is "tension."

[0992] Based on this sentiment data, the server concisely organizes and provides important information to the user.

[0993] 5. Examples of data distribution

[0994] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[0995] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[0996] Through these steps, the system effectively communicates messages from managers and executives to employees, and further improves overall consistency and efficiency within the company by customizing information according to the user's emotions.

[0997] The following describes the processing flow.

[0998] Step 1:

[0999] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). Specifically, the server sends an HTTP request, parses the HTML or text received as a response using the BeautifulSoup library, and extracts the body text.

[1000] Step 2:

[1001] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[1002] Step 3:

[1003] The server saves the analysis results to a database. The analyzed summaries and action plans are structured and stored in an SQLite database, allowing for efficient searching and retrieval.

[1004] Step 4:

[1005] The terminal receives a request from the user. The user uses a dedicated terminal or application to send a request to access the analyzed data.

[1006] Step 5:

[1007] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[1008] Step 6:

[1009] The emotion engine recognizes the user's emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones connected to the device, and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[1010] Step 7:

[1011] The server customizes the information it provides based on emotional data obtained from the emotion engine. For example, if a user is feeling anxious, it adjusts how information is presented in the most optimal format depending on the user's state, such as providing information in a concise manner.

[1012] Step 8:

[1013] The terminal displays the analysis results and customized information received from the server to the user. The user views the displayed information and develops an action plan based on it.

[1014] (Example 2)

[1015] Next, we will describe Example 2. 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."

[1016] Traditional systems have struggled to effectively communicate messages from management or executives to employees, leading to inconsistent employee behavior. Furthermore, they lack the ability to customize information based on user sentiment, often resulting in ineffective communication. Solving this problem is essential.

[1017] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1018] In this invention, the server includes means for acquiring messages from managers or executives from a data source, means for using a natural language processing model to analyze the acquired messages, and means for storing the analysis results in a database. This makes it possible to accurately and effectively analyze messages from managers and executives and provide them to employees. The server further includes application means for providing the stored analysis results to users, emotion recognition engine means for recognizing the user's emotions, and means for adjusting the content and format of the information provided based on emotion data acquired from the emotion recognition engine. This allows information to be customized according to the user's emotions, resulting in more effective information transmission.

[1019] A "data source" refers to an external or internal information provider that a user or system uses to collect information.

[1020] "Manager or executive" refers to a person in a position to make major decisions within a company or organization.

[1021] A "message" refers to information or instructions that a manager or executive communicates to employees or stakeholders.

[1022] "To acquire" refers to collecting information from a specified data source and incorporating it into the system.

[1023] "Analyzing" refers to the process of converting an acquired message into an easily understandable form using natural language processing techniques and other methods.

[1024] A "natural language processing model" refers to artificial intelligence technology that analyzes and interprets text data, and includes models that perform tasks such as summarization and semantic extraction.

[1025] A "database" refers to a system or collection of structured data used to manage and store analysis results and other information.

[1026] "To remember" refers to saving the analyzed information to a storage device such as a database, making it accessible later.

[1027] "Application means" refers to software or an interface used to present analysis results and other information to the user.

[1028] An "emotion recognition engine" refers to a technology that detects emotions by analyzing data such as the user's facial expressions and voice.

[1029] "Emotional data" refers to information obtained by an emotion recognition engine analyzing the user's emotions.

[1030] "Adjusting the content and format of information provision" refers to appropriately changing the type of information provided and how it is displayed according to the user's needs and circumstances.

[1031] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. The system is implemented in the following steps:

[1032] Data collection

[1033] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). This is done using libraries like requests and web scraping tools like BeautifulSoup. The server sends HTTP requests and parses the HTML or text received as responses to extract the message body.

[1034] Specific example:

[1035] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[1036] The server sends an HTTP request and receives an HTML response.

[1037] We will use BeautifulSoup to extract the main text of the article.

[1038] Data Analysis

[1039] The server analyzes the collected messages using natural language processing (NLP) techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and key action guidelines.

[1040] Specific example:

[1041] The server analyzes the collected blog posts using pipeline("summarization").

[1042] The analysis results extract the summary: "Prioritize customer satisfaction."

[1043] Data Gateway

[1044] The server stores the analysis results in a database. A lightweight database such as SQLite is used, and the analysis results are structured to allow for efficient searching and retrieval.

[1045] Specific example:

[1046] The server saves the extracted summary to an SQLite database.

[1047] Each summary is saved as a table row, making it easy to search and refer to.

[1048] Data distribution

[1049] Users access the database and retrieve necessary information using dedicated terminals or applications. The terminal receives requests from users and queries the server for the required information.

[1050] Specific example:

[1051] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[1052] Emotional Engine

[1053] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones to acquire emotional data. This data is used to customize the information provided to the user.

[1054] Specific example:

[1055] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user is "stressed."

[1056] The server provides users with important information in a concise and organized manner.

[1057] Customization of information provision

[1058] The server adjusts the content and format of the information it provides to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it will provide particularly important information in a concise format.

[1059] Specific example:

[1060] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[1061] This invention can improve the overall consistency and efficiency of a company.

[1062] Example of a prompt:

[1063] "Summarize the latest blog post by a CEO."

[1064] "Identify key behavioral guidelines for employees."

[1065] "Adjust the information you provide according to the user's emotions."

[1066] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1067] Step 1:

[1068] The server retrieves messages from executives or managers from a specified data source. Specifically, the server uses the requests library to send HTTP requests and receive HTML responses. For example, the server executes requests.get("https: / / example.com / ceo-blog") to retrieve blog posts. A specified URL is given as input, and an HTML document is obtained as output.

[1069] Step 2:

[1070] The server parses the received HTML document using the BeautifulSoup library and extracts the message body. Specifically, it extracts text from paragraph tags, like soup.find_all("p"). An HTML document is given as input, and the output is the text of the message body.

[1071] Step 3:

[1072] The server analyzes the extracted message body using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines. For example, it uses pipeline("summarization") to summarize the text. The message body is given as input, and the summarized text is obtained as output.

[1073] Step 4:

[1074] The server saves the analysis results to an SQLite database. Specifically, it establishes a database connection using the sqlite3 library and inserts the analysis results using an SQL query like INSERT INTO summaries (summary_text, date) VALUES (?, ?). The input is the summary text and date and time, and the output is a record inserted into the database.

[1075] Step 5:

[1076] The server receives a request from the user and retrieves the necessary information from the database. Specifically, it receives an HTTP request and extracts data using an SQL query such as SELECT FROM summaries WHERE date = ?. The request parameters are given as input, and the output is the summary text extracted from the database.

[1077] Step 6:

[1078] The device displays the retrieved summary text to the user. Specifically, the user accesses the information through the application, and it is displayed on the screen. The retrieved summary text is given as input, and the output is displayed on the user's screen.

[1079] Step 7:

[1080] The emotion engine uses the camera and microphone to analyze the user's facial expressions and voice in order to recognize the user's emotions. Specifically, it analyzes audio using the librosa library and detects facial expressions using the OpenCV library. Camera video and audio data are given as input, and user emotion data is obtained as output.

[1081] Step 8:

[1082] The server adjusts the content and format of the information provided based on sentiment data obtained from the sentiment engine. Specifically, if the user is experiencing stress, the information is presented in a concise summary. Sentiment data and a summary text are provided as input, and customized information is provided to the user as output.

[1083] (Application Example 2)

[1084] Next, we will explain application example 2. In the following explanation, 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."

[1085] In conventional systems, messages from managers and executives were not effectively communicated to employees, making it difficult for everyone to act in a unified manner. Furthermore, because employees' emotions and psychological states were not considered, messages were sometimes not effectively received. In addition, employees experiencing specific situations or stress levels were not provided with appropriate information, raising concerns about decreased work efficiency and motivation.

[1086] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing the acquired messages, means for storing the analysis results, means for providing the stored analysis results to the user, means for recognizing the user's emotions, and means for customizing the information provided based on the recognized emotions. This enables effective communication of messages from managers and executives to employees, and allows for the provision of information that takes into account the emotions and psychological state of employees. This is expected to improve work efficiency and maintain employee motivation.

[1087] "Management" refers to a manager or leader who makes important decisions regarding the operation of a company or organization.

[1088] A "message" refers to instructions, policies, information, etc., that a manager or executive communicates to employees of a company or organization.

[1089] "Analysis" refers to the process of analyzing the content of acquired messages and extracting important information and guidelines for action.

[1090] "Memory" refers to saving analysis results to a database or storage device, making them easily searchable and retrievable.

[1091] "Providing" refers to presenting the stored analysis results to the user through a device or application.

[1092] "Users" refer to employees of companies or organizations who use the system and receive the stored analysis results.

[1093] "Emotion recognition" refers to technology that detects and analyzes a user's emotions and psychological state using cameras, microphones, sensors, etc.

[1094] "Customization" refers to the process of individually adjusting the content and format of information provided based on recognized emotional data.

[1095] Modes for carrying out the invention

[1096] This invention is a system that enables employees to effectively receive messages from managers and supervisors and to act consistently based on that content. Furthermore, it aims to reduce employee stress and improve work efficiency by understanding employees' emotional states and customizing the information delivery method accordingly.

[1097] System program generation

[1098] The system consists of the following main components:

[1099] 1. Message acquisition method

[1100] 2. Data Analysis Methods

[1101] 3. Storage means

[1102] 4. Means of provision

[1103] 5. Emotion recognition means

[1104] 6. Customization methods

[1105] Detailed explanation of the process

[1106] Message creation method

[1107] The server sends HTTP requests to retrieve messages from managers and administrators. For example, it uses the requests library to retrieve messages from a specified web page or mail server.

[1108] Data analysis means

[1109] The acquired messages are analyzed using natural language processing techniques with the transformers library. Specifically, message summaries and key action guidelines are extracted. To achieve this, generative AI models such as BERT are utilized to perform the summarization function.

[1110] storage means

[1111] The analyzed results are stored in a database such as SQLite and structured for efficient searching and retrieval. This database is accessible to employees via a smartphone application.

[1112] Providing means

[1113] The server retrieves analysis results from the database based on employee requests and provides them in an appropriate format. Delivery methods include smartphone applications and digital signage.

[1114] emotion recognition means

[1115] The system analyzes employees' facial expressions and voices through sensors such as cameras and microphones installed in smartphones and dedicated devices, and acquires emotional data. Libraries such as mediapipe and cv2 (OpenCV) are used for facial recognition and voice analysis.

[1116] Customization methods

[1117] Based on recognized emotion data, the server adjusts the content and format of the information provided. For example, if an employee is stressed, it provides only essential information in a concise format, while if they are relaxed, it also provides detailed information. This customization can reduce the psychological burden on employees.

[1118] Specific example

[1119] For example, this could be applied when an employee in a physical store is assisting a customer and receives the latest instructions from their manager via an app. If the employee is under stress, the app will display only the essential, summarized instructions concisely, keeping them in a state where they can act quickly. Conversely, if the employee is calm, the app will also provide detailed instructions and supplementary information.

[1120] Example of a prompt

[1121] "Create a system to receive new instructions from management and deliver them to employees in the most appropriate format. This system should recognize employees' emotions and provide only summarized, essential information if they are feeling stressed, and also provide detailed information if they are calm."

[1122] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1123] Step 1:

[1124] The server retrieves messages from managers or administrators. Specifically, the server uses the requests library to send HTTP requests from a specified URL to retrieve messages. The input data is the URL of the message, and the output data is the retrieved HTML content.

[1125] Step 2:

[1126] The server parses the retrieved HTML content and extracts the message body. Specifically, it uses the BeautifulSoup library to parse the HTML and extract the text portion containing the message. The input data is the retrieved HTML content, and the output data is the extracted message body.

[1127] Step 3:

[1128] The server analyzes the extracted messages using natural language processing techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines. A generative AI model is used to generate the summaries. The input data is the extracted message text, and the output data is the summary result.

[1129] Step 4:

[1130] The server stores the analysis results in a database. Specifically, it stores the summarized results in an SQLite database and structures them to facilitate future searching and retrieval. The input data is the summarized results, and the output data is the analysis results stored in the database.

[1131] Step 5:

[1132] The device recognizes the user's emotions through the camera and microphone. Specifically, it uses the cv2 and mediapipe libraries to analyze the user's facial expressions and voice using an emotion recognition algorithm. The input data is real-time video and audio obtained from the camera and microphone, and the output data is the recognized emotion data.

[1133] Step 6:

[1134] The server customizes the information it provides based on the recognized emotion data. Specifically, if the emotion is recognized as "stress," it provides only essential summary information; if the emotion is recognized as "relaxed," it also provides detailed information. The input data consists of the recognized emotion data and the results of database analysis, while the output data is the customized information.

[1135] Step 7:

[1136] The server sends customized information to the terminal, which then displays it to the user. Specifically, the display method is adjusted through the application interface to ensure the user receives the information in the most optimal format. The input data is customized information, and the output data is the information best displayed on the user's terminal.

[1137] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1138] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1139] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1140] [Fourth Embodiment]

[1141] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1142] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1144] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1145] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1148] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1149] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1150] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1151] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1152] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1153] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1154] This invention provides a system for enabling employees to take consistent actions based on messages from managers and executives, and will provide a specific description of its embodiments.

[1155] overview

[1156] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[1157] Data collection

[1158] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. The retrieved messages are in HTML or text format, and the text portion is extracted using libraries such as BeautifulSoup.

[1159] Data Analysis

[1160] The server analyzes the collected messages using natural language processing techniques (e.g., the Transformers library's pipeline). The purpose of the analysis is to extract message summaries and action guidelines. This allows employees to quickly understand the important points from redundant information.

[1161] Data Gateway

[1162] The server stores the analyzed summaries and action plans in a database. This database serves as a centralized source of information accessible to employees. SQLite is used for the database to enhance data reliability and availability.

[1163] Data distribution

[1164] Users can access the database using dedicated terminals or applications to obtain the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information.

[1165] Specific example

[1166] 1. Example of data collection

[1167] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[1168] The server sends an HTTP request and receives an HTML response.

[1169] We will use BeautifulSoup to extract the main text of the article.

[1170] 2. Examples of data analysis

[1171] The server analyzes the collected blog posts using pipeline("summarization").

[1172] The analysis results extract the summary: "Prioritize customer satisfaction."

[1173] 3. Examples of data storage

[1174] The server saves the extracted summary to an SQLite database.

[1175] Each summary is saved as a table row, making it easy to search and refer to.

[1176] 4. Examples of data distribution

[1177] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[1178] The device displays the acquired summary to the user, who then uses it to create an action plan.

[1179] As described above, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[1180] The following describes the processing flow.

[1181] Step 1:

[1182] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). The server sends an HTTP request and uses BeautifulSoup to parse the HTML or text received as a response and extract the body.

[1183] Step 2:

[1184] The server analyzes the acquired messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[1185] Step 3:

[1186] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. During storage, the data format is standardized and structured to enable efficient searching and retrieval.

[1187] Step 4:

[1188] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[1189] Step 5:

[1190] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[1191] Step 6:

[1192] The terminal displays the analysis results received from the server to the user. Based on the displayed information, the user formulates a direction for their work and an action plan.

[1193] Through the steps outlined above, this system enables effective communication of messages from managers and executives to employees, allowing for the implementation of management policies while maintaining consistency across the entire company.

[1194] (Example 1)

[1195] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1196] In today's business environment, it is crucial to quickly and accurately communicate messages from company executives and managers to all employees. However, the lack of efficient systems for achieving this often leads to communication gaps and undermines consistency and uniformity of behavior across the entire company. Furthermore, extracting and understanding key points from vast amounts of information requires considerable time and effort, highlighting the need for efficient systems to address this challenge.

[1197] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1198] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages using natural language processing technology, means for sending HTTP requests to collect data, means for processing the extracted text data, means for storing the analyzed messages in a database, and means for querying the database in response to user requests to provide necessary information. This makes it possible to efficiently collect, analyze, and store important messages from managers and executives, and to quickly and accurately communicate them to all employees.

[1199] A "manager" is a person who, as the highest-ranking officer of a company or organization, is responsible for determining the overall strategy and policies.

[1200] A "management officer" is a person who oversees practical management activities within a company or organization and manages departments or areas based on the instructions of management.

[1201] "Means of obtaining messages" refers to the technologies and methods used to collect messages from executives and managers from specific sources on the internet.

[1202] "Means of analysis" refers to the techniques and methods used to analyze collected messages and extract their gist and important information.

[1203] "Means of memory" refers to the technologies and methods used to store summaries of analyzed messages and action guidelines in storage such as databases.

[1204] "Means of providing" refers to the technologies and methods used to appropriately display and make available the stored analysis results to the user.

[1205] "Natural language processing technology" refers to artificial intelligence technology used to process and understand human language using computers.

[1206] "Means of sending HTTP requests to collect data" refers to the techniques and methods of sending requests using the HTTP protocol to obtain information from a web server.

[1207] "Means for processing extracted text data" refers to the techniques and methods used to extract necessary information from acquired raw text data and to format it.

[1208] "Means of saving to a database" refers to the technologies and methods used to organize and store analyzed summaries and action plans in a database.

[1209] "Means of querying and providing necessary information" refers to the technologies and methods used to search a database in response to a user's request, retrieve the necessary information, and provide it to them.

[1210] A "generative AI model" refers to a machine learning model that is generated by artificial intelligence and trained to perform a specific task.

[1211] This invention is a system designed to ensure that employees take consistent actions based on messages from managers and executives. A specific description of its embodiments follows.

[1212] overview

[1213] This system uses a server to retrieve messages from executives or managers and analyze them using natural language processing technology. The analyzed messages, along with summaries and action plans, are stored in a database and provided to employees (users) through their terminals.

[1214] Data collection

[1215] The server sends HTTP requests from specified sources (e.g., blogs, press releases, internal emails, etc.) to retrieve messages from executives and managers. Specifically, the server uses a pre-configured list of URLs or RSS feeds to access web-based sources and retrieve messages in HTML or text format. This process utilizes the BeautifulSoup library to extract the text portion, allowing for efficient collection of necessary messages.

[1216] Data Analysis

[1217] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes, for example, the pipeline function of the transformers library. Specifically, the server inputs the collected messages into pipeline("summarization") to generate a summary. This summary helps users quickly understand the key points and eliminates redundant parts of the message.

[1218] Data Gateway

[1219] The server stores the analyzed summaries and action plans in a database. SQLite is used as the database to structure and store the analysis results. For example, summaries and action plans can be stored as rows in a table. This ensures data reliability and availability.

[1220] Data distribution

[1221] Users can access the analyzed data using a dedicated terminal or application. Upon receiving a request from a user, the server queries the database to retrieve the necessary information. This information is then sent back to the user's terminal in JSON format. The terminal displays this data, allowing the user to develop an action plan based on it.

[1222] Specific example

[1223] 1. Example of data collection

[1224] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog. For example, the server sends an HTTP GET request and receives an HTML response.

[1225] Next, BeautifulSoup is used to extract the main text of the article.

[1226] 2. Examples of data analysis

[1227] The server generates summaries by analyzing the collected blog posts using the transformers library's pipeline("summarization") function. For example, it might extract the summary "Prioritize customer satisfaction."

[1228] 3. Examples of data storage

[1229] The server saves the analysis results, which are summaries, to an SQLite database. Each summary is stored as a row in the table.

[1230] 4. Examples of data distribution

[1231] The user accesses a database through a dedicated application and retrieves a summary, such as "Prioritize customer satisfaction." The terminal displays the retrieved summary to the user, who then develops an action plan based on it.

[1232] Thus, the present invention enables the efficient transmission of messages from managers and executives to employees, and allows for the implementation of management policies while maintaining consistency throughout the company.

[1233] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1234] Step 1:

[1235] The server retrieves messages from the executive or management from the specified source.

[1236] Input: A pre-configured list of URLs or RSS feeds.

[1237] Data processing: The server sends an HTTP request to each URL and receives an HTML response.

[1238] Output: Message data in HTML or text format.

[1239] Specific operation: The server uses the requests library to send an HTTP GET request, and the HTML response is parsed using the BeautifulSoup library to extract text.

[1240] Step 2:

[1241] The server analyzes the collected messages using natural language processing techniques.

[1242] Input: Extracted text data.

[1243] Data processing: Use the pipeline function of the transformers library to summarize the text data.

[1244] Output: Summarized message and action plan.

[1245] Specific operation: The server passes the extracted text data to pipeline("summarization") to generate a summary. For example, it extracts the summary "Prioritize customer satisfaction."

[1246] Step 3:

[1247] The server saves the analyzed summary and action plan to a database.

[1248] Input: Summarized message and action plan.

[1249] Data processing: Structure this data and store it in an SQLite database.

[1250] Output: Analysis results stored in the database.

[1251] Specific operation: The server connects to the SQLite database and inserts the summary and action plan into the table using an INSERT INTO query.

[1252] Step 4:

[1253] Users access the analyzed data using dedicated terminals or applications.

[1254] Input: Information request from the user.

[1255] Data processing: The server queries the database to retrieve the necessary information.

[1256] Output: Analysis results sent back to the user's terminal.

[1257] Specific operation: When a user accesses the API endpoint through a dedicated application, the server executes a SELECT query to retrieve the necessary analysis results from the database and sends them back to the terminal in JSON format.

[1258] Step 5:

[1259] The device displays the information it has acquired to the user.

[1260] Input: Analysis results (in JSON format) returned from the server.

[1261] Data processing: Convert the analysis results to an appropriate format and display them on the device.

[1262] Output: A summary and action plan displayed to the user.

[1263] Specific operation: The user's device interprets the analysis results received from the server and displays a summary and action plan on the application interface. The user then uses this information to create an action plan.

[1264] Through the processing steps described above, the server can efficiently collect, analyze, and store messages from executives and managers, and provide users with appropriate information. This makes it possible to quickly communicate message content to employees while maintaining consistency across the entire company.

[1265] (Application Example 1)

[1266] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1267] Traditional methods for efficiently communicating messages from managers and executives to employees were time-consuming and often lacked consistency. This made it difficult to quickly and accurately convey key messages and action guidelines to employees, ultimately hindering the achievement of overall company goals and the implementation of management policies.

[1268] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1269] In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing acquired messages, means for storing the analysis results, means for providing the stored analysis results to users, means for summarizing messages and extracting action guidelines, means for storing the analyzed summaries and action guidelines in a centrally managed database, and means for searching and notifying users of the analysis results via their terminals. This enables managers' and executives' policies and guidelines to be communicated to employees quickly and accurately, allowing for consistent action throughout the entire company.

[1270] A "manager" is a person or position in which a company or organization makes major decisions.

[1271] A "management officer" is a person who has the responsibility of managing, planning strategies for, and overseeing the operations of a company or organization.

[1272] A "message" refers to documents or communications containing information, instructions, policies, and goals issued by a manager or executive.

[1273] "Means of acquisition" refers to the methods and techniques used to extract data from a specified source.

[1274] "Means of analysis" refer to methods and techniques for processing acquired messages, summarizing their content, and extracting actionable guidelines.

[1275] "Means of storage" refers to methods and technologies for saving analyzed information in a database or similar format.

[1276] "Means of providing information to users" refers to methods and technologies that enable users to access stored information.

[1277] A "centralized database" is a data management system that centrally manages analyzed information and is designed to allow efficient access to it.

[1278] A "user's device" is a device that a user uses to view or manipulate information.

[1279] "Means of searching and notifying" refers to functions that allow users to find specific information, or technologies that inform users of the latest information.

[1280] A "summary" is a concise compilation of the main points and important aspects of a message.

[1281] A "guideline of action" is a set of specific actions that should be taken based on the analyzed message.

[1282] This invention is a system that enables messages from managers and executives to be conveyed to employees quickly and accurately. The following describes a specific method for implementing this invention.

[1283] Data collection

[1284] The server collects messages from executives or managers from specified sources. Specifically, it sends HTTP requests to sources such as blogs, press releases, and internal emails to retrieve messages in text format. The BeautifulSoup library is used to extract the text portion.

[1285] Data Analysis

[1286] The server analyzes the collected messages using natural language processing techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and action guidelines. The summaries are concise summaries of the main points of the message, while the action guidelines indicate specific actions that employees should take.

[1287] Data Gateway

[1288] The analyzed summaries and action plans are stored in a centrally managed database. This database utilizes SQLite, enabling rapid storage and retrieval of analysis results.

[1289] Data distribution

[1290] Users access the database using devices such as smartphones to retrieve the latest messages and action guidelines. The server queries the database in response to user requests and provides the necessary information. Furthermore, important information is pushed to enable employees to take immediate action.

[1291] Specific example

[1292] 1. Example of data collection

[1293] The server retrieves blog posts from the company's CEO at https: / / example.com / ceo-blog. The HTML of the article obtained via HTTP request is then used with BeautifulSoup to extract the article's body text.

[1294] 2. Examples of data analysis

[1295] The server analyzes the collected blog posts using pipeline("summarization"). This analysis extracts the summary, "Prioritize customer satisfaction." Based on this summary, the action plan, "Take the following action: Prioritize customer satisfaction," is also generated.

[1296] 3. Examples of data storage

[1297] The server extracts the summary "Prioritize customer satisfaction" and the action plan "Take the following action: Prioritize customer satisfaction" and saves them to an SQLite database.

[1298] 4. Examples of data distribution

[1299] The user accesses the database through a smartphone application and retrieves a summary titled "Prioritize customer satisfaction" and action guidelines titled "Take the next step: Prioritize customer satisfaction." The device then pushes this information to the user.

[1300] Example of a prompt

[1301] Message sample: "Our company plans to double its sales in the next five years..."

[1302] Prompt: summarizer("We plan to double our sales in the next five years...")

[1303] Expected output: "Plan to double sales"

[1304] In this way, this invention efficiently analyzes and distributes important messages within a company, enabling employees to take swift and coordinated action.

[1305] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1306] Step 1:

[1307] The server retrieves messages from the executive or management from the specified source.

[1308] Input: URL of the source (e.g., https: / / example.com / ceo-blog)

[1309] Data processing: Use the requests library to send an HTTP request and retrieve an HTML response.

[1310] Output: Message in HTML format

[1311] Step 2:

[1312] Extract text from the HTML message received by the server.

[1313] Input: HTML message

[1314] Data processing: Extract text from HTML using the BeautifulSoup library.

[1315] Output: Message in text format

[1316] Step 3:

[1317] The server analyzes text-based messages using natural language processing techniques to generate summaries and action plans.

[1318] Input: Text message

[1319] Data processing: Summarize the message using the transformers library's pipeline("summarization") and extract action guidelines.

[1320] Output: Summary and action plan (Example: "Summary: Prioritize customer satisfaction," "Action plan: Take the following action: Prioritize customer satisfaction")

[1321] Step 4:

[1322] The server stores the analyzed summary and action plan in a centrally managed database.

[1323] Input: Summary and action plan

[1324] Data storage: Summaries and action plans are stored in an SQLite database.

[1325] Output: Summaries and action plans stored in the database

[1326] Step 5:

[1327] Users access the database through their devices to obtain the latest summaries and action plans.

[1328] Input: Data request from user

[1329] Data processing: Query databases to retrieve relevant summaries and action plans.

[1330] Output: Summary and action plan displayed on the user's terminal.

[1331] Step 6:

[1332] The device will push notifications to the user with important action guidelines based on specific conditions.

[1333] Input: New analysis results or important messages

[1334] Data manipulation: Determine the trigger conditions for push notifications and generate notifications.

[1335] Output: Action guidelines displayed as push notifications on the user's device.

[1336] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1337] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. This embodiment will be described in detail.

[1338] overview

[1339] The system begins with a server receiving messages from executives or managers and analyzing them using natural language processing technology. The analysis results are stored in a database and provided to employees (users) through their terminals. The system also incorporates an emotion engine that recognizes user emotions, and the information provided is customized based on the user's emotional data.

[1340] Data collection

[1341] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). The server sends HTTP requests and uses the BeautifulSoup library to parse the HTML or text received as responses and extract the body.

[1342] Data Analysis

[1343] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines.

[1344] Data Gateway

[1345] The server saves the analysis results to a database. A database such as SQLite is used to store the analyzed summaries and action plans. The data is structured to allow for efficient searching and retrieval.

[1346] Data distribution

[1347] Users access the database using dedicated terminals or applications. The terminal receives requests from users and queries the server for the necessary information.

[1348] Emotional Engine

[1349] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones, acquiring emotional data such as joy, anger, sadness, and happiness. This emotional data is used to customize how the analysis results are delivered.

[1350] Data customization

[1351] The server adjusts the content and format of information provided to the user based on emotional data received from the emotion engine. For example, if a user is experiencing stress, it will provide only the most important information in a concise manner, providing optimal information tailored to the user's state.

[1352] Specific example

[1353] 1. Example of data collection

[1354] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[1355] The server sends an HTTP request and receives an HTML response.

[1356] We will use BeautifulSoup to extract the main text of the article.

[1357] 2. Examples of data analysis

[1358] The server analyzes the collected blog posts using pipeline("summarization").

[1359] The analysis results extract the summary: "Prioritize customer satisfaction."

[1360] 3. Examples of data storage

[1361] The server saves the extracted summary to an SQLite database.

[1362] Each summary is saved as a table row, making it easy to search and refer to.

[1363] 4. Examples of emotional engines

[1364] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user's state is "tension."

[1365] Based on this sentiment data, the server concisely organizes and provides important information to the user.

[1366] 5. Examples of data distribution

[1367] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[1368] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[1369] Through these steps, the system effectively communicates messages from managers and executives to employees, and further improves overall consistency and efficiency within the company by customizing information according to the user's emotions.

[1370] The following describes the processing flow.

[1371] Step 1:

[1372] The server retrieves messages from executives or managers from a specified source (e.g., blogs, press releases, internal emails). Specifically, the server sends an HTTP request, parses the HTML or text received as a response using the BeautifulSoup library, and extracts the body text.

[1373] Step 2:

[1374] The server analyzes the collected messages using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines.

[1375] Step 3:

[1376] The server saves the analysis results to a database. The analyzed summaries and action plans are structured and stored in an SQLite database, allowing for efficient searching and retrieval.

[1377] Step 4:

[1378] The terminal receives a request from the user. The user uses a dedicated terminal or application to send a request to access the analyzed data.

[1379] Step 5:

[1380] The server queries the database in response to a request from the terminal and retrieves the relevant analysis results (summary and action plan). The retrieved data is then sent to the terminal.

[1381] Step 6:

[1382] The emotion engine recognizes the user's emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones connected to the device, and identifies the user's emotional state (e.g., joy, anger, sadness, etc.).

[1383] Step 7:

[1384] The server customizes the information it provides based on emotional data obtained from the emotion engine. For example, if a user is feeling anxious, it adjusts how information is presented in the most optimal format depending on the user's state, such as providing information in a concise manner.

[1385] Step 8:

[1386] The terminal displays the analysis results and customized information received from the server to the user. The user views the displayed information and develops an action plan based on it.

[1387] (Example 2)

[1388] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1389] Traditional systems have struggled to effectively communicate messages from management or executives to employees, leading to inconsistent employee behavior. Furthermore, they lack the ability to customize information based on user sentiment, often resulting in ineffective communication. Solving this problem is essential.

[1390] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1391] In this invention, the server includes means for acquiring messages from managers or executives from a data source, means for using a natural language processing model to analyze the acquired messages, and means for storing the analysis results in a database. This makes it possible to accurately and effectively analyze messages from managers and executives and provide them to employees. The server further includes application means for providing the stored analysis results to users, emotion recognition engine means for recognizing the user's emotions, and means for adjusting the content and format of the information provided based on emotion data acquired from the emotion recognition engine. This allows information to be customized according to the user's emotions, resulting in more effective information transmission.

[1392] A "data source" refers to an external or internal information provider that a user or system uses to collect information.

[1393] "Manager or executive" refers to a person in a position to make major decisions within a company or organization.

[1394] A "message" refers to information or instructions that a manager or executive communicates to employees or stakeholders.

[1395] "To acquire" refers to collecting information from a specified data source and incorporating it into the system.

[1396] "Analyzing" refers to the process of converting an acquired message into an easily understandable form using natural language processing techniques and other methods.

[1397] A "natural language processing model" refers to artificial intelligence technology that analyzes and interprets text data, and includes models that perform tasks such as summarization and semantic extraction.

[1398] A "database" refers to a system or collection of structured data used to manage and store analysis results and other information.

[1399] "To remember" refers to saving the analyzed information to a storage device such as a database, making it accessible later.

[1400] "Application means" refers to software or an interface used to present analysis results and other information to the user.

[1401] An "emotion recognition engine" refers to a technology that detects emotions by analyzing data such as the user's facial expressions and voice.

[1402] "Emotional data" refers to information obtained by an emotion recognition engine analyzing the user's emotions.

[1403] "Adjusting the content and format of information provision" refers to appropriately changing the type of information provided and how it is displayed according to the user's needs and circumstances.

[1404] This invention combines a system designed to ensure employees take consistent actions based on messages from managers and executives with an emotion engine that recognizes user emotions. The system is implemented in the following steps:

[1405] Data collection

[1406] The server retrieves messages from executives and managers from specified sources (e.g., blogs, press releases, internal emails). This is done using libraries like requests and web scraping tools like BeautifulSoup. The server sends HTTP requests and parses the HTML or text received as responses to extract the message body.

[1407] Specific example:

[1408] The server retrieves the CEO's blog posts from https: / / example.com / ceo-blog.

[1409] The server sends an HTTP request and receives an HTML response.

[1410] We will use BeautifulSoup to extract the main text of the article.

[1411] Data Analysis

[1412] The server analyzes the collected messages using natural language processing (NLP) techniques. This analysis utilizes the pipeline function of the transformers library to extract message summaries and key action guidelines.

[1413] Specific example:

[1414] The server analyzes the collected blog posts using pipeline("summarization").

[1415] The analysis results extract the summary: "Prioritize customer satisfaction."

[1416] Data Gateway

[1417] The server stores the analysis results in a database. A lightweight database such as SQLite is used, and the analysis results are structured to allow for efficient searching and retrieval.

[1418] Specific example:

[1419] The server saves the extracted summary to an SQLite database.

[1420] Each summary is saved as a table row, making it easy to search and refer to.

[1421] Data distribution

[1422] Users access the database and retrieve necessary information using dedicated terminals or applications. The terminal receives requests from users and queries the server for the required information.

[1423] Specific example:

[1424] The user accesses the database through the application and retrieves the summary, "Prioritize customer satisfaction."

[1425] Emotional Engine

[1426] The emotion engine includes technology for recognizing user emotions. It analyzes the user's facial expressions and voice through sensors such as cameras and microphones to acquire emotional data. This data is used to customize the information provided to the user.

[1427] Specific example:

[1428] The emotion engine analyzes the user's facial expressions and voice, and recognizes that the user is "stressed."

[1429] The server provides users with important information in a concise and organized manner.

[1430] Customization of information provision

[1431] The server adjusts the content and format of the information it provides to the user based on emotional data obtained from the emotion engine. For example, if the user is feeling stressed, it will provide particularly important information in a concise format.

[1432] Specific example:

[1433] Based on the results of the emotion engine, information is displayed to the user in an appropriate format.

[1434] This invention can improve the overall consistency and efficiency of a company.

[1435] Example of a prompt:

[1436] "Summarize the latest blog post by a CEO."

[1437] "Identify key behavioral guidelines for employees."

[1438] "Adjust the information you provide according to the user's emotions."

[1439] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1440] Step 1:

[1441] The server retrieves messages from executives or managers from a specified data source. Specifically, the server uses the requests library to send HTTP requests and receive HTML responses. For example, the server executes requests.get("https: / / example.com / ceo-blog") to retrieve blog posts. A specified URL is given as input, and an HTML document is obtained as output.

[1442] Step 2:

[1443] The server parses the received HTML document using the BeautifulSoup library and extracts the message body. Specifically, it extracts text from paragraph tags, like soup.find_all("p"). An HTML document is given as input, and the output is the text of the message body.

[1444] Step 3:

[1445] The server analyzes the extracted message body using natural language processing (NLP) techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and important action guidelines. For example, it uses pipeline("summarization") to summarize the text. The message body is given as input, and the summarized text is obtained as output.

[1446] Step 4:

[1447] The server saves the analysis results to an SQLite database. Specifically, it establishes a database connection using the sqlite3 library and inserts the analysis results using an SQL query like INSERT INTO summaries (summary_text, date) VALUES (?, ?). The input is the summary text and date and time, and the output is a record inserted into the database.

[1448] Step 5:

[1449] The server receives a request from the user and retrieves the necessary information from the database. Specifically, it receives an HTTP request and extracts data using an SQL query such as SELECT FROM summaries WHERE date = ?. The request parameters are given as input, and the output is the summary text extracted from the database.

[1450] Step 6:

[1451] The device displays the retrieved summary text to the user. Specifically, the user accesses the information through the application, and it is displayed on the screen. The retrieved summary text is given as input, and the output is displayed on the user's screen.

[1452] Step 7:

[1453] The emotion engine uses the camera and microphone to analyze the user's facial expressions and voice in order to recognize the user's emotions. Specifically, it analyzes audio using the librosa library and detects facial expressions using the OpenCV library. Camera video and audio data are given as input, and user emotion data is obtained as output.

[1454] Step 8:

[1455] The server adjusts the content and format of the information provided based on sentiment data obtained from the sentiment engine. Specifically, if the user is experiencing stress, the information is presented in a concise summary. Sentiment data and a summary text are provided as input, and customized information is provided to the user as output.

[1456] (Application Example 2)

[1457] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1458] In conventional systems, messages from managers and executives were not effectively communicated to employees, making it difficult for everyone to act in a unified manner. Furthermore, because employees' emotions and psychological states were not considered, messages were sometimes not effectively received. In addition, employees experiencing specific situations or stress levels were not provided with appropriate information, raising concerns about decreased work efficiency and motivation.

[1459] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for acquiring messages from managers or executives, means for analyzing the acquired messages, means for storing the analysis results, means for providing the stored analysis results to the user, means for recognizing the user's emotions, and means for customizing the information provided based on the recognized emotions. This enables effective communication of messages from managers and executives to employees, and allows for the provision of information that takes into account the emotions and psychological state of employees. This is expected to improve work efficiency and maintain employee motivation.

[1460] "Management" refers to a manager or leader who makes important decisions regarding the operation of a company or organization.

[1461] A "message" refers to instructions, policies, information, etc., that a manager or executive communicates to employees of a company or organization.

[1462] "Analysis" refers to the process of analyzing the content of acquired messages and extracting important information and guidelines for action.

[1463] "Memory" refers to saving analysis results to a database or storage device, making them easily searchable and retrievable.

[1464] "Providing" refers to presenting the stored analysis results to the user through a device or application.

[1465] "Users" refer to employees of companies or organizations who use the system and receive the stored analysis results.

[1466] "Emotion recognition" refers to technology that detects and analyzes a user's emotions and psychological state using cameras, microphones, sensors, etc.

[1467] "Customization" refers to the process of individually adjusting the content and format of information provided based on recognized emotional data.

[1468] Modes for carrying out the invention

[1469] This invention is a system that enables employees to effectively receive messages from managers and supervisors and to act consistently based on that content. Furthermore, it aims to reduce employee stress and improve work efficiency by understanding employees' emotional states and customizing the information delivery method accordingly.

[1470] System program generation

[1471] The system consists of the following main components:

[1472] 1. Message acquisition method

[1473] 2. Data Analysis Methods

[1474] 3. Storage means

[1475] 4. Means of provision

[1476] 5. Emotion recognition means

[1477] 6. Customization methods

[1478] Detailed explanation of the process

[1479] Message creation method

[1480] The server sends HTTP requests to retrieve messages from managers and administrators. For example, it uses the requests library to retrieve messages from a specified web page or mail server.

[1481] Data analysis means

[1482] The acquired messages are analyzed using natural language processing techniques with the transformers library. Specifically, message summaries and key action guidelines are extracted. To achieve this, generative AI models such as BERT are utilized to perform the summarization function.

[1483] storage means

[1484] The analyzed results are stored in a database such as SQLite and structured for efficient searching and retrieval. This database is accessible to employees via a smartphone application.

[1485] Providing means

[1486] The server retrieves analysis results from the database based on employee requests and provides them in an appropriate format. Delivery methods include smartphone applications and digital signage.

[1487] emotion recognition means

[1488] The system analyzes employees' facial expressions and voices through sensors such as cameras and microphones installed in smartphones and dedicated devices, and acquires emotional data. Libraries such as mediapipe and cv2 (OpenCV) are used for facial recognition and voice analysis.

[1489] Customization methods

[1490] Based on recognized emotion data, the server adjusts the content and format of the information provided. For example, if an employee is stressed, it provides only essential information in a concise format, while if they are relaxed, it also provides detailed information. This customization can reduce the psychological burden on employees.

[1491] Specific example

[1492] For example, this could be applied when an employee in a physical store is assisting a customer and receives the latest instructions from their manager via an app. If the employee is under stress, the app will display only the essential, summarized instructions concisely, keeping them in a state where they can act quickly. Conversely, if the employee is calm, the app will also provide detailed instructions and supplementary information.

[1493] Example of a prompt

[1494] "Create a system to receive new instructions from management and deliver them to employees in the most appropriate format. This system should recognize employees' emotions and provide only summarized, essential information if they are feeling stressed, and also provide detailed information if they are calm."

[1495] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1496] Step 1:

[1497] The server retrieves messages from managers or administrators. Specifically, the server uses the requests library to send HTTP requests from a specified URL to retrieve messages. The input data is the URL of the message, and the output data is the retrieved HTML content.

[1498] Step 2:

[1499] The server parses the retrieved HTML content and extracts the message body. Specifically, it uses the BeautifulSoup library to parse the HTML and extract the text portion containing the message. The input data is the retrieved HTML content, and the output data is the extracted message body.

[1500] Step 3:

[1501] The server analyzes the extracted messages using natural language processing techniques. Specifically, it uses the pipeline function of the transformers library to extract message summaries and key action guidelines. A generative AI model is used to generate the summaries. The input data is the extracted message text, and the output data is the summary result.

[1502] Step 4:

[1503] The server stores the analysis results in a database. Specifically, it stores the summarized results in an SQLite database and structures them to facilitate future searching and retrieval. The input data is the summarized results, and the output data is the analysis results stored in the database.

[1504] Step 5:

[1505] The device recognizes the user's emotions through the camera and microphone. Specifically, it uses the cv2 and mediapipe libraries to analyze the user's facial expressions and voice using an emotion recognition algorithm. The input data is real-time video and audio obtained from the camera and microphone, and the output data is the recognized emotion data.

[1506] Step 6:

[1507] The server customizes the information it provides based on the recognized emotion data. Specifically, if the emotion is recognized as "stress," it provides only essential summary information; if the emotion is recognized as "relaxed," it also provides detailed information. The input data consists of the recognized emotion data and the results of database analysis, while the output data is the customized information.

[1508] Step 7:

[1509] The server sends customized information to the terminal, which then displays it to the user. Specifically, the display method is adjusted through the application interface to ensure the user receives the information in the most optimal format. The input data is customized information, and the output data is the information best displayed on the user's terminal.

[1510] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1511] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1512] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1513] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1514] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1515] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1516] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1517] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1518] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1519] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1520] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1521] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1522] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1523] 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.

[1524] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1525] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1526] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1527] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1528] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1529] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1530] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1531] The following is further disclosed regarding the embodiments described above.

[1532] (Claim 1)

[1533] Means of obtaining messages from managers or executives,

[1534] A means of analyzing the acquired message,

[1535] A means for storing the analysis results,

[1536] A system that includes means for providing stored analysis results to users.

[1537] (Claim 2)

[1538] The system according to claim 1, comprising a terminal for displaying stored analysis results.

[1539] (Claim 3)

[1540] The system according to claim 1, comprising means for analyzing a message using natural language processing technology.

[1541] "Example 1"

[1542] (Claim 1)

[1543] Means of obtaining messages from managers or executives,

[1544] A means of analyzing the acquired message,

[1545] A means for storing the analysis results,

[1546] A means of providing the stored analysis results to the user,

[1547] A means of summarizing a message using natural language processing technology,

[1548] A means of collecting data by sending an HTTP request,

[1549] A means of processing the extracted text data,

[1550] A means of saving the analyzed message to a database,

[1551] A system that includes means of querying a database in response to a user's request to provide the necessary information.

[1552] (Claim 2)

[1553] The system according to claim 1, comprising a terminal for displaying stored analysis results.

[1554] (Claim 3)

[1555] The system according to claim 1, comprising means for summarizing data analyzed using a generative AI model.

[1556] "Application Example 1"

[1557] (Claim 1)

[1558] Means of obtaining messages from managers or executives,

[1559] A means of analyzing the acquired message,

[1560] A means for storing the analysis results,

[1561] A means of providing the stored analysis results to the user,

[1562] A means of summarizing the message and extracting action guidelines,

[1563] A means of storing the analyzed summaries and action guidelines in a centrally managed database,

[1564] A means for searching and notifying the user of analysis results via the user's terminal,

[1565] A system that includes this.

[1566] (Claim 2)

[1567] The system according to claim 1, comprising a terminal for displaying stored analysis results.

[1568] (Claim 3)

[1569] The system according to claim 1, comprising means for analyzing a message using natural language processing technology.

[1570] "Example 2 of combining an emotion engine"

[1571] (Claim 1)

[1572] A means of obtaining messages from executives or managers from a data source,

[1573] A means of using a natural language processing model to analyze the acquired message,

[1574] A means of storing the analysis results in a database,

[1575] An application means that provides the stored analysis results to the user,

[1576] An emotion recognition engine means for recognizing the user's emotions,

[1577] A means of adjusting the content and format of information provided based on emotional data obtained from an emotion recognition engine,

[1578] A system that includes this.

[1579] (Claim 2)

[1580] The system according to claim 1, comprising a terminal for displaying stored analysis results.

[1581] (Claim 3)

[1582] The system according to claim 1, comprising means for analyzing a message using natural language processing technology.

[1583] "Application example 2 when combining with an emotional engine"

[1584] (Claim 1)

[1585] Means of obtaining messages from managers or executives,

[1586] A means of analyzing the acquired message,

[1587] A means for storing the analysis results,

[1588] A means of providing the stored analysis results to the user,

[1589] Means for recognizing the user's emotions,

[1590] A means of customizing the information requested based on recognized emotions.

[1591] A system that includes this.

[1592] (Claim 2)

[1593] The system according to claim 1, comprising a terminal for presenting stored analysis results and a sensor for recognizing the user's emotions.

[1594] (Claim 3)

[1595] The system according to claim 1, comprising means for analyzing a message using natural language processing technology, and means for changing the method of providing the analysis results according to the user's emotions. [Explanation of Symbols]

[1596] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining messages from managers or executives, A means of analyzing the acquired message, A means for storing the analysis results, A system that includes means for providing stored analysis results to users.

2. The system according to claim 1, comprising a terminal for displaying stored analysis results.

3. The system according to claim 1, comprising means for analyzing a message using natural language processing technology.

Images