system

Abstract

We provide the system. [Solution] A means for uploading the business manual, A means of storing uploaded work manuals in a database, A method for analyzing stored business manuals and extracting keywords and phrases, A method for grouping similar tasks based on extracted keywords and phrases, A means of comparing the efficiency of business processes in each department, A means of generating and sending improvement suggestion notifications to departments that are performing inefficient work, A system that includes setting up meetings and collaboration tools for coordinating with other departments, and a means of notifying relevant parties.

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 performed by at least one processor, the method including: 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 as a 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 a conventional business manual management system, work efficiency and standardization were not sufficiently carried out. As a result, knowledge regarding similar work was not shared among departments, and there were many inefficient operations. In addition, improvement proposals from efficient departments to inefficient departments were often not properly made, making it difficult to improve the performance of the entire organization. Therefore, there has been a demand for a system that automatically extracts similar work, compares work efficiency among departments, and makes improvement proposals to improve the work efficiency of the entire organization.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for uploading business manuals, means for storing the uploaded business manuals in a database, means for text analysis of the stored business manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of business processes in each department, means for generating and sending notifications of improvement suggestions to departments performing inefficient tasks, and means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties. According to the present invention, by analyzing business manuals using natural language processing technology, it becomes possible to identify efficient processes and automatically make improvement suggestions for inefficient business processes. This achieves an unprecedented effect of improving the overall operational efficiency of the organization.

[0006] A "business manual" is a document that describes the procedures and guidelines for each department to use when carrying out their work.

[0007] "Upload method" refers to the function of a device or software that provides a procedure or method for sending data from a terminal to a server.

[0008] A "database" is an electronic information aggregation system used to systematically store and manage business manuals and related information.

[0009] "Text analysis" is the process of extracting and analyzing keywords and phrases from a document using natural language processing techniques to understand its meaning and structure.

[0010] "Keywords and phrases" refer to important terms and expressions within the work manual, serving as indicators for identifying the content of the work.

[0011] "Grouping methods" refer to methods or functions that classify similar tasks based on extracted keywords or phrases and group them together into related categories.

[0012] "Efficiency comparison methods" refer to methods and techniques for measuring the performance of each department's business processes, evaluating their efficiency based on numerical data, and comparing them with other departments.

[0013] A "notification method for improvement suggestions" refers to a method or function for generating and notifying departments that are performing inefficient tasks of specific suggestions for improving efficiency.

[0014] "Meeting and collaboration tools" refer to online meeting systems and software tools that support collaborative work, used to facilitate coordination and information sharing between departments.

[0015] "Means of notifying stakeholders" refers to communication methods and notification functions for effectively conveying necessary information and meeting details to stakeholders. [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] Shows an emotion map where multiple emotions are mapped. [Figure 10] Shows an emotion map where multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined. **Modes for Carrying Out the Invention**

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

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

[0019] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as 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] The system of this invention aims to improve internal business efficiency by analyzing the work manuals of each department, extracting similar tasks, and proposing efficient business processes. A specific embodiment of the system is described below.

[0038] Program Processing Overview

[0039] Collection of operational manuals

[0040] Terminal (user):

[0041] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[0042] server:

[0043] The server receives the uploaded work manuals and stores them in the database. During this process, they are categorized into appropriate folders and categories.

[0044] Analysis of business manuals

[0045] server:

[0046] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[0047] Specific example

[0048] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[0049] Extraction of similar tasks

[0050] server:

[0051] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[0052] Specific example

[0053] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[0054] Comparison of efficiency

[0055] server:

[0056] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[0057] Specific example

[0058] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[0059] Notification of improvement suggestions

[0060] server:

[0061] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage them to adopt more efficient methods.

[0062] Specific example

[0063] The server sends a notification to the accounting department suggesting that they adopt the sales department's method for "data entry" tasks.

[0064] Promoting interdepartmental collaboration

[0065] server:

[0066] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[0067] Specific example

[0068] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement ideas.

[0069] This system allows users to easily upload operational manuals, which are then automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. As a result, inter-departmental efficiency improves, and overall organizational performance increases.

[0070] The following describes the processing flow.

[0071] Step 1:

[0072] Terminal (User): Users upload their departmental work manuals from their terminals to the server. Specifically, users open a file selection dialog, select the work manual (PDF, Word, Excel, etc.), and click the upload button.

[0073] Step 2:

[0074] Server: The server receives uploaded work manuals and stores them in the database. The received files are automatically sorted into folders and categorized by department.

[0075] Step 3:

[0076] Server: The server starts the text analysis engine and analyzes the stored business manuals. It uses natural language processing (NLP) tools to break down the text within the document and extract keywords and phrases to identify the business tasks.

[0077] Step 4:

[0078] Server: Based on the extracted keywords and phrases, the server calculates the similarity of the tasks and uses a clustering algorithm to group similar tasks together. For example, manuals with the same tasks, such as "data entry" and "daily reporting," are grouped into a single cluster.

[0079] Step 5:

[0080] Server: The server analyzes metrics related to each department's business processes (e.g., execution time, frequency of work, error rate) and compares the efficiency of operations. This allows it to identify, for example, which department is performing the same task most efficiently.

[0081] Step 6:

[0082] Server: The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include changes to workflows and the adoption of new methods.

[0083] Step 7:

[0084] Server: The server will send notifications to the relevant department's representatives via email or the internal messaging system to inform them of improvement suggestions. The notifications will include specific details of the improvements and suggested efficient methods.

[0085] Step 8:

[0086] Server: The server automates the setup of online meetings and collaboration tools for coordinating with other departments. For example, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[0087] Step 9:

[0088] Terminal (User): Users (each person in charge) check received notifications and meeting invitations, review business processes based on proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall work efficiency.

[0089] Through these steps, the system automatically manages and improves operational manuals efficiently, thereby enhancing the overall performance of the organization.

[0090] (Example 1)

[0091] 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."

[0092] Traditionally, internal operational manuals were created and managed independently by each department, making it difficult to standardize and streamline business processes. Furthermore, duplication of work and lack of coordination between departments led to a decline in overall operational efficiency. Additionally, the lack of a method to identify and improve inefficient processes made it difficult to enhance overall organizational performance.

[0093] 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.

[0094] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in a data set, means for text analysis of the stored business documents using natural language processing and extracting characteristic words and phrases, means for classifying similar tasks based on the extracted characteristic words and phrases, means for evaluating the efficiency of work procedures in each department, means for generating and sending notifications of improvement suggestions to departments performing inefficient work, and means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties. This makes it possible to analyze the work manuals of each department in a unified and automatic manner, propose efficient work processes, and improve the overall operational efficiency of the organization.

[0095] "Business documents" refer to the procedures and guidelines used by each department when carrying out their work, and their format includes file formats such as PDF, Word, and Excel.

[0096] A "data set" refers to an area or database where multiple business documents uploaded to a server are stored.

[0097] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, and is used for text analysis and meaning extraction.

[0098] "Keywords" refer to words and phrases that have important meaning, identified from business documents, and extracted as keywords within the analysis target.

[0099] A "phrase" refers to a segment of the elements that make up a sentence, and is the unit that is analyzed in natural language processing.

[0100] "Similar tasks" refer to tasks that are performed in different departments but share common content and processes.

[0101] "Work procedure efficiency" refers to the degree of efficiency of a task, which is evaluated based on factors such as the time required to perform a particular task, the frequency of the task, and the error rate.

[0102] A "notification of improvement suggestion" refers to a message generated to a department that is performing inefficient tasks, as a suggestion to adopt more efficient methods.

[0103] "Meeting and collaboration tools" refers to online meeting systems and collaboration software used to facilitate inter-departmental communication.

[0104] This invention is a system developed to improve the efficiency of internal business operations, and it automatically collects, analyzes, evaluates, notifies, and links business data. Specific embodiments of the system of this invention will be described below.

[0105] Collection and storage of business documents

[0106] Terminal (user):

[0107] Users upload business documents from their respective departments to the server via their terminals. These documents can be in formats such as PDF, Word, or Excel.

[0108] server:

[0109] The server receives business documents uploaded by users and stores them in a data set. Specifically, it saves the uploaded documents to a database and classifies them into appropriate folders and categories. This classification is based on department name and work content.

[0110] Specific example:

[0111] When a user uploads business documents from the sales department to the server in PDF format, the server receives the file and saves it in the "Sales Department / Business Documents / 2023" folder.

[0112] Analysis of business documents

[0113] server:

[0114] The server retrieves business documents stored in the data set and performs text analysis using natural language processing (NLP) tools. This analysis extracts characteristic words and phrases that identify the business content. For example, using an NLP tool (such as Spacy or NLTK), characteristic words and phrases such as "customer management" and "contract creation" are extracted.

[0115] Specific example:

[0116] The server uses NLP tools to analyze the PDF file and extract keywords such as "customer management" and "contract creation."

[0117] Extraction of similar tasks

[0118] server:

[0119] The server clusters all internal business documents based on the characteristic words extracted through analysis. Here, a clustering algorithm (e.g., K-means clustering) is used to identify groups with similar work content.

[0120] Specific example:

[0121] The server uses the K-means clustering algorithm to group together documents that contain a large number of items related to "customer management" and "contract drafting" into a single cluster.

[0122] Efficiency evaluation of work procedures

[0123] server:

[0124] The server analyzes work procedure data (execution time, frequency, error rate, etc.) in each cluster and evaluates the efficiency of operations, thereby comparing the performance of different departments for the same task.

[0125] Specific example:

[0126] The server evaluates that the sales department takes an average of 10 minutes to complete "data entry," while the accounting department takes 20 minutes, and concludes that the sales department is more efficient.

[0127] Notification of improvement suggestions

[0128] server:

[0129] The server automatically generates improvement suggestions for departments that are performing inefficient tasks, and sends notifications to encourage them to adopt more efficient methods.

[0130] Specific example:

[0131] The server sends an email notification to the accounting department stating, "We propose adopting the sales department's method for data entry."

[0132] Promoting interdepartmental collaboration

[0133] server:

[0134] The server automatically configures online meetings and collaboration tools and sends notifications to relevant parties to facilitate smooth collaboration with other departments. For example, it utilizes the Google Calendar API and the Zoom API.

[0135] Specific example:

[0136] The server uses the Google Calendar API to create online meeting invitation links for sales and accounting departments and sends them via email.

[0137] Example of a prompt

[0138] "Please upload the operational manuals for each department. The server will analyze the manuals, extract similar tasks, and automatically provide suggestions for efficiency improvements."

[0139] This allows users to easily upload business documents, and the server automatically analyzes and compares their efficiency, providing appropriate improvement suggestions for inefficient processes.

[0140] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0141] Step 1: Upload business documents

[0142] Terminal (user):

[0143] Input: Business documents from each department (PDF, Word, Excel format)

[0144] Operation: Users upload work documents from their devices to the server.

[0145] Output: Business documents are transferred to the server.

[0146] Step 2: Receiving and storing business documents

[0147] server:

[0148] Input: User-uploaded business document file

[0149] Operation: The server receives uploaded business documents, analyzes their metadata (file name, department name, file format, etc.), and stores it in the database. It then categorizes them into appropriate folders or categories.

[0150] Output: Business documents stored in the database

[0151] Step 3: Analysis of business documents

[0152] server:

[0153] Input: Business data files stored in the database

[0154] Operation: The server uses natural language processing (NLP) tools to analyze business documents as text and extract key words and phrases. Examples of NLP tools used include Spacy and NLTK.

[0155] Output: List of analyzed feature words and phrases

[0156] Step 4: Extract similar tasks

[0157] server:

[0158] Input: A list of characteristic words and phrases obtained through text analysis.

[0159] Operation: The server uses a clustering algorithm (e.g., K-means clustering) to classify tasks with similar content. Clustering groups similar tasks together.

[0160] Output: List of clustered business groups

[0161] Step 5: Evaluating the efficiency of the work procedure

[0162] server:

[0163] Input: A list of clustered work groups, and work procedure data for each department (execution time, frequency, error rate, etc.)

[0164] Operation: The server analyzes work procedure data in each cluster and evaluates the efficiency of operations. This allows for comparison of the performance of different departments on the same task.

[0165] Output: Efficiency evaluation results of work procedures in each department

[0166] Step 6: Notification of improvement suggestions

[0167] server:

[0168] Input: Efficiency evaluation results

[0169] Operation: The server automatically generates improvement suggestions and sends notifications to departments that are performing inefficient tasks, encouraging them to adopt more efficient methods.

[0170] Output: Notification message for improvement suggestions

[0171] Step 7: Promote interdepartmental collaboration

[0172] server:

[0173] Input: Notification message for improvement suggestions, and contact information of relevant parties.

[0174] Operation: The server automatically configures online meeting and collaboration tools and sends notifications to relevant parties. It utilizes the Google Calendar API and Zoom API.

[0175] Output: Meeting invitation link and notification email

[0176] The above outlines the specific processing steps of this system.

[0177] (Application Example 1)

[0178] 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."

[0179] Improving productivity in modern factories requires optimizing business processes. However, because different departments and production lines use different work manuals, finding effective work procedures is difficult. Furthermore, even for the same task, different work methods are adopted from department to department, leading to a decrease in overall operational efficiency. A system is needed to solve this problem.

[0180] 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.

[0181] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to factory robots based on the analysis results of the work manuals and proposing efficient work methods, and means for recommending efficient work methods using efficiency data for each cluster. This makes it possible for robots used in the factory to analyze different work manuals and propose and apply the optimal work procedure.

[0182] A "work manual" is a document that details work procedures, operating methods, and other related information.

[0183] A "server" is a computer system used for storing, managing, and analyzing data.

[0184] "Text analysis" is the process of extracting meaningful information from document data.

[0185] A "keyword" is an important word that represents the content of a document.

[0186] A "phrase" is a combination of words that have meaning.

[0187] "Grouping" is the process of gathering similar items together into a single group.

[0188] A "business process" refers to a series of activities and procedures necessary to carry out a business task.

[0189] "Efficiency" refers to the degree to which a goal is achieved using a given amount of time and resources.

[0190] A "cluster" is a group classified based on specific common characteristics.

[0191] An "improvement suggestion" refers to specific advice or proposals for making current operations more efficient.

[0192] A "meeting" is a gathering of stakeholders to exchange opinions and engage in discussions.

[0193] "Collaboration tools" are software or tools that allow multiple people to work together.

[0194] A "work procedure" refers to the specific steps and methods for completing a particular task.

[0195] A "factory robot" is a mechanical device that performs tasks automatically within a factory.

[0196] "Efficiency data" refers to specific numerical data used to evaluate the efficiency of business operations.

[0197] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending notifications of improvement suggestions to departments that are performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to a factory robot based on the analysis results of the work manuals and proposing an efficient work method, and means for recommending an efficient work method using efficiency data for each cluster.

[0198] Users first upload their departmental operational manuals to the server in formats such as PDF, Word, or Excel. The server stores these manuals in a database and categorizes them into appropriate folders and categories. For example, manufacturing manuals are automatically placed in a "Manufacturing" folder, and sales manuals in a "Sales" folder.

[0199] The server analyzes the stored business manuals using natural language processing (NLP) technology to extract keywords and phrases that identify the business content. For example, keywords such as "product inspection" and "quality control" are extracted from the manufacturing business manual, and "customer management" and "contract creation" are extracted from the sales business manual.

[0200] Next, the server clusters similar tasks based on the extracted keywords. By using a clustering algorithm, if there are common tasks in the manuals for the sales department and the accounting department (e.g., "data entry," "daily reporting"), these tasks will be classified into the same cluster.

[0201] For each cluster, the server analyzes business process data (execution time, frequency of work, error rate, etc.) to evaluate the efficiency of the work. This allows for comparison of the performance of different departments on the same task. For example, if the sales department takes an average of 10 minutes to perform "data entry" and the accounting department takes an average of 20 minutes, the sales department can be identified as more efficient.

[0202] The server automatically generates and notifies departments that are performing inefficient tasks of improvement suggestions to adopt more efficient methods. For example, the server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks.

[0203] Furthermore, it automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, the server sends online meeting invitation links to sales and accounting department personnel to encourage the sharing of improvement methods.

[0204] When this invention's system is applied to a factory robot, the robot generates the optimal work procedure based on the analysis results of the work manual and proposes an efficient work method. Furthermore, it uses efficiency data for each cluster to apply and recommend the most efficient cluster's work procedure. For example, it analyzes manual 1 used in line 1 of factory A, manual 2 used in line 2 of factory A, and manual 3 used in factory B. If the method for line 1 is the most efficient, it recommends applying that method to other lines or factories.

[0205] Example of a prompt:

[0206] "Analyze the work procedure manuals for lines 1 and 2 of Factory A and propose efficient work processes. Each manual is provided in PDF, Word, and Excel formats."

[0207] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0208] Step 1:

[0209] Users upload work manuals. Input is in PDF, Word, or Excel format, and output is a file uploaded to the server. This includes the specific actions taken by the user to send the work manual to the server via their device.

[0210] Step 2:

[0211] The server stores the uploaded work manuals in a database. The input is the uploaded files, and the output is the work manuals stored in the database. This includes specific actions such as classifying the files into appropriate folders and categories.

[0212] Step 3:

[0213] The server analyzes the stored business manuals and extracts keywords and phrases. The input is the business manuals in the database, and the output is the extracted keywords and phrases. This includes specific actions to extract important noun and verb phrases from the documents using natural language processing (NLP) tools (e.g., NLTK).

[0214] Step 4:

[0215] The server groups similar tasks based on extracted keywords and phrases. The input is keywords and phrases, and the output is clustered task groups. This includes the specific operation of grouping similar task content using a clustering algorithm (e.g., KMeans).

[0216] Step 5:

[0217] The server compares the efficiency of business processes in each department. Inputs are clustered business groups and business process data (execution time, frequency, error rate, etc.), and output is the efficiency evaluation result for each cluster. This includes specific actions such as analyzing process data like execution time and error rate to compare efficiency.

[0218] Step 6:

[0219] The server generates and sends improvement suggestion notifications to departments performing inefficient operations. The input is the efficiency evaluation result, and the output is the improvement suggestion notification. The system includes specific actions to automatically generate and send notifications to inefficient departments based on the evaluation results.

[0220] Step 7:

[0221] The server sets up meetings and collaboration tools for coordinating with other departments and notifies relevant parties. Input is improvement suggestion notifications, and output is online meeting invitation links and collaboration tool settings. This includes specific actions such as setting up and notifying meetings using the calendar API and online meeting tools.

[0222] Step 8:

[0223] The server applies the optimal work procedure to the factory robot based on the analysis results of the work manual, proposing an efficient work method. The input is the analysis results and efficiency data, and the output is instructions based on the optimal work procedure. This includes applying the analysis results to the robot's control system and providing specific actions to instruct the robot on the efficient work procedure.

[0224] Step 9:

[0225] The server uses efficiency data for each cluster to recommend efficient work methods. The input is efficiency data for each cluster, and the output is the recommended work method. This includes specific actions to recommend the most efficient work procedure from the most efficient cluster to other departments.

[0226] 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.

[0227] The system of this invention is built to improve the efficiency of internal business operations, and in particular, it analyzes the work manuals of each department, extracts similar tasks, and proposes efficient work processes. Furthermore, by combining it with an emotion engine that recognizes user emotions, notifications and suggestions are conveyed in the most optimal way for the user. A specific embodiment of the system is described below.

[0228] Program Processing Overview

[0229] Collection of operational manuals

[0230] Terminal (user):

[0231] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[0232] server:

[0233] The server receives the uploaded work manuals and stores them in the database. During this process, the database is categorized into appropriate folders and categories.

[0234] Analysis of business manuals

[0235] server:

[0236] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[0237] Specific example

[0238] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[0239] Extraction of similar tasks

[0240] server:

[0241] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[0242] Specific example

[0243] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[0244] Comparison of efficiency

[0245] server:

[0246] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[0247] Specific example

[0248] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[0249] Notification of improvement suggestions

[0250] server:

[0251] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage the adoption of more efficient methods. This process incorporates an emotion engine that adjusts based on the user's emotional state.

[0252] Specific example

[0253] The server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks. At this time, the emotion engine analyzes the emotional state of the accounting department staff and adjusts the content and tone of the suggestion.

[0254] Promoting interdepartmental collaboration

[0255] server:

[0256] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[0257] Specific example

[0258] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement methods. This notification, too, is delivered at the optimal time and in the right tone, thanks to the emotion engine.

[0259] This system allows users to easily upload operational manuals, which are automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. Furthermore, the introduction of an emotional engine ensures that notifications and suggestions are communicated in the most effective way for the user. As a result, interdepartmental efficiency improves, and overall organizational performance significantly improves.

[0260] The following describes the processing flow.

[0261] Step 1:

[0262] Terminal (user):

[0263] Users upload their departmental work manuals from their terminals to the server. First, users access the web interface that provides the upload function and open the file selection dialog. Next, they select the work manual file (PDF, Word, Excel, etc.) and click the upload button. This sends the file to the server.

[0264] Step 2:

[0265] server:

[0266] The server receives the uploaded business manuals and stores them in the database. It analyzes the received data and organizes it into appropriate folders and categories. For example, files for the sales department are stored in the "Sales Department" folder, and files for the accounting department are stored in the "Accounting Department" folder.

[0267] Step 3:

[0268] server:

[0269] The server activates a text analysis engine and analyzes the contents of the stored business manuals. Using natural language processing (NLP) techniques, it extracts keywords and phrases from each manual. For example, business-related keywords such as "customer management," "contract creation," "product inspection," and "quality control" are identified.

[0270] Step 4:

[0271] server:

[0272] The server calculates the similarity of the work content based on the extracted keywords and phrases, and uses a clustering algorithm to group similar tasks together. For example, manuals with common tasks such as "data entry" and "daily reporting" can be grouped into a single cluster.

[0273] Step 5:

[0274] Server:

[0275] The server analyzes the business process data (e.g., implementation time, operation frequency, error rate) of each department, evaluates the efficiency of the business, compares the performances of different departments for the same business, and identifies which department is the most efficient.

[0276] Step 6:

[0277] Server:

[0278] The server arranges and displays efficient and inefficient business processes, and automatically generates improvement suggestions for the departments conducting inefficient operations. These improvement suggestions include specific methods and examples, and changes to the business flow or introduction of new methods are recommended.

[0279] Step 7:

[0280] Server:

[0281] The server activates the emotion engine and adjusts the notification content according to the user's emotional state. For example, when the user is in a stressed state, the emotion engine creates notifications in a soft tone, making the suggestions more acceptable.

[0282] Step 8: [[ID=​​​​​​​​​​​​​​​​​The server automates the setup of online meetings and collaboration tools for coordinating with other departments. Specifically, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[0288] Step 10:

[0289] Terminal (user):

[0290] Users (each person in charge) review received notifications and meeting invitations, revise their business processes based on the proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall operational efficiency.

[0291] (Example 2)

[0292] 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".

[0293] In modern companies, numerous departments often operate according to different operational manuals, leading to duplication of tasks and inefficiencies. Furthermore, inadequate evaluation of operational efficiency and notification of improvement suggestions, along with a lack of inter-departmental collaboration, can result in overall decreased operational efficiency and negatively impact the company's overall performance.

[0294] 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.

[0295] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in data storage, means for text analysis of the stored business documents and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of business processes in each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties, and means for analyzing the emotional state of users and optimizing the content and tone of notifications. This enables improved operational efficiency within the company and strengthened collaboration between departments.

[0296] "Business documents" refer to documents that describe business procedures and work content used within a company or organization. They come in formats such as PDF, Word, and Excel.

[0297] "Means for uploading" refers to the methods or means by which users send business documents to a server. This is usually done via a web interface or a dedicated application.

[0298] "Means of storing data in data storage" refers to databases and file systems used by servers to store business documents they receive. This ensures that documents are properly managed and saved.

[0299] "Text analysis" refers to technologies and methods for automatically reading the content of business documents and extracting specific keywords or phrases.

[0300] "Keywords and phrases" refer to words or phrases that summarize information within business documents and indicate important business content.

[0301] "Methods for grouping similar tasks" refer to algorithms and methods for classifying tasks that are similar in content, based on extracted keywords or phrases.

[0302] The means for comparing efficiency refers to the means for evaluating the business processes of each department and comparing their respective efficient or inefficient points. This includes indicators such as implementation time and error rate.

[0303] The means for generating and sending improvement proposal notifications refers to the technology and method for automatically generating proposals for efficiency improvement and notifying the departments conducting inefficient operations in an appropriate manner.

[0304] The means for setting up meetings and collaboration tools for cooperation refers to the technology and method for automatically setting up the meetings and online collaboration tools necessary for effective cooperation with other departments.

[0305] The means for analyzing the emotional state of users refers to the technology for judging the emotional state of users and providing appropriate feedback and notifications. For example, it uses the analysis of voice and text.

[0306] The means for optimizing the content and tone of notifications refers to the technology for optimizing the message content and tone of notifications according to the emotional state of users to make them more acceptable.

[0307] Modes for implementing the invention

[0308] The present invention is a system that analyzes business documents and proposes efficient business processes in order to improve the in-company business efficiency. This system is implemented through the following main steps.

[0309] Collection of business documents

[0310] Terminal (user):

[0311] The user uploads the business documents of each department from the terminal to the server. The documents can be in formats such as PDF, Word, Excel, etc.

[0312] Server:

[0313] The server receives uploaded business documents and stores them in data storage. At this time, they are classified into appropriate folders and categories according to their file format. Specifically, PDF files are stored in the PDF folder, and Word files are stored in the Word folder.

[0314] Analysis of business documents

[0315] server:

[0316] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. Keywords and phrases are then extracted from the converted text data using natural language processing (NLP) tools. Specifically, SpaCy is used as the NLP tool to analyze noun and verb phrases that frequently occur in specific contexts.

[0317] Extraction of similar tasks

[0318] server:

[0319] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). Similar processes are grouped together, and related information is compiled for each cluster. K-means clustering vectorizes keywords and calculates Euclidean distances to form clusters.

[0320] Collection and analysis of business process data

[0321] server:

[0322] Daily business process data (execution time, frequency of work, error rate, etc.) is collected regularly from each department and stored in data storage. By analyzing this data, the efficiency of operations and the performance of each department are evaluated. For example, the Pandas library in Python is used to manipulate data frames and calculate various statistics.

[0323] Generation and notification of improvement suggestions

[0324] server:

[0325] For inefficient departments, the system automatically generates improvement suggestions and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions based on the user's emotional state. Emotion analysis uses technologies such as IBM Watson's Tone Analyzer API.

[0326] Promoting interdepartmental collaboration

[0327] server:

[0328] To set up meetings and collaboration tools for coordinating with other departments and notify relevant parties, we use APIs such as Google Calendar API and Zoom API. The server automatically schedules meetings, generates online meeting links, and sends notifications.

[0329] Hardware and software used

[0330] Hardware: Servers, terminals (PCs, tablets, smartphones, etc.)

[0331] software:

[0332] Natural language processing tools (e.g., SpaCy)

[0333] Database Management System

[0334] Emotion engine (e.g., IBM Watson Tone Analyzer API)

[0335] Calendar API (e.g., Google Calendar API)

[0336] Online meeting tools (e.g., Zoom API)

[0337] Data analysis libraries (e.g., Pandas in Python)

[0338] Specific example

[0339] Documents from both the sales and accounting departments contain common tasks such as "customer management" and "data entry." The server analyzes these keywords and compares the business processes of the two departments. For example, it might determine that the sales department can complete "data entry" in 10 minutes, while the accounting department takes 20 minutes. Based on this data, the server sends a notification to the accounting department suggesting more efficient methods from the sales department. This notification is sent with content and tone that takes the recipient's feelings into consideration.

[0340] Example of a prompt

[0341] "Analyze the business documents of the sales and accounting departments, extract common tasks, and cluster them. Also, design a system to identify efficient business processes and notify inefficient departments with improvement suggestions. Use an emotion engine for notifications, adjusting the tone based on the recipient's emotional state."

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] The processing flow of this system's program

[0344] Step 1: Collect business documents

[0345] Terminal (user):

[0346] Users upload business documents (PDF, Word, Excel format) from their respective departments to the server from their terminal. When a user selects a file and presses the upload button, the terminal sends the file to the server via an HTTP POST request.

[0347] server:

[0348] The server receives uploaded business documents and saves them to data storage. They are automatically sorted into appropriate folders and categories based on their file format. For example, it checks the MIME type and stores PDF files in a PDF folder and Word files in a Word folder.

[0349] Input: Uploaded business document file

[0350] Output: Files saved in data storage

[0351] Step 2: Text analysis of business documents

[0352] server:

[0353] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. This extracts the text data from each file. For example, it uses the Python PyPDF2 library to extract text from PDFs and the python-docx library to extract text from Word files. Furthermore, it uses natural language processing (NLP) tools to extract keywords and phrases from the extracted text data.

[0354] Input: Business document files stored in data storage

[0355] Output: Extracted text data, identified keywords and phrases

[0356] Step 3: Clustering similar tasks

[0357] server:

[0358] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). The keywords are vectorized, and Euclidean distances are calculated to form clusters. This groups together highly similar business processes.

[0359] Input: Extracted keywords or phrases

[0360] Output: Tasks categorized by cluster

[0361] Specific example: Run a Python script that implements K-means clustering and divide keywords such as "customer management" and "data entry" into clusters.

[0362] Step 4: Collect business process data

[0363] server:

[0364] Data on daily work processes (execution time, frequency of work, error rate, etc.) is collected regularly from each department. This data is automatically retrieved from the business management system and log data and stored in data storage.

[0365] Input: Business process data for each department

[0366] Output: Business process data stored in data storage

[0367] Specific example: Retrieve data in JSON format from a business management system API and store it in a database.

[0368] Step 5: Comparing the efficiency of business processes

[0369] server:

[0370] The server analyzes collected business process data and compares operational efficiency within each cluster. Specifically, it performs statistical analysis on various metrics (e.g., average execution time, error rate, etc.) to identify efficient and inefficient departments. For example, it uses the Python Pandas library to manipulate dataframes and calculate various statistics.

[0371] Input: Saved business process data

[0372] Output: Comparison results of operational efficiency within each cluster

[0373] Specific example: By manipulating data frames, statistical data is analyzed to identify that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes 20 minutes.

[0374] Step 6: Generate and notify improvement suggestions

[0375] server:

[0376] The server automatically generates improvement suggestions for departments with low operational efficiency, encouraging them to learn from the methods of more efficient departments, and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions according to the user's emotional state. For emotion analysis, it uses, for example, IBM Watson's Tone Analyzer API.

[0377] Input: Business efficiency comparison results, user sentiment data

[0378] Output: Improvement suggestion notification sent to the user

[0379] Specific example: A notification is sent to the accounting department regarding a suggestion for improving the "data entry" process, and the emotional engine sends the suggestion in a softer tone depending on the recipient's emotional state.

[0380] Step 7: Promote interdepartmental collaboration

[0381] server:

[0382] It provides dedicated meeting and collaboration tools for coordinating with other departments and sends notifications to relevant parties. It uses APIs such as Google Calendar API and Zoom API to automatically schedule meetings and generate online meeting links.

[0383] Input: Information on the need for interdepartmental collaboration

[0384] Output: Notification of the schedule and meeting link for the collaborative meeting.

[0385] Specific example: Use the Google Calendar API to schedule meetings for sales and accounting department staff, and then use the Zoom API to generate meeting links and send notifications.

[0386] (Application Example 2)

[0387] 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."

[0388] Conventional factory robot systems have struggled to perform detailed business process analysis to improve operational efficiency and to make optimal suggestions based on the emotional state of workers. Furthermore, the sharing of business processes and the communication of improvement suggestions between departments were often ineffective, resulting in insufficient overall productivity improvements.

[0389] 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 uploading business manuals, means for storing the uploaded business manuals in a database, means for text analysis of the stored business manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the business processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and communication tools for collaboration with other departments and notifying relevant parties, means for analyzing the emotional state of workers using an emotion engine and transmitting notifications and suggestions in the most optimal way, and means for instructing robots to execute each business process. This enables efficient analysis of business manuals and optimization of business processes.

[0390] An "operations manual" is a document that details the work procedures and methods used by each department within an organization.

[0391] "Uploading" refers to the operation of transferring data from a local device to a server on a network.

[0392] A "database" is a structured collection of data designed to efficiently store, search, and manage other data.

[0393] "Text analysis" is the process of analyzing the content of a document using natural language processing technology and extracting specific information.

[0394] "Keywords" are the main words or phrases that summarize the content of a document.

[0395] A "phrase" is a set of words within a document that expresses a specific meaning or context within that document.

[0396] "Grouping" is the process of combining data with similar characteristics or attributes into a single set.

[0397] "Efficiency" is an indicator that shows how effectively the time and effort required for a particular task or process are being used.

[0398] "Comparison" is the process of comparing two or more objects and evaluating their similarities and differences.

[0399] An "improvement suggestion" is a proposal for specific methods or procedures to improve the efficiency of a particular business process.

[0400] "Notification" is the act of conveying specific information or a message to relevant parties.

[0401] A "meeting" is a gathering of stakeholders to discuss and make decisions on a specific topic.

[0402] A "communication tool" is software or a platform designed to efficiently share information and communicate with stakeholders.

[0403] An "emotional engine" is a technology that analyzes the emotional state of workers and uses that information to optimize the content of suggestions and notifications.

[0404] A "robot" is a mechanical device designed to automatically perform specific tasks or operations.

[0405] The system of the present invention is designed to improve operational efficiency within a factory and primarily performs tasks such as analyzing work manuals, proposing efficient work processes, and analyzing the emotional state of workers using an emotion engine. A detailed embodiment of this system is described below.

[0406] The system includes terminals for uploading work manuals, a server for storing the uploaded work manuals in a database, and software for text analysis of the stored work manuals. It also includes a clustering algorithm for grouping similar tasks based on extracted keywords and phrases, an analysis tool for comparing the efficiency of business processes in each department, and a process for notifying departments that are performing inefficient tasks with improvement suggestions.

[0407] Hardware and software to be used

[0408] hardware

[0409] Robot: A mechanical device used to automatically perform tasks within a factory (e.g., ABB IRB 6700).

[0410] Server: A high-performance server for data analysis and storage.

[0411] software

[0412] Natural language processing tools: Software for analyzing the text of business manuals (e.g., SpaCy, NLTK).

[0413] Clustering algorithm: An algorithm for grouping similar tasks based on keywords or phrases (e.g., KMeans clustering).

[0414] Emotion Engine: A deep learning model (e.g., a customized version of BERT or GPT-3®) that analyzes the emotional state of workers and provides optimal suggestions.

[0415] Data processing and data calculation

[0416] The server first receives the user-uploaded work manuals and stores them in a database. Then, it uses a text analysis tool to analyze the content of the work manuals and extract keywords and phrases. Based on the extracted keywords and phrases, it uses a clustering algorithm to group the tasks. Next, it compares the efficiency of each department's work processes based on data (e.g., execution time, frequency of work, error rate) and generates and notifies departments that are performing inefficient tasks with improvement suggestions.

[0417] Furthermore, the system uses an emotion engine to analyze the emotional state of workers and adjust suggestions in the most optimal way. For example, if the server analyzes the average time spent on "parts assembly" in the manufacturing department and determines that the sales department is more efficient, it will propose and notify the manufacturing department of how to improve this. At the same time, if the emotion engine determines that a worker is highly fatigued, it will also send a notification in a gentle tone and suggest additional breaks.

[0418] Examples of prompt statements

[0419] Use the following prompts to have the generating AI model analyze the business manual and suggest improvements:

[0420] Analyze the following work manual and extract keywords:

[0421] Assembly of parts

[0422] quality control

[0423] Data entry

[0424] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] Users upload operational manuals for each department via a terminal. Input is in PDF, Word, or Excel format, and output is data transfer to a server. Specifically, users select documents describing work procedures performed within the factory and upload them to the system.

[0428] Step 2:

[0429] The server receives uploaded work manuals and stores them in the database. The input is the data of the work manuals submitted by the user, and the output is the saving of the stored documents to the database. Specifically, the server categorizes the files into appropriate folders and categories and saves them to the database.

[0430] Step 3:

[0431] The server uses natural language processing tools to analyze the stored business manuals and extract keywords and phrases. The input is the text data of the business manuals stored in the database, and the output is a list of extracted keywords and phrases. Specifically, natural language processing technology is used to identify key noun phrases and verb phrases such as "parts assembly" and "quality control."

[0432] Step 4:

[0433] Based on the extracted keywords and phrases, the server uses a clustering algorithm to group similar tasks. The input is a list of keywords and phrases, and the output is the clustering result. Specifically, the KMeans algorithm is applied to group departments with similar tasks into a single cluster.

[0434] Step 5:

[0435] The server compares efficiency based on data related to each department's business processes (e.g., execution time, frequency of work, error rate). The input is efficiency data collected for each department, and the output is the efficiency score for each task. Specifically, it aggregates data from each department and evaluates which department is more efficient.

[0436] Step 6:

[0437] The server generates and sends notifications to departments performing inefficient operations, suggesting more efficient methods. The input is the efficiency evaluation result, and the output is a notification with improvement suggestions. Specifically, it generates and sends notifications to low-efficiency departments encouraging them to adopt methods from high-efficiency departments.

[0438] Step 7:

[0439] The server uses an emotion engine to analyze the worker's emotional state and adjusts suggestions and notifications in the most optimal way. The input is the worker's emotional data, and the output is a notification message that reflects their emotional state. Specifically, it analyzes the worker's stress level and fatigue level and adjusts the tone and content of notifications accordingly.

[0440] Step 8:

[0441] The server instructs the robot to execute each business process. The input consists of improvement suggestions and work instruction data, and the output is the automated work performed by the robot. Specifically, the server instructs the robot to adopt efficient work methods and perform the actual tasks.

[0442] Examples of prompt statements include the following:

[0443] Analyze the following work manual and extract keywords:

[0444] Assembly of parts

[0445] quality control

[0446] Data entry

[0447] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] [Second Embodiment]

[0452] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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".

[0464] The system of this invention aims to improve internal business efficiency by analyzing the work manuals of each department, extracting similar tasks, and proposing efficient business processes. A specific embodiment of the system is described below.

[0465] Program Processing Overview

[0466] Collection of operational manuals

[0467] Terminal (user):

[0468] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[0469] server:

[0470] The server receives the uploaded work manuals and stores them in the database. During this process, they are categorized into appropriate folders and categories.

[0471] Analysis of business manuals

[0472] server:

[0473] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[0474] Specific example

[0475] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[0476] Extraction of similar tasks

[0477] server:

[0478] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[0479] Specific example

[0480] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[0481] Comparison of efficiency

[0482] server:

[0483] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[0484] Specific example

[0485] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[0486] Notification of improvement suggestions

[0487] server:

[0488] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage them to adopt more efficient methods.

[0489] Specific example

[0490] The server sends a notification to the accounting department suggesting that they adopt the sales department's method for "data entry" tasks.

[0491] Promoting interdepartmental collaboration

[0492] server:

[0493] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[0494] Specific example

[0495] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement ideas.

[0496] This system allows users to easily upload operational manuals, which are then automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. As a result, inter-departmental efficiency improves, and overall organizational performance increases.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] Terminal (User): Users upload their departmental work manuals from their terminals to the server. Specifically, users open a file selection dialog, select the work manual (PDF, Word, Excel, etc.), and click the upload button.

[0500] Step 2:

[0501] Server: The server receives uploaded work manuals and stores them in the database. The received files are automatically sorted into folders and categorized by department.

[0502] Step 3:

[0503] Server: The server starts the text analysis engine and analyzes the stored business manuals. It uses natural language processing (NLP) tools to break down the text within the document and extract keywords and phrases to identify the business tasks.

[0504] Step 4:

[0505] Server: Based on the extracted keywords and phrases, the server calculates the similarity of the tasks and uses a clustering algorithm to group similar tasks together. For example, manuals with the same tasks, such as "data entry" and "daily reporting," are grouped into a single cluster.

[0506] Step 5:

[0507] Server: The server analyzes metrics related to each department's business processes (e.g., execution time, frequency of work, error rate) and compares the efficiency of operations. This allows it to identify, for example, which department is performing the same task most efficiently.

[0508] Step 6:

[0509] Server: The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include changes to workflows and the adoption of new methods.

[0510] Step 7:

[0511] Server: The server will send notifications to the relevant department's representatives via email or the internal messaging system to inform them of improvement suggestions. The notifications will include specific details of the improvements and suggested efficient methods.

[0512] Step 8:

[0513] Server: The server automates the setup of online meetings and collaboration tools for coordinating with other departments. For example, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[0514] Step 9:

[0515] Terminal (User): Users (each person in charge) check received notifications and meeting invitations, review business processes based on proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall work efficiency.

[0516] Through these steps, the system automatically manages and improves operational manuals efficiently, thereby enhancing the overall performance of the organization.

[0517] (Example 1)

[0518] 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".

[0519] Traditionally, internal operational manuals were created and managed independently by each department, making it difficult to standardize and streamline business processes. Furthermore, duplication of work and lack of coordination between departments led to a decline in overall operational efficiency. Additionally, the lack of a method to identify and improve inefficient processes made it difficult to enhance overall organizational performance.

[0520] 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.

[0521] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in a data set, means for text analysis of the stored business documents using natural language processing and extracting characteristic words and phrases, means for classifying similar tasks based on the extracted characteristic words and phrases, means for evaluating the efficiency of work procedures in each department, means for generating and sending notifications of improvement suggestions to departments performing inefficient work, and means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties. This makes it possible to analyze the work manuals of each department in a unified and automatic manner, propose efficient work processes, and improve the overall operational efficiency of the organization.

[0522] "Business documents" refer to the procedures and guidelines used by each department when carrying out their work, and their format includes file formats such as PDF, Word, and Excel.

[0523] A "data set" refers to an area or database where multiple business documents uploaded to a server are stored.

[0524] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, and is used for text analysis and meaning extraction.

[0525] "Keywords" refer to words and phrases that have important meaning, identified from business documents, and extracted as keywords within the analysis target.

[0526] A "phrase" refers to a segment of the elements that make up a sentence, and is the unit that is analyzed in natural language processing.

[0527] "Similar tasks" refer to tasks that are performed in different departments but share common content and processes.

[0528] "Work procedure efficiency" refers to the degree of efficiency of a task, which is evaluated based on factors such as the time required to perform a particular task, the frequency of the task, and the error rate.

[0529] A "notification of improvement suggestion" refers to a message generated to a department that is performing inefficient tasks, as a suggestion to adopt more efficient methods.

[0530] "Meeting and collaboration tools" refers to online meeting systems and collaboration software used to facilitate inter-departmental communication.

[0531] This invention is a system developed to improve the efficiency of internal business operations, and it automatically collects, analyzes, evaluates, notifies, and links business data. Specific embodiments of the system of this invention will be described below.

[0532] Collection and storage of business documents

[0533] Terminal (user):

[0534] Users upload business documents from their respective departments to the server via their terminals. These documents can be in formats such as PDF, Word, or Excel.

[0535] server:

[0536] The server receives business documents uploaded by users and stores them in a data set. Specifically, it saves the uploaded documents to a database and classifies them into appropriate folders and categories. This classification is based on department name and work content.

[0537] Specific example:

[0538] When a user uploads business documents from the sales department to the server in PDF format, the server receives the file and saves it in the "Sales Department / Business Documents / 2023" folder.

[0539] Analysis of business documents

[0540] server:

[0541] The server retrieves business documents stored in the data set and performs text analysis using natural language processing (NLP) tools. This analysis extracts characteristic words and phrases that identify the business content. For example, using an NLP tool (such as Spacy or NLTK), characteristic words and phrases such as "customer management" and "contract creation" are extracted.

[0542] Specific example:

[0543] The server uses NLP tools to analyze the PDF file and extract keywords such as "customer management" and "contract creation."

[0544] Extraction of similar tasks

[0545] server:

[0546] The server clusters all internal business documents based on the characteristic words extracted through analysis. Here, a clustering algorithm (e.g., K-means clustering) is used to identify groups with similar work content.

[0547] Specific example:

[0548] The server uses the K-means clustering algorithm to group together documents that contain a large number of items related to "customer management" and "contract drafting" into a single cluster.

[0549] Efficiency evaluation of work procedures

[0550] server:

[0551] The server analyzes work procedure data (execution time, frequency, error rate, etc.) in each cluster and evaluates the efficiency of operations, thereby comparing the performance of different departments for the same task.

[0552] Specific example:

[0553] The server evaluates that the sales department takes an average of 10 minutes to complete "data entry," while the accounting department takes 20 minutes, and concludes that the sales department is more efficient.

[0554] Notification of improvement suggestions

[0555] server:

[0556] The server automatically generates improvement suggestions for departments that are performing inefficient tasks, and sends notifications to encourage them to adopt more efficient methods.

[0557] Specific example:

[0558] The server sends an email notification to the accounting department stating, "We propose adopting the sales department's method for data entry."

[0559] Promoting interdepartmental collaboration

[0560] server:

[0561] The server automatically configures online meetings and collaboration tools and sends notifications to relevant parties to facilitate smooth collaboration with other departments. For example, it utilizes the Google Calendar API and the Zoom API.

[0562] Specific example:

[0563] The server uses the Google Calendar API to create online meeting invitation links for sales and accounting departments and sends them via email.

[0564] Example of a prompt

[0565] "Please upload the operational manuals for each department. The server will analyze the manuals, extract similar tasks, and automatically provide suggestions for efficiency improvements."

[0566] This allows users to easily upload business documents, and the server automatically analyzes and compares their efficiency, providing appropriate improvement suggestions for inefficient processes.

[0567] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0568] Step 1: Upload business documents

[0569] Terminal (user):

[0570] Input: Business documents from each department (PDF, Word, Excel format)

[0571] Operation: Users upload work documents from their devices to the server.

[0572] Output: Business documents are transferred to the server.

[0573] Step 2: Receiving and storing business documents

[0574] server:

[0575] Input: User-uploaded business document file

[0576] Operation: The server receives uploaded business documents, analyzes their metadata (file name, department name, file format, etc.), and stores it in the database. It then categorizes them into appropriate folders or categories.

[0577] Output: Business documents stored in the database

[0578] Step 3: Analysis of business documents

[0579] server:

[0580] Input: Business data files stored in the database

[0581] Operation: The server uses natural language processing (NLP) tools to analyze business documents as text and extract key words and phrases. Examples of NLP tools used include Spacy and NLTK.

[0582] Output: List of analyzed feature words and phrases

[0583] Step 4: Extract similar tasks

[0584] server:

[0585] Input: A list of characteristic words and phrases obtained through text analysis.

[0586] Operation: The server uses a clustering algorithm (e.g., K-means clustering) to classify tasks with similar content. Clustering groups similar tasks together.

[0587] Output: List of clustered business groups

[0588] Step 5: Evaluating the efficiency of the work procedure

[0589] server:

[0590] Input: A list of clustered work groups, and work procedure data for each department (execution time, frequency, error rate, etc.)

[0591] Operation: The server analyzes work procedure data in each cluster and evaluates the efficiency of operations. This allows for comparison of the performance of different departments on the same task.

[0592] Output: Efficiency evaluation results of work procedures in each department

[0593] Step 6: Notification of improvement suggestions

[0594] server:

[0595] Input: Efficiency evaluation results

[0596] Operation: The server automatically generates improvement suggestions and sends notifications to departments that are performing inefficient tasks, encouraging them to adopt more efficient methods.

[0597] Output: Notification message for improvement suggestions

[0598] Step 7: Promote interdepartmental collaboration

[0599] server:

[0600] Input: Notification message for improvement suggestions, and contact information of relevant parties.

[0601] Operation: The server automatically configures online meeting and collaboration tools and sends notifications to relevant parties. It utilizes the Google Calendar API and Zoom API.

[0602] Output: Meeting invitation link and notification email

[0603] The above outlines the specific processing steps of this system.

[0604] (Application Example 1)

[0605] 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."

[0606] Improving productivity in modern factories requires optimizing business processes. However, because different departments and production lines use different work manuals, finding effective work procedures is difficult. Furthermore, even for the same task, different work methods are adopted from department to department, leading to a decrease in overall operational efficiency. A system is needed to solve this problem.

[0607] 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.

[0608] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to factory robots based on the analysis results of the work manuals and proposing efficient work methods, and means for recommending efficient work methods using efficiency data for each cluster. This makes it possible for robots used in the factory to analyze different work manuals and propose and apply the optimal work procedure.

[0609] A "work manual" is a document that details work procedures, operating methods, and other related information.

[0610] A "server" is a computer system used for storing, managing, and analyzing data.

[0611] "Text analysis" is the process of extracting meaningful information from document data.

[0612] A "keyword" is an important word that represents the content of a document.

[0613] A "phrase" is a combination of words that have meaning.

[0614] "Grouping" is the process of gathering similar items together into a single group.

[0615] A "business process" refers to a series of activities and procedures necessary to carry out a business task.

[0616] "Efficiency" refers to the degree to which a goal is achieved using a given amount of time and resources.

[0617] A "cluster" is a group classified based on specific common characteristics.

[0618] An "improvement suggestion" refers to specific advice or proposals for making current operations more efficient.

[0619] A "meeting" is a gathering of stakeholders to exchange opinions and engage in discussions.

[0620] "Collaboration tools" are software or tools that allow multiple people to work together.

[0621] A "work procedure" refers to the specific steps and methods for completing a particular task.

[0622] A "factory robot" is a mechanical device that performs tasks automatically within a factory.

[0623] "Efficiency data" refers to specific numerical data used to evaluate the efficiency of business operations.

[0624] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending notifications of improvement suggestions to departments that are performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to a factory robot based on the analysis results of the work manuals and proposing an efficient work method, and means for recommending an efficient work method using efficiency data for each cluster.

[0625] Users first upload their departmental operational manuals to the server in formats such as PDF, Word, or Excel. The server stores these manuals in a database and categorizes them into appropriate folders and categories. For example, manufacturing manuals are automatically placed in a "Manufacturing" folder, and sales manuals in a "Sales" folder.

[0626] The server analyzes the stored business manuals using natural language processing (NLP) technology to extract keywords and phrases that identify the business content. For example, keywords such as "product inspection" and "quality control" are extracted from the manufacturing business manual, and "customer management" and "contract creation" are extracted from the sales business manual.

[0627] Next, the server clusters similar tasks based on the extracted keywords. By using a clustering algorithm, if there are common tasks in the manuals for the sales department and the accounting department (e.g., "data entry," "daily reporting"), these tasks will be classified into the same cluster.

[0628] For each cluster, the server analyzes business process data (execution time, frequency of work, error rate, etc.) to evaluate the efficiency of the work. This allows for comparison of the performance of different departments on the same task. For example, if the sales department takes an average of 10 minutes to perform "data entry" and the accounting department takes an average of 20 minutes, the sales department can be identified as more efficient.

[0629] The server automatically generates and notifies departments that are performing inefficient tasks of improvement suggestions to adopt more efficient methods. For example, the server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks.

[0630] Furthermore, it automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, the server sends online meeting invitation links to sales and accounting department personnel to encourage the sharing of improvement methods.

[0631] When this invention's system is applied to a factory robot, the robot generates the optimal work procedure based on the analysis results of the work manual and proposes an efficient work method. Furthermore, it uses efficiency data for each cluster to apply and recommend the most efficient cluster's work procedure. For example, it analyzes manual 1 used in line 1 of factory A, manual 2 used in line 2 of factory A, and manual 3 used in factory B. If the method for line 1 is the most efficient, it recommends applying that method to other lines or factories.

[0632] Example of a prompt:

[0633] "Analyze the work procedure manuals for lines 1 and 2 of Factory A and propose efficient work processes. Each manual is provided in PDF, Word, and Excel formats."

[0634] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0635] Step 1:

[0636] Users upload work manuals. Input is in PDF, Word, or Excel format, and output is a file uploaded to the server. This includes the specific actions taken by the user to send the work manual to the server via their device.

[0637] Step 2:

[0638] The server stores the uploaded work manuals in a database. The input is the uploaded files, and the output is the work manuals stored in the database. This includes specific actions such as classifying the files into appropriate folders and categories.

[0639] Step 3:

[0640] The server analyzes the stored business manuals and extracts keywords and phrases. The input is the business manuals in the database, and the output is the extracted keywords and phrases. This includes specific actions to extract important noun and verb phrases from the documents using natural language processing (NLP) tools (e.g., NLTK).

[0641] Step 4:

[0642] The server groups similar tasks based on extracted keywords and phrases. The input is keywords and phrases, and the output is clustered task groups. This includes the specific operation of grouping similar task content using a clustering algorithm (e.g., KMeans).

[0643] Step 5:

[0644] The server compares the efficiency of business processes in each department. Inputs are clustered business groups and business process data (execution time, frequency, error rate, etc.), and output is the efficiency evaluation result for each cluster. This includes specific actions such as analyzing process data like execution time and error rate to compare efficiency.

[0645] Step 6:

[0646] The server generates and sends improvement suggestion notifications to departments performing inefficient operations. The input is the efficiency evaluation result, and the output is the improvement suggestion notification. The system includes specific actions to automatically generate and send notifications to inefficient departments based on the evaluation results.

[0647] Step 7:

[0648] The server sets up meetings and collaboration tools for coordinating with other departments and notifies relevant parties. Input is improvement suggestion notifications, and output is online meeting invitation links and collaboration tool settings. This includes specific actions such as setting up and notifying meetings using the calendar API and online meeting tools.

[0649] Step 8:

[0650] The server applies the optimal work procedure to the factory robot based on the analysis results of the work manual, proposing an efficient work method. The input is the analysis results and efficiency data, and the output is instructions based on the optimal work procedure. This includes applying the analysis results to the robot's control system and providing specific actions to instruct the robot on the efficient work procedure.

[0651] Step 9:

[0652] The server uses efficiency data for each cluster to recommend efficient work methods. The input is efficiency data for each cluster, and the output is the recommended work method. This includes specific actions to recommend the most efficient work procedure from the most efficient cluster to other departments.

[0653] 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.

[0654] The system of this invention is built to improve the efficiency of internal business operations, and in particular, it analyzes the work manuals of each department, extracts similar tasks, and proposes efficient work processes. Furthermore, by combining it with an emotion engine that recognizes user emotions, notifications and suggestions are conveyed in the most optimal way for the user. A specific embodiment of the system is described below.

[0655] Program Processing Overview

[0656] Collection of operational manuals

[0657] Terminal (user):

[0658] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[0659] server:

[0660] The server receives the uploaded work manuals and stores them in the database. During this process, the database is categorized into appropriate folders and categories.

[0661] Analysis of business manuals

[0662] server:

[0663] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[0664] Specific example

[0665] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[0666] Extraction of similar tasks

[0667] server:

[0668] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[0669] Specific example

[0670] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[0671] Comparison of efficiency

[0672] server:

[0673] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[0674] Specific example

[0675] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[0676] Notification of improvement suggestions

[0677] server:

[0678] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage the adoption of more efficient methods. This process incorporates an emotion engine that adjusts based on the user's emotional state.

[0679] Specific example

[0680] The server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks. At this time, the emotion engine analyzes the emotional state of the accounting department staff and adjusts the content and tone of the suggestion.

[0681] Promoting interdepartmental collaboration

[0682] server:

[0683] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[0684] Specific example

[0685] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement methods. This notification, too, is delivered at the optimal time and in the right tone, thanks to the emotion engine.

[0686] This system allows users to easily upload operational manuals, which are automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. Furthermore, the introduction of an emotional engine ensures that notifications and suggestions are communicated in the most effective way for the user. As a result, interdepartmental efficiency improves, and overall organizational performance significantly improves.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] Terminal (user):

[0690] Users upload their departmental work manuals from their terminals to the server. First, users access the web interface that provides the upload function and open the file selection dialog. Next, they select the work manual file (PDF, Word, Excel, etc.) and click the upload button. This sends the file to the server.

[0691] Step 2:

[0692] server:

[0693] The server receives the uploaded business manuals and stores them in the database. It analyzes the received data and organizes it into appropriate folders and categories. For example, files for the sales department are stored in the "Sales Department" folder, and files for the accounting department are stored in the "Accounting Department" folder.

[0694] Step 3:

[0695] server:

[0696] The server activates a text analysis engine and analyzes the contents of the stored business manuals. Using natural language processing (NLP) techniques, it extracts keywords and phrases from each manual. For example, business-related keywords such as "customer management," "contract creation," "product inspection," and "quality control" are identified.

[0697] Step 4:

[0698] server:

[0699] The server calculates the similarity of the work content based on the extracted keywords and phrases, and uses a clustering algorithm to group similar tasks together. For example, manuals with common tasks such as "data entry" and "daily reporting" can be grouped into a single cluster.

[0700] Step 5:

[0701] server:

[0702] The server analyzes business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. It compares the performance of different departments on the same task to identify which department is the most efficient.

[0703] Step 6:

[0704] server:

[0705] The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include specific methods and examples, recommending changes to workflows or the introduction of new methods.

[0706] Step 7:

[0707] server:

[0708] The server activates an emotion engine, which adjusts notification content to match the user's emotional state. For example, if the user is stressed, the emotion engine will create a notification in a softer tone. This makes the suggestion more likely to be accepted.

[0709] Step 8:

[0710] server:

[0711] The server will send notifications to the relevant departments via email or the company's internal messaging system to inform them of improvement suggestions. These notifications will include specific details of the improvements and suggested efficient methods.

[0712] Step 9:

[0713] server:

[0714] The server automates the setup of online meetings and collaboration tools for coordinating with other departments. Specifically, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[0715] Step 10:

[0716] Terminal (user):

[0717] Users (each person in charge) review received notifications and meeting invitations, revise their business processes based on the proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall operational efficiency.

[0718] (Example 2)

[0719] 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".

[0720] In modern companies, numerous departments often operate according to different operational manuals, leading to duplication of tasks and inefficiencies. Furthermore, inadequate evaluation of operational efficiency and notification of improvement suggestions, along with a lack of inter-departmental collaboration, can result in overall decreased operational efficiency and negatively impact the company's overall performance.

[0721] 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.

[0722] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in data storage, means for text analysis of the stored business documents and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of business processes in each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties, and means for analyzing the emotional state of users and optimizing the content and tone of notifications. This enables improved operational efficiency within the company and strengthened collaboration between departments.

[0723] "Business documents" refer to documents that describe business procedures and work content used within a company or organization. They come in formats such as PDF, Word, and Excel.

[0724] "Means for uploading" refers to the methods or means by which users send business documents to a server. This is usually done via a web interface or a dedicated application.

[0725] "Means of storing data in data storage" refers to databases and file systems used by servers to store business documents they receive. This ensures that documents are properly managed and saved.

[0726] "Text analysis" refers to technologies and methods for automatically reading the content of business documents and extracting specific keywords or phrases.

[0727] "Keywords and phrases" refer to words or phrases that summarize information within business documents and indicate important business content.

[0728] "Methods for grouping similar tasks" refer to algorithms and methods for classifying tasks that are similar in content, based on extracted keywords or phrases.

[0729] "Means of comparing efficiency" refers to methods for evaluating the business processes of each department and comparing their efficiency or inefficiency. This includes indicators such as execution time and error rate.

[0730] "Means for generating and sending improvement suggestion notifications" refers to technologies and methods that automatically generate suggestions for efficiency improvements to departments performing inefficient operations and notify them in an appropriate manner.

[0731] "Means for setting up meetings and collaboration tools for coordination" refers to technologies and methods for automatically setting up meetings and online collaboration tools necessary for effective coordination with other departments.

[0732] "Means for analyzing a user's emotional state" refers to technologies that determine a user's emotional state and provide appropriate feedback or notifications. For example, this may involve analyzing speech or text.

[0733] "Methods for optimizing notification content and tone" refer to technologies that optimize the content and tone of notification messages according to the user's emotional state, making them more acceptable.

[0734] Modes for carrying out the invention

[0735] This invention is a system that analyzes business documents and proposes efficient business processes in order to improve the efficiency of internal operations. This system is implemented through the following main steps.

[0736] Collection of business documents

[0737] Terminal (user):

[0738] Users upload their departmental work documents from their terminals to the server. Documents can be in formats such as PDF, Word, and Excel.

[0739] server:

[0740] The server receives uploaded business documents and stores them in data storage. At this time, they are classified into appropriate folders and categories according to their file format. Specifically, PDF files are stored in the PDF folder, and Word files are stored in the Word folder.

[0741] Analysis of business documents

[0742] server:

[0743] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. Keywords and phrases are then extracted from the converted text data using natural language processing (NLP) tools. Specifically, SpaCy is used as the NLP tool to analyze noun and verb phrases that frequently occur in specific contexts.

[0744] Extraction of similar tasks

[0745] server:

[0746] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). Similar processes are grouped together, and related information is compiled for each cluster. K-means clustering vectorizes keywords and calculates Euclidean distances to form clusters.

[0747] Collection and analysis of business process data

[0748] server:

[0749] Daily business process data (execution time, frequency of work, error rate, etc.) is collected regularly from each department and stored in data storage. By analyzing this data, the efficiency of operations and the performance of each department are evaluated. For example, the Pandas library in Python is used to manipulate data frames and calculate various statistics.

[0750] Generation and notification of improvement suggestions

[0751] server:

[0752] For inefficient departments, the system automatically generates improvement suggestions and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions based on the user's emotional state. Emotion analysis uses tools such as IBM Watson's Tone Analyzer API.

[0753] Promoting interdepartmental collaboration

[0754] server:

[0755] To set up meetings and collaboration tools for coordinating with other departments and notify relevant parties, we use APIs such as Google Calendar API and Zoom API. The server automatically schedules meetings, generates online meeting links, and sends notifications.

[0756] Hardware and software used

[0757] Hardware: Servers, terminals (PCs, tablets, smartphones, etc.)

[0758] software:

[0759] Natural language processing tools (e.g., SpaCy)

[0760] Database Management System

[0761] Emotion engine (e.g., IBM Watson Tone Analyzer API)

[0762] Calendar API (e.g., Google Calendar API)

[0763] Online meeting tools (e.g., Zoom API)

[0764] Data analysis libraries (e.g., Pandas in Python)

[0765] Specific example

[0766] Documents from both the sales and accounting departments contain common tasks such as "customer management" and "data entry." The server analyzes these keywords and compares the business processes of the two departments. For example, it might determine that the sales department can complete "data entry" in 10 minutes, while the accounting department takes 20 minutes. Based on this data, the server sends a notification to the accounting department suggesting more efficient methods from the sales department. This notification is sent with content and tone that takes the recipient's feelings into consideration.

[0767] Example of a prompt

[0768] "Analyze the business documents of the sales and accounting departments, extract common tasks, and cluster them. Also, design a system to identify efficient business processes and notify inefficient departments with improvement suggestions. Use an emotion engine for notifications, adjusting the tone based on the recipient's emotional state."

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] The processing flow of this system's program

[0771] Step 1: Collect business documents

[0772] Terminal (user):

[0773] Users upload business documents (PDF, Word, Excel format) from their respective departments to the server from their terminal. When a user selects a file and presses the upload button, the terminal sends the file to the server via an HTTP POST request.

[0774] server:

[0775] The server receives uploaded business documents and saves them to data storage. They are automatically sorted into appropriate folders and categories based on their file format. For example, it checks the MIME type and stores PDF files in a PDF folder and Word files in a Word folder.

[0776] Input: Uploaded business document file

[0777] Output: Files saved in data storage

[0778] Step 2: Text analysis of business documents

[0779] server:

[0780] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. This extracts the text data from each file. For example, it uses the Python PyPDF2 library to extract text from PDFs and the python-docx library to extract text from Word files. Furthermore, it uses natural language processing (NLP) tools to extract keywords and phrases from the extracted text data.

[0781] Input: Business document files stored in data storage

[0782] Output: Extracted text data, identified keywords and phrases

[0783] Step 3: Clustering similar tasks

[0784] server:

[0785] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). The keywords are vectorized, and Euclidean distances are calculated to form clusters. This groups together highly similar business processes.

[0786] Input: Extracted keywords or phrases

[0787] Output: Tasks categorized by cluster

[0788] Specific example: Run a Python script that implements K-means clustering and divide keywords such as "customer management" and "data entry" into clusters.

[0789] Step 4: Collect business process data

[0790] server:

[0791] Data on daily work processes (execution time, frequency of work, error rate, etc.) is collected regularly from each department. This data is automatically retrieved from the business management system and log data and stored in data storage.

[0792] Input: Business process data for each department

[0793] Output: Business process data stored in data storage

[0794] Specific example: Retrieve data in JSON format from a business management system API and store it in a database.

[0795] Step 5: Comparing the efficiency of business processes

[0796] server:

[0797] The server analyzes collected business process data and compares operational efficiency within each cluster. Specifically, it performs statistical analysis on various metrics (e.g., average execution time, error rate, etc.) to identify efficient and inefficient departments. For example, it uses the Python Pandas library to manipulate dataframes and calculate various statistics.

[0798] Input: Saved business process data

[0799] Output: Comparison results of operational efficiency within each cluster

[0800] Specific example: By manipulating data frames, statistical data is analyzed to identify that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes 20 minutes.

[0801] Step 6: Generate and notify improvement suggestions

[0802] server:

[0803] The server automatically generates improvement suggestions for departments with low operational efficiency, encouraging them to learn from the methods of more efficient departments, and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions according to the user's emotional state. For emotion analysis, it uses, for example, IBM Watson's Tone Analyzer API.

[0804] Input: Business efficiency comparison results, user sentiment data

[0805] Output: Improvement suggestion notification sent to the user

[0806] Specific example: A notification is sent to the accounting department regarding a suggestion for improving the "data entry" process, and the emotional engine sends the suggestion in a softer tone depending on the recipient's emotional state.

[0807] Step 7: Promote interdepartmental collaboration

[0808] server:

[0809] It provides dedicated meeting and collaboration tools for coordinating with other departments and sends notifications to relevant parties. It uses APIs such as Google Calendar API and Zoom API to automatically schedule meetings and generate online meeting links.

[0810] Input: Information on the need for interdepartmental collaboration

[0811] Output: Notification of the schedule and meeting link for the collaborative meeting.

[0812] Specific example: Use the Google Calendar API to schedule meetings for sales and accounting department staff, and then use the Zoom API to generate meeting links and send notifications.

[0813] (Application Example 2)

[0814] 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."

[0815] Conventional factory robot systems have struggled to perform detailed business process analysis to improve operational efficiency and to make optimal suggestions based on the emotional state of workers. Furthermore, the sharing of business processes and the communication of improvement suggestions between departments were often ineffective, resulting in insufficient overall productivity improvements.

[0816] 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 uploading business manuals, means for storing the uploaded business manuals in a database, means for text analysis of the stored business manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the business processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and communication tools for collaboration with other departments and notifying relevant parties, means for analyzing the emotional state of workers using an emotion engine and transmitting notifications and suggestions in the most optimal way, and means for instructing robots to execute each business process. This enables efficient analysis of business manuals and optimization of business processes.

[0817] An "operations manual" is a document that details the work procedures and methods used by each department within an organization.

[0818] "Uploading" refers to the operation of transferring data from a local device to a server on a network.

[0819] A "database" is a structured collection of data designed to efficiently store, search, and manage other data.

[0820] "Text analysis" is the process of analyzing the content of a document using natural language processing technology and extracting specific information.

[0821] "Keywords" are the main words or phrases that summarize the content of a document.

[0822] A "phrase" is a set of words within a document that expresses a specific meaning or context within that document.

[0823] "Grouping" is the process of combining data with similar characteristics or attributes into a single set.

[0824] "Efficiency" is an indicator that shows how effectively the time and effort required for a particular task or process are being used.

[0825] "Comparison" is the process of comparing two or more objects and evaluating their similarities and differences.

[0826] An "improvement suggestion" is a proposal for specific methods or procedures to improve the efficiency of a particular business process.

[0827] "Notification" is the act of conveying specific information or a message to relevant parties.

[0828] A "meeting" is a gathering of stakeholders to discuss and make decisions on a specific topic.

[0829] A "communication tool" is software or a platform designed to efficiently share information and communicate with stakeholders.

[0830] An "emotional engine" is a technology that analyzes the emotional state of workers and uses that information to optimize the content of suggestions and notifications.

[0831] A "robot" is a mechanical device designed to automatically perform specific tasks or operations.

[0832] The system of the present invention is designed to improve operational efficiency within a factory and primarily performs tasks such as analyzing work manuals, proposing efficient work processes, and analyzing the emotional state of workers using an emotion engine. A detailed embodiment of this system is described below.

[0833] The system includes terminals for uploading work manuals, a server for storing the uploaded work manuals in a database, and software for text analysis of the stored work manuals. It also includes a clustering algorithm for grouping similar tasks based on extracted keywords and phrases, an analysis tool for comparing the efficiency of business processes in each department, and a process for notifying departments that are performing inefficient tasks with improvement suggestions.

[0834] Hardware and software to be used

[0835] hardware

[0836] Robot: A mechanical device used to automatically perform tasks within a factory (e.g., ABB IRB 6700).

[0837] Server: A high-performance server for data analysis and storage.

[0838] software

[0839] Natural language processing tools: Software for analyzing the text of business manuals (e.g., SpaCy, NLTK).

[0840] Clustering algorithm: An algorithm for grouping similar tasks based on keywords or phrases (e.g., KMeans clustering).

[0841] Emotion Engine: A deep learning model (e.g., a customized BERT or GPT-3) that analyzes the emotional state of workers and provides optimal suggestions.

[0842] Data processing and data calculation

[0843] The server first receives the user-uploaded work manuals and stores them in a database. Then, it uses a text analysis tool to analyze the content of the work manuals and extract keywords and phrases. Based on the extracted keywords and phrases, it uses a clustering algorithm to group the tasks. Next, it compares the efficiency of each department's work processes based on data (e.g., execution time, frequency of work, error rate) and generates and notifies departments that are performing inefficient tasks with improvement suggestions.

[0844] Furthermore, the system uses an emotion engine to analyze the emotional state of workers and adjust suggestions in the most optimal way. For example, if the server analyzes the average time spent on "parts assembly" in the manufacturing department and determines that the sales department is more efficient, it will propose and notify the manufacturing department of how to improve this. At the same time, if the emotion engine determines that a worker is highly fatigued, it will also send a notification in a gentle tone and suggest additional breaks.

[0845] Examples of prompt statements

[0846] Use the following prompts to have the generating AI model analyze the business manual and suggest improvements:

[0847] Analyze the following work manual and extract keywords:

[0848] Assembly of parts

[0849] quality control

[0850] Data entry

[0851] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[0852] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0853] Step 1:

[0854] Users upload operational manuals for each department via a terminal. Input is in PDF, Word, or Excel format, and output is data transfer to a server. Specifically, users select documents describing work procedures performed within the factory and upload them to the system.

[0855] Step 2:

[0856] The server receives uploaded work manuals and stores them in the database. The input is the data of the work manuals submitted by the user, and the output is the saving of the stored documents to the database. Specifically, the server categorizes the files into appropriate folders and categories and saves them to the database.

[0857] Step 3:

[0858] The server uses natural language processing tools to analyze the stored business manuals and extract keywords and phrases. The input is the text data of the business manuals stored in the database, and the output is a list of extracted keywords and phrases. Specifically, natural language processing technology is used to identify key noun phrases and verb phrases such as "parts assembly" and "quality control."

[0859] Step 4:

[0860] Based on the extracted keywords and phrases, the server uses a clustering algorithm to group similar tasks. The input is a list of keywords and phrases, and the output is the clustering result. Specifically, the KMeans algorithm is applied to group departments with similar tasks into a single cluster.

[0861] Step 5:

[0862] The server compares efficiency based on data related to each department's business processes (e.g., execution time, frequency of work, error rate). The input is efficiency data collected for each department, and the output is the efficiency score for each task. Specifically, it aggregates data from each department and evaluates which department is more efficient.

[0863] Step 6:

[0864] The server generates and sends notifications to departments performing inefficient operations, suggesting more efficient methods. The input is the efficiency evaluation result, and the output is a notification with improvement suggestions. Specifically, it generates and sends notifications to low-efficiency departments encouraging them to adopt methods from high-efficiency departments.

[0865] Step 7:

[0866] The server uses an emotion engine to analyze the worker's emotional state and adjusts suggestions and notifications in the most optimal way. The input is the worker's emotional data, and the output is a notification message that reflects their emotional state. Specifically, it analyzes the worker's stress level and fatigue level and adjusts the tone and content of notifications accordingly.

[0867] Step 8:

[0868] The server instructs the robot to execute each business process. The input consists of improvement suggestions and work instruction data, and the output is the automated work performed by the robot. Specifically, the server instructs the robot to adopt efficient work methods and perform the actual tasks.

[0869] Examples of prompt statements include the following:

[0870] Analyze the following work manual and extract keywords:

[0871] Assembly of parts

[0872] quality control

[0873] Data entry

[0874] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] [Third Embodiment]

[0879] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0880] 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.

[0881] 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).

[0882] 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.

[0883] 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.

[0884] 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).

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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".

[0891] The system of this invention aims to improve internal business efficiency by analyzing the work manuals of each department, extracting similar tasks, and proposing efficient business processes. A specific embodiment of the system is described below.

[0892] Program Processing Overview

[0893] Collection of operational manuals

[0894] Terminal (user):

[0895] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[0896] server:

[0897] The server receives the uploaded work manuals and stores them in the database. During this process, they are categorized into appropriate folders and categories.

[0898] Analysis of business manuals

[0899] server:

[0900] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[0901] Specific example

[0902] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[0903] Extraction of similar tasks

[0904] server:

[0905] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[0906] Specific example

[0907] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[0908] Comparison of efficiency

[0909] server:

[0910] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[0911] Specific example

[0912] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[0913] Notification of improvement suggestions

[0914] server:

[0915] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage them to adopt more efficient methods.

[0916] Specific example

[0917] The server sends a notification to the accounting department suggesting that they adopt the sales department's method for "data entry" tasks.

[0918] Promoting interdepartmental collaboration

[0919] server:

[0920] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[0921] Specific example

[0922] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement ideas.

[0923] This system allows users to easily upload operational manuals, which are then automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. As a result, inter-departmental efficiency improves, and overall organizational performance increases.

[0924] The following describes the processing flow.

[0925] Step 1:

[0926] Terminal (User): Users upload their departmental work manuals from their terminals to the server. Specifically, users open a file selection dialog, select the work manual (PDF, Word, Excel, etc.), and click the upload button.

[0927] Step 2:

[0928] Server: The server receives uploaded work manuals and stores them in the database. The received files are automatically sorted into folders and categorized by department.

[0929] Step 3:

[0930] Server: The server starts the text analysis engine and analyzes the stored business manuals. It uses natural language processing (NLP) tools to break down the text within the document and extract keywords and phrases to identify the business tasks.

[0931] Step 4:

[0932] Server: Based on the extracted keywords and phrases, the server calculates the similarity of the tasks and uses a clustering algorithm to group similar tasks together. For example, manuals with the same tasks, such as "data entry" and "daily reporting," are grouped into a single cluster.

[0933] Step 5:

[0934] Server: The server analyzes metrics related to each department's business processes (e.g., execution time, frequency of work, error rate) and compares the efficiency of operations. This allows it to identify, for example, which department is performing the same task most efficiently.

[0935] Step 6:

[0936] Server: The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include changes to workflows and the adoption of new methods.

[0937] Step 7:

[0938] Server: The server will send notifications to the relevant department's representatives via email or the internal messaging system to inform them of improvement suggestions. The notifications will include specific details of the improvements and suggested efficient methods.

[0939] Step 8:

[0940] Server: The server automates the setup of online meetings and collaboration tools for coordinating with other departments. For example, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[0941] Step 9:

[0942] Terminal (User): Users (each person in charge) check received notifications and meeting invitations, review business processes based on proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall work efficiency.

[0943] Through these steps, the system automatically manages and improves operational manuals efficiently, thereby enhancing the overall performance of the organization.

[0944] (Example 1)

[0945] 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."

[0946] Traditionally, internal operational manuals were created and managed independently by each department, making it difficult to standardize and streamline business processes. Furthermore, duplication of work and lack of coordination between departments led to a decline in overall operational efficiency. Additionally, the lack of a method to identify and improve inefficient processes made it difficult to enhance overall organizational performance.

[0947] 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.

[0948] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in a data set, means for text analysis of the stored business documents using natural language processing and extracting characteristic words and phrases, means for classifying similar tasks based on the extracted characteristic words and phrases, means for evaluating the efficiency of work procedures in each department, means for generating and sending notifications of improvement suggestions to departments performing inefficient work, and means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties. This makes it possible to analyze the work manuals of each department in a unified and automatic manner, propose efficient work processes, and improve the overall operational efficiency of the organization.

[0949] "Business documents" refer to the procedures and guidelines used by each department when carrying out their work, and their format includes file formats such as PDF, Word, and Excel.

[0950] A "data set" refers to an area or database where multiple business documents uploaded to a server are stored.

[0951] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, and is used for text analysis and meaning extraction.

[0952] "Keywords" refer to words and phrases that have important meaning, identified from business documents, and extracted as keywords within the analysis target.

[0953] A "phrase" refers to a segment of the elements that make up a sentence, and is the unit that is analyzed in natural language processing.

[0954] "Similar tasks" refer to tasks that are performed in different departments but share common content and processes.

[0955] "Work procedure efficiency" refers to the degree of efficiency of a task, which is evaluated based on factors such as the time required to perform a particular task, the frequency of the task, and the error rate.

[0956] A "notification of improvement suggestion" refers to a message generated to a department that is performing inefficient tasks, as a suggestion to adopt more efficient methods.

[0957] "Meeting and collaboration tools" refers to online meeting systems and collaboration software used to facilitate inter-departmental communication.

[0958] This invention is a system developed to improve the efficiency of internal business operations, and it automatically collects, analyzes, evaluates, notifies, and links business data. Specific embodiments of the system of this invention will be described below.

[0959] Collection and storage of business documents

[0960] Terminal (user):

[0961] Users upload business documents from their respective departments to the server via their terminals. These documents can be in formats such as PDF, Word, or Excel.

[0962] server:

[0963] The server receives business documents uploaded by users and stores them in a data set. Specifically, it saves the uploaded documents to a database and classifies them into appropriate folders and categories. This classification is based on department name and work content.

[0964] Specific example:

[0965] When a user uploads business documents from the sales department to the server in PDF format, the server receives the file and saves it in the "Sales Department / Business Documents / 2023" folder.

[0966] Analysis of business documents

[0967] server:

[0968] The server retrieves business documents stored in the data set and performs text analysis using natural language processing (NLP) tools. This analysis extracts characteristic words and phrases that identify the business content. For example, using an NLP tool (such as Spacy or NLTK), characteristic words and phrases such as "customer management" and "contract creation" are extracted.

[0969] Specific example:

[0970] The server uses NLP tools to analyze the PDF file and extract keywords such as "customer management" and "contract creation."

[0971] Extraction of similar tasks

[0972] server:

[0973] The server clusters all internal business documents based on the characteristic words extracted through analysis. Here, a clustering algorithm (e.g., K-means clustering) is used to identify groups with similar work content.

[0974] Specific example:

[0975] The server uses the K-means clustering algorithm to group together documents that contain a large number of items related to "customer management" and "contract drafting" into a single cluster.

[0976] Efficiency evaluation of work procedures

[0977] server:

[0978] The server analyzes work procedure data (execution time, frequency, error rate, etc.) in each cluster and evaluates the efficiency of operations, thereby comparing the performance of different departments for the same task.

[0979] Specific example:

[0980] The server evaluates that the sales department takes an average of 10 minutes to complete "data entry," while the accounting department takes 20 minutes, and concludes that the sales department is more efficient.

[0981] Notification of improvement suggestions

[0982] server:

[0983] The server automatically generates improvement suggestions for departments that are performing inefficient tasks, and sends notifications to encourage them to adopt more efficient methods.

[0984] Specific example:

[0985] The server sends an email notification to the accounting department stating, "We propose adopting the sales department's method for data entry."

[0986] Promoting interdepartmental collaboration

[0987] server:

[0988] The server automatically configures online meetings and collaboration tools and sends notifications to relevant parties to facilitate smooth collaboration with other departments. For example, it utilizes the Google Calendar API and the Zoom API.

[0989] Specific example:

[0990] The server uses the Google Calendar API to create online meeting invitation links for sales and accounting departments and sends them via email.

[0991] Example of a prompt

[0992] "Please upload the operational manuals for each department. The server will analyze the manuals, extract similar tasks, and automatically provide suggestions for efficiency improvements."

[0993] This allows users to easily upload business documents, and the server automatically analyzes and compares their efficiency, providing appropriate improvement suggestions for inefficient processes.

[0994] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0995] Step 1: Upload business documents

[0996] Terminal (user):

[0997] Input: Business documents from each department (PDF, Word, Excel format)

[0998] Operation: Users upload work documents from their devices to the server.

[0999] Output: Business documents are transferred to the server.

[1000] Step 2: Receiving and storing business documents

[1001] server:

[1002] Input: User-uploaded business document file

[1003] Operation: The server receives uploaded business documents, analyzes their metadata (file name, department name, file format, etc.), and stores it in the database. It then categorizes them into appropriate folders or categories.

[1004] Output: Business documents stored in the database

[1005] Step 3: Analysis of business documents

[1006] server:

[1007] Input: Business data files stored in the database

[1008] Operation: The server uses natural language processing (NLP) tools to analyze business documents as text and extract key words and phrases. Examples of NLP tools used include Spacy and NLTK.

[1009] Output: List of analyzed feature words and phrases

[1010] Step 4: Extract similar tasks

[1011] server:

[1012] Input: A list of characteristic words and phrases obtained through text analysis.

[1013] Operation: The server uses a clustering algorithm (e.g., K-means clustering) to classify tasks with similar content. Clustering groups similar tasks together.

[1014] Output: List of clustered business groups

[1015] Step 5: Evaluating the efficiency of the work procedure

[1016] server:

[1017] Input: A list of clustered work groups, and work procedure data for each department (execution time, frequency, error rate, etc.)

[1018] Operation: The server analyzes work procedure data in each cluster and evaluates the efficiency of operations. This allows for comparison of the performance of different departments on the same task.

[1019] Output: Efficiency evaluation results of work procedures in each department

[1020] Step 6: Notification of improvement suggestions

[1021] server:

[1022] Input: Efficiency evaluation results

[1023] Operation: The server automatically generates improvement suggestions and sends notifications to departments that are performing inefficient tasks, encouraging them to adopt more efficient methods.

[1024] Output: Notification message for improvement suggestions

[1025] Step 7: Promote interdepartmental collaboration

[1026] server:

[1027] Input: Notification message for improvement suggestions, and contact information of relevant parties.

[1028] Operation: The server automatically configures online meeting and collaboration tools and sends notifications to relevant parties. It utilizes the Google Calendar API and Zoom API.

[1029] Output: Meeting invitation link and notification email

[1030] The above outlines the specific processing steps of this system.

[1031] (Application Example 1)

[1032] 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."

[1033] Improving productivity in modern factories requires optimizing business processes. However, because different departments and production lines use different work manuals, finding effective work procedures is difficult. Furthermore, even for the same task, different work methods are adopted from department to department, leading to a decrease in overall operational efficiency. A system is needed to solve this problem.

[1034] 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.

[1035] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to factory robots based on the analysis results of the work manuals and proposing efficient work methods, and means for recommending efficient work methods using efficiency data for each cluster. This makes it possible for robots used in the factory to analyze different work manuals and propose and apply the optimal work procedure.

[1036] A "work manual" is a document that details work procedures, operating methods, and other related information.

[1037] A "server" is a computer system used for storing, managing, and analyzing data.

[1038] "Text analysis" is the process of extracting meaningful information from document data.

[1039] A "keyword" is an important word that represents the content of a document.

[1040] A "phrase" is a combination of words that have meaning.

[1041] "Grouping" is the process of gathering similar items together into a single group.

[1042] A "business process" refers to a series of activities and procedures necessary to carry out a business task.

[1043] "Efficiency" refers to the degree to which a goal is achieved using a given amount of time and resources.

[1044] A "cluster" is a group classified based on specific common characteristics.

[1045] An "improvement suggestion" refers to specific advice or proposals for making current operations more efficient.

[1046] A "meeting" is a gathering of stakeholders to exchange opinions and engage in discussions.

[1047] "Collaboration tools" are software or tools that allow multiple people to work together.

[1048] A "work procedure" refers to the specific steps and methods for completing a particular task.

[1049] A "factory robot" is a mechanical device that performs tasks automatically within a factory.

[1050] "Efficiency data" refers to specific numerical data used to evaluate the efficiency of business operations.

[1051] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending notifications of improvement suggestions to departments that are performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to a factory robot based on the analysis results of the work manuals and proposing an efficient work method, and means for recommending an efficient work method using efficiency data for each cluster.

[1052] Users first upload their departmental operational manuals to the server in formats such as PDF, Word, or Excel. The server stores these manuals in a database and categorizes them into appropriate folders and categories. For example, manufacturing manuals are automatically placed in a "Manufacturing" folder, and sales manuals in a "Sales" folder.

[1053] The server analyzes the stored business manuals using natural language processing (NLP) technology to extract keywords and phrases that identify the business content. For example, keywords such as "product inspection" and "quality control" are extracted from the manufacturing business manual, and "customer management" and "contract creation" are extracted from the sales business manual.

[1054] Next, the server clusters similar tasks based on the extracted keywords. By using a clustering algorithm, if there are common tasks in the manuals for the sales department and the accounting department (e.g., "data entry," "daily reporting"), these tasks will be classified into the same cluster.

[1055] For each cluster, the server analyzes business process data (execution time, frequency of work, error rate, etc.) to evaluate the efficiency of the work. This allows for comparison of the performance of different departments on the same task. For example, if the sales department takes an average of 10 minutes to perform "data entry" and the accounting department takes an average of 20 minutes, the sales department can be identified as more efficient.

[1056] The server automatically generates and notifies departments that are performing inefficient tasks of improvement suggestions to adopt more efficient methods. For example, the server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks.

[1057] Furthermore, it automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, the server sends online meeting invitation links to sales and accounting department personnel to encourage the sharing of improvement methods.

[1058] When this invention's system is applied to a factory robot, the robot generates the optimal work procedure based on the analysis results of the work manual and proposes an efficient work method. Furthermore, it uses efficiency data for each cluster to apply and recommend the most efficient cluster's work procedure. For example, it analyzes manual 1 used in line 1 of factory A, manual 2 used in line 2 of factory A, and manual 3 used in factory B. If the method for line 1 is the most efficient, it recommends applying that method to other lines or factories.

[1059] Example of a prompt:

[1060] "Analyze the work procedure manuals for lines 1 and 2 of Factory A and propose efficient work processes. Each manual is provided in PDF, Word, and Excel formats."

[1061] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1062] Step 1:

[1063] Users upload work manuals. Input is in PDF, Word, or Excel format, and output is a file uploaded to the server. This includes the specific actions taken by the user to send the work manual to the server via their device.

[1064] Step 2:

[1065] The server stores the uploaded work manuals in a database. The input is the uploaded files, and the output is the work manuals stored in the database. This includes specific actions such as classifying the files into appropriate folders and categories.

[1066] Step 3:

[1067] The server analyzes the stored business manuals and extracts keywords and phrases. The input is the business manuals in the database, and the output is the extracted keywords and phrases. This includes specific actions to extract important noun and verb phrases from the documents using natural language processing (NLP) tools (e.g., NLTK).

[1068] Step 4:

[1069] The server groups similar tasks based on extracted keywords and phrases. The input is keywords and phrases, and the output is clustered task groups. This includes the specific operation of grouping similar task content using a clustering algorithm (e.g., KMeans).

[1070] Step 5:

[1071] The server compares the efficiency of business processes in each department. Inputs are clustered business groups and business process data (execution time, frequency, error rate, etc.), and output is the efficiency evaluation result for each cluster. This includes specific actions such as analyzing process data like execution time and error rate to compare efficiency.

[1072] Step 6:

[1073] The server generates and sends improvement suggestion notifications to departments performing inefficient operations. The input is the efficiency evaluation result, and the output is the improvement suggestion notification. The system includes specific actions to automatically generate and send notifications to inefficient departments based on the evaluation results.

[1074] Step 7:

[1075] The server sets up meetings and collaboration tools for coordinating with other departments and notifies relevant parties. Input is improvement suggestion notifications, and output is online meeting invitation links and collaboration tool settings. This includes specific actions such as setting up and notifying meetings using the calendar API and online meeting tools.

[1076] Step 8:

[1077] The server applies the optimal work procedure to the factory robot based on the analysis results of the work manual, proposing an efficient work method. The input is the analysis results and efficiency data, and the output is instructions based on the optimal work procedure. This includes applying the analysis results to the robot's control system and providing specific actions to instruct the robot on the efficient work procedure.

[1078] Step 9:

[1079] The server uses efficiency data for each cluster to recommend efficient work methods. The input is efficiency data for each cluster, and the output is the recommended work method. This includes specific actions to recommend the most efficient work procedure from the most efficient cluster to other departments.

[1080] 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.

[1081] The system of this invention is built to improve the efficiency of internal business operations, and in particular, it analyzes the work manuals of each department, extracts similar tasks, and proposes efficient work processes. Furthermore, by combining it with an emotion engine that recognizes user emotions, notifications and suggestions are conveyed in the most optimal way for the user. A specific embodiment of the system is described below.

[1082] Program Processing Overview

[1083] Collection of operational manuals

[1084] Terminal (user):

[1085] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[1086] server:

[1087] The server receives the uploaded work manuals and stores them in the database. During this process, the database is categorized into appropriate folders and categories.

[1088] Analysis of business manuals

[1089] server:

[1090] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[1091] Specific example

[1092] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[1093] Extraction of similar tasks

[1094] server:

[1095] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[1096] Specific example

[1097] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[1098] Comparison of efficiency

[1099] server:

[1100] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[1101] Specific example

[1102] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[1103] Notification of improvement suggestions

[1104] server:

[1105] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage the adoption of more efficient methods. This process incorporates an emotion engine that adjusts based on the user's emotional state.

[1106] Specific example

[1107] The server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks. At this time, the emotion engine analyzes the emotional state of the accounting department staff and adjusts the content and tone of the suggestion.

[1108] Promoting interdepartmental collaboration

[1109] server:

[1110] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[1111] Specific example

[1112] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement methods. This notification, too, is delivered at the optimal time and in the right tone, thanks to the emotion engine.

[1113] This system allows users to easily upload operational manuals, which are automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. Furthermore, the introduction of an emotional engine ensures that notifications and suggestions are communicated in the most effective way for the user. As a result, interdepartmental efficiency improves, and overall organizational performance significantly improves.

[1114] The following describes the processing flow.

[1115] Step 1:

[1116] Terminal (user):

[1117] Users upload their departmental work manuals from their terminals to the server. First, users access the web interface that provides the upload function and open the file selection dialog. Next, they select the work manual file (PDF, Word, Excel, etc.) and click the upload button. This sends the file to the server.

[1118] Step 2:

[1119] server:

[1120] The server receives the uploaded business manuals and stores them in the database. It analyzes the received data and organizes it into appropriate folders and categories. For example, files for the sales department are stored in the "Sales Department" folder, and files for the accounting department are stored in the "Accounting Department" folder.

[1121] Step 3:

[1122] server:

[1123] The server activates a text analysis engine and analyzes the contents of the stored business manuals. Using natural language processing (NLP) techniques, it extracts keywords and phrases from each manual. For example, business-related keywords such as "customer management," "contract creation," "product inspection," and "quality control" are identified.

[1124] Step 4:

[1125] server:

[1126] The server calculates the similarity of the work content based on the extracted keywords and phrases, and uses a clustering algorithm to group similar tasks together. For example, manuals with common tasks such as "data entry" and "daily reporting" can be grouped into a single cluster.

[1127] Step 5:

[1128] server:

[1129] The server analyzes business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. It compares the performance of different departments on the same task to identify which department is the most efficient.

[1130] Step 6:

[1131] server:

[1132] The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include specific methods and examples, recommending changes to workflows or the introduction of new methods.

[1133] Step 7:

[1134] server:

[1135] The server activates an emotion engine, which adjusts notification content to match the user's emotional state. For example, if the user is stressed, the emotion engine will create a notification in a softer tone. This makes the suggestion more likely to be accepted.

[1136] Step 8:

[1137] server:

[1138] The server will send notifications to the relevant departments via email or the company's internal messaging system to inform them of improvement suggestions. These notifications will include specific details of the improvements and suggested efficient methods.

[1139] Step 9:

[1140] server:

[1141] The server automates the setup of online meetings and collaboration tools for coordinating with other departments. Specifically, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[1142] Step 10:

[1143] Terminal (user):

[1144] Users (each person in charge) review received notifications and meeting invitations, revise their business processes based on the proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall operational efficiency.

[1145] (Example 2)

[1146] 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."

[1147] In modern companies, numerous departments often operate according to different operational manuals, leading to duplication of tasks and inefficiencies. Furthermore, inadequate evaluation of operational efficiency and notification of improvement suggestions, along with a lack of inter-departmental collaboration, can result in overall decreased operational efficiency and negatively impact the company's overall performance.

[1148] 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.

[1149] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in data storage, means for text analysis of the stored business documents and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of business processes in each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties, and means for analyzing the emotional state of users and optimizing the content and tone of notifications. This enables improved operational efficiency within the company and strengthened collaboration between departments.

[1150] "Business documents" refer to documents that describe business procedures and work content used within a company or organization. They come in formats such as PDF, Word, and Excel.

[1151] "Means for uploading" refers to the methods or means by which users send business documents to a server. This is usually done via a web interface or a dedicated application.

[1152] "Means of storing data in data storage" refers to databases and file systems used by servers to store business documents they receive. This ensures that documents are properly managed and saved.

[1153] "Text analysis" refers to technologies and methods for automatically reading the content of business documents and extracting specific keywords or phrases.

[1154] "Keywords and phrases" refer to words or phrases that summarize information within business documents and indicate important business content.

[1155] "Methods for grouping similar tasks" refer to algorithms and methods for classifying tasks that are similar in content, based on extracted keywords or phrases.

[1156] "Means of comparing efficiency" refers to methods for evaluating the business processes of each department and comparing their efficiency or inefficiency. This includes indicators such as execution time and error rate.

[1157] "Means for generating and sending improvement suggestion notifications" refers to technologies and methods that automatically generate suggestions for efficiency improvements to departments performing inefficient operations and notify them in an appropriate manner.

[1158] "Means for setting up meetings and collaboration tools for coordination" refers to technologies and methods for automatically setting up meetings and online collaboration tools necessary for effective coordination with other departments.

[1159] "Means for analyzing a user's emotional state" refers to technologies that determine a user's emotional state and provide appropriate feedback or notifications. For example, this may involve analyzing speech or text.

[1160] "Methods for optimizing notification content and tone" refer to technologies that optimize the content and tone of notification messages according to the user's emotional state, making them more acceptable.

[1161] Modes for carrying out the invention

[1162] This invention is a system that analyzes business documents and proposes efficient business processes in order to improve the efficiency of internal operations. This system is implemented through the following main steps.

[1163] Collection of business documents

[1164] Terminal (user):

[1165] Users upload their departmental work documents from their terminals to the server. Documents can be in formats such as PDF, Word, and Excel.

[1166] server:

[1167] The server receives uploaded business documents and stores them in data storage. At this time, they are classified into appropriate folders and categories according to their file format. Specifically, PDF files are stored in the PDF folder, and Word files are stored in the Word folder.

[1168] Analysis of business documents

[1169] server:

[1170] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. Keywords and phrases are then extracted from the converted text data using natural language processing (NLP) tools. Specifically, SpaCy is used as the NLP tool to analyze noun and verb phrases that frequently occur in specific contexts.

[1171] Extraction of similar tasks

[1172] server:

[1173] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). Similar processes are grouped together, and related information is compiled for each cluster. K-means clustering vectorizes keywords and calculates Euclidean distances to form clusters.

[1174] Collection and analysis of business process data

[1175] server:

[1176] Daily business process data (execution time, frequency of work, error rate, etc.) is collected regularly from each department and stored in data storage. By analyzing this data, the efficiency of operations and the performance of each department are evaluated. For example, the Pandas library in Python is used to manipulate data frames and calculate various statistics.

[1177] Generation and notification of improvement suggestions

[1178] server:

[1179] For inefficient departments, the system automatically generates improvement suggestions and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions based on the user's emotional state. Emotion analysis uses tools such as IBM Watson's Tone Analyzer API.

[1180] Promoting interdepartmental collaboration

[1181] server:

[1182] To set up meetings and collaboration tools for coordinating with other departments and notify relevant parties, we use APIs such as Google Calendar API and Zoom API. The server automatically schedules meetings, generates online meeting links, and sends notifications.

[1183] Hardware and software used

[1184] Hardware: Servers, terminals (PCs, tablets, smartphones, etc.)

[1185] software:

[1186] Natural language processing tools (e.g., SpaCy)

[1187] Database Management System

[1188] Emotion engine (e.g., IBM Watson Tone Analyzer API)

[1189] Calendar API (e.g., Google Calendar API)

[1190] Online meeting tools (e.g., Zoom API)

[1191] Data analysis libraries (e.g., Pandas in Python)

[1192] Specific example

[1193] Documents from both the sales and accounting departments contain common tasks such as "customer management" and "data entry." The server analyzes these keywords and compares the business processes of the two departments. For example, it might determine that the sales department can complete "data entry" in 10 minutes, while the accounting department takes 20 minutes. Based on this data, the server sends a notification to the accounting department suggesting more efficient methods from the sales department. This notification is sent with content and tone that takes the recipient's feelings into consideration.

[1194] Example of a prompt

[1195] "Analyze the business documents of the sales and accounting departments, extract common tasks, and cluster them. Also, design a system to identify efficient business processes and notify inefficient departments with improvement suggestions. Use an emotion engine for notifications, adjusting the tone based on the recipient's emotional state."

[1196] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1197] The processing flow of this system's program

[1198] Step 1: Collect business documents

[1199] Terminal (user):

[1200] Users upload business documents (PDF, Word, Excel format) from their respective departments to the server from their terminal. When a user selects a file and presses the upload button, the terminal sends the file to the server via an HTTP POST request.

[1201] server:

[1202] The server receives uploaded business documents and saves them to data storage. They are automatically sorted into appropriate folders and categories based on their file format. For example, it checks the MIME type and stores PDF files in a PDF folder and Word files in a Word folder.

[1203] Input: Uploaded business document file

[1204] Output: Files saved in data storage

[1205] Step 2: Text analysis of business documents

[1206] server:

[1207] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. This extracts the text data from each file. For example, it uses the Python PyPDF2 library to extract text from PDFs and the python-docx library to extract text from Word files. Furthermore, it uses natural language processing (NLP) tools to extract keywords and phrases from the extracted text data.

[1208] Input: Business document files stored in data storage

[1209] Output: Extracted text data, identified keywords and phrases

[1210] Step 3: Clustering similar tasks

[1211] server:

[1212] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). The keywords are vectorized, and Euclidean distances are calculated to form clusters. This groups together highly similar business processes.

[1213] Input: Extracted keywords or phrases

[1214] Output: Tasks categorized by cluster

[1215] Specific example: Run a Python script that implements K-means clustering and divide keywords such as "customer management" and "data entry" into clusters.

[1216] Step 4: Collect business process data

[1217] server:

[1218] Data on daily work processes (execution time, frequency of work, error rate, etc.) is collected regularly from each department. This data is automatically retrieved from the business management system and log data and stored in data storage.

[1219] Input: Business process data for each department

[1220] Output: Business process data stored in data storage

[1221] Specific example: Retrieve data in JSON format from a business management system API and store it in a database.

[1222] Step 5: Comparing the efficiency of business processes

[1223] server:

[1224] The server analyzes collected business process data and compares operational efficiency within each cluster. Specifically, it performs statistical analysis on various metrics (e.g., average execution time, error rate, etc.) to identify efficient and inefficient departments. For example, it uses the Python Pandas library to manipulate dataframes and calculate various statistics.

[1225] Input: Saved business process data

[1226] Output: Comparison results of operational efficiency within each cluster

[1227] Specific example: By manipulating data frames, statistical data is analyzed to identify that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes 20 minutes.

[1228] Step 6: Generate and notify improvement suggestions

[1229] server:

[1230] The server automatically generates improvement suggestions for departments with low operational efficiency, encouraging them to learn from the methods of more efficient departments, and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions according to the user's emotional state. For emotion analysis, it uses, for example, IBM Watson's Tone Analyzer API.

[1231] Input: Business efficiency comparison results, user sentiment data

[1232] Output: Improvement suggestion notification sent to the user

[1233] Specific example: A notification is sent to the accounting department regarding a suggestion for improving the "data entry" process, and the emotional engine sends the suggestion in a softer tone depending on the recipient's emotional state.

[1234] Step 7: Promote interdepartmental collaboration

[1235] server:

[1236] It provides dedicated meeting and collaboration tools for coordinating with other departments and sends notifications to relevant parties. It uses APIs such as Google Calendar API and Zoom API to automatically schedule meetings and generate online meeting links.

[1237] Input: Information on the need for interdepartmental collaboration

[1238] Output: Notification of the schedule and meeting link for the collaborative meeting.

[1239] Specific example: Use the Google Calendar API to schedule meetings for sales and accounting department staff, and then use the Zoom API to generate meeting links and send notifications.

[1240] (Application Example 2)

[1241] 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."

[1242] Conventional factory robot systems have struggled to perform detailed business process analysis to improve operational efficiency and to make optimal suggestions based on the emotional state of workers. Furthermore, the sharing of business processes and the communication of improvement suggestions between departments were often ineffective, resulting in insufficient overall productivity improvements.

[1243] 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 uploading business manuals, means for storing the uploaded business manuals in a database, means for text analysis of the stored business manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the business processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and communication tools for collaboration with other departments and notifying relevant parties, means for analyzing the emotional state of workers using an emotion engine and transmitting notifications and suggestions in the most optimal way, and means for instructing robots to execute each business process. This enables efficient analysis of business manuals and optimization of business processes.

[1244] An "operations manual" is a document that details the work procedures and methods used by each department within an organization.

[1245] "Uploading" refers to the operation of transferring data from a local device to a server on a network.

[1246] A "database" is a structured collection of data designed to efficiently store, search, and manage other data.

[1247] "Text analysis" is the process of analyzing the content of a document using natural language processing technology and extracting specific information.

[1248] "Keywords" are the main words or phrases that summarize the content of a document.

[1249] A "phrase" is a set of words within a document that expresses a specific meaning or context within that document.

[1250] "Grouping" is the process of combining data with similar characteristics or attributes into a single set.

[1251] "Efficiency" is an indicator that shows how effectively the time and effort required for a particular task or process are being used.

[1252] "Comparison" is the process of comparing two or more objects and evaluating their similarities and differences.

[1253] An "improvement suggestion" is a proposal for specific methods or procedures to improve the efficiency of a particular business process.

[1254] "Notification" is the act of conveying specific information or a message to relevant parties.

[1255] A "meeting" is a gathering of stakeholders to discuss and make decisions on a specific topic.

[1256] A "communication tool" is software or a platform designed to efficiently share information and communicate with stakeholders.

[1257] An "emotional engine" is a technology that analyzes the emotional state of workers and uses that information to optimize the content of suggestions and notifications.

[1258] A "robot" is a mechanical device designed to automatically perform specific tasks or operations.

[1259] The system of the present invention is designed to improve operational efficiency within a factory and primarily performs tasks such as analyzing work manuals, proposing efficient work processes, and analyzing the emotional state of workers using an emotion engine. A detailed embodiment of this system is described below.

[1260] The system includes terminals for uploading work manuals, a server for storing the uploaded work manuals in a database, and software for text analysis of the stored work manuals. It also includes a clustering algorithm for grouping similar tasks based on extracted keywords and phrases, an analysis tool for comparing the efficiency of business processes in each department, and a process for notifying departments that are performing inefficient tasks with improvement suggestions.

[1261] Hardware and software to be used

[1262] hardware

[1263] Robot: A mechanical device used to automatically perform tasks within a factory (e.g., ABB IRB 6700).

[1264] Server: A high-performance server for data analysis and storage.

[1265] software

[1266] Natural language processing tools: Software for analyzing the text of business manuals (e.g., SpaCy, NLTK).

[1267] Clustering algorithm: An algorithm for grouping similar tasks based on keywords or phrases (e.g., KMeans clustering).

[1268] Emotion Engine: A deep learning model (e.g., a customized BERT or GPT-3) that analyzes the emotional state of workers and provides optimal suggestions.

[1269] Data processing and data calculation

[1270] The server first receives the user-uploaded work manuals and stores them in a database. Then, it uses a text analysis tool to analyze the content of the work manuals and extract keywords and phrases. Based on the extracted keywords and phrases, it uses a clustering algorithm to group the tasks. Next, it compares the efficiency of each department's work processes based on data (e.g., execution time, frequency of work, error rate) and generates and notifies departments that are performing inefficient tasks with improvement suggestions.

[1271] Furthermore, the system uses an emotion engine to analyze the emotional state of workers and adjust suggestions in the most optimal way. For example, if the server analyzes the average time spent on "parts assembly" in the manufacturing department and determines that the sales department is more efficient, it will propose and notify the manufacturing department of how to improve this. At the same time, if the emotion engine determines that a worker is highly fatigued, it will also send a notification in a gentle tone and suggest additional breaks.

[1272] Examples of prompt statements

[1273] Use the following prompts to have the generating AI model analyze the business manual and suggest improvements:

[1274] Analyze the following work manual and extract keywords:

[1275] Assembly of parts

[1276] quality control

[1277] Data entry

[1278] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[1279] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1280] Step 1:

[1281] Users upload operational manuals for each department via a terminal. Input is in PDF, Word, or Excel format, and output is data transfer to a server. Specifically, users select documents describing work procedures performed within the factory and upload them to the system.

[1282] Step 2:

[1283] The server receives uploaded work manuals and stores them in the database. The input is the data of the work manuals submitted by the user, and the output is the saving of the stored documents to the database. Specifically, the server categorizes the files into appropriate folders and categories and saves them to the database.

[1284] Step 3:

[1285] The server uses natural language processing tools to analyze the stored business manuals and extract keywords and phrases. The input is the text data of the business manuals stored in the database, and the output is a list of extracted keywords and phrases. Specifically, natural language processing technology is used to identify key noun phrases and verb phrases such as "parts assembly" and "quality control."

[1286] Step 4:

[1287] Based on the extracted keywords and phrases, the server uses a clustering algorithm to group similar tasks. The input is a list of keywords and phrases, and the output is the clustering result. Specifically, the KMeans algorithm is applied to group departments with similar tasks into a single cluster.

[1288] Step 5:

[1289] The server compares efficiency based on data related to each department's business processes (e.g., execution time, frequency of work, error rate). The input is efficiency data collected for each department, and the output is the efficiency score for each task. Specifically, it aggregates data from each department and evaluates which department is more efficient.

[1290] Step 6:

[1291] The server generates and sends notifications to departments performing inefficient operations, suggesting more efficient methods. The input is the efficiency evaluation result, and the output is a notification with improvement suggestions. Specifically, it generates and sends notifications to low-efficiency departments encouraging them to adopt methods from high-efficiency departments.

[1292] Step 7:

[1293] The server uses an emotion engine to analyze the worker's emotional state and adjusts suggestions and notifications in the most optimal way. The input is the worker's emotional data, and the output is a notification message that reflects their emotional state. Specifically, it analyzes the worker's stress level and fatigue level and adjusts the tone and content of notifications accordingly.

[1294] Step 8:

[1295] The server instructs the robot to execute each business process. The input consists of improvement suggestions and work instruction data, and the output is the automated work performed by the robot. Specifically, the server instructs the robot to adopt efficient work methods and perform the actual tasks.

[1296] Examples of prompt statements include the following:

[1297] Analyze the following work manual and extract keywords:

[1298] Assembly of parts

[1299] quality control

[1300] Data entry

[1301] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[1302] 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.

[1303] 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.

[1304] 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.

[1305] [Fourth Embodiment]

[1306] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1307] 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.

[1308] 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).

[1309] 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.

[1310] 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.

[1311] 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).

[1312] 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.

[1313] 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.

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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".

[1319] The system of this invention aims to improve internal business efficiency by analyzing the work manuals of each department, extracting similar tasks, and proposing efficient business processes. A specific embodiment of the system is described below.

[1320] Program Processing Overview

[1321] Collection of operational manuals

[1322] Terminal (user):

[1323] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[1324] server:

[1325] The server receives the uploaded work manuals and stores them in the database. During this process, they are categorized into appropriate folders and categories.

[1326] Analysis of business manuals

[1327] server:

[1328] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[1329] Specific example

[1330] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[1331] Extraction of similar tasks

[1332] server:

[1333] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[1334] Specific example

[1335] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[1336] Comparison of efficiency

[1337] server:

[1338] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[1339] Specific example

[1340] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[1341] Notification of improvement suggestions

[1342] server:

[1343] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage them to adopt more efficient methods.

[1344] Specific example

[1345] The server sends a notification to the accounting department suggesting that they adopt the sales department's method for "data entry" tasks.

[1346] Promoting interdepartmental collaboration

[1347] server:

[1348] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[1349] Specific example

[1350] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement ideas.

[1351] This system allows users to easily upload operational manuals, which are then automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. As a result, inter-departmental efficiency improves, and overall organizational performance increases.

[1352] The following describes the processing flow.

[1353] Step 1:

[1354] Terminal (User): Users upload their departmental work manuals from their terminals to the server. Specifically, users open a file selection dialog, select the work manual (PDF, Word, Excel, etc.), and click the upload button.

[1355] Step 2:

[1356] Server: The server receives uploaded work manuals and stores them in the database. The received files are automatically sorted into folders and categorized by department.

[1357] Step 3:

[1358] Server: The server starts the text analysis engine and analyzes the stored business manuals. It uses natural language processing (NLP) tools to break down the text within the document and extract keywords and phrases to identify the business tasks.

[1359] Step 4:

[1360] Server: Based on the extracted keywords and phrases, the server calculates the similarity of the tasks and uses a clustering algorithm to group similar tasks together. For example, manuals with the same tasks, such as "data entry" and "daily reporting," are grouped into a single cluster.

[1361] Step 5:

[1362] Server: The server analyzes metrics related to each department's business processes (e.g., execution time, frequency of work, error rate) and compares the efficiency of operations. This allows it to identify, for example, which department is performing the same task most efficiently.

[1363] Step 6:

[1364] Server: The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include changes to workflows and the adoption of new methods.

[1365] Step 7:

[1366] Server: The server will send notifications to the relevant department's representatives via email or the internal messaging system to inform them of improvement suggestions. The notifications will include specific details of the improvements and suggested efficient methods.

[1367] Step 8:

[1368] Server: The server automates the setup of online meetings and collaboration tools for coordinating with other departments. For example, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[1369] Step 9:

[1370] Terminal (User): Users (each person in charge) check received notifications and meeting invitations, review business processes based on proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall work efficiency.

[1371] Through these steps, the system automatically manages and improves operational manuals efficiently, thereby enhancing the overall performance of the organization.

[1372] (Example 1)

[1373] 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".

[1374] Traditionally, internal operational manuals were created and managed independently by each department, making it difficult to standardize and streamline business processes. Furthermore, duplication of work and lack of coordination between departments led to a decline in overall operational efficiency. Additionally, the lack of a method to identify and improve inefficient processes made it difficult to enhance overall organizational performance.

[1375] 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.

[1376] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in a data set, means for text analysis of the stored business documents using natural language processing and extracting characteristic words and phrases, means for classifying similar tasks based on the extracted characteristic words and phrases, means for evaluating the efficiency of work procedures in each department, means for generating and sending notifications of improvement suggestions to departments performing inefficient work, and means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties. This makes it possible to analyze the work manuals of each department in a unified and automatic manner, propose efficient work processes, and improve the overall operational efficiency of the organization.

[1377] "Business documents" refer to the procedures and guidelines used by each department when carrying out their work, and their format includes file formats such as PDF, Word, and Excel.

[1378] A "data set" refers to an area or database where multiple business documents uploaded to a server are stored.

[1379] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, and is used for text analysis and meaning extraction.

[1380] "Keywords" refer to words and phrases that have important meaning, identified from business documents, and extracted as keywords within the analysis target.

[1381] A "phrase" refers to a segment of the elements that make up a sentence, and is the unit that is analyzed in natural language processing.

[1382] "Similar tasks" refer to tasks that are performed in different departments but share common content and processes.

[1383] "Work procedure efficiency" refers to the degree of efficiency of a task, which is evaluated based on factors such as the time required to perform a particular task, the frequency of the task, and the error rate.

[1384] A "notification of improvement suggestion" refers to a message generated to a department that is performing inefficient tasks, as a suggestion to adopt more efficient methods.

[1385] "Meeting and collaboration tools" refers to online meeting systems and collaboration software used to facilitate inter-departmental communication.

[1386] This invention is a system developed to improve the efficiency of internal business operations, and it automatically collects, analyzes, evaluates, notifies, and links business data. Specific embodiments of the system of this invention will be described below.

[1387] Collection and storage of business documents

[1388] Terminal (user):

[1389] Users upload business documents from their respective departments to the server via their terminals. These documents can be in formats such as PDF, Word, or Excel.

[1390] server:

[1391] The server receives business documents uploaded by users and stores them in a data set. Specifically, it saves the uploaded documents to a database and classifies them into appropriate folders and categories. This classification is based on department name and work content.

[1392] Specific example:

[1393] When a user uploads business documents from the sales department to the server in PDF format, the server receives the file and saves it in the "Sales Department / Business Documents / 2023" folder.

[1394] Analysis of business documents

[1395] server:

[1396] The server retrieves business documents stored in the data set and performs text analysis using natural language processing (NLP) tools. This analysis extracts characteristic words and phrases that identify the business content. For example, using an NLP tool (such as Spacy or NLTK), characteristic words and phrases such as "customer management" and "contract creation" are extracted.

[1397] Specific example:

[1398] The server uses NLP tools to analyze the PDF file and extract keywords such as "customer management" and "contract creation."

[1399] Extraction of similar tasks

[1400] server:

[1401] The server clusters all internal business documents based on the characteristic words extracted through analysis. Here, a clustering algorithm (e.g., K-means clustering) is used to identify groups with similar work content.

[1402] Specific example:

[1403] The server uses the K-means clustering algorithm to group together documents that contain a large number of items related to "customer management" and "contract drafting" into a single cluster.

[1404] Efficiency evaluation of work procedures

[1405] server:

[1406] The server analyzes work procedure data (execution time, frequency, error rate, etc.) in each cluster and evaluates the efficiency of operations, thereby comparing the performance of different departments for the same task.

[1407] Specific example:

[1408] The server evaluates that the sales department takes an average of 10 minutes to complete "data entry," while the accounting department takes 20 minutes, and concludes that the sales department is more efficient.

[1409] Notification of improvement suggestions

[1410] server:

[1411] The server automatically generates improvement suggestions for departments that are performing inefficient tasks, and sends notifications to encourage them to adopt more efficient methods.

[1412] Specific example:

[1413] The server sends an email notification to the accounting department stating, "We propose adopting the sales department's method for data entry."

[1414] Promoting interdepartmental collaboration

[1415] server:

[1416] The server automatically configures online meetings and collaboration tools and sends notifications to relevant parties to facilitate smooth collaboration with other departments. For example, it utilizes the Google Calendar API and the Zoom API.

[1417] Specific example:

[1418] The server uses the Google Calendar API to create online meeting invitation links for sales and accounting departments and sends them via email.

[1419] Example of a prompt

[1420] "Please upload the operational manuals for each department. The server will analyze the manuals, extract similar tasks, and automatically provide suggestions for efficiency improvements."

[1421] This allows users to easily upload business documents, and the server automatically analyzes and compares their efficiency, providing appropriate improvement suggestions for inefficient processes.

[1422] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1423] Step 1: Upload business documents

[1424] Terminal (user):

[1425] Input: Business documents from each department (PDF, Word, Excel format)

[1426] Operation: Users upload work documents from their devices to the server.

[1427] Output: Business documents are transferred to the server.

[1428] Step 2: Receiving and storing business documents

[1429] server:

[1430] Input: User-uploaded business document file

[1431] Operation: The server receives uploaded business documents, analyzes their metadata (file name, department name, file format, etc.), and stores it in the database. It then categorizes them into appropriate folders or categories.

[1432] Output: Business documents stored in the database

[1433] Step 3: Analysis of business documents

[1434] server:

[1435] Input: Business data files stored in the database

[1436] Operation: The server uses natural language processing (NLP) tools to analyze business documents as text and extract key words and phrases. Examples of NLP tools used include Spacy and NLTK.

[1437] Output: List of analyzed feature words and phrases

[1438] Step 4: Extract similar tasks

[1439] server:

[1440] Input: A list of characteristic words and phrases obtained through text analysis.

[1441] Operation: The server uses a clustering algorithm (e.g., K-means clustering) to classify tasks with similar content. Clustering groups similar tasks together.

[1442] Output: List of clustered business groups

[1443] Step 5: Evaluating the efficiency of the work procedure

[1444] server:

[1445] Input: A list of clustered work groups, and work procedure data for each department (execution time, frequency, error rate, etc.)

[1446] Operation: The server analyzes work procedure data in each cluster and evaluates the efficiency of operations. This allows for comparison of the performance of different departments on the same task.

[1447] Output: Efficiency evaluation results of work procedures in each department

[1448] Step 6: Notification of improvement suggestions

[1449] server:

[1450] Input: Efficiency evaluation results

[1451] Operation: The server automatically generates improvement suggestions and sends notifications to departments that are performing inefficient tasks, encouraging them to adopt more efficient methods.

[1452] Output: Notification message for improvement suggestions

[1453] Step 7: Promote interdepartmental collaboration

[1454] server:

[1455] Input: Notification message for improvement suggestions, and contact information of relevant parties.

[1456] Operation: The server automatically configures online meeting and collaboration tools and sends notifications to relevant parties. It utilizes the Google Calendar API and Zoom API.

[1457] Output: Meeting invitation link and notification email

[1458] The above outlines the specific processing steps of this system.

[1459] (Application Example 1)

[1460] 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".

[1461] Improving productivity in modern factories requires optimizing business processes. However, because different departments and production lines use different work manuals, finding effective work procedures is difficult. Furthermore, even for the same task, different work methods are adopted from department to department, leading to a decrease in overall operational efficiency. A system is needed to solve this problem.

[1462] 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.

[1463] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to factory robots based on the analysis results of the work manuals and proposing efficient work methods, and means for recommending efficient work methods using efficiency data for each cluster. This makes it possible for robots used in the factory to analyze different work manuals and propose and apply the optimal work procedure.

[1464] A "work manual" is a document that details work procedures, operating methods, and other related information.

[1465] A "server" is a computer system used for storing, managing, and analyzing data.

[1466] "Text analysis" is the process of extracting meaningful information from document data.

[1467] A "keyword" is an important word that represents the content of a document.

[1468] A "phrase" is a combination of words that have meaning.

[1469] "Grouping" is the process of gathering similar items together into a single group.

[1470] A "business process" refers to a series of activities and procedures necessary to carry out a business task.

[1471] "Efficiency" refers to the degree to which a goal is achieved using a given amount of time and resources.

[1472] A "cluster" is a group classified based on specific common characteristics.

[1473] An "improvement suggestion" refers to specific advice or proposals for making current operations more efficient.

[1474] A "meeting" is a gathering of stakeholders to exchange opinions and engage in discussions.

[1475] "Collaboration tools" are software or tools that allow multiple people to work together.

[1476] A "work procedure" refers to the specific steps and methods for completing a particular task.

[1477] A "factory robot" is a mechanical device that performs tasks automatically within a factory.

[1478] "Efficiency data" refers to specific numerical data used to evaluate the efficiency of business operations.

[1479] In this invention, the server includes means for uploading work manuals, means for storing the uploaded work manuals in a database, means for text analysis of the stored work manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the work processes of each department, means for generating and sending notifications of improvement suggestions to departments that are performing inefficient tasks, means for setting up meetings and collaboration tools for coordinating with other departments and notifying relevant parties, means for applying the optimal work procedure to a factory robot based on the analysis results of the work manuals and proposing an efficient work method, and means for recommending an efficient work method using efficiency data for each cluster.

[1480] Users first upload their departmental operational manuals to the server in formats such as PDF, Word, or Excel. The server stores these manuals in a database and categorizes them into appropriate folders and categories. For example, manufacturing manuals are automatically placed in a "Manufacturing" folder, and sales manuals in a "Sales" folder.

[1481] The server analyzes the stored business manuals using natural language processing (NLP) technology to extract keywords and phrases that identify the business content. For example, keywords such as "product inspection" and "quality control" are extracted from the manufacturing business manual, and "customer management" and "contract creation" are extracted from the sales business manual.

[1482] Next, the server clusters similar tasks based on the extracted keywords. By using a clustering algorithm, if there are common tasks in the manuals for the sales department and the accounting department (e.g., "data entry," "daily reporting"), these tasks will be classified into the same cluster.

[1483] For each cluster, the server analyzes business process data (execution time, frequency of work, error rate, etc.) to evaluate the efficiency of the work. This allows for comparison of the performance of different departments on the same task. For example, if the sales department takes an average of 10 minutes to perform "data entry" and the accounting department takes an average of 20 minutes, the sales department can be identified as more efficient.

[1484] The server automatically generates and notifies departments that are performing inefficient tasks of improvement suggestions to adopt more efficient methods. For example, the server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks.

[1485] Furthermore, it automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, the server sends online meeting invitation links to sales and accounting department personnel to encourage the sharing of improvement methods.

[1486] When this invention's system is applied to a factory robot, the robot generates the optimal work procedure based on the analysis results of the work manual and proposes an efficient work method. Furthermore, it uses efficiency data for each cluster to apply and recommend the most efficient cluster's work procedure. For example, it analyzes manual 1 used in line 1 of factory A, manual 2 used in line 2 of factory A, and manual 3 used in factory B. If the method for line 1 is the most efficient, it recommends applying that method to other lines or factories.

[1487] Example of a prompt:

[1488] "Analyze the work procedure manuals for lines 1 and 2 of Factory A and propose efficient work processes. Each manual is provided in PDF, Word, and Excel formats."

[1489] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1490] Step 1:

[1491] Users upload work manuals. Input is in PDF, Word, or Excel format, and output is a file uploaded to the server. This includes the specific actions taken by the user to send the work manual to the server via their device.

[1492] Step 2:

[1493] The server stores the uploaded work manuals in a database. The input is the uploaded files, and the output is the work manuals stored in the database. This includes specific actions such as classifying the files into appropriate folders and categories.

[1494] Step 3:

[1495] The server analyzes the stored business manuals and extracts keywords and phrases. The input is the business manuals in the database, and the output is the extracted keywords and phrases. This includes specific actions to extract important noun and verb phrases from the documents using natural language processing (NLP) tools (e.g., NLTK).

[1496] Step 4:

[1497] The server groups similar tasks based on extracted keywords and phrases. The input is keywords and phrases, and the output is clustered task groups. This includes the specific operation of grouping similar task content using a clustering algorithm (e.g., KMeans).

[1498] Step 5:

[1499] The server compares the efficiency of business processes in each department. Inputs are clustered business groups and business process data (execution time, frequency, error rate, etc.), and output is the efficiency evaluation result for each cluster. This includes specific actions such as analyzing process data like execution time and error rate to compare efficiency.

[1500] Step 6:

[1501] The server generates and sends improvement suggestion notifications to departments performing inefficient operations. The input is the efficiency evaluation result, and the output is the improvement suggestion notification. The system includes specific actions to automatically generate and send notifications to inefficient departments based on the evaluation results.

[1502] Step 7:

[1503] The server sets up meetings and collaboration tools for coordinating with other departments and notifies relevant parties. Input is improvement suggestion notifications, and output is online meeting invitation links and collaboration tool settings. This includes specific actions such as setting up and notifying meetings using the calendar API and online meeting tools.

[1504] Step 8:

[1505] The server applies the optimal work procedure to the factory robot based on the analysis results of the work manual, proposing an efficient work method. The input is the analysis results and efficiency data, and the output is instructions based on the optimal work procedure. This includes applying the analysis results to the robot's control system and providing specific actions to instruct the robot on the efficient work procedure.

[1506] Step 9:

[1507] The server uses efficiency data for each cluster to recommend efficient work methods. The input is efficiency data for each cluster, and the output is the recommended work method. This includes specific actions to recommend the most efficient work procedure from the most efficient cluster to other departments.

[1508] 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.

[1509] The system of this invention is built to improve the efficiency of internal business operations, and in particular, it analyzes the work manuals of each department, extracts similar tasks, and proposes efficient work processes. Furthermore, by combining it with an emotion engine that recognizes user emotions, notifications and suggestions are conveyed in the most optimal way for the user. A specific embodiment of the system is described below.

[1510] Program Processing Overview

[1511] Collection of operational manuals

[1512] Terminal (user):

[1513] Users upload their departmental work manuals from their terminals to the server. The manuals can be in formats such as PDF, Word, or Excel.

[1514] server:

[1515] The server receives the uploaded work manuals and stores them in the database. During this process, the database is categorized into appropriate folders and categories.

[1516] Analysis of business manuals

[1517] server:

[1518] The server analyzes the stored business manuals and extracts keywords and phrases to identify the business content. For example, it uses natural language processing (NLP) tools to identify noun phrases and verb phrases such as "customer management" and "contract creation."

[1519] Specific example

[1520] Keywords such as "customer management" and "contract creation" are extracted from the sales department's manual, and keywords such as "product inspection" and "quality control" are extracted from the manufacturing department's manual. This clarifies the work content of each department.

[1521] Extraction of similar tasks

[1522] server:

[1523] Based on the extracted keywords, similar tasks are clustered from the company's overall business manuals. A clustering algorithm is used to identify groups of tasks with similar content.

[1524] Specific example

[1525] If the sales and accounting departments have common tasks such as "data entry" and "daily reporting" in their manuals, the server will classify these tasks into the same cluster.

[1526] Comparison of efficiency

[1527] server:

[1528] We analyze business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. This allows us to compare the performance of different departments on the same task.

[1529] Specific example

[1530] The server evaluates that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes an average of 20 minutes, and identifies the sales department as being more efficient.

[1531] Notification of improvement suggestions

[1532] server:

[1533] For departments performing inefficient tasks, the system automatically generates improvement suggestions and sends notifications to encourage the adoption of more efficient methods. This process incorporates an emotion engine that adjusts based on the user's emotional state.

[1534] Specific example

[1535] The server sends a notification to the accounting department suggesting that they adopt the sales department's methods for "data entry" tasks. At this time, the emotion engine analyzes the emotional state of the accounting department staff and adjusts the content and tone of the suggestion.

[1536] Promoting interdepartmental collaboration

[1537] server:

[1538] It automatically sets up online meetings and collaboration tools for coordinating with other departments and notifies relevant parties. For example, it sets up meetings using calendar APIs and online meeting tools.

[1539] Specific example

[1540] The server sends online meeting invitation links to sales and accounting departments, encouraging them to share improvement methods. This notification, too, is delivered at the optimal time and in the right tone, thanks to the emotion engine.

[1541] This system allows users to easily upload operational manuals, which are automatically analyzed and compared for efficiency on the server side, providing appropriate improvement suggestions for inefficient processes. Furthermore, the introduction of an emotional engine ensures that notifications and suggestions are communicated in the most effective way for the user. As a result, interdepartmental efficiency improves, and overall organizational performance significantly improves.

[1542] The following describes the processing flow.

[1543] Step 1:

[1544] Terminal (user):

[1545] Users upload their departmental work manuals from their terminals to the server. First, users access the web interface that provides the upload function and open the file selection dialog. Next, they select the work manual file (PDF, Word, Excel, etc.) and click the upload button. This sends the file to the server.

[1546] Step 2:

[1547] server:

[1548] The server receives the uploaded business manuals and stores them in the database. It analyzes the received data and organizes it into appropriate folders and categories. For example, files for the sales department are stored in the "Sales Department" folder, and files for the accounting department are stored in the "Accounting Department" folder.

[1549] Step 3:

[1550] server:

[1551] The server activates a text analysis engine and analyzes the contents of the stored business manuals. Using natural language processing (NLP) techniques, it extracts keywords and phrases from each manual. For example, business-related keywords such as "customer management," "contract creation," "product inspection," and "quality control" are identified.

[1552] Step 4:

[1553] server:

[1554] The server calculates the similarity of the work content based on the extracted keywords and phrases, and uses a clustering algorithm to group similar tasks together. For example, manuals with common tasks such as "data entry" and "daily reporting" can be grouped into a single cluster.

[1555] Step 5:

[1556] server:

[1557] The server analyzes business process data from each department (e.g., execution time, frequency of work, error rate) to evaluate the efficiency of operations. It compares the performance of different departments on the same task to identify which department is the most efficient.

[1558] Step 6:

[1559] server:

[1560] The server displays efficient and inefficient business processes side-by-side and automatically generates improvement suggestions for departments performing inefficient tasks. These suggestions include specific methods and examples, recommending changes to workflows or the introduction of new methods.

[1561] Step 7:

[1562] server:

[1563] The server activates an emotion engine, which adjusts notification content to match the user's emotional state. For example, if the user is stressed, the emotion engine will create a notification in a softer tone. This makes the suggestion more likely to be accepted.

[1564] Step 8:

[1565] server:

[1566] The server will send notifications to the relevant departments via email or the company's internal messaging system to inform them of improvement suggestions. These notifications will include specific details of the improvements and suggested efficient methods.

[1567] Step 9:

[1568] server:

[1569] The server automates the setup of online meetings and collaboration tools for coordinating with other departments. Specifically, it uses the Calendar API to generate meeting schedules and sends meeting invitations to relevant departments.

[1570] Step 10:

[1571] Terminal (user):

[1572] Users (each person in charge) review received notifications and meeting invitations, revise their business processes based on the proposed improvement methods, and make necessary adjustments. This facilitates smoother collaboration between departments and improves overall operational efficiency.

[1573] (Example 2)

[1574] 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".

[1575] In modern companies, numerous departments often operate according to different operational manuals, leading to duplication of tasks and inefficiencies. Furthermore, inadequate evaluation of operational efficiency and notification of improvement suggestions, along with a lack of inter-departmental collaboration, can result in overall decreased operational efficiency and negatively impact the company's overall performance.

[1576] 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.

[1577] In this invention, the server includes means for uploading business documents, means for storing the uploaded business documents in data storage, means for text analysis of the stored business documents and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of business processes in each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and collaboration tools for cooperation with other departments and notifying relevant parties, and means for analyzing the emotional state of users and optimizing the content and tone of notifications. This enables improved operational efficiency within the company and strengthened collaboration between departments.

[1578] "Business documents" refer to documents that describe business procedures and work content used within a company or organization. They come in formats such as PDF, Word, and Excel.

[1579] "Means for uploading" refers to the methods or means by which users send business documents to a server. This is usually done via a web interface or a dedicated application.

[1580] "Means of storing data in data storage" refers to databases and file systems used by servers to store business documents they receive. This ensures that documents are properly managed and saved.

[1581] "Text analysis" refers to technologies and methods for automatically reading the content of business documents and extracting specific keywords or phrases.

[1582] "Keywords and phrases" refer to words or phrases that summarize information within business documents and indicate important business content.

[1583] "Methods for grouping similar tasks" refer to algorithms and methods for classifying tasks that are similar in content, based on extracted keywords or phrases.

[1584] "Means of comparing efficiency" refers to methods for evaluating the business processes of each department and comparing their efficiency or inefficiency. This includes indicators such as execution time and error rate.

[1585] "Means for generating and sending improvement suggestion notifications" refers to technologies and methods that automatically generate suggestions for efficiency improvements to departments performing inefficient operations and notify them in an appropriate manner.

[1586] "Means for setting up meetings and collaboration tools for coordination" refers to technologies and methods for automatically setting up meetings and online collaboration tools necessary for effective coordination with other departments.

[1587] "Means for analyzing a user's emotional state" refers to technologies that determine a user's emotional state and provide appropriate feedback or notifications. For example, this may involve analyzing speech or text.

[1588] "Methods for optimizing notification content and tone" refer to technologies that optimize the content and tone of notification messages according to the user's emotional state, making them more acceptable.

[1589] Modes for carrying out the invention

[1590] This invention is a system that analyzes business documents and proposes efficient business processes in order to improve the efficiency of internal operations. This system is implemented through the following main steps.

[1591] Collection of business documents

[1592] Terminal (user):

[1593] Users upload their departmental work documents from their terminals to the server. Documents can be in formats such as PDF, Word, and Excel.

[1594] server:

[1595] The server receives uploaded business documents and stores them in data storage. At this time, they are classified into appropriate folders and categories according to their file format. Specifically, PDF files are stored in the PDF folder, and Word files are stored in the Word folder.

[1596] Analysis of business documents

[1597] server:

[1598] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. Keywords and phrases are then extracted from the converted text data using natural language processing (NLP) tools. Specifically, SpaCy is used as the NLP tool to analyze noun and verb phrases that frequently occur in specific contexts.

[1599] Extraction of similar tasks

[1600] server:

[1601] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). Similar processes are grouped together, and related information is compiled for each cluster. K-means clustering vectorizes keywords and calculates Euclidean distances to form clusters.

[1602] Collection and analysis of business process data

[1603] server:

[1604] Daily business process data (execution time, frequency of work, error rate, etc.) is collected regularly from each department and stored in data storage. By analyzing this data, the efficiency of operations and the performance of each department are evaluated. For example, the Pandas library in Python is used to manipulate data frames and calculate various statistics.

[1605] Generation and notification of improvement suggestions

[1606] server:

[1607] For inefficient departments, the system automatically generates improvement suggestions and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions based on the user's emotional state. Emotion analysis uses tools such as IBM Watson's Tone Analyzer API.

[1608] Promoting interdepartmental collaboration

[1609] server:

[1610] To set up meetings and collaboration tools for coordinating with other departments and notify relevant parties, we use APIs such as Google Calendar API and Zoom API. The server automatically schedules meetings, generates online meeting links, and sends notifications.

[1611] Hardware and software used

[1612] Hardware: Servers, terminals (PCs, tablets, smartphones, etc.)

[1613] software:

[1614] Natural language processing tools (e.g., SpaCy)

[1615] Database Management System

[1616] Emotion engine (e.g., IBM Watson Tone Analyzer API)

[1617] Calendar API (e.g., Google Calendar API)

[1618] Online meeting tools (e.g., Zoom API)

[1619] Data analysis libraries (e.g., Pandas in Python)

[1620] Specific example

[1621] Documents from both the sales and accounting departments contain common tasks such as "customer management" and "data entry." The server analyzes these keywords and compares the business processes of the two departments. For example, it might determine that the sales department can complete "data entry" in 10 minutes, while the accounting department takes 20 minutes. Based on this data, the server sends a notification to the accounting department suggesting more efficient methods from the sales department. This notification is sent with content and tone that takes the recipient's feelings into consideration.

[1622] Example of a prompt

[1623] "Analyze the business documents of the sales and accounting departments, extract common tasks, and cluster them. Also, design a system to identify efficient business processes and notify inefficient departments with improvement suggestions. Use an emotion engine for notifications, adjusting the tone based on the recipient's emotional state."

[1624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1625] The processing flow of this system's program

[1626] Step 1: Collect business documents

[1627] Terminal (user):

[1628] Users upload business documents (PDF, Word, Excel format) from their respective departments to the server from their terminal. When a user selects a file and presses the upload button, the terminal sends the file to the server via an HTTP POST request.

[1629] server:

[1630] The server receives uploaded business documents and saves them to data storage. They are automatically sorted into appropriate folders and categories based on their file format. For example, it checks the MIME type and stores PDF files in a PDF folder and Word files in a Word folder.

[1631] Input: Uploaded business document file

[1632] Output: Files saved in data storage

[1633] Step 2: Text analysis of business documents

[1634] server:

[1635] The server uses libraries such as PDF parsers and Word file parsers to convert stored business documents into text format. This extracts the text data from each file. For example, it uses the Python PyPDF2 library to extract text from PDFs and the python-docx library to extract text from Word files. Furthermore, it uses natural language processing (NLP) tools to extract keywords and phrases from the extracted text data.

[1636] Input: Business document files stored in data storage

[1637] Output: Extracted text data, identified keywords and phrases

[1638] Step 3: Clustering similar tasks

[1639] server:

[1640] The server uses the extracted keywords to classify internal business processes based on a clustering algorithm (e.g., K-means). The keywords are vectorized, and Euclidean distances are calculated to form clusters. This groups together highly similar business processes.

[1641] Input: Extracted keywords or phrases

[1642] Output: Tasks categorized by cluster

[1643] Specific example: Run a Python script that implements K-means clustering and divide keywords such as "customer management" and "data entry" into clusters.

[1644] Step 4: Collect business process data

[1645] server:

[1646] Data on daily work processes (execution time, frequency of work, error rate, etc.) is collected regularly from each department. This data is automatically retrieved from the business management system and log data and stored in data storage.

[1647] Input: Business process data for each department

[1648] Output: Business process data stored in data storage

[1649] Specific example: Retrieve data in JSON format from a business management system API and store it in a database.

[1650] Step 5: Comparing the efficiency of business processes

[1651] server:

[1652] The server analyzes collected business process data and compares operational efficiency within each cluster. Specifically, it performs statistical analysis on various metrics (e.g., average execution time, error rate, etc.) to identify efficient and inefficient departments. For example, it uses the Python Pandas library to manipulate dataframes and calculate various statistics.

[1653] Input: Saved business process data

[1654] Output: Comparison results of operational efficiency within each cluster

[1655] Specific example: By manipulating data frames, statistical data is analyzed to identify that the sales department takes an average of 10 minutes to perform "data entry," while the accounting department takes 20 minutes.

[1656] Step 6: Generate and notify improvement suggestions

[1657] server:

[1658] The server automatically generates improvement suggestions for departments with low operational efficiency, encouraging them to learn from the methods of more efficient departments, and sends notifications. This process incorporates an emotion engine that adjusts the content and tone of the suggestions according to the user's emotional state. For emotion analysis, it uses, for example, IBM Watson's Tone Analyzer API.

[1659] Input: Business efficiency comparison results, user sentiment data

[1660] Output: Improvement suggestion notification sent to the user

[1661] Specific example: A notification is sent to the accounting department regarding a suggestion for improving the "data entry" process, and the emotional engine sends the suggestion in a softer tone depending on the recipient's emotional state.

[1662] Step 7: Promote interdepartmental collaboration

[1663] server:

[1664] It provides dedicated meeting and collaboration tools for coordinating with other departments and sends notifications to relevant parties. It uses APIs such as Google Calendar API and Zoom API to automatically schedule meetings and generate online meeting links.

[1665] Input: Information on the need for interdepartmental collaboration

[1666] Output: Notification of the schedule and meeting link for the collaborative meeting.

[1667] Specific example: Use the Google Calendar API to schedule meetings for sales and accounting department staff, and then use the Zoom API to generate meeting links and send notifications.

[1668] (Application Example 2)

[1669] 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".

[1670] Conventional factory robot systems have struggled to perform detailed business process analysis to improve operational efficiency and to make optimal suggestions based on the emotional state of workers. Furthermore, the sharing of business processes and the communication of improvement suggestions between departments were often ineffective, resulting in insufficient overall productivity improvements.

[1671] 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 uploading business manuals, means for storing the uploaded business manuals in a database, means for text analysis of the stored business manuals and extracting keywords and phrases, means for grouping similar tasks based on the extracted keywords and phrases, means for comparing the efficiency of the business processes of each department, means for generating and sending improvement suggestion notifications to departments performing inefficient tasks, means for setting up meetings and communication tools for collaboration with other departments and notifying relevant parties, means for analyzing the emotional state of workers using an emotion engine and transmitting notifications and suggestions in the most optimal way, and means for instructing robots to execute each business process. This enables efficient analysis of business manuals and optimization of business processes.

[1672] An "operations manual" is a document that details the work procedures and methods used by each department within an organization.

[1673] "Uploading" refers to the operation of transferring data from a local device to a server on a network.

[1674] A "database" is a structured collection of data designed to efficiently store, search, and manage other data.

[1675] "Text analysis" is the process of analyzing the content of a document using natural language processing technology and extracting specific information.

[1676] "Keywords" are the main words or phrases that summarize the content of a document.

[1677] A "phrase" is a set of words within a document that expresses a specific meaning or context within that document.

[1678] "Grouping" is the process of combining data with similar characteristics or attributes into a single set.

[1679] "Efficiency" is an indicator that shows how effectively the time and effort required for a particular task or process are being used.

[1680] "Comparison" is the process of comparing two or more objects and evaluating their similarities and differences.

[1681] An "improvement suggestion" is a proposal for specific methods or procedures to improve the efficiency of a particular business process.

[1682] "Notification" is the act of conveying specific information or a message to relevant parties.

[1683] A "meeting" is a gathering of stakeholders to discuss and make decisions on a specific topic.

[1684] A "communication tool" is software or a platform designed to efficiently share information and communicate with stakeholders.

[1685] An "emotional engine" is a technology that analyzes the emotional state of workers and uses that information to optimize the content of suggestions and notifications.

[1686] A "robot" is a mechanical device designed to automatically perform specific tasks or operations.

[1687] The system of the present invention is designed to improve operational efficiency within a factory and primarily performs tasks such as analyzing work manuals, proposing efficient work processes, and analyzing the emotional state of workers using an emotion engine. A detailed embodiment of this system is described below.

[1688] The system includes terminals for uploading work manuals, a server for storing the uploaded work manuals in a database, and software for text analysis of the stored work manuals. It also includes a clustering algorithm for grouping similar tasks based on extracted keywords and phrases, an analysis tool for comparing the efficiency of business processes in each department, and a process for notifying departments that are performing inefficient tasks with improvement suggestions.

[1689] Hardware and software to be used

[1690] hardware

[1691] Robot: A mechanical device used to automatically perform tasks within a factory (e.g., ABB IRB 6700).

[1692] Server: A high-performance server for data analysis and storage.

[1693] software

[1694] Natural language processing tools: Software for analyzing the text of business manuals (e.g., SpaCy, NLTK).

[1695] Clustering algorithm: An algorithm for grouping similar tasks based on keywords or phrases (e.g., KMeans clustering).

[1696] Emotion Engine: A deep learning model (e.g., a customized BERT or GPT-3) that analyzes the emotional state of workers and provides optimal suggestions.

[1697] Data processing and data calculation

[1698] The server first receives the user-uploaded work manuals and stores them in a database. Then, it uses a text analysis tool to analyze the content of the work manuals and extract keywords and phrases. Based on the extracted keywords and phrases, it uses a clustering algorithm to group the tasks. Next, it compares the efficiency of each department's work processes based on data (e.g., execution time, frequency of work, error rate) and generates and notifies departments that are performing inefficient tasks with improvement suggestions.

[1699] Furthermore, the system uses an emotion engine to analyze the emotional state of workers and adjust suggestions in the most optimal way. For example, if the server analyzes the average time spent on "parts assembly" in the manufacturing department and determines that the sales department is more efficient, it will propose and notify the manufacturing department of how to improve this. At the same time, if the emotion engine determines that a worker is highly fatigued, it will also send a notification in a gentle tone and suggest additional breaks.

[1700] Examples of prompt statements

[1701] Use the following prompts to have the generating AI model analyze the business manual and suggest improvements:

[1702] Analyze the following work manual and extract keywords:

[1703] Assembly of parts

[1704] quality control

[1705] Data entry

[1706] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[1707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1708] Step 1:

[1709] Users upload operational manuals for each department via a terminal. Input is in PDF, Word, or Excel format, and output is data transfer to a server. Specifically, users select documents describing work procedures performed within the factory and upload them to the system.

[1710] Step 2:

[1711] The server receives uploaded work manuals and stores them in the database. The input is the data of the work manuals submitted by the user, and the output is the saving of the stored documents to the database. Specifically, the server categorizes the files into appropriate folders and categories and saves them to the database.

[1712] Step 3:

[1713] The server uses natural language processing tools to analyze the stored business manuals and extract keywords and phrases. The input is the text data of the business manuals stored in the database, and the output is a list of extracted keywords and phrases. Specifically, natural language processing technology is used to identify key noun phrases and verb phrases such as "parts assembly" and "quality control."

[1714] Step 4:

[1715] Based on the extracted keywords and phrases, the server uses a clustering algorithm to group similar tasks. The input is a list of keywords and phrases, and the output is the clustering result. Specifically, the KMeans algorithm is applied to group departments with similar tasks into a single cluster.

[1716] Step 5:

[1717] The server compares efficiency based on data related to each department's business processes (e.g., execution time, frequency of work, error rate). The input is efficiency data collected for each department, and the output is the efficiency score for each task. Specifically, it aggregates data from each department and evaluates which department is more efficient.

[1718] Step 6:

[1719] The server generates and sends notifications to departments performing inefficient operations, suggesting more efficient methods. The input is the efficiency evaluation result, and the output is a notification with improvement suggestions. Specifically, it generates and sends notifications to low-efficiency departments encouraging them to adopt methods from high-efficiency departments.

[1720] Step 7:

[1721] The server uses an emotion engine to analyze the worker's emotional state and adjusts suggestions and notifications in the most optimal way. The input is the worker's emotional data, and the output is a notification message that reflects their emotional state. Specifically, it analyzes the worker's stress level and fatigue level and adjusts the tone and content of notifications accordingly.

[1722] Step 8:

[1723] The server instructs the robot to execute each business process. The input consists of improvement suggestions and work instruction data, and the output is the automated work performed by the robot. Specifically, the server instructs the robot to adopt efficient work methods and perform the actual tasks.

[1724] Examples of prompt statements include the following:

[1725] Analyze the following work manual and extract keywords:

[1726] Assembly of parts

[1727] quality control

[1728] Data entry

[1729] Next, compare efficiencies and propose improvements. Finally, generate notification messages based on the worker's emotional state.

[1730] 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.

[1731] 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.

[1732] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] 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."

[1739] 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.

[1740] 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.

[1741] 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.

[1742] 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.

[1743] 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.

[1744] 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.

[1745] 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.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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 to be incorporated by reference.

[1751] The following is further disclosed regarding the embodiments described above.

[1752] (Claim 1)

[1753] A means of uploading the work manual,

[1754] A means of storing uploaded work manuals in a database,

[1755] A method for analyzing stored business manuals and extracting keywords and phrases,

[1756] A method for grouping similar tasks based on extracted keywords and phrases,

[1757] A means of comparing the efficiency of business processes in each department,

[1758] A means of generating and sending improvement suggestion notifications to departments that are performing inefficient work,

[1759] A system that includes setting up meetings and collaboration tools for coordinating with other departments, and a means of notifying relevant parties.

[1760] (Claim 2)

[1761] The system according to claim 1, which analyzes business manuals using natural language processing technology and extracts keywords and phrases.

[1762] (Claim 3)

[1763] The system according to claim 1, which identifies efficient and inefficient processes based on data related to the business processes of each department.

[1764] "Example 1"

[1765] (Claim 1)

[1766] A means of uploading business documents,

[1767] A means of storing uploaded business documents in a data set,

[1768] A method for analyzing stored business documents using natural language processing to extract characteristic words and phrases,

[1769] A means of classifying similar tasks based on extracted characteristic words and phrases,

[1770] A means of evaluating the efficiency of work procedures in each department,

[1771] A means of generating and sending improvement suggestion notifications to departments that are performing inefficient work,

[1772] A system that includes setting up meetings and collaboration tools for coordinating with other departments, and a means of notifying relevant parties.

[1773] (Claim 2)

[1774] The system according to claim 1, which analyzes business documents using natural language processing technology and extracts characteristic words and phrases.

[1775] (Claim 3)

[1776] The system according to claim 1, which identifies efficient and inefficient procedures based on information regarding the work procedures of each department.

[1777] "Application Example 1"

[1778] (Claim 1)

[1779] A means of uploading the work manual,

[1780] A means of storing uploaded work manuals in a database,

[1781] A method for analyzing stored business manuals and extracting keywords and phrases,

[1782] A method for grouping similar tasks based on extracted keywords and phrases,

[1783] A means of comparing the efficiency of business processes in each department,

[1784] A means of generating and sending improvement suggestion notifications to departments that are performing inefficient work,

[1785] Setting up meetings and collaboration tools to coordinate with other departments, and a means of notifying relevant parties,

[1786] A means of applying optimal work procedures to factory robots based on the analysis results of work manuals and proposing efficient work methods,

[1787] A system that includes means for recommending efficient work methods using efficiency data for each cluster.

[1788] (Claim 2)

[1789] The system according to claim 1, which analyzes business manuals using natural language processing technology and extracts keywords and phrases.

[1790] (Claim 3)

[1791] The system according to claim 1, which identifies efficient and inefficient clusters based on efficiency data for each cluster.

[1792] "Example 2 of combining an emotion engine"

[1793] (Claim 1)

[1794] Methods for uploading business documents,

[1795] A means of storing uploaded business documents in data storage,

[1796] A method for analyzing stored business documents and extracting keywords and phrases,

[1797] A method for grouping similar tasks based on extracted keywords and phrases,

[1798] A means of comparing the efficiency of business processes in each department,

[1799] A means of generating and sending improvement suggestion notifications to departments that are performing inefficient operations,

[1800] Setting up meetings and collaboration tools to coordinate with other departments, and a means of notifying relevant parties,

[1801] A system that includes means for analyzing the user's emotional state and optimizing the content and tone of notifications.

[1802] (Claim 2)

[1803] The system according to claim 1, which analyzes business documents using natural language processing technology and extracts keywords and phrases.

[1804] (Claim 3)

[1805] The system according to claim 1, which identifies efficient and inefficient processes based on data related to the business processes of each department.

[1806] "Application example 2 of combining emotional engines"

[1807] (Claim 1)

[1808] A means of uploading the work manual,

[1809] A means of storing uploaded work manuals in a database,

[1810] A method for analyzing stored business manuals and extracting keywords and phrases,

[1811] A method for grouping similar tasks based on extracted keywords and phrases,

[1812] A means of comparing the efficiency of business processes in each department,

[1813] A means of generating and sending improvement suggestion notifications to departments that are performing inefficient operations,

[1814] Setting up meetings and communication tools to collaborate with other departments, and a means of notifying relevant parties,

[1815] A means of analyzing the emotional state of workers using an emotion engine and communicating notifications and suggestions in the most optimal way,

[1816] A system that includes means for instructing a robot to execute each business process.

[1817] (Claim 2)

[1818] The system according to claim 1, which analyzes business manuals using natural language processing technology and clustering algorithms, extracts keywords and phrases, and groups business processes.

[1819] (Claim 3)

[1820] The system according to claim 1, which identifies efficient and inefficient processes based on data related to the business processes of each department and adjusts the proposed content using an emotion engine. [Explanation of symbols]

[1821] 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. A means of uploading the work manual, A means of storing uploaded work manuals in a database, A method for analyzing stored business manuals and extracting keywords and phrases, A method for grouping similar tasks based on extracted keywords and phrases, A means of comparing the efficiency of business processes in each department, A means of generating and sending improvement suggestion notifications to departments that are performing inefficient work, A system that includes setting up meetings and collaboration tools for coordinating with other departments, and a means of notifying relevant parties.

2. The system according to claim 1, which analyzes business manuals using natural language processing technology and extracts keywords and phrases.

3. The system according to claim 1, which identifies efficient and inefficient processes based on data related to the business processes of each department.

Images