system

Abstract

We provide the system. [Solution] A means of saving the knowledge acquired during the progress of a project to a database, A method for generating advice for new project managers using knowledge, A means of providing the generated advice to the user's terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional business process, a person newly in charge of a case may not be able to effectively utilize past knowledge and information, and similar problems may occur repeatedly. Also, due to the lack of sharing of tacit rules and important points, the progress of the business may not be smooth. As a result, there are problems of reduced business efficiency and quality variations.

Means for Solving the Problems

[0005] This invention provides a system for storing implicit rules and operational knowledge acquired during the progress of a project in a database. This system includes means for generating advice for new project managers using the acquired knowledge, and means for providing the generated advice to the user's terminal. This allows new project managers to effectively utilize past knowledge and improve work efficiency and quality. Furthermore, the knowledge is organized by project and searchable based on the project ID, enabling quick retrieval of necessary information.

[0006] A "project" is a collection of tasks or work related to the progress and management of a specific business or project.

[0007] "Knowledge" refers to insights gained during the course of work, implicit rules, success principles, and information obtained through feedback.

[0008] A "database" is an electronic record system for systematically storing knowledge and other information, making it efficiently searchable and available for use.

[0009] A "new project manager" refers to an individual or team that has been assigned to a specific project for the first time and is responsible for managing and executing its tasks.

[0010] "Advice" refers to instructions and suggestions generated based on knowledge, serving as guidance for new project managers to efficiently carry out their tasks.

[0011] A "terminal" is an electronic device used by a user to access a system and obtain advice and knowledge.

[0012] "Means" refers to a process, method, or tool designed to achieve a specific objective.

[0013] A "Project ID" is an identification number or code assigned to uniquely identify each project.

[0014] "Searching" is the act of finding specific information from stored data and knowledge. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[0037] Knowledge base initialization

[0038] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes. This database includes implicit rules and important considerations associated with each project ID.

[0039] Adding Knowledge

[0040] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[0041] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[0042] Initialization of the advice generator

[0043] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[0044] Generating advice

[0045] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0046] Providing advice

[0047] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[0048] Points to note:

[0049] We value regular communication with our customers.

[0050] Thoroughly implement version control for documents.

[0051] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[0052] Specific example

[0053] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[0054] Points to note:

[0055] We value regular communication with our customers.

[0056] Thoroughly implement version control for documents.

[0057] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[0058] The following describes the processing flow.

[0059] Step 1:

[0060] The server initializes the knowledge base. This is done by creating an instance of the KnowledgeBase class. Specifically, the __init__ method is called, and an empty data dictionary self.data is initialized.

[0061] Step 2:

[0062] Users input knowledge gained during their work and send it to the server. For example, for project ID 1, they might input the entry "Value regular communication with customers."

[0063] Step 3:

[0064] The server saves the submitted knowledge to the database. Specifically, the add_entry method is called, and project ID 1 and the entry are added to self.data.

[0065] Step 4:

[0066] The server initializes the advice generator. This is done by creating an instance of the AdviceGenerator class and passing the knowledge base as an argument. Specifically, the __init__ method is called, and the knowledge base is stored in the instance variable self.knowledge_base.

[0067] Step 5:

[0068] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[0069] Step 6:

[0070] The server generates advice based on the project ID through the `generate_advice` method. Specifically, the `get_entries` method is called to retrieve entries related to project ID 1. Then, advice statements are generated based on the retrieved entries.

[0071] Step 7:

[0072] The device provides the generated advice to the user. Specifically, the advice text is displayed on the user's device. For example, the following advice may be presented:

[0073] Points to note:

[0074] We value regular communication with our customers.

[0075] Thoroughly implement version control for documents.

[0076] Step 8:

[0077] Users will use this advice to guide their work. This will lead to smoother project progress and prevent past problems from occurring.

[0078] (Example 1)

[0079] 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."

[0080] Traditional advice systems fail to effectively utilize knowledge gained from past projects, potentially leading new project managers to repeat past mistakes and pitfalls. Furthermore, a lack of systematic methods for storing and retrieving knowledge makes it difficult to provide necessary information quickly.

[0081] 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.

[0082] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for users to input and transmit knowledge obtained during the progress of their work to the server, means for the server to store project-related knowledge in a database, means for the server to initialize a generation AI model in order to generate advice using the stored knowledge, means for a terminal to generate advice based on the project ID when a new case manager requests advice, and means for providing the generated advice to the user's terminal. This makes it possible to effectively store and retrieve knowledge and to quickly provide appropriate advice.

[0083] A "project" refers to an ongoing project or a portion of a business activity, each with its own unique identifier.

[0084] "Knowledge" refers to information such as insights, experience, unwritten rules, and points to note that are gained during the course of work.

[0085] A "database" refers to a system that systematically stores information and facilitates searching and management.

[0086] A "server" refers to a computer system that manages and runs databases and advice generators.

[0087] A "user" refers to an entity that uses the system to input knowledge and receive advice.

[0088] "Terminal" refers to a device or interface that a user accesses.

[0089] An "advice generator" refers to a tool or algorithm that generates advice relevant to a specific project based on stored knowledge.

[0090] A "generative AI model" refers to a system that uses artificial intelligence technologies, such as large-scale language models, to generate text and extract knowledge.

[0091] "Project ID" refers to an identifier used to uniquely identify each project.

[0092] A "prompt" refers to an instruction or question that is input to a generative AI model.

[0093] "Initialization" refers to setting a system or tool to a usable state.

[0094] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[0095] Knowledge base initialization

[0096] The server first initializes the knowledge base. This knowledge base is a database for systematically storing knowledge acquired during business processes. Specifically, the server uses database software (e.g., MySQL®) to generate the necessary tables. The tables include a project ID to uniquely identify each project and columns for storing knowledge entries.

[0097] Adding Knowledge

[0098] Users input knowledge gained during their work into the system from their terminal. For example, they might add the knowledge "Value regular communication with customers" to "Project ID 1". The terminal sends this input data to the server via API, and the server saves the received data to a database. SQL queries are used for this saving process.

[0099] Initialization of the advice generator

[0100] The server initializes a generative AI model (e.g., a GPT model) for generating advice. This involves loading the model file and setting the configuration to apply. For example, the model might be loaded using a Python library.

[0101] Generating and providing advice

[0102] When a user takes on a new project, they request advice on a specific project from their terminal. This request is sent to the server, which, upon receiving the request, retrieves knowledge related to the specified project ID from its database. Using the retrieved knowledge, a generation AI model generates prompts, and an advice generator then generates specific advice based on that knowledge.

[0103] The generated advice is provided to the user via the terminal. This allows the user to obtain the knowledge necessary for their work in real time, contributing to improved work efficiency and quality. Examples of specific prompt messages are as follows:

[0104] Generate advice for Project ID 1. Extract relevant information from previously entered knowledge base entries and create an advice statement based on that information.

[0105] Specific example

[0106] For example, suppose a user has been newly assigned to "Project ID 1". This user will receive the following advice based on a knowledge base gained from past projects:

[0107] Points to note:

[0108] We value regular communication with our customers.

[0109] Thoroughly implement version control for documents.

[0110] This advice helps support the smooth progress of the project and prevents past problems from occurring. By using the advice received as a guide, users can achieve higher work efficiency.

[0111] The above describes embodiments for carrying out the present invention.

[0112] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0113] Step 1: Knowledge Base Initialization

[0114] The server initializes the knowledge base when the system starts up. Specifically, it uses database software (e.g., MySQL) to create the necessary tables. These tables include columns such as project ID, knowledge entry, and timestamp. The server establishes a connection to the database and executes an SQL query like the following: CREATE TABLE IF NOT EXISTS knowledge_entries (entry_id INT AUTO_INCREMENT PRIMARY KEY, project_id INT, knowledge_text TEXT, timestamp DATETIME);

[0115] Input: None

[0116] Output: Initialized database

[0117] Step 2: Enter and submit knowledge

[0118] Users input knowledge gained during their work into the system from their terminal. For example, they might input the knowledge "Value regular communication with customers" for "Project ID 1." The terminal then sends this input data to the server via an API.

[0119] Input: Knowledge information entered by the user into the terminal.

[0120] Output: Knowledge data sent to the server

[0121] Step 3: Knowledge Preservation

[0122] The server receives the submitted knowledge data and stores it in the database. Specifically, it generates and executes the SQL query: INSERT INTO knowledge_entries (project_id, knowledge_text, timestamp) VALUES (1, 'We value regular communication with our customers', NOW()); This stores the knowledge in the database.

[0123] Input: Knowledge data received from the API

[0124] Output: Knowledge entries stored in the database

[0125] Step 4: Initialize the advice generator

[0126] The server initializes a generative AI model (e.g., a GPT model) to generate advice. This involves loading the model file and performing the necessary configuration. For example, it loads the model using Python libraries. It then executes the code `from transformers import GPT2LMHeadModel, GPT2Tokenizer` to initialize the model and tokenizer.

[0127] Input: Model file and configuration information

[0128] Output: Initialized Generative AI Model

[0129] Step 5: Receiving a request for advice

[0130] The user requests advice on a specific project through their device. For example, they might request, "Please give me advice on Project ID 1." The device then sends this request data to the server via the API.

[0131] Input: User advice request data

[0132] Output: Request data sent to the server

[0133] Step 6: Knowledge Search

[0134] After receiving the request data, the server searches the database for knowledge related to the specified project ID. For example, it executes an SQL query such as SELECT knowledge_text FROM knowledge_entries WHERE project_id = 1; to retrieve the relevant knowledge.

[0135] Input: Request data based on Project ID

[0136] Output: Acquired knowledge data

[0137] Step 7: Generating Advice

[0138] The server generates prompts based on the acquired knowledge and inputs them into the generating AI model. For example, a generated prompt might be, "Generate advice for Project ID 1: Prioritize regular communication with customers and thoroughly manage document versions." The server then uses the generating AI model to generate an advice statement and sends the result to the terminal.

[0139] Input: Prompt text and knowledge data

[0140] Output: Generated advice text

[0141] Step 8: Providing advice

[0142] The device analyzes the advice received from the server and presents it to the user. For example, the following content will be displayed on the device's UI:

[0143] Points to note:

[0144] We value regular communication with our customers.

[0145] Thoroughly implement version control for documents.

[0146] Input: Generated advice text

[0147] Output: Advice message presented to the user

[0148] (Application Example 1)

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

[0150] In factory manufacturing and maintenance processes, there is a need for systems that properly manage acquired knowledge and enable new workers and maintenance personnel to effectively utilize past knowledge. However, current systems often do not properly organize knowledge, making it difficult to quickly obtain necessary information. As a result, they cannot contribute to operational efficiency or quality improvement, and this is a major challenge, especially for newly joined workers.

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

[0152] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using the knowledge, means for providing the generated advice to the user's terminal, means for systematically storing knowledge related to a specific project, means for searching for knowledge based on a project ID and generating advice statements, and means for applying the advice to improve the efficiency of manufacturing and maintenance processes in the factory. This enables improved efficiency in manufacturing and maintenance processes in the factory, as well as smooth knowledge utilization by workers and maintenance personnel.

[0153] A "project" is a unit of work or project set up to achieve a specific objective.

[0154] "Knowledge" refers to the knowledge, information, and technical know-how acquired during the course of work or projects.

[0155] A "database" is an information management system that systematically stores acquired knowledge and allows for searching and retrieval as needed.

[0156] A "device" refers to a computer, smartphone, tablet, or other device used by a user to receive advice.

[0157] A "Project ID" is an identifier used to uniquely identify a specific project.

[0158] "Advice" refers to suggestions and instructions generated based on past knowledge, with the aim of improving work efficiency and quality.

[0159] A "manufacturing process" refers to a series of work steps involved in the production of a product in a factory.

[0160] A "maintenance process" refers to a series of steps involved in the maintenance and management of machinery and equipment in a factory.

[0161] "Efficiency improvement" refers to improving processes and methods to perform tasks and work more quickly and effectively.

[0162] A "new project manager" refers to a worker or staff member newly assigned to a specific project or task.

[0163] This invention relates to a system aimed at improving the efficiency of factory manufacturing and maintenance processes. It stores knowledge acquired during a project in a database and generates and provides that knowledge as advice for new project managers.

[0164] First, the server initializes the knowledge base. The knowledge base is a database for systematically storing acquired knowledge. This database includes operational notes and important advice related to each project ID.

[0165] The server has the functionality to add knowledge acquired by users during their work to the database. For example, practical knowledge such as "regularly inspect the robot's sensors" or "inspect all screws during regular maintenance" in manufacturing and maintenance processes can be added.

[0166] Next, the server initializes an advice generator to generate advice using the stored knowledge. The advice generator searches for relevant knowledge based on a specific project ID and generates an advice statement based on its content.

[0167] When a user takes on a new project or works on a similar project, their device (smartphone or tablet) generates advice for the new project manager. This advice generator searches the knowledge base based on the project ID, retrieves relevant entries, and then generates the advice text.

[0168] As a concrete example, the following advice may be generated during the maintenance process:

[0169] "We will regularly inspect the robot's sensors."

[0170] "Inspect all screws during routine maintenance."

[0171] This advice is designed to help ensure the smooth progress of projects and streamline maintenance tasks. Users can receive real-time advice via their devices and use it to advance their work, thereby achieving high work efficiency.

[0172] As an example of a prompt, the server might instruct the system to generate advice in the form of, "If the project ID is 'maintenance_1', please provide advice based on the relevant knowledge base." This allows the AI ​​model to provide appropriate advice.

[0173] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0174] Step 1:

[0175] The server initializes the knowledge base. First, it creates an empty database and sets up a structure for organizing knowledge based on the project ID. For example, it can use a JSON database file or an SQL database. The input to this process is an empty database structure, and the output is an initialized database.

[0176] Step 2:

[0177] The system sends knowledge acquired by the user during their work to the server. This is a process in which the user inputs knowledge through a dedicated interface and transfers it to the server. The input is the knowledge information entered by the user (e.g., "Regularly inspect the robot's sensors"), and the output is the database with a new knowledge entry added.

[0178] Step 3:

[0179] The server stores the received knowledge in a database. During storage, the knowledge is organized by project ID. The input is the knowledge information and project ID submitted by the user, and the output is the knowledge entry that has been securely stored in the database.

[0180] Step 4:

[0181] The server initializes the advice generator. This is the process of setting up an algorithm to search the knowledge base and generate appropriate advice statements. The input is the initialization configuration file, and the output is the available advice generators.

[0182] Step 5:

[0183] When a user takes on a new project, the terminal sends a specific project ID to the server. The server then begins generating advice based on that project ID. The input is the project ID sent by the user, and the output is the project ID as it reaches the server.

[0184] Step 6:

[0185] The server searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is a list of knowledge entries associated with that ID.

[0186] Step 7:

[0187] The server generates advice statements based on the acquired knowledge entries. In this process, it uses a generation AI model (e.g., GPT-3®) to construct advice statements based on past knowledge. The input is a list of knowledge entries, and the output is the generated advice statement.

[0188] Step 8:

[0189] The server sends the generated advice message to the terminal. The terminal displays the advice message, making it available for the user to view. The input is the generated advice message, and the output is the advice message displayed on the user's terminal.

[0190] Step 9:

[0191] Users proceed with their tasks while referring to advice generated using the terminal. This will improve work efficiency and ensure smoother manufacturing and maintenance processes. The input is the advice displayed on the terminal, and the output is the efficient progress of the tasks.

[0192] 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.

[0193] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and adjusts the content and format of the generated advice based on the user's emotions.

[0194] Knowledge base initialization

[0195] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[0196] Adding Knowledge

[0197] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[0198] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[0199] Initialization of the advice generator

[0200] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[0201] Emotion engine initialization

[0202] The server initializes an emotion engine to recognize the user's emotions. The emotion engine recognizes emotions from the user's voice, facial expressions, or text.

[0203] Generating advice

[0204] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0205] Adjusting emotion-based advice

[0206] The server uses an emotion engine to recognize the user's emotions. Based on the recognized emotions, it adjusts the content and format of the advice it generates. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[0207] Providing advice

[0208] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[0209] Points to note:

[0210] We value regular communication with our customers.

[0211] Thoroughly implement version control for documents.

[0212] In addition, the system provides additional advice tailored to the user's emotions. For example, if the user is feeling anxious, it might offer the following advice:

[0213] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0214] We hold regular meetings with the team.

[0215] We will quickly incorporate customer feedback.

[0216] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[0217] Specific example

[0218] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[0219] Points to note:

[0220] We value regular communication with our customers.

[0221] Thoroughly implement version control for documents.

[0222] Furthermore, if the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[0223] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0224] We hold regular meetings with the team.

[0225] We will quickly incorporate customer feedback.

[0226] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] The server initializes the knowledge base. This involves creating an instance of the KnowledgeBase class, which initializes an empty data dictionary, self.data.

[0230] Step 2:

[0231] Users input knowledge gained during their work and send it to the server. Specifically, this involves entering the entry "Value regular communication with customers" for "Project ID 1" through the interface.

[0232] Step 3:

[0233] The server saves the submitted knowledge to the database. Calling the add_entry method adds project ID 1 and an entry to self.data.

[0234] Step 4:

[0235] The server initializes the advice generator. This involves creating an instance of the AdviceGenerator class, passing the knowledge base as an argument, and calling the __init__ method to store the knowledge base in the instance variable self.knowledge_base.

[0236] Step 5:

[0237] The server initializes the emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, or text, and it loads the necessary libraries and models, creates instances, and initializes them.

[0238] Step 6:

[0239] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[0240] Step 7:

[0241] The server generates advice based on the project ID through the `generate_advice` method. First, it calls the `get_entries` method to retrieve entries related to project ID 1, and then generates an advice statement based on their contents.

[0242] Step 8:

[0243] The server uses an emotion engine to recognize the user's emotions. User voice and text data are input into the emotion engine for emotion classification.

[0244] Step 9:

[0245] The server adjusts the content and format of the advice based on the recognized emotions. If the user expresses positive emotions, it generates motivational advice; if they express negative emotions, it generates advice that includes encouragement and specific solutions.

[0246] Step 10:

[0247] The device provides the generated advice to the user. The generated advice text is displayed on the user's screen so that the user can refer to it.

[0248] For example, the following advice is offered:

[0249] Points to note:

[0250] We value regular communication with our customers.

[0251] Thoroughly implement version control for documents.

[0252] If the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[0253] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0254] We hold regular meetings with the team.

[0255] We will quickly incorporate customer feedback.

[0256] (Example 2)

[0257] 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".

[0258] Traditional project management systems struggled to accumulate knowledge gained during project progress and effectively provide it to new project managers. Furthermore, they were unable to provide advice that considered user emotions or offer appropriate support tailored to the user's situation. This made it difficult to improve work efficiency and quality, sometimes leading to user stress and confusion.

[0259] 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.

[0260] In this invention, the server includes means for storing knowledge acquired during the progress of a case in data storage, means for generating advice for new case managers using the stored knowledge, and means for adjusting the content of the advice using an emotion recognition engine that recognizes the user's emotions. This makes it possible to systematically accumulate knowledge acquired during the progress of a case and provide situation-appropriate advice to new case managers. Furthermore, by recognizing the user's emotions and adjusting the content of the advice, it is possible to provide appropriate support tailored to the user's situation, thereby improving the efficiency and quality of operations.

[0261] A "case" is a unit of work activity, such as a project or task, that has a specific purpose and deadline.

[0262] "Knowledge" refers to information acquired during the course of work, including experience, know-how, unwritten rules, and points to note when carrying out work.

[0263] "Data storage" refers to a storage device or database used to accumulate and preserve acquired knowledge.

[0264] "Advice" refers to recommendations, points of caution, and suggestions provided to help a new project manager perform their duties efficiently.

[0265] An "emotion recognition engine" is a technology or software that analyzes and recognizes emotions from a user's voice, facial expressions, text, etc.

[0266] "Users" refer to individuals or corporations that use the system, and in this context, specifically to employees or staff responsible for a project.

[0267] A "device" refers to a computer, smartphone, or other device accessible to a user.

[0268] "Project identification information" refers to information used to uniquely identify each project, and includes project IDs, task IDs, etc.

[0269] This system stores knowledge acquired during business processes in data storage and uses that knowledge to generate advice for new project managers. Furthermore, by combining it with an emotion recognition engine, the content and format of the advice can be adjusted according to the user's emotions.

[0270] Knowledge base initialization

[0271] The server initializes a database to store knowledge acquired during business processes. Specifically, it uses a database management system (DBMS) such as SQL to create tables that store project IDs and knowledge items.

[0272] Adding Knowledge

[0273] Users input knowledge gained during their work and send it to the server. Using the terminal interface, users enter the acquired knowledge into a text box and press the send button to send the data to the server.

[0274] The server receives the submitted knowledge and stores it in the database. Specifically, it parses the data received via the API and inserts it into the appropriate table. For example, it adds an entry "Value regular communication with customers" to Project ID 1.

[0275] Initialization of the advice generator

[0276] The server initializes an advice generator to generate advice using stored knowledge. This generator uses a generative AI model to produce advice based on knowledge related to a specific project ID.

[0277] Initialization of the Emotion Engine

[0278] The server initializes an emotion recognition engine for recognizing the user's emotions. This engine combines speech recognition, facial expression analysis, text analysis, etc. to analyze the user's emotions. As specific technologies, Google (registered trademark) Cloud Speech-to-Text is used for speech recognition, OpenCV for facial expression analysis, and a natural language processing library for text analysis.

[0279] Generation and Provision of Advice

[0280] When a new case handler requests advice, the terminal generates advice for a specific project ID. When the user enters the project ID and sends it to the server via the send button, the server searches the database based on that project ID and retrieves the relevant entries.

[0281] Based on the retrieved entries, the advice generator generates an advice sentence. The generated advice sentence is adjusted to the content and form considering the user's emotions and provided to the user through the terminal.

[0282] Specific Example

[0283] For example, there is a new user assigned to project ID 1. That user can receive the following advice.

[0284] Points to Note for the Case:

[0285] Value regular communication with customers

[0286] Thoroughly implement document version management

[0287] Furthermore, when the emotion recognition engine recognizes that the user is feeling anxious, the following additional advice is provided.

[0288] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0289] We hold regular meetings with the team.

[0290] We will quickly incorporate customer feedback.

[0291] This allows users to receive necessary advice in real time, improving the efficiency and quality of their work. The system effectively utilizes knowledge gained during project progress and enables the provision of appropriate support tailored to the user's needs and emotions.

[0292] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0293] Step 1:

[0294] Knowledge base initialization

[0295] The server initializes a database to store knowledge acquired during business processes. This involves using a database management system (DBMS) to create the necessary tables (for example, tables to store project IDs and knowledge items).

[0296] The specific operation involves creating a table using an SQL statement and inserting initial data.

[0297] Input: Connection information to the DBMS

[0298] Output: Initialized database

[0299] Step 2:

[0300] Adding Knowledge

[0301] The user inputs the knowledge obtained during business operations and sends it to the server. The user uses the interface of the terminal, enters the acquired knowledge into the text box, and presses the send button.

[0302] The server receives the sent knowledge and saves it in the database. Specifically, the received data is processed by the API and inserted into the appropriate table.

[0303] Input: Knowledge information input by the user, project ID

[0304] Output: Knowledge saved in the database

[0305] Step 3:

[0306] Initialization of the advice generator

[0307] The server initializes an advice generator for generating advice using the saved knowledge. This generator is set by loading the generation AI model and importing the learning data.

[0308] Specific operations include importing the library of the generation AI model, loading the model, and feeding the data.

[0309] Input: Saved knowledge database, generation AI model

[0310] Output: Initialized advice generator

[0311] Step 4:

[0312] Initialization of the emotion engine

[0313] The server initializes an emotion recognition engine to recognize the user's emotions. This emotion recognition engine is built by combining speech recognition, facial expression analysis, and text analysis technologies. Specifically, it utilizes Google Cloud Speech-to-Text and OpenCV libraries.

[0314] In terms of specific actions, this involves importing these libraries, reading the configuration file, and initializing the model.

[0315] Input: Configuration file for emotion recognition engine, a set of recognition technology libraries

[0316] Output: Initialized emotion recognition engine

[0317] Step 5:

[0318] Generating advice

[0319] When a new project manager requests advice, the terminal sends the project ID to the server. The server searches the database based on that project ID and retrieves the relevant knowledge.

[0320] The server generates advice using an AI model based on the acquired knowledge.

[0321] Specifically, the process involves performing an SQL search based on the project ID, inputting the retrieved data into a generation AI model, and then generating advice statements.

[0322] Input: Project ID, Knowledge Database

[0323] Output: Generated advice

[0324] Step 6:

[0325] Adjusting emotion-based advice

[0326] The server recognizes the user's emotions using an emotion recognition engine. When the user inputs voice or text, the emotion recognition engine analyzes that data.

[0327] Based on the recognized emotions, the content and format of the generated advice text are adjusted.

[0328] Specifically, this involves applying an algorithm to modify the advice text generated based on the analyzed sentiment data.

[0329] Input: User sentiment data, generated advice

[0330] Output: Adjusted advice

[0331] Step 7:

[0332] Providing advice

[0333] When a user takes on a new project, the device displays generated advice to the user. The user reviews the advice on the device screen to use as a reference for proceeding with the work.

[0334] Specifically, this involves displaying advice messages on the user interface so that users can review them.

[0335] Input: Adjusted advice

[0336] Output: Advice displayed on the user's terminal

[0337] (Application Example 2)

[0338] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0339] Improving efficiency and accuracy in logistics centers is crucial. However, adapting to inexperienced workers and newly added work processes requires the efficient use of past knowledge and know-how. Furthermore, stress and anxiety experienced by workers during work often negatively impact operational efficiency. Therefore, it is necessary to understand the psychological state of workers and provide appropriate advice.

[0340] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0341] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using that knowledge, means for providing the generated advice to the user's terminal, and means for adjusting the content and format of the advice using an emotion engine that recognizes the user's emotions. This makes it possible to store knowledge acquired during work in a database and recognize the emotions of workers to provide appropriate advice in order to optimize the efficiency of logistics operations in real time.

[0342] "Knowledge" refers to the information and know-how acquired during the progress of a project.

[0343] A "database" is a system for systematically storing acquired knowledge and managing it in a searchable format.

[0344] "Advice" refers to specific advice given to a new project manager based on past knowledge.

[0345] "User's device" refers to the device used to display the advice (e.g., a smartphone, tablet, or computer).

[0346] An "emotion engine" is a system that recognizes emotions from a user's voice, facial expressions, or text.

[0347] "Real-time" refers to a state where work can be reflected and responded to immediately without delay while it is in progress.

[0348] This invention is a system for optimizing operational efficiency in logistics centers and consists of multiple elements. Specific embodiments are described below.

[0349] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[0350] Next, the user inputs the knowledge gained during the process and sends it to the server. For example, an entry such as "Ensure all packages are correctly labeled" might be added. The server stores this knowledge in a database and organizes the knowledge relevant to each project by project ID.

[0351] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on that content.

[0352] The emotion engine is also initialized. The emotion engine recognizes emotions from the user's voice, facial expressions, or text. This engine is used to analyze the user's emotions and adjust the content and format of the advice.

[0353] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0354] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[0355] When a user takes on a new project or works on a similar one, the device provides generated advice. For example, in addition to general precautions such as "Make sure your packages are properly labeled," it also offers emotionally-based advice such as "Don't worry, taking breaks will help you work more efficiently."

[0356] Specific example

[0357] scenario

[0358] A new logistics worker was assigned to the center. During his work, he felt overwhelmed by the workload and sent a request for an "emotion check" via the application.

[0359] Prompt example

[0360] "I'm feeling a bit overwhelmed by the amount of work."

[0361] Application response

[0362] Basic advice:

[0363] Make sure your package is correctly labeled.

[0364] Organize your workspace to avoid errors.

[0365] Emotional advice:

[0366] Don't worry, take a deep breath and work without rushing. This will make it easier to calmly solve the problem.

[0367] This embodiment allows logistics center workers to receive appropriate advice in real time, improving work efficiency and psychological stability.

[0368] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0369] Step 1:

[0370] The server initializes the knowledge base. During this process, it creates a database and prepares tables to store knowledge related to cases and projects. The input here is the system's initial settings, and the output is an empty database.

[0371] Step 2:

[0372] Users input knowledge gained during their work and send it to the server. The server stores this input knowledge in a database. The input data is knowledge information for a specific project ID, and the output is the knowledge stored in the database. Specifically, users might input something like, "Verify that the packages are correctly labeled."

[0373] Step 3:

[0374] The server initializes the advice generator to generate advice using stored knowledge. The advice generator extracts knowledge related to a specific project ID and generates advice based on that content. The input is the project ID, and the output is the generated advice.

[0375] Step 4:

[0376] The server initializes the emotion engine. The emotion engine is a module that recognizes emotions from the user's voice, facial expressions, or text. The input here is the user's facial expressions or text data, and the output is the recognized emotion. Specifically, the emotion recognition algorithm performs analysis to determine whether the user is experiencing stress.

[0377] Step 5:

[0378] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is the corresponding advice statement. Specifically, it executes a database query to retrieve relevant knowledge and generates an advice statement based on that.

[0379] Step 6:

[0380] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. The input is the emotion recognition result and the generated advice text, and the output is the adjusted advice text. For example, if a negative emotion is recognized, the server will add advice text that includes words of encouragement and specific countermeasures.

[0381] Step 7:

[0382] When a user takes on a new project or works on a similar one, the terminal presents the user with generated advice. The input is the adjusted advice text, and the output is the advice message displayed on the user's terminal. Specifically, the generated advice text is displayed on the user's screen, and audio guidance is provided if necessary.

[0383] By following these steps, logistics center workers can receive accurate advice in real time, improving work efficiency and psychological well-being.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] [Second Embodiment]

[0388] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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".

[0400] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[0401] Knowledge base initialization

[0402] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes. This database includes implicit rules and important considerations associated with each project ID.

[0403] Adding Knowledge

[0404] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[0405] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[0406] Initialization of the advice generator

[0407] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[0408] Generating advice

[0409] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0410] Providing advice

[0411] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[0412] Points to note:

[0413] We value regular communication with our customers.

[0414] Thoroughly implement version control for documents.

[0415] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[0416] Specific example

[0417] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[0418] Points to note:

[0419] We value regular communication with our customers.

[0420] Thoroughly implement version control for documents.

[0421] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server initializes the knowledge base. This is done by creating an instance of the KnowledgeBase class. Specifically, the __init__ method is called, and an empty data dictionary self.data is initialized.

[0425] Step 2:

[0426] Users input knowledge gained during their work and send it to the server. For example, for project ID 1, they might input the entry "Value regular communication with customers."

[0427] Step 3:

[0428] The server saves the submitted knowledge to the database. Specifically, the add_entry method is called, and project ID 1 and the entry are added to self.data.

[0429] Step 4:

[0430] The server initializes the advice generator. This is done by creating an instance of the AdviceGenerator class and passing the knowledge base as an argument. Specifically, the __init__ method is called, and the knowledge base is stored in the instance variable self.knowledge_base.

[0431] Step 5:

[0432] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[0433] Step 6:

[0434] The server generates advice based on the project ID through the `generate_advice` method. Specifically, the `get_entries` method is called to retrieve entries related to project ID 1. Then, advice statements are generated based on the retrieved entries.

[0435] Step 7:

[0436] The device provides the generated advice to the user. Specifically, the advice text is displayed on the user's device. For example, the following advice may be presented:

[0437] Points to note:

[0438] We value regular communication with our customers.

[0439] Thoroughly implement version control for documents.

[0440] Step 8:

[0441] Users will use this advice to guide their work. This will lead to smoother project progress and prevent past problems from occurring.

[0442] (Example 1)

[0443] 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".

[0444] Traditional advice systems fail to effectively utilize knowledge gained from past projects, potentially leading new project managers to repeat past mistakes and pitfalls. Furthermore, a lack of systematic methods for storing and retrieving knowledge makes it difficult to provide necessary information quickly.

[0445] 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.

[0446] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for users to input and transmit knowledge obtained during the progress of their work to the server, means for the server to store project-related knowledge in a database, means for the server to initialize a generation AI model in order to generate advice using the stored knowledge, means for a terminal to generate advice based on the project ID when a new case manager requests advice, and means for providing the generated advice to the user's terminal. This makes it possible to effectively store and retrieve knowledge and to quickly provide appropriate advice.

[0447] A "project" refers to an ongoing project or a portion of a business activity, each with its own unique identifier.

[0448] "Knowledge" refers to information such as insights, experience, unwritten rules, and points to note that are gained during the course of work.

[0449] A "database" refers to a system that systematically stores information and facilitates searching and management.

[0450] A "server" refers to a computer system that manages and runs databases and advice generators.

[0451] A "user" refers to an entity that uses the system to input knowledge and receive advice.

[0452] "Terminal" refers to a device or interface that a user accesses.

[0453] An "advice generator" refers to a tool or algorithm that generates advice relevant to a specific project based on stored knowledge.

[0454] A "generative AI model" refers to a system that uses artificial intelligence technologies, such as large-scale language models, to generate text and extract knowledge.

[0455] "Project ID" refers to an identifier used to uniquely identify each project.

[0456] A "prompt" refers to an instruction or question that is input to a generative AI model.

[0457] "Initialization" refers to setting a system or tool to a usable state.

[0458] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[0459] Knowledge base initialization

[0460] The server first initializes the knowledge base. This knowledge base is a database for systematically storing knowledge acquired during business processes. Specifically, the server uses database software (e.g., MySQL) to generate the necessary tables. The tables include a project ID to uniquely identify each project and columns for storing knowledge entries.

[0461] Adding Knowledge

[0462] Users input knowledge gained during their work into the system from their terminal. For example, they might add the knowledge "Value regular communication with customers" to "Project ID 1". The terminal sends this input data to the server via API, and the server saves the received data to a database. SQL queries are used for this saving process.

[0463] Initialization of the advice generator

[0464] The server initializes a generative AI model (e.g., a GPT model) for generating advice. This involves loading the model file and setting the configuration to apply. For example, the model might be loaded using a Python library.

[0465] Generating and providing advice

[0466] When a user takes on a new project, they request advice on a specific project from their terminal. This request is sent to the server, which, upon receiving the request, retrieves knowledge related to the specified project ID from its database. Using the retrieved knowledge, a generation AI model generates prompts, and an advice generator then generates specific advice based on that knowledge.

[0467] The generated advice is provided to the user via the terminal. This allows the user to obtain the knowledge necessary for their work in real time, contributing to improved work efficiency and quality. Examples of specific prompt messages are as follows:

[0468] Generate advice for Project ID 1. Extract relevant information from previously entered knowledge base entries and create an advice statement based on that information.

[0469] Specific example

[0470] For example, suppose a user has been newly assigned to "Project ID 1". This user will receive the following advice based on a knowledge base gained from past projects:

[0471] Points to note:

[0472] We value regular communication with our customers.

[0473] Thoroughly implement version control for documents.

[0474] This advice helps support the smooth progress of the project and prevents past problems from occurring. By using the advice received as a guide, users can achieve higher work efficiency.

[0475] The above describes embodiments for carrying out the present invention.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1: Knowledge Base Initialization

[0478] The server initializes the knowledge base when the system starts up. Specifically, it uses database software (e.g., MySQL) to create the necessary tables. These tables include columns such as project ID, knowledge entry, and timestamp. The server establishes a connection to the database and executes an SQL query like the following: CREATE TABLE IF NOT EXISTS knowledge_entries (entry_id INT AUTO_INCREMENT PRIMARY KEY, project_id INT, knowledge_text TEXT, timestamp DATETIME);

[0479] Input: None

[0480] Output: Initialized database

[0481] Step 2: Enter and submit knowledge

[0482] Users input knowledge gained during their work into the system from their terminal. For example, they might input the knowledge "Value regular communication with customers" for "Project ID 1." The terminal then sends this input data to the server via an API.

[0483] Input: Knowledge information entered by the user into the terminal.

[0484] Output: Knowledge data sent to the server

[0485] Step 3: Knowledge Preservation

[0486] The server receives the submitted knowledge data and stores it in the database. Specifically, it generates and executes the SQL query: INSERT INTO knowledge_entries (project_id, knowledge_text, timestamp) VALUES (1, 'We value regular communication with our customers', NOW()); This stores the knowledge in the database.

[0487] Input: Knowledge data received from the API

[0488] Output: Knowledge entries stored in the database

[0489] Step 4: Initialize the advice generator

[0490] The server initializes a generative AI model (e.g., a GPT model) to generate advice. This involves loading the model file and performing the necessary configuration. For example, it loads the model using Python libraries. It then executes the code `from transformers import GPT2LMHeadModel, GPT2Tokenizer` to initialize the model and tokenizer.

[0491] Input: Model file and configuration information

[0492] Output: Initialized Generative AI Model

[0493] Step 5: Receiving a request for advice

[0494] The user requests advice on a specific project through their device. For example, they might request, "Please give me advice on Project ID 1." The device then sends this request data to the server via the API.

[0495] Input: User advice request data

[0496] Output: Request data sent to the server

[0497] Step 6: Knowledge Search

[0498] After receiving the request data, the server searches the database for knowledge related to the specified project ID. For example, it executes an SQL query such as SELECT knowledge_text FROM knowledge_entries WHERE project_id = 1; to retrieve the relevant knowledge.

[0499] Input: Request data based on Project ID

[0500] Output: Acquired knowledge data

[0501] Step 7: Generating Advice

[0502] The server generates prompts based on the acquired knowledge and inputs them into the generating AI model. For example, a generated prompt might be, "Generate advice for Project ID 1: Prioritize regular communication with customers and thoroughly manage document versions." The server then uses the generating AI model to generate an advice statement and sends the result to the terminal.

[0503] Input: Prompt text and knowledge data

[0504] Output: Generated advice text

[0505] Step 8: Providing advice

[0506] The device analyzes the advice received from the server and presents it to the user. For example, the following content will be displayed on the device's UI:

[0507] Points to note:

[0508] We value regular communication with our customers.

[0509] Thoroughly implement version control for documents.

[0510] Input: Generated advice text

[0511] Output: Advice message presented to the user

[0512] (Application Example 1)

[0513] 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."

[0514] In factory manufacturing and maintenance processes, there is a need for systems that properly manage acquired knowledge and enable new workers and maintenance personnel to effectively utilize past knowledge. However, current systems often do not properly organize knowledge, making it difficult to quickly obtain necessary information. As a result, they cannot contribute to operational efficiency or quality improvement, and this is a major challenge, especially for newly joined workers.

[0515] 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.

[0516] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using the knowledge, means for providing the generated advice to the user's terminal, means for systematically storing knowledge related to a specific project, means for searching for knowledge based on a project ID and generating advice statements, and means for applying the advice to improve the efficiency of manufacturing and maintenance processes in the factory. This enables improved efficiency in manufacturing and maintenance processes in the factory, as well as smooth knowledge utilization by workers and maintenance personnel.

[0517] A "project" is a unit of work or project set up to achieve a specific objective.

[0518] "Knowledge" refers to the knowledge, information, and technical know-how acquired during the course of work or projects.

[0519] A "database" is an information management system that systematically stores acquired knowledge and allows for searching and retrieval as needed.

[0520] A "device" refers to a computer, smartphone, tablet, or other device used by a user to receive advice.

[0521] A "Project ID" is an identifier used to uniquely identify a specific project.

[0522] "Advice" refers to suggestions and instructions generated based on past knowledge, with the aim of improving work efficiency and quality.

[0523] A "manufacturing process" refers to a series of work steps involved in the production of a product in a factory.

[0524] A "maintenance process" refers to a series of steps involved in the maintenance and management of machinery and equipment in a factory.

[0525] "Efficiency improvement" refers to improving processes and methods to perform tasks and work more quickly and effectively.

[0526] A "new project manager" refers to a worker or staff member newly assigned to a specific project or task.

[0527] This invention relates to a system aimed at improving the efficiency of factory manufacturing and maintenance processes. It stores knowledge acquired during a project in a database and generates and provides that knowledge as advice for new project managers.

[0528] First, the server initializes the knowledge base. The knowledge base is a database for systematically storing acquired knowledge. This database includes operational notes and important advice related to each project ID.

[0529] The server has the functionality to add knowledge acquired by users during their work to the database. For example, practical knowledge such as "regularly inspect the robot's sensors" or "inspect all screws during regular maintenance" in manufacturing and maintenance processes can be added.

[0530] Next, the server initializes an advice generator to generate advice using the stored knowledge. The advice generator searches for relevant knowledge based on a specific project ID and generates an advice statement based on its content.

[0531] When a user takes on a new project or works on a similar project, their device (smartphone or tablet) generates advice for the new project manager. This advice generator searches the knowledge base based on the project ID, retrieves relevant entries, and then generates the advice text.

[0532] As a concrete example, the following advice may be generated during the maintenance process:

[0533] "We will regularly inspect the robot's sensors."

[0534] "Inspect all screws during routine maintenance."

[0535] This advice is designed to help ensure the smooth progress of projects and streamline maintenance tasks. Users can receive real-time advice via their devices and use it to advance their work, thereby achieving high work efficiency.

[0536] As an example of a prompt, the server might instruct the system to generate advice in the form of, "If the project ID is 'maintenance_1', please provide advice based on the relevant knowledge base." This allows the AI ​​model to provide appropriate advice.

[0537] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0538] Step 1:

[0539] The server initializes the knowledge base. First, it creates an empty database and sets up a structure for organizing knowledge based on the project ID. For example, it can use a JSON database file or an SQL database. The input to this process is an empty database structure, and the output is an initialized database.

[0540] Step 2:

[0541] The system sends knowledge acquired by the user during their work to the server. This is a process in which the user inputs knowledge through a dedicated interface and transfers it to the server. The input is the knowledge information entered by the user (e.g., "Regularly inspect the robot's sensors"), and the output is the database with a new knowledge entry added.

[0542] Step 3:

[0543] The server stores the received knowledge in a database. During storage, the knowledge is organized by project ID. The input is the knowledge information and project ID submitted by the user, and the output is the knowledge entry that has been securely stored in the database.

[0544] Step 4:

[0545] The server initializes the advice generator. This is the process of setting up an algorithm to search the knowledge base and generate appropriate advice statements. The input is the initialization configuration file, and the output is the available advice generators.

[0546] Step 5:

[0547] When a user takes on a new project, the terminal sends a specific project ID to the server. The server then begins generating advice based on that project ID. The input is the project ID sent by the user, and the output is the project ID as it reaches the server.

[0548] Step 6:

[0549] The server searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is a list of knowledge entries associated with that ID.

[0550] Step 7:

[0551] The server generates advice statements based on the acquired knowledge entries. In this process, it uses a generation AI model (e.g., GPT-3) to construct advice statements based on past knowledge. The input is a list of knowledge entries, and the output is the generated advice statement.

[0552] Step 8:

[0553] The server sends the generated advice message to the terminal. The terminal displays the advice message, making it available for the user to view. The input is the generated advice message, and the output is the advice message displayed on the user's terminal.

[0554] Step 9:

[0555] Users proceed with their tasks while referring to advice generated using the terminal. This will improve work efficiency and ensure smoother manufacturing and maintenance processes. The input is the advice displayed on the terminal, and the output is the efficient progress of the tasks.

[0556] 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.

[0557] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and adjusts the content and format of the generated advice based on the user's emotions.

[0558] Knowledge base initialization

[0559] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[0560] Adding Knowledge

[0561] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[0562] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[0563] Initialization of the advice generator

[0564] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[0565] Emotion engine initialization

[0566] The server initializes an emotion engine to recognize the user's emotions. The emotion engine recognizes emotions from the user's voice, facial expressions, or text.

[0567] Generating advice

[0568] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0569] Adjusting emotion-based advice

[0570] The server uses an emotion engine to recognize the user's emotions. Based on the recognized emotions, it adjusts the content and format of the advice it generates. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[0571] Providing advice

[0572] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[0573] Points to note:

[0574] We value regular communication with our customers.

[0575] Thoroughly implement version control for documents.

[0576] In addition, the system provides additional advice tailored to the user's emotions. For example, if the user is feeling anxious, it might offer the following advice:

[0577] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0578] We hold regular meetings with the team.

[0579] We will quickly incorporate customer feedback.

[0580] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[0581] Specific example

[0582] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[0583] Points to note:

[0584] We value regular communication with our customers.

[0585] Thoroughly implement version control for documents.

[0586] Furthermore, if the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[0587] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0588] We hold regular meetings with the team.

[0589] We will quickly incorporate customer feedback.

[0590] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The server initializes the knowledge base. This involves creating an instance of the KnowledgeBase class, which initializes an empty data dictionary, self.data.

[0594] Step 2:

[0595] Users input knowledge gained during their work and send it to the server. Specifically, this involves entering the entry "Value regular communication with customers" for "Project ID 1" through the interface.

[0596] Step 3:

[0597] The server saves the submitted knowledge to the database. Calling the add_entry method adds project ID 1 and an entry to self.data.

[0598] Step 4:

[0599] The server initializes the advice generator. This involves creating an instance of the AdviceGenerator class, passing the knowledge base as an argument, and calling the __init__ method to store the knowledge base in the instance variable self.knowledge_base.

[0600] Step 5:

[0601] The server initializes the emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, or text, and it loads the necessary libraries and models, creates instances, and initializes them.

[0602] Step 6:

[0603] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[0604] Step 7:

[0605] The server generates advice based on the project ID through the `generate_advice` method. First, it calls the `get_entries` method to retrieve entries related to project ID 1, and then generates an advice statement based on their contents.

[0606] Step 8:

[0607] The server uses an emotion engine to recognize the user's emotions. User voice and text data are input into the emotion engine for emotion classification.

[0608] Step 9:

[0609] The server adjusts the content and format of the advice based on the recognized emotions. If the user expresses positive emotions, it generates motivational advice; if they express negative emotions, it generates advice that includes encouragement and specific solutions.

[0610] Step 10:

[0611] The device provides the generated advice to the user. The generated advice text is displayed on the user's screen so that the user can refer to it.

[0612] For example, the following advice is offered:

[0613] Points to note:

[0614] We value regular communication with our customers.

[0615] Thoroughly implement version control for documents.

[0616] If the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[0617] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0618] We hold regular meetings with the team.

[0619] We will quickly incorporate customer feedback.

[0620] (Example 2)

[0621] 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".

[0622] Traditional project management systems struggled to accumulate knowledge gained during project progress and effectively provide it to new project managers. Furthermore, they were unable to provide advice that considered user emotions or offer appropriate support tailored to the user's situation. This made it difficult to improve work efficiency and quality, sometimes leading to user stress and confusion.

[0623] 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.

[0624] In this invention, the server includes means for storing knowledge acquired during the progress of a case in data storage, means for generating advice for new case managers using the stored knowledge, and means for adjusting the content of the advice using an emotion recognition engine that recognizes the user's emotions. This makes it possible to systematically accumulate knowledge acquired during the progress of a case and provide situation-appropriate advice to new case managers. Furthermore, by recognizing the user's emotions and adjusting the content of the advice, it is possible to provide appropriate support tailored to the user's situation, thereby improving the efficiency and quality of operations.

[0625] A "case" is a unit of work activity, such as a project or task, that has a specific purpose and deadline.

[0626] "Knowledge" refers to information acquired during the course of work, including experience, know-how, unwritten rules, and points to note when carrying out work.

[0627] "Data storage" refers to a storage device or database used to accumulate and preserve acquired knowledge.

[0628] "Advice" refers to recommendations, points of caution, and suggestions provided to help a new project manager perform their duties efficiently.

[0629] An "emotion recognition engine" is a technology or software that analyzes and recognizes emotions from a user's voice, facial expressions, text, etc.

[0630] "Users" refer to individuals or corporations that use the system, and in this context, specifically to employees or staff responsible for a project.

[0631] A "device" refers to a computer, smartphone, or other device accessible to a user.

[0632] "Project identification information" refers to information used to uniquely identify each project, and includes project IDs, task IDs, etc.

[0633] This system stores knowledge acquired during business processes in data storage and uses that knowledge to generate advice for new project managers. Furthermore, by combining it with an emotion recognition engine, the content and format of the advice can be adjusted according to the user's emotions.

[0634] Knowledge base initialization

[0635] The server initializes a database to store knowledge acquired during business processes. Specifically, it uses a database management system (DBMS) such as SQL to create tables that store project IDs and knowledge items.

[0636] Adding Knowledge

[0637] Users input knowledge gained during their work and send it to the server. Using the terminal interface, users enter the acquired knowledge into a text box and press the send button to send the data to the server.

[0638] The server receives the submitted knowledge and stores it in the database. Specifically, it parses the data received via the API and inserts it into the appropriate table. For example, it adds an entry "Value regular communication with customers" to Project ID 1.

[0639] Initialization of the advice generator

[0640] The server initializes an advice generator to generate advice using stored knowledge. This generator uses a generative AI model to produce advice based on knowledge related to a specific project ID.

[0641] Emotion engine initialization

[0642] The server initializes an emotion recognition engine to recognize the user's emotions. This engine analyzes the user's emotions by combining speech recognition, facial expression analysis, text analysis, and other technologies. Specifically, it uses Google Cloud Speech-to-Text for speech recognition, OpenCV for facial expression analysis, and a natural language processing library for text analysis.

[0643] Generating and providing advice

[0644] When a new project manager requests advice, the terminal generates advice for a specific project ID. Once the user enters the project ID and sends it to the server using the submit button, the server searches its database based on that project ID and retrieves the relevant entry.

[0645] Based on the acquired entries, the advice generator produces advice text. The generated advice text is adjusted in content and format to take the user's emotions into consideration and is provided to the user through the device.

[0646] Specific example

[0647] For example, suppose a new user has been assigned to Project ID 1. That user might receive the following advice:

[0648] Points to note:

[0649] We value regular communication with our customers.

[0650] Thoroughly implement version control for documents.

[0651] Furthermore, if the emotion recognition engine detects that the user is feeling anxious, the following additional advice will be provided:

[0652] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0653] We hold regular meetings with the team.

[0654] We will quickly incorporate customer feedback.

[0655] This allows users to receive necessary advice in real time, improving the efficiency and quality of their work. The system effectively utilizes knowledge gained during project progress and enables the provision of appropriate support tailored to the user's needs and emotions.

[0656] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0657] Step 1:

[0658] Knowledge base initialization

[0659] The server initializes a database to store knowledge acquired during business processes. This involves using a database management system (DBMS) to create the necessary tables (for example, tables to store project IDs and knowledge items).

[0660] The specific operation involves creating a table using an SQL statement and inserting initial data.

[0661] Input: Connection information to the DBMS

[0662] Output: Initialized database

[0663] Step 2:

[0664] Adding Knowledge

[0665] The user inputs the knowledge gained during the course of their work and sends it to the server. The user uses the terminal interface to enter the acquired knowledge into the text box and press the submit button.

[0666] The server receives the submitted knowledge and stores it in a database. Specifically, it processes the received data using an API and inserts it into the appropriate table.

[0667] Input: Knowledge information entered by the user, Project ID

[0668] Output: Knowledge stored in the database

[0669] Step 3:

[0670] Initialization of the advice generator

[0671] The server initializes an advice generator to generate advice using stored knowledge. This generator is configured by loading a generative AI model and ingesting training data.

[0672] The specific steps involve importing a library of generative AI models, loading the models, and feeding them data.

[0673] Input: Stored knowledge database, generative AI model

[0674] Output: Initialized advice generator

[0675] Step 4:

[0676] Emotion engine initialization

[0677] The server initializes an emotion recognition engine to recognize the user's emotions. This emotion recognition engine is built by combining speech recognition, facial expression analysis, and text analysis technologies. Specifically, it utilizes Google Cloud Speech-to-Text and OpenCV libraries.

[0678] In terms of specific actions, this involves importing these libraries, reading the configuration file, and initializing the model.

[0679] Input: Configuration file for emotion recognition engine, a set of recognition technology libraries

[0680] Output: Initialized emotion recognition engine

[0681] Step 5:

[0682] Generating advice

[0683] When a new project manager requests advice, the terminal sends the project ID to the server. The server searches the database based on that project ID and retrieves the relevant knowledge.

[0684] The server generates advice using an AI model based on the acquired knowledge.

[0685] Specifically, the process involves performing an SQL search based on the project ID, inputting the retrieved data into a generation AI model, and then generating advice statements.

[0686] Input: Project ID, Knowledge Database

[0687] Output: Generated advice

[0688] Step 6:

[0689] Adjusting emotion-based advice

[0690] The server recognizes the user's emotions using an emotion recognition engine. When the user inputs voice or text, the emotion recognition engine analyzes that data.

[0691] Based on the recognized emotions, the content and format of the generated advice text are adjusted.

[0692] Specifically, this involves applying an algorithm to modify the advice text generated based on the analyzed sentiment data.

[0693] Input: User sentiment data, generated advice

[0694] Output: Adjusted advice

[0695] Step 7:

[0696] Providing advice

[0697] When a user takes on a new project, the device displays generated advice to the user. The user reviews the advice on the device screen to use as a reference for proceeding with the work.

[0698] Specifically, this involves displaying advice messages on the user interface so that users can review them.

[0699] Input: Adjusted advice

[0700] Output: Advice displayed on the user's terminal

[0701] (Application Example 2)

[0702] 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."

[0703] Improving efficiency and accuracy in logistics centers is crucial. However, adapting to inexperienced workers and newly added work processes requires the efficient use of past knowledge and know-how. Furthermore, stress and anxiety experienced by workers during work often negatively impact operational efficiency. Therefore, it is necessary to understand the psychological state of workers and provide appropriate advice.

[0704] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0705] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using that knowledge, means for providing the generated advice to the user's terminal, and means for adjusting the content and format of the advice using an emotion engine that recognizes the user's emotions. This makes it possible to store knowledge acquired during work in a database and recognize the emotions of workers to provide appropriate advice in order to optimize the efficiency of logistics operations in real time.

[0706] "Knowledge" refers to the information and know-how acquired during the progress of a project.

[0707] A "database" is a system for systematically storing acquired knowledge and managing it in a searchable format.

[0708] "Advice" refers to specific advice given to a new project manager based on past knowledge.

[0709] "User's device" refers to the device used to display the advice (e.g., a smartphone, tablet, or computer).

[0710] An "emotion engine" is a system that recognizes emotions from a user's voice, facial expressions, or text.

[0711] "Real-time" refers to a state where work can be reflected and responded to immediately without delay while it is in progress.

[0712] This invention is a system for optimizing operational efficiency in logistics centers and consists of multiple elements. Specific embodiments are described below.

[0713] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[0714] Next, the user inputs the knowledge gained during the process and sends it to the server. For example, an entry such as "Ensure all packages are correctly labeled" might be added. The server stores this knowledge in a database and organizes the knowledge relevant to each project by project ID.

[0715] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on that content.

[0716] The emotion engine is also initialized. The emotion engine recognizes emotions from the user's voice, facial expressions, or text. This engine is used to analyze the user's emotions and adjust the content and format of the advice.

[0717] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0718] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[0719] When a user takes on a new project or works on a similar one, the device provides generated advice. For example, in addition to general precautions such as "Make sure your packages are properly labeled," it also offers emotionally-based advice such as "Don't worry, taking breaks will help you work more efficiently."

[0720] Specific example

[0721] scenario

[0722] A new logistics worker was assigned to the center. During his work, he felt overwhelmed by the workload and sent a request for an "emotion check" via the application.

[0723] Prompt example

[0724] "I'm feeling a bit overwhelmed by the amount of work."

[0725] Application response

[0726] Basic advice:

[0727] Make sure your package is correctly labeled.

[0728] Organize your workspace to avoid errors.

[0729] Emotional advice:

[0730] Don't worry, take a deep breath and work without rushing. This will make it easier to calmly solve the problem.

[0731] This embodiment allows logistics center workers to receive appropriate advice in real time, improving work efficiency and psychological stability.

[0732] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0733] Step 1:

[0734] The server initializes the knowledge base. During this process, it creates a database and prepares tables to store knowledge related to cases and projects. The input here is the system's initial settings, and the output is an empty database.

[0735] Step 2:

[0736] Users input knowledge gained during their work and send it to the server. The server stores this input knowledge in a database. The input data is knowledge information for a specific project ID, and the output is the knowledge stored in the database. Specifically, users might input something like, "Verify that the packages are correctly labeled."

[0737] Step 3:

[0738] The server initializes the advice generator to generate advice using stored knowledge. The advice generator extracts knowledge related to a specific project ID and generates advice based on that content. The input is the project ID, and the output is the generated advice.

[0739] Step 4:

[0740] The server initializes the emotion engine. The emotion engine is a module that recognizes emotions from the user's voice, facial expressions, or text. The input here is the user's facial expressions or text data, and the output is the recognized emotion. Specifically, the emotion recognition algorithm performs analysis to determine whether the user is experiencing stress.

[0741] Step 5:

[0742] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is the corresponding advice statement. Specifically, it executes a database query to retrieve relevant knowledge and generates an advice statement based on that.

[0743] Step 6:

[0744] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. The input is the emotion recognition result and the generated advice text, and the output is the adjusted advice text. For example, if a negative emotion is recognized, the server will add advice text that includes words of encouragement and specific countermeasures.

[0745] Step 7:

[0746] When a user takes on a new project or works on a similar one, the terminal presents the user with generated advice. The input is the adjusted advice text, and the output is the advice message displayed on the user's terminal. Specifically, the generated advice text is displayed on the user's screen, and audio guidance is provided if necessary.

[0747] By following these steps, logistics center workers can receive accurate advice in real time, improving work efficiency and psychological well-being.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] [Third Embodiment]

[0752] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0753] 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.

[0754] 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).

[0755] 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.

[0756] 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.

[0757] 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).

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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".

[0764] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[0765] Knowledge base initialization

[0766] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes. This database includes implicit rules and important considerations associated with each project ID.

[0767] Adding Knowledge

[0768] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[0769] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[0770] Initialization of the advice generator

[0771] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[0772] Generating advice

[0773] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0774] Providing advice

[0775] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[0776] Points to note:

[0777] We value regular communication with our customers.

[0778] Thoroughly implement version control for documents.

[0779] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[0780] Specific example

[0781] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[0782] Points to note:

[0783] We value regular communication with our customers.

[0784] Thoroughly implement version control for documents.

[0785] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[0786] The following describes the processing flow.

[0787] Step 1:

[0788] The server initializes the knowledge base. This is done by creating an instance of the KnowledgeBase class. Specifically, the __init__ method is called, and an empty data dictionary self.data is initialized.

[0789] Step 2:

[0790] Users input knowledge gained during their work and send it to the server. For example, for project ID 1, they might input the entry "Value regular communication with customers."

[0791] Step 3:

[0792] The server saves the submitted knowledge to the database. Specifically, the add_entry method is called, and project ID 1 and the entry are added to self.data.

[0793] Step 4:

[0794] The server initializes the advice generator. This is done by creating an instance of the AdviceGenerator class and passing the knowledge base as an argument. Specifically, the __init__ method is called, and the knowledge base is stored in the instance variable self.knowledge_base.

[0795] Step 5:

[0796] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[0797] Step 6:

[0798] The server generates advice based on the project ID through the `generate_advice` method. Specifically, the `get_entries` method is called to retrieve entries related to project ID 1. Then, advice statements are generated based on the retrieved entries.

[0799] Step 7:

[0800] The device provides the generated advice to the user. Specifically, the advice text is displayed on the user's device. For example, the following advice may be presented:

[0801] Points to note:

[0802] We value regular communication with our customers.

[0803] Thoroughly implement version control for documents.

[0804] Step 8:

[0805] Users will use this advice to guide their work. This will lead to smoother project progress and prevent past problems from occurring.

[0806] (Example 1)

[0807] 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."

[0808] Traditional advice systems fail to effectively utilize knowledge gained from past projects, potentially leading new project managers to repeat past mistakes and pitfalls. Furthermore, a lack of systematic methods for storing and retrieving knowledge makes it difficult to provide necessary information quickly.

[0809] 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.

[0810] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for users to input and transmit knowledge obtained during the progress of their work to the server, means for the server to store project-related knowledge in a database, means for the server to initialize a generation AI model in order to generate advice using the stored knowledge, means for a terminal to generate advice based on the project ID when a new case manager requests advice, and means for providing the generated advice to the user's terminal. This makes it possible to effectively store and retrieve knowledge and to quickly provide appropriate advice.

[0811] A "project" refers to an ongoing project or a portion of a business activity, each with its own unique identifier.

[0812] "Knowledge" refers to information such as insights, experience, unwritten rules, and points to note that are gained during the course of work.

[0813] A "database" refers to a system that systematically stores information and facilitates searching and management.

[0814] A "server" refers to a computer system that manages and runs databases and advice generators.

[0815] A "user" refers to an entity that uses the system to input knowledge and receive advice.

[0816] "Terminal" refers to a device or interface that a user accesses.

[0817] An "advice generator" refers to a tool or algorithm that generates advice relevant to a specific project based on stored knowledge.

[0818] A "generative AI model" refers to a system that uses artificial intelligence technologies, such as large-scale language models, to generate text and extract knowledge.

[0819] "Project ID" refers to an identifier used to uniquely identify each project.

[0820] A "prompt" refers to an instruction or question that is input to a generative AI model.

[0821] "Initialization" refers to setting a system or tool to a usable state.

[0822] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[0823] Knowledge base initialization

[0824] The server first initializes the knowledge base. This knowledge base is a database for systematically storing knowledge acquired during business processes. Specifically, the server uses database software (e.g., MySQL) to generate the necessary tables. The tables include a project ID to uniquely identify each project and columns for storing knowledge entries.

[0825] Adding Knowledge

[0826] Users input knowledge gained during their work into the system from their terminal. For example, they might add the knowledge "Value regular communication with customers" to "Project ID 1". The terminal sends this input data to the server via API, and the server saves the received data to a database. SQL queries are used for this saving process.

[0827] Initialization of the advice generator

[0828] The server initializes a generative AI model (e.g., a GPT model) for generating advice. This involves loading the model file and setting the configuration to apply. For example, the model might be loaded using a Python library.

[0829] Generating and providing advice

[0830] When a user takes on a new project, they request advice on a specific project from their terminal. This request is sent to the server, which, upon receiving the request, retrieves knowledge related to the specified project ID from its database. Using the retrieved knowledge, a generation AI model generates prompts, and an advice generator then generates specific advice based on that knowledge.

[0831] The generated advice is provided to the user via the terminal. This allows the user to obtain the knowledge necessary for their work in real time, contributing to improved work efficiency and quality. Examples of specific prompt messages are as follows:

[0832] Generate advice for Project ID 1. Extract relevant information from previously entered knowledge base entries and create an advice statement based on that information.

[0833] Specific example

[0834] For example, suppose a user has been newly assigned to "Project ID 1". This user will receive the following advice based on a knowledge base gained from past projects:

[0835] Points to note:

[0836] We value regular communication with our customers.

[0837] Thoroughly implement version control for documents.

[0838] This advice helps support the smooth progress of the project and prevents past problems from occurring. By using the advice received as a guide, users can achieve higher work efficiency.

[0839] The above describes embodiments for carrying out the present invention.

[0840] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0841] Step 1: Knowledge Base Initialization

[0842] The server initializes the knowledge base when the system starts up. Specifically, it uses database software (e.g., MySQL) to create the necessary tables. These tables include columns such as project ID, knowledge entry, and timestamp. The server establishes a connection to the database and executes an SQL query like the following: CREATE TABLE IF NOT EXISTS knowledge_entries (entry_id INT AUTO_INCREMENT PRIMARY KEY, project_id INT, knowledge_text TEXT, timestamp DATETIME);

[0843] Input: None

[0844] Output: Initialized database

[0845] Step 2: Enter and submit knowledge

[0846] Users input knowledge gained during their work into the system from their terminal. For example, they might input the knowledge "Value regular communication with customers" for "Project ID 1." The terminal then sends this input data to the server via an API.

[0847] Input: Knowledge information entered by the user into the terminal.

[0848] Output: Knowledge data sent to the server

[0849] Step 3: Knowledge Preservation

[0850] The server receives the submitted knowledge data and stores it in the database. Specifically, it generates and executes the SQL query: INSERT INTO knowledge_entries (project_id, knowledge_text, timestamp) VALUES (1, 'We value regular communication with our customers', NOW()); This stores the knowledge in the database.

[0851] Input: Knowledge data received from the API

[0852] Output: Knowledge entries stored in the database

[0853] Step 4: Initialize the advice generator

[0854] The server initializes a generative AI model (e.g., a GPT model) to generate advice. This involves loading the model file and performing the necessary configuration. For example, it loads the model using Python libraries. It then executes the code `from transformers import GPT2LMHeadModel, GPT2Tokenizer` to initialize the model and tokenizer.

[0855] Input: Model file and configuration information

[0856] Output: Initialized Generative AI Model

[0857] Step 5: Receiving a request for advice

[0858] The user requests advice on a specific project through their device. For example, they might request, "Please give me advice on Project ID 1." The device then sends this request data to the server via the API.

[0859] Input: User advice request data

[0860] Output: Request data sent to the server

[0861] Step 6: Knowledge Search

[0862] After receiving the request data, the server searches the database for knowledge related to the specified project ID. For example, it executes an SQL query such as SELECT knowledge_text FROM knowledge_entries WHERE project_id = 1; to retrieve the relevant knowledge.

[0863] Input: Request data based on Project ID

[0864] Output: Acquired knowledge data

[0865] Step 7: Generating Advice

[0866] The server generates prompts based on the acquired knowledge and inputs them into the generating AI model. For example, a generated prompt might be, "Generate advice for Project ID 1: Prioritize regular communication with customers and thoroughly manage document versions." The server then uses the generating AI model to generate an advice statement and sends the result to the terminal.

[0867] Input: Prompt text and knowledge data

[0868] Output: Generated advice text

[0869] Step 8: Providing advice

[0870] The device analyzes the advice received from the server and presents it to the user. For example, the following content will be displayed on the device's UI:

[0871] Points to note:

[0872] We value regular communication with our customers.

[0873] Thoroughly implement version control for documents.

[0874] Input: Generated advice text

[0875] Output: Advice message presented to the user

[0876] (Application Example 1)

[0877] 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."

[0878] In factory manufacturing and maintenance processes, there is a need for systems that properly manage acquired knowledge and enable new workers and maintenance personnel to effectively utilize past knowledge. However, current systems often do not properly organize knowledge, making it difficult to quickly obtain necessary information. As a result, they cannot contribute to operational efficiency or quality improvement, and this is a major challenge, especially for newly joined workers.

[0879] 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.

[0880] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using the knowledge, means for providing the generated advice to the user's terminal, means for systematically storing knowledge related to a specific project, means for searching for knowledge based on a project ID and generating advice statements, and means for applying the advice to improve the efficiency of manufacturing and maintenance processes in the factory. This enables improved efficiency in manufacturing and maintenance processes in the factory, as well as smooth knowledge utilization by workers and maintenance personnel.

[0881] A "project" is a unit of work or project set up to achieve a specific objective.

[0882] "Knowledge" refers to the knowledge, information, and technical know-how acquired during the course of work or projects.

[0883] A "database" is an information management system that systematically stores acquired knowledge and allows for searching and retrieval as needed.

[0884] A "device" refers to a computer, smartphone, tablet, or other device used by a user to receive advice.

[0885] A "Project ID" is an identifier used to uniquely identify a specific project.

[0886] "Advice" refers to suggestions and instructions generated based on past knowledge, with the aim of improving work efficiency and quality.

[0887] A "manufacturing process" refers to a series of work steps involved in the production of a product in a factory.

[0888] A "maintenance process" refers to a series of steps involved in the maintenance and management of machinery and equipment in a factory.

[0889] "Efficiency improvement" refers to improving processes and methods to perform tasks and work more quickly and effectively.

[0890] A "new project manager" refers to a worker or staff member newly assigned to a specific project or task.

[0891] This invention relates to a system aimed at improving the efficiency of factory manufacturing and maintenance processes. It stores knowledge acquired during a project in a database and generates and provides that knowledge as advice for new project managers.

[0892] First, the server initializes the knowledge base. The knowledge base is a database for systematically storing acquired knowledge. This database includes operational notes and important advice related to each project ID.

[0893] The server has the functionality to add knowledge acquired by users during their work to the database. For example, practical knowledge such as "regularly inspect the robot's sensors" or "inspect all screws during regular maintenance" in manufacturing and maintenance processes can be added.

[0894] Next, the server initializes an advice generator to generate advice using the stored knowledge. The advice generator searches for relevant knowledge based on a specific project ID and generates an advice statement based on its content.

[0895] When a user takes on a new project or works on a similar project, their device (smartphone or tablet) generates advice for the new project manager. This advice generator searches the knowledge base based on the project ID, retrieves relevant entries, and then generates the advice text.

[0896] As a concrete example, the following advice may be generated during the maintenance process:

[0897] "We will regularly inspect the robot's sensors."

[0898] "Inspect all screws during routine maintenance."

[0899] This advice is designed to help ensure the smooth progress of projects and streamline maintenance tasks. Users can receive real-time advice via their devices and use it to advance their work, thereby achieving high work efficiency.

[0900] As an example of a prompt, the server might instruct the system to generate advice in the form of, "If the project ID is 'maintenance_1', please provide advice based on the relevant knowledge base." This allows the AI ​​model to provide appropriate advice.

[0901] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0902] Step 1:

[0903] The server initializes the knowledge base. First, it creates an empty database and sets up a structure for organizing knowledge based on the project ID. For example, it can use a JSON database file or an SQL database. The input to this process is an empty database structure, and the output is an initialized database.

[0904] Step 2:

[0905] The system sends knowledge acquired by the user during their work to the server. This is a process in which the user inputs knowledge through a dedicated interface and transfers it to the server. The input is the knowledge information entered by the user (e.g., "Regularly inspect the robot's sensors"), and the output is the database with a new knowledge entry added.

[0906] Step 3:

[0907] The server stores the received knowledge in a database. During storage, the knowledge is organized by project ID. The input is the knowledge information and project ID submitted by the user, and the output is the knowledge entry that has been securely stored in the database.

[0908] Step 4:

[0909] The server initializes the advice generator. This is the process of setting up an algorithm to search the knowledge base and generate appropriate advice statements. The input is the initialization configuration file, and the output is the available advice generators.

[0910] Step 5:

[0911] When a user takes on a new project, the terminal sends a specific project ID to the server. The server then begins generating advice based on that project ID. The input is the project ID sent by the user, and the output is the project ID as it reaches the server.

[0912] Step 6:

[0913] The server searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is a list of knowledge entries associated with that ID.

[0914] Step 7:

[0915] The server generates advice statements based on the acquired knowledge entries. In this process, it uses a generation AI model (e.g., GPT-3) to construct advice statements based on past knowledge. The input is a list of knowledge entries, and the output is the generated advice statement.

[0916] Step 8:

[0917] The server sends the generated advice message to the terminal. The terminal displays the advice message, making it available for the user to view. The input is the generated advice message, and the output is the advice message displayed on the user's terminal.

[0918] Step 9:

[0919] Users proceed with their tasks while referring to advice generated using the terminal. This will improve work efficiency and ensure smoother manufacturing and maintenance processes. The input is the advice displayed on the terminal, and the output is the efficient progress of the tasks.

[0920] 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.

[0921] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and adjusts the content and format of the generated advice based on the user's emotions.

[0922] Knowledge base initialization

[0923] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[0924] Adding Knowledge

[0925] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[0926] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[0927] Initialization of the advice generator

[0928] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[0929] Emotion engine initialization

[0930] The server initializes an emotion engine to recognize the user's emotions. The emotion engine recognizes emotions from the user's voice, facial expressions, or text.

[0931] Generating advice

[0932] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[0933] Adjusting emotion-based advice

[0934] The server uses an emotion engine to recognize the user's emotions. Based on the recognized emotions, it adjusts the content and format of the advice it generates. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[0935] Providing advice

[0936] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[0937] Points to note:

[0938] We value regular communication with our customers.

[0939] Thoroughly implement version control for documents.

[0940] In addition, the system provides additional advice tailored to the user's emotions. For example, if the user is feeling anxious, it might offer the following advice:

[0941] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0942] We hold regular meetings with the team.

[0943] We will quickly incorporate customer feedback.

[0944] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[0945] Specific example

[0946] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[0947] Points to note:

[0948] We value regular communication with our customers.

[0949] Thoroughly implement version control for documents.

[0950] Furthermore, if the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[0951] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0952] We hold regular meetings with the team.

[0953] We will quickly incorporate customer feedback.

[0954] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[0955] The following describes the processing flow.

[0956] Step 1:

[0957] The server initializes the knowledge base. This involves creating an instance of the KnowledgeBase class, which initializes an empty data dictionary, self.data.

[0958] Step 2:

[0959] Users input knowledge gained during their work and send it to the server. Specifically, this involves entering the entry "Value regular communication with customers" for "Project ID 1" through the interface.

[0960] Step 3:

[0961] The server saves the submitted knowledge to the database. Calling the add_entry method adds project ID 1 and an entry to self.data.

[0962] Step 4:

[0963] The server initializes the advice generator. This involves creating an instance of the AdviceGenerator class, passing the knowledge base as an argument, and calling the __init__ method to store the knowledge base in the instance variable self.knowledge_base.

[0964] Step 5:

[0965] The server initializes the emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, or text, and it loads the necessary libraries and models, creates instances, and initializes them.

[0966] Step 6:

[0967] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[0968] Step 7:

[0969] The server generates advice based on the project ID through the `generate_advice` method. First, it calls the `get_entries` method to retrieve entries related to project ID 1, and then generates an advice statement based on their contents.

[0970] Step 8:

[0971] The server uses an emotion engine to recognize the user's emotions. User voice and text data are input into the emotion engine for emotion classification.

[0972] Step 9:

[0973] The server adjusts the content and format of the advice based on the recognized emotions. If the user expresses positive emotions, it generates motivational advice; if they express negative emotions, it generates advice that includes encouragement and specific solutions.

[0974] Step 10:

[0975] The device provides the generated advice to the user. The generated advice text is displayed on the user's screen so that the user can refer to it.

[0976] For example, the following advice is offered:

[0977] Points to note:

[0978] We value regular communication with our customers.

[0979] Thoroughly implement version control for documents.

[0980] If the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[0981] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[0982] We hold regular meetings with the team.

[0983] We will quickly incorporate customer feedback.

[0984] (Example 2)

[0985] 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."

[0986] Traditional project management systems struggled to accumulate knowledge gained during project progress and effectively provide it to new project managers. Furthermore, they were unable to provide advice that considered user emotions or offer appropriate support tailored to the user's situation. This made it difficult to improve work efficiency and quality, sometimes leading to user stress and confusion.

[0987] 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.

[0988] In this invention, the server includes means for storing knowledge acquired during the progress of a case in data storage, means for generating advice for new case managers using the stored knowledge, and means for adjusting the content of the advice using an emotion recognition engine that recognizes the user's emotions. This makes it possible to systematically accumulate knowledge acquired during the progress of a case and provide situation-appropriate advice to new case managers. Furthermore, by recognizing the user's emotions and adjusting the content of the advice, it is possible to provide appropriate support tailored to the user's situation, thereby improving the efficiency and quality of operations.

[0989] A "case" is a unit of work activity, such as a project or task, that has a specific purpose and deadline.

[0990] "Knowledge" refers to information acquired during the course of work, including experience, know-how, unwritten rules, and points to note when carrying out work.

[0991] "Data storage" refers to a storage device or database used to accumulate and preserve acquired knowledge.

[0992] "Advice" refers to recommendations, points of caution, and suggestions provided to help a new project manager perform their duties efficiently.

[0993] An "emotion recognition engine" is a technology or software that analyzes and recognizes emotions from a user's voice, facial expressions, text, etc.

[0994] "Users" refer to individuals or corporations that use the system, and in this context, specifically to employees or staff responsible for a project.

[0995] A "device" refers to a computer, smartphone, or other device accessible to a user.

[0996] "Project identification information" refers to information used to uniquely identify each project, and includes project IDs, task IDs, etc.

[0997] This system stores knowledge acquired during business processes in data storage and uses that knowledge to generate advice for new project managers. Furthermore, by combining it with an emotion recognition engine, the content and format of the advice can be adjusted according to the user's emotions.

[0998] Knowledge base initialization

[0999] The server initializes a database to store knowledge acquired during business processes. Specifically, it uses a database management system (DBMS) such as SQL to create tables that store project IDs and knowledge items.

[1000] Adding Knowledge

[1001] Users input knowledge gained during their work and send it to the server. Using the terminal interface, users enter the acquired knowledge into a text box and press the send button to send the data to the server.

[1002] The server receives the submitted knowledge and stores it in the database. Specifically, it parses the data received via the API and inserts it into the appropriate table. For example, it adds an entry "Value regular communication with customers" to Project ID 1.

[1003] Initialization of the advice generator

[1004] The server initializes an advice generator to generate advice using stored knowledge. This generator uses a generative AI model to produce advice based on knowledge related to a specific project ID.

[1005] Emotion engine initialization

[1006] The server initializes an emotion recognition engine to recognize the user's emotions. This engine analyzes the user's emotions by combining speech recognition, facial expression analysis, text analysis, and other technologies. Specifically, it uses Google Cloud Speech-to-Text for speech recognition, OpenCV for facial expression analysis, and a natural language processing library for text analysis.

[1007] Generating and providing advice

[1008] When a new project manager requests advice, the terminal generates advice for a specific project ID. Once the user enters the project ID and sends it to the server using the submit button, the server searches its database based on that project ID and retrieves the relevant entry.

[1009] Based on the acquired entries, the advice generator produces advice text. The generated advice text is adjusted in content and format to take the user's emotions into consideration and is provided to the user through the device.

[1010] Specific example

[1011] For example, suppose a new user has been assigned to Project ID 1. That user might receive the following advice:

[1012] Points to note:

[1013] We value regular communication with our customers.

[1014] Thoroughly implement version control for documents.

[1015] Furthermore, if the emotion recognition engine detects that the user is feeling anxious, the following additional advice will be provided:

[1016] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[1017] We hold regular meetings with the team.

[1018] We will quickly incorporate customer feedback.

[1019] This allows users to receive necessary advice in real time, improving the efficiency and quality of their work. The system effectively utilizes knowledge gained during project progress and enables the provision of appropriate support tailored to the user's needs and emotions.

[1020] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1021] Step 1:

[1022] Knowledge base initialization

[1023] The server initializes a database to store knowledge acquired during business processes. This involves using a database management system (DBMS) to create the necessary tables (for example, tables to store project IDs and knowledge items).

[1024] The specific operation involves creating a table using an SQL statement and inserting initial data.

[1025] Input: Connection information to the DBMS

[1026] Output: Initialized database

[1027] Step 2:

[1028] Adding Knowledge

[1029] The user inputs the knowledge gained during the course of their work and sends it to the server. The user uses the terminal interface to enter the acquired knowledge into the text box and press the submit button.

[1030] The server receives the submitted knowledge and stores it in a database. Specifically, it processes the received data using an API and inserts it into the appropriate table.

[1031] Input: Knowledge information entered by the user, Project ID

[1032] Output: Knowledge stored in the database

[1033] Step 3:

[1034] Initialization of the advice generator

[1035] The server initializes an advice generator to generate advice using stored knowledge. This generator is configured by loading a generative AI model and ingesting training data.

[1036] The specific steps involve importing a library of generative AI models, loading the models, and feeding them data.

[1037] Input: Stored knowledge database, generative AI model

[1038] Output: Initialized advice generator

[1039] Step 4:

[1040] Emotion engine initialization

[1041] The server initializes an emotion recognition engine to recognize the user's emotions. This emotion recognition engine is built by combining speech recognition, facial expression analysis, and text analysis technologies. Specifically, it utilizes Google Cloud Speech-to-Text and OpenCV libraries.

[1042] In terms of specific actions, this involves importing these libraries, reading the configuration file, and initializing the model.

[1043] Input: Configuration file for emotion recognition engine, a set of recognition technology libraries

[1044] Output: Initialized emotion recognition engine

[1045] Step 5:

[1046] Generating advice

[1047] When a new project manager requests advice, the terminal sends the project ID to the server. The server searches the database based on that project ID and retrieves the relevant knowledge.

[1048] The server generates advice using an AI model based on the acquired knowledge.

[1049] Specifically, the process involves performing an SQL search based on the project ID, inputting the retrieved data into a generation AI model, and then generating advice statements.

[1050] Input: Project ID, Knowledge Database

[1051] Output: Generated advice

[1052] Step 6:

[1053] Adjusting emotion-based advice

[1054] The server recognizes the user's emotions using an emotion recognition engine. When the user inputs voice or text, the emotion recognition engine analyzes that data.

[1055] Based on the recognized emotions, the content and format of the generated advice text are adjusted.

[1056] Specifically, this involves applying an algorithm to modify the advice text generated based on the analyzed sentiment data.

[1057] Input: User sentiment data, generated advice

[1058] Output: Adjusted advice

[1059] Step 7:

[1060] Providing advice

[1061] When a user takes on a new project, the device displays generated advice to the user. The user reviews the advice on the device screen to use as a reference for proceeding with the work.

[1062] Specifically, this involves displaying advice messages on the user interface so that users can review them.

[1063] Input: Adjusted advice

[1064] Output: Advice displayed on the user's terminal

[1065] (Application Example 2)

[1066] 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."

[1067] Improving efficiency and accuracy in logistics centers is crucial. However, adapting to inexperienced workers and newly added work processes requires the efficient use of past knowledge and know-how. Furthermore, stress and anxiety experienced by workers during work often negatively impact operational efficiency. Therefore, it is necessary to understand the psychological state of workers and provide appropriate advice.

[1068] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1069] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using that knowledge, means for providing the generated advice to the user's terminal, and means for adjusting the content and format of the advice using an emotion engine that recognizes the user's emotions. This makes it possible to store knowledge acquired during work in a database and recognize the emotions of workers to provide appropriate advice in order to optimize the efficiency of logistics operations in real time.

[1070] "Knowledge" refers to the information and know-how acquired during the progress of a project.

[1071] A "database" is a system for systematically storing acquired knowledge and managing it in a searchable format.

[1072] "Advice" refers to specific advice given to a new project manager based on past knowledge.

[1073] "User's device" refers to the device used to display the advice (e.g., a smartphone, tablet, or computer).

[1074] An "emotion engine" is a system that recognizes emotions from a user's voice, facial expressions, or text.

[1075] "Real-time" refers to a state where work can be reflected and responded to immediately without delay while it is in progress.

[1076] This invention is a system for optimizing operational efficiency in logistics centers and consists of multiple elements. Specific embodiments are described below.

[1077] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[1078] Next, the user inputs the knowledge gained during the process and sends it to the server. For example, an entry such as "Ensure all packages are correctly labeled" might be added. The server stores this knowledge in a database and organizes the knowledge relevant to each project by project ID.

[1079] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on that content.

[1080] The emotion engine is also initialized. The emotion engine recognizes emotions from the user's voice, facial expressions, or text. This engine is used to analyze the user's emotions and adjust the content and format of the advice.

[1081] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[1082] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[1083] When a user takes on a new project or works on a similar one, the device provides generated advice. For example, in addition to general precautions such as "Make sure your packages are properly labeled," it also offers emotionally-based advice such as "Don't worry, taking breaks will help you work more efficiently."

[1084] Specific example

[1085] scenario

[1086] A new logistics worker was assigned to the center. During his work, he felt overwhelmed by the workload and sent a request for an "emotion check" via the application.

[1087] Prompt example

[1088] "I'm feeling a bit overwhelmed by the amount of work."

[1089] Application response

[1090] Basic advice:

[1091] Make sure your package is correctly labeled.

[1092] Organize your workspace to avoid errors.

[1093] Emotional advice:

[1094] Don't worry, take a deep breath and work without rushing. This will make it easier to calmly solve the problem.

[1095] This embodiment allows logistics center workers to receive appropriate advice in real time, improving work efficiency and psychological stability.

[1096] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1097] Step 1:

[1098] The server initializes the knowledge base. During this process, it creates a database and prepares tables to store knowledge related to cases and projects. The input here is the system's initial settings, and the output is an empty database.

[1099] Step 2:

[1100] Users input knowledge gained during their work and send it to the server. The server stores this input knowledge in a database. The input data is knowledge information for a specific project ID, and the output is the knowledge stored in the database. Specifically, users might input something like, "Verify that the packages are correctly labeled."

[1101] Step 3:

[1102] The server initializes the advice generator to generate advice using stored knowledge. The advice generator extracts knowledge related to a specific project ID and generates advice based on that content. The input is the project ID, and the output is the generated advice.

[1103] Step 4:

[1104] The server initializes the emotion engine. The emotion engine is a module that recognizes emotions from the user's voice, facial expressions, or text. The input here is the user's facial expressions or text data, and the output is the recognized emotion. Specifically, the emotion recognition algorithm performs analysis to determine whether the user is experiencing stress.

[1105] Step 5:

[1106] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is the corresponding advice statement. Specifically, it executes a database query to retrieve relevant knowledge and generates an advice statement based on that.

[1107] Step 6:

[1108] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. The input is the emotion recognition result and the generated advice text, and the output is the adjusted advice text. For example, if a negative emotion is recognized, the server will add advice text that includes words of encouragement and specific countermeasures.

[1109] Step 7:

[1110] When a user takes on a new project or works on a similar one, the terminal presents the user with generated advice. The input is the adjusted advice text, and the output is the advice message displayed on the user's terminal. Specifically, the generated advice text is displayed on the user's screen, and audio guidance is provided if necessary.

[1111] By following these steps, logistics center workers can receive accurate advice in real time, improving work efficiency and psychological well-being.

[1112] 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.

[1113] 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.

[1114] 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.

[1115] [Fourth Embodiment]

[1116] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1117] 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.

[1118] 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).

[1119] 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.

[1120] 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.

[1121] 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).

[1122] 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.

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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".

[1129] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[1130] Knowledge base initialization

[1131] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes. This database includes implicit rules and important considerations associated with each project ID.

[1132] Adding Knowledge

[1133] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[1134] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[1135] Initialization of the advice generator

[1136] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[1137] Generating advice

[1138] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[1139] Providing advice

[1140] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[1141] Points to note:

[1142] We value regular communication with our customers.

[1143] Thoroughly implement version control for documents.

[1144] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[1145] Specific example

[1146] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[1147] Points to note:

[1148] We value regular communication with our customers.

[1149] Thoroughly implement version control for documents.

[1150] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[1151] The following describes the processing flow.

[1152] Step 1:

[1153] The server initializes the knowledge base. This is done by creating an instance of the KnowledgeBase class. Specifically, the __init__ method is called, and an empty data dictionary self.data is initialized.

[1154] Step 2:

[1155] Users input knowledge gained during their work and send it to the server. For example, for project ID 1, they might input the entry "Value regular communication with customers."

[1156] Step 3:

[1157] The server saves the submitted knowledge to the database. Specifically, the add_entry method is called, and project ID 1 and the entry are added to self.data.

[1158] Step 4:

[1159] The server initializes the advice generator. This is done by creating an instance of the AdviceGenerator class and passing the knowledge base as an argument. Specifically, the __init__ method is called, and the knowledge base is stored in the instance variable self.knowledge_base.

[1160] Step 5:

[1161] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[1162] Step 6:

[1163] The server generates advice based on the project ID through the `generate_advice` method. Specifically, the `get_entries` method is called to retrieve entries related to project ID 1. Then, advice statements are generated based on the retrieved entries.

[1164] Step 7:

[1165] The device provides the generated advice to the user. Specifically, the advice text is displayed on the user's device. For example, the following advice may be presented:

[1166] Points to note:

[1167] We value regular communication with our customers.

[1168] Thoroughly implement version control for documents.

[1169] Step 8:

[1170] Users will use this advice to guide their work. This will lead to smoother project progress and prevent past problems from occurring.

[1171] (Example 1)

[1172] 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".

[1173] Traditional advice systems fail to effectively utilize knowledge gained from past projects, potentially leading new project managers to repeat past mistakes and pitfalls. Furthermore, a lack of systematic methods for storing and retrieving knowledge makes it difficult to provide necessary information quickly.

[1174] 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.

[1175] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for users to input and transmit knowledge obtained during the progress of their work to the server, means for the server to store project-related knowledge in a database, means for the server to initialize a generation AI model in order to generate advice using the stored knowledge, means for a terminal to generate advice based on the project ID when a new case manager requests advice, and means for providing the generated advice to the user's terminal. This makes it possible to effectively store and retrieve knowledge and to quickly provide appropriate advice.

[1176] A "project" refers to an ongoing project or a portion of a business activity, each with its own unique identifier.

[1177] "Knowledge" refers to information such as insights, experience, unwritten rules, and points to note that are gained during the course of work.

[1178] A "database" refers to a system that systematically stores information and facilitates searching and management.

[1179] A "server" refers to a computer system that manages and runs databases and advice generators.

[1180] A "user" refers to an entity that uses the system to input knowledge and receive advice.

[1181] "Terminal" refers to a device or interface that a user accesses.

[1182] An "advice generator" refers to a tool or algorithm that generates advice relevant to a specific project based on stored knowledge.

[1183] A "generative AI model" refers to a system that uses artificial intelligence technologies, such as large-scale language models, to generate text and extract knowledge.

[1184] "Project ID" refers to an identifier used to uniquely identify each project.

[1185] A "prompt" refers to an instruction or question that is input to a generative AI model.

[1186] "Initialization" refers to setting a system or tool to a usable state.

[1187] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Specific embodiments of this system are described below.

[1188] Knowledge base initialization

[1189] The server first initializes the knowledge base. This knowledge base is a database for systematically storing knowledge acquired during business processes. Specifically, the server uses database software (e.g., MySQL) to generate the necessary tables. The tables include a project ID to uniquely identify each project and columns for storing knowledge entries.

[1190] Adding Knowledge

[1191] Users input knowledge gained during their work into the system from their terminal. For example, they might add the knowledge "Value regular communication with customers" to "Project ID 1". The terminal sends this input data to the server via API, and the server saves the received data to a database. SQL queries are used for this saving process.

[1192] Initialization of the advice generator

[1193] The server initializes a generative AI model (e.g., a GPT model) for generating advice. This involves loading the model file and setting the configuration to apply. For example, the model might be loaded using a Python library.

[1194] Generating and providing advice

[1195] When a user takes on a new project, they request advice on a specific project from their terminal. This request is sent to the server, which, upon receiving the request, retrieves knowledge related to the specified project ID from its database. Using the retrieved knowledge, a generation AI model generates prompts, and an advice generator then generates specific advice based on that knowledge.

[1196] The generated advice is provided to the user via the terminal. This allows the user to obtain the knowledge necessary for their work in real time, contributing to improved work efficiency and quality. Examples of specific prompt messages are as follows:

[1197] Generate advice for Project ID 1. Extract relevant information from previously entered knowledge base entries and create an advice statement based on that information.

[1198] Specific example

[1199] For example, suppose a user has been newly assigned to "Project ID 1". This user will receive the following advice based on a knowledge base gained from past projects:

[1200] Points to note:

[1201] We value regular communication with our customers.

[1202] Thoroughly implement version control for documents.

[1203] This advice helps support the smooth progress of the project and prevents past problems from occurring. By using the advice received as a guide, users can achieve higher work efficiency.

[1204] The above describes embodiments for carrying out the present invention.

[1205] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1206] Step 1: Knowledge Base Initialization

[1207] The server initializes the knowledge base when the system starts up. Specifically, it uses database software (e.g., MySQL) to create the necessary tables. These tables include columns such as project ID, knowledge entry, and timestamp. The server establishes a connection to the database and executes an SQL query like the following: CREATE TABLE IF NOT EXISTS knowledge_entries (entry_id INT AUTO_INCREMENT PRIMARY KEY, project_id INT, knowledge_text TEXT, timestamp DATETIME);

[1208] Input: None

[1209] Output: Initialized database

[1210] Step 2: Enter and submit knowledge

[1211] Users input knowledge gained during their work into the system from their terminal. For example, they might input the knowledge "Value regular communication with customers" for "Project ID 1." The terminal then sends this input data to the server via an API.

[1212] Input: Knowledge information entered by the user into the terminal.

[1213] Output: Knowledge data sent to the server

[1214] Step 3: Knowledge Preservation

[1215] The server receives the submitted knowledge data and stores it in the database. Specifically, it generates and executes the SQL query: INSERT INTO knowledge_entries (project_id, knowledge_text, timestamp) VALUES (1, 'We value regular communication with our customers', NOW()); This stores the knowledge in the database.

[1216] Input: Knowledge data received from the API

[1217] Output: Knowledge entries stored in the database

[1218] Step 4: Initialize the advice generator

[1219] The server initializes a generative AI model (e.g., a GPT model) to generate advice. This involves loading the model file and performing the necessary configuration. For example, it loads the model using Python libraries. It then executes the code `from transformers import GPT2LMHeadModel, GPT2Tokenizer` to initialize the model and tokenizer.

[1220] Input: Model file and configuration information

[1221] Output: Initialized Generative AI Model

[1222] Step 5: Receiving a request for advice

[1223] The user requests advice on a specific project through their device. For example, they might request, "Please give me advice on Project ID 1." The device then sends this request data to the server via the API.

[1224] Input: User advice request data

[1225] Output: Request data sent to the server

[1226] Step 6: Knowledge Search

[1227] After receiving the request data, the server searches the database for knowledge related to the specified project ID. For example, it executes an SQL query such as SELECT knowledge_text FROM knowledge_entries WHERE project_id = 1; to retrieve the relevant knowledge.

[1228] Input: Request data based on Project ID

[1229] Output: Acquired knowledge data

[1230] Step 7: Generating Advice

[1231] The server generates prompts based on the acquired knowledge and inputs them into the generating AI model. For example, a generated prompt might be, "Generate advice for Project ID 1: Prioritize regular communication with customers and thoroughly manage document versions." The server then uses the generating AI model to generate an advice statement and sends the result to the terminal.

[1232] Input: Prompt text and knowledge data

[1233] Output: Generated advice text

[1234] Step 8: Providing advice

[1235] The device analyzes the advice received from the server and presents it to the user. For example, the following content will be displayed on the device's UI:

[1236] Points to note:

[1237] We value regular communication with our customers.

[1238] Thoroughly implement version control for documents.

[1239] Input: Generated advice text

[1240] Output: Advice message presented to the user

[1241] (Application Example 1)

[1242] 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".

[1243] In factory manufacturing and maintenance processes, there is a need for systems that properly manage acquired knowledge and enable new workers and maintenance personnel to effectively utilize past knowledge. However, current systems often do not properly organize knowledge, making it difficult to quickly obtain necessary information. As a result, they cannot contribute to operational efficiency or quality improvement, and this is a major challenge, especially for newly joined workers.

[1244] 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.

[1245] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using the knowledge, means for providing the generated advice to the user's terminal, means for systematically storing knowledge related to a specific project, means for searching for knowledge based on a project ID and generating advice statements, and means for applying the advice to improve the efficiency of manufacturing and maintenance processes in the factory. This enables improved efficiency in manufacturing and maintenance processes in the factory, as well as smooth knowledge utilization by workers and maintenance personnel.

[1246] A "project" is a unit of work or project set up to achieve a specific objective.

[1247] "Knowledge" refers to the knowledge, information, and technical know-how acquired during the course of work or projects.

[1248] A "database" is an information management system that systematically stores acquired knowledge and allows for searching and retrieval as needed.

[1249] A "device" refers to a computer, smartphone, tablet, or other device used by a user to receive advice.

[1250] A "Project ID" is an identifier used to uniquely identify a specific project.

[1251] "Advice" refers to suggestions and instructions generated based on past knowledge, with the aim of improving work efficiency and quality.

[1252] A "manufacturing process" refers to a series of work steps involved in the production of a product in a factory.

[1253] A "maintenance process" refers to a series of steps involved in the maintenance and management of machinery and equipment in a factory.

[1254] "Efficiency improvement" refers to improving processes and methods to perform tasks and work more quickly and effectively.

[1255] A "new project manager" refers to a worker or staff member newly assigned to a specific project or task.

[1256] This invention relates to a system aimed at improving the efficiency of factory manufacturing and maintenance processes. It stores knowledge acquired during a project in a database and generates and provides that knowledge as advice for new project managers.

[1257] First, the server initializes the knowledge base. The knowledge base is a database for systematically storing acquired knowledge. This database includes operational notes and important advice related to each project ID.

[1258] The server has the functionality to add knowledge acquired by users during their work to the database. For example, practical knowledge such as "regularly inspect the robot's sensors" or "inspect all screws during regular maintenance" in manufacturing and maintenance processes can be added.

[1259] Next, the server initializes an advice generator to generate advice using the stored knowledge. The advice generator searches for relevant knowledge based on a specific project ID and generates an advice statement based on its content.

[1260] When a user takes on a new project or works on a similar project, their device (smartphone or tablet) generates advice for the new project manager. This advice generator searches the knowledge base based on the project ID, retrieves relevant entries, and then generates the advice text.

[1261] As a concrete example, the following advice may be generated during the maintenance process:

[1262] "We will regularly inspect the robot's sensors."

[1263] "Inspect all screws during routine maintenance."

[1264] This advice is designed to help ensure the smooth progress of projects and streamline maintenance tasks. Users can receive real-time advice via their devices and use it to advance their work, thereby achieving high work efficiency.

[1265] As an example of a prompt, the server might instruct the system to generate advice in the form of, "If the project ID is 'maintenance_1', please provide advice based on the relevant knowledge base." This allows the AI ​​model to provide appropriate advice.

[1266] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1267] Step 1:

[1268] The server initializes the knowledge base. First, it creates an empty database and sets up a structure for organizing knowledge based on the project ID. For example, it can use a JSON database file or an SQL database. The input to this process is an empty database structure, and the output is an initialized database.

[1269] Step 2:

[1270] The system sends knowledge acquired by the user during their work to the server. This is a process in which the user inputs knowledge through a dedicated interface and transfers it to the server. The input is the knowledge information entered by the user (e.g., "Regularly inspect the robot's sensors"), and the output is the database with a new knowledge entry added.

[1271] Step 3:

[1272] The server stores the received knowledge in a database. During storage, the knowledge is organized by project ID. The input is the knowledge information and project ID submitted by the user, and the output is the knowledge entry that has been securely stored in the database.

[1273] Step 4:

[1274] The server initializes the advice generator. This is the process of setting up an algorithm to search the knowledge base and generate appropriate advice statements. The input is the initialization configuration file, and the output is the available advice generators.

[1275] Step 5:

[1276] When a user takes on a new project, the terminal sends a specific project ID to the server. The server then begins generating advice based on that project ID. The input is the project ID sent by the user, and the output is the project ID as it reaches the server.

[1277] Step 6:

[1278] The server searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is a list of knowledge entries associated with that ID.

[1279] Step 7:

[1280] The server generates advice statements based on the acquired knowledge entries. In this process, it uses a generation AI model (e.g., GPT-3) to construct advice statements based on past knowledge. The input is a list of knowledge entries, and the output is the generated advice statement.

[1281] Step 8:

[1282] The server sends the generated advice message to the terminal. The terminal displays the advice message, making it available for the user to view. The input is the generated advice message, and the output is the advice message displayed on the user's terminal.

[1283] Step 9:

[1284] Users proceed with their tasks while referring to advice generated using the terminal. This will improve work efficiency and ensure smoother manufacturing and maintenance processes. The input is the advice displayed on the terminal, and the output is the efficient progress of the tasks.

[1285] 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.

[1286] This invention relates to a system that stores knowledge acquired during the progress of a case in a database and generates and provides it as advice for new case managers. Furthermore, it incorporates an emotion engine that recognizes the user's emotions and adjusts the content and format of the generated advice based on the user's emotions.

[1287] Knowledge base initialization

[1288] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[1289] Adding Knowledge

[1290] Users input knowledge gained during their work and send it to the server. For example, an entry titled "Value regular communication with customers" might be added for Project ID 1. An entry regarding the importance of document management might also be added.

[1291] The server stores this knowledge in a database. Knowledge related to each project is organized by project ID and stored in a way that allows for unique identification.

[1292] Initialization of the advice generator

[1293] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on its content.

[1294] Emotion engine initialization

[1295] The server initializes an emotion engine to recognize the user's emotions. The emotion engine recognizes emotions from the user's voice, facial expressions, or text.

[1296] Generating advice

[1297] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[1298] Adjusting emotion-based advice

[1299] The server uses an emotion engine to recognize the user's emotions. Based on the recognized emotions, it adjusts the content and format of the advice it generates. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[1300] Providing advice

[1301] When a user takes on a new project or works on a similar one, the device presents the user with generated advice. The advice is provided in the following format:

[1302] Points to note:

[1303] We value regular communication with our customers.

[1304] Thoroughly implement version control for documents.

[1305] In addition, the system provides additional advice tailored to the user's emotions. For example, if the user is feeling anxious, it might offer the following advice:

[1306] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[1307] We hold regular meetings with the team.

[1308] We will quickly incorporate customer feedback.

[1309] In this way, users can receive necessary advice in real time, contributing to improvements in the efficiency and quality of their work.

[1310] Specific example

[1311] For example, suppose a user has been newly assigned to Project ID 1. This user receives the following advice based on a knowledge base gained from past projects.

[1312] Points to note:

[1313] We value regular communication with our customers.

[1314] Thoroughly implement version control for documents.

[1315] Furthermore, if the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[1316] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[1317] We hold regular meetings with the team.

[1318] We will quickly incorporate customer feedback.

[1319] This advice helps support the smooth progress of the project and prevents past problems from occurring. By taking the received advice into consideration when carrying out their work, users can achieve higher work efficiency. The above is an embodiment for carrying out the present invention.

[1320] The following describes the processing flow.

[1321] Step 1:

[1322] The server initializes the knowledge base. This involves creating an instance of the KnowledgeBase class, which initializes an empty data dictionary, self.data.

[1323] Step 2:

[1324] Users input knowledge gained during their work and send it to the server. Specifically, this involves entering the entry "Value regular communication with customers" for "Project ID 1" through the interface.

[1325] Step 3:

[1326] The server saves the submitted knowledge to the database. Calling the add_entry method adds project ID 1 and an entry to self.data.

[1327] Step 4:

[1328] The server initializes the advice generator. This involves creating an instance of the AdviceGenerator class, passing the knowledge base as an argument, and calling the __init__ method to store the knowledge base in the instance variable self.knowledge_base.

[1329] Step 5:

[1330] The server initializes the emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, or text, and it loads the necessary libraries and models, creates instances, and initializes them.

[1331] Step 6:

[1332] The terminal requests advice for a specific project. For example, the generate_advice method is called to generate advice for project ID 1.

[1333] Step 7:

[1334] The server generates advice based on the project ID through the `generate_advice` method. First, it calls the `get_entries` method to retrieve entries related to project ID 1, and then generates an advice statement based on their contents.

[1335] Step 8:

[1336] The server uses an emotion engine to recognize the user's emotions. User voice and text data are input into the emotion engine for emotion classification.

[1337] Step 9:

[1338] The server adjusts the content and format of the advice based on the recognized emotions. If the user expresses positive emotions, it generates motivational advice; if they express negative emotions, it generates advice that includes encouragement and specific solutions.

[1339] Step 10:

[1340] The device provides the generated advice to the user. The generated advice text is displayed on the user's screen so that the user can refer to it.

[1341] For example, the following advice is offered:

[1342] Points to note:

[1343] We value regular communication with our customers.

[1344] Thoroughly implement version control for documents.

[1345] If the emotion engine detects that the user is feeling anxious, it will provide additional advice such as the following:

[1346] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[1347] We hold regular meetings with the team.

[1348] We will quickly incorporate customer feedback.

[1349] (Example 2)

[1350] 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".

[1351] Traditional project management systems struggled to accumulate knowledge gained during project progress and effectively provide it to new project managers. Furthermore, they were unable to provide advice that considered user emotions or offer appropriate support tailored to the user's situation. This made it difficult to improve work efficiency and quality, sometimes leading to user stress and confusion.

[1352] 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.

[1353] In this invention, the server includes means for storing knowledge acquired during the progress of a case in data storage, means for generating advice for new case managers using the stored knowledge, and means for adjusting the content of the advice using an emotion recognition engine that recognizes the user's emotions. This makes it possible to systematically accumulate knowledge acquired during the progress of a case and provide situation-appropriate advice to new case managers. Furthermore, by recognizing the user's emotions and adjusting the content of the advice, it is possible to provide appropriate support tailored to the user's situation, thereby improving the efficiency and quality of operations.

[1354] A "case" is a unit of work activity, such as a project or task, that has a specific purpose and deadline.

[1355] "Knowledge" refers to information acquired during the course of work, including experience, know-how, unwritten rules, and points to note when carrying out work.

[1356] "Data storage" refers to a storage device or database used to accumulate and preserve acquired knowledge.

[1357] "Advice" refers to recommendations, points of caution, and suggestions provided to help a new project manager perform their duties efficiently.

[1358] An "emotion recognition engine" is a technology or software that analyzes and recognizes emotions from a user's voice, facial expressions, text, etc.

[1359] "Users" refer to individuals or corporations that use the system, and in this context, specifically to employees or staff responsible for a project.

[1360] A "device" refers to a computer, smartphone, or other device accessible to a user.

[1361] "Project identification information" refers to information used to uniquely identify each project, and includes project IDs, task IDs, etc.

[1362] This system stores knowledge acquired during business processes in data storage and uses that knowledge to generate advice for new project managers. Furthermore, by combining it with an emotion recognition engine, the content and format of the advice can be adjusted according to the user's emotions.

[1363] Knowledge base initialization

[1364] The server initializes a database to store knowledge acquired during business processes. Specifically, it uses a database management system (DBMS) such as SQL to create tables that store project IDs and knowledge items.

[1365] Adding Knowledge

[1366] Users input knowledge gained during their work and send it to the server. Using the terminal interface, users enter the acquired knowledge into a text box and press the send button to send the data to the server.

[1367] The server receives the submitted knowledge and stores it in the database. Specifically, it parses the data received via the API and inserts it into the appropriate table. For example, it adds an entry "Value regular communication with customers" to Project ID 1.

[1368] Initialization of the advice generator

[1369] The server initializes an advice generator to generate advice using stored knowledge. This generator uses a generative AI model to produce advice based on knowledge related to a specific project ID.

[1370] Emotion engine initialization

[1371] The server initializes an emotion recognition engine to recognize the user's emotions. This engine analyzes the user's emotions by combining speech recognition, facial expression analysis, text analysis, and other technologies. Specifically, it uses Google Cloud Speech-to-Text for speech recognition, OpenCV for facial expression analysis, and a natural language processing library for text analysis.

[1372] Generating and providing advice

[1373] When a new project manager requests advice, the terminal generates advice for a specific project ID. Once the user enters the project ID and sends it to the server using the submit button, the server searches its database based on that project ID and retrieves the relevant entry.

[1374] Based on the acquired entries, the advice generator produces advice text. The generated advice text is adjusted in content and format to take the user's emotions into consideration and is provided to the user through the device.

[1375] Specific example

[1376] For example, suppose a new user has been assigned to Project ID 1. That user might receive the following advice:

[1377] Points to note:

[1378] We value regular communication with our customers.

[1379] Thoroughly implement version control for documents.

[1380] Furthermore, if the emotion recognition engine detects that the user is feeling anxious, the following additional advice will be provided:

[1381] Don't worry. We've had similar problems in past projects, but we solved them with the following measures.

[1382] We hold regular meetings with the team.

[1383] We will quickly incorporate customer feedback.

[1384] This allows users to receive necessary advice in real time, improving the efficiency and quality of their work. The system effectively utilizes knowledge gained during project progress and enables the provision of appropriate support tailored to the user's needs and emotions.

[1385] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1386] Step 1:

[1387] Knowledge base initialization

[1388] The server initializes a database to store knowledge acquired during business processes. This involves using a database management system (DBMS) to create the necessary tables (for example, tables to store project IDs and knowledge items).

[1389] The specific operation involves creating a table using an SQL statement and inserting initial data.

[1390] Input: Connection information to the DBMS

[1391] Output: Initialized database

[1392] Step 2:

[1393] Adding Knowledge

[1394] The user inputs the knowledge gained during the course of their work and sends it to the server. The user uses the terminal interface to enter the acquired knowledge into the text box and press the submit button.

[1395] The server receives the submitted knowledge and stores it in a database. Specifically, it processes the received data using an API and inserts it into the appropriate table.

[1396] Input: Knowledge information entered by the user, Project ID

[1397] Output: Knowledge stored in the database

[1398] Step 3:

[1399] Initialization of the advice generator

[1400] The server initializes an advice generator to generate advice using stored knowledge. This generator is configured by loading a generative AI model and ingesting training data.

[1401] The specific steps involve importing a library of generative AI models, loading the models, and feeding them data.

[1402] Input: Stored knowledge database, generative AI model

[1403] Output: Initialized advice generator

[1404] Step 4:

[1405] Emotion engine initialization

[1406] The server initializes an emotion recognition engine to recognize the user's emotions. This emotion recognition engine is built by combining speech recognition, facial expression analysis, and text analysis technologies. Specifically, it utilizes Google Cloud Speech-to-Text and OpenCV libraries.

[1407] In terms of specific actions, this involves importing these libraries, reading the configuration file, and initializing the model.

[1408] Input: Configuration file for emotion recognition engine, a set of recognition technology libraries

[1409] Output: Initialized emotion recognition engine

[1410] Step 5:

[1411] Generating advice

[1412] When a new project manager requests advice, the terminal sends the project ID to the server. The server searches the database based on that project ID and retrieves the relevant knowledge.

[1413] The server generates advice using an AI model based on the acquired knowledge.

[1414] Specifically, the process involves performing an SQL search based on the project ID, inputting the retrieved data into a generation AI model, and then generating advice statements.

[1415] Input: Project ID, Knowledge Database

[1416] Output: Generated advice

[1417] Step 6:

[1418] Adjusting emotion-based advice

[1419] The server recognizes the user's emotions using an emotion recognition engine. When the user inputs voice or text, the emotion recognition engine analyzes that data.

[1420] Based on the recognized emotions, the content and format of the generated advice text are adjusted.

[1421] Specifically, this involves applying an algorithm to modify the advice text generated based on the analyzed sentiment data.

[1422] Input: User sentiment data, generated advice

[1423] Output: Adjusted advice

[1424] Step 7:

[1425] Providing advice

[1426] When a user takes on a new project, the device displays generated advice to the user. The user reviews the advice on the device screen to use as a reference for proceeding with the work.

[1427] Specifically, this involves displaying advice messages on the user interface so that users can review them.

[1428] Input: Adjusted advice

[1429] Output: Advice displayed on the user's terminal

[1430] (Application Example 2)

[1431] 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".

[1432] Improving efficiency and accuracy in logistics centers is crucial. However, adapting to inexperienced workers and newly added work processes requires the efficient use of past knowledge and know-how. Furthermore, stress and anxiety experienced by workers during work often negatively impact operational efficiency. Therefore, it is necessary to understand the psychological state of workers and provide appropriate advice.

[1433] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1434] In this invention, the server includes means for storing knowledge acquired during the progress of a case in a database, means for generating advice for new case managers using that knowledge, means for providing the generated advice to the user's terminal, and means for adjusting the content and format of the advice using an emotion engine that recognizes the user's emotions. This makes it possible to store knowledge acquired during work in a database and recognize the emotions of workers to provide appropriate advice in order to optimize the efficiency of logistics operations in real time.

[1435] "Knowledge" refers to the information and know-how acquired during the progress of a project.

[1436] A "database" is a system for systematically storing acquired knowledge and managing it in a searchable format.

[1437] "Advice" refers to specific advice given to a new project manager based on past knowledge.

[1438] "User's device" refers to the device used to display the advice (e.g., a smartphone, tablet, or computer).

[1439] An "emotion engine" is a system that recognizes emotions from a user's voice, facial expressions, or text.

[1440] "Real-time" refers to a state where work can be reflected and responded to immediately without delay while it is in progress.

[1441] This invention is a system for optimizing operational efficiency in logistics centers and consists of multiple elements. Specific embodiments are described below.

[1442] The server first initializes the knowledge base. The knowledge base is a database for systematically storing knowledge acquired during business processes, and includes implicit rules and important considerations associated with each project ID.

[1443] Next, the user inputs the knowledge gained during the process and sends it to the server. For example, an entry such as "Ensure all packages are correctly labeled" might be added. The server stores this knowledge in a database and organizes the knowledge relevant to each project by project ID.

[1444] The server initializes an advice generator to generate advice using stored knowledge. This generator extracts relevant knowledge for a specific project ID and generates advice based on that content.

[1445] The emotion engine is also initialized. The emotion engine recognizes emotions from the user's voice, facial expressions, or text. This engine is used to analyze the user's emotions and adjust the content and format of the advice.

[1446] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. Then, it generates an advice statement based on the retrieved entries.

[1447] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. For example, if the user expresses negative emotions, it generates advice that includes encouragement and specific countermeasures.

[1448] When a user takes on a new project or works on a similar one, the device provides generated advice. For example, in addition to general precautions such as "Make sure your packages are properly labeled," it also offers emotionally-based advice such as "Don't worry, taking breaks will help you work more efficiently."

[1449] Specific example

[1450] scenario

[1451] A new logistics worker was assigned to the center. During his work, he felt overwhelmed by the workload and sent a request for an "emotion check" via the application.

[1452] Prompt example

[1453] "I'm feeling a bit overwhelmed by the amount of work."

[1454] Application response

[1455] Basic advice:

[1456] Make sure your package is correctly labeled.

[1457] Organize your workspace to avoid errors.

[1458] Emotional advice:

[1459] Don't worry, take a deep breath and work without rushing. This will make it easier to calmly solve the problem.

[1460] This embodiment allows logistics center workers to receive appropriate advice in real time, improving work efficiency and psychological stability.

[1461] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1462] Step 1:

[1463] The server initializes the knowledge base. During this process, it creates a database and prepares tables to store knowledge related to cases and projects. The input here is the system's initial settings, and the output is an empty database.

[1464] Step 2:

[1465] Users input knowledge gained during their work and send it to the server. The server stores this input knowledge in a database. The input data is knowledge information for a specific project ID, and the output is the knowledge stored in the database. Specifically, users might input something like, "Verify that the packages are correctly labeled."

[1466] Step 3:

[1467] The server initializes the advice generator to generate advice using stored knowledge. The advice generator extracts knowledge related to a specific project ID and generates advice based on that content. The input is the project ID, and the output is the generated advice.

[1468] Step 4:

[1469] The server initializes the emotion engine. The emotion engine is a module that recognizes emotions from the user's voice, facial expressions, or text. The input here is the user's facial expressions or text data, and the output is the recognized emotion. Specifically, the emotion recognition algorithm performs analysis to determine whether the user is experiencing stress.

[1470] Step 5:

[1471] The terminal generates advice for a specific project ID when a new project manager requests advice. The advice generator searches the knowledge base based on the project ID and retrieves relevant entries. The input is the project ID, and the output is the corresponding advice statement. Specifically, it executes a database query to retrieve relevant knowledge and generates an advice statement based on that.

[1472] Step 6:

[1473] The server uses an emotion engine to recognize the user's emotions and adjusts the content and format of the advice generated based on those emotions. The input is the emotion recognition result and the generated advice text, and the output is the adjusted advice text. For example, if a negative emotion is recognized, the server will add advice text that includes words of encouragement and specific countermeasures.

[1474] Step 7:

[1475] When a user takes on a new project or works on a similar one, the terminal presents the user with generated advice. The input is the adjusted advice text, and the output is the advice message displayed on the user's terminal. Specifically, the generated advice text is displayed on the user's screen, and audio guidance is provided if necessary.

[1476] By following these steps, logistics center workers can receive accurate advice in real time, improving work efficiency and psychological well-being.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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."

[1486] 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.

[1487] 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.

[1488] 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.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] The following is further disclosed regarding the embodiments described above.

[1499] (Claim 1)

[1500] A means of saving the knowledge acquired during the progress of a project to a database,

[1501] A method for generating advice for new project managers using knowledge,

[1502] A means of providing the generated advice to the user's terminal,

[1503] A system that includes this.

[1504] (Claim 2)

[1505] The system according to claim 1, characterized in that the acquired knowledge includes implicit rules and points to note regarding the progress of business operations.

[1506] (Claim 3)

[1507] The system according to claim 1, characterized in that knowledge is organized by project and searchable based on the project ID.

[1508] "Example 1"

[1509] (Claim 1)

[1510] A means of saving the knowledge acquired during the progress of a project to a database,

[1511] A means for users to input knowledge gained during the course of their work and send it to the server,

[1512] A means for the server to store project-related knowledge in a database,

[1513] A means for initializing a generative AI model in order for the server to generate advice using stored knowledge,

[1514] A means by which a terminal generates advice based on the project ID when a new project manager requests advice,

[1515] A means of providing the generated advice to the user's terminal,

[1516] A system that includes this.

[1517] (Claim 2)

[1518] The system according to claim 1, characterized in that the acquired knowledge includes implicit rules and points to note regarding the progress of business operations.

[1519] (Claim 3)

[1520] The system according to claim 1, characterized in that knowledge is organized by project and searchable based on the project ID.

[1521] "Application Example 1"

[1522] (Claim 1)

[1523] A means of saving the knowledge acquired during the progress of a project to a database,

[1524] A method for generating advice for new project managers using knowledge,

[1525] A means of providing the generated advice to the user's terminal,

[1526] A means of systematically storing knowledge related to a specific project,

[1527] A means of searching for knowledge and generating advice based on the project ID,

[1528] Methods for applying advice to improve the efficiency of manufacturing and maintenance processes in factories,

[1529] A system that includes this.

[1530] (Claim 2)

[1531] The system according to claim 1, characterized in that the acquired knowledge includes implicit rules and points to note regarding the progress of business operations.

[1532] (Claim 3)

[1533] The system according to claim 1, characterized in that knowledge is organized by project and searchable based on the project ID.

[1534] "Example 2 of combining an emotion engine"

[1535] (Claim 1)

[1536] A means of saving the knowledge acquired during the progress of a project to data storage,

[1537] A means of generating advice for new project managers using stored knowledge,

[1538] A means of adjusting the content of advice using an emotion recognition engine that recognizes the user's emotions,

[1539] Means for providing the generated advice to the user's device,

[1540] A system that includes this.

[1541] (Claim 2)

[1542] The system according to claim 1, characterized in that the acquired knowledge includes implicit rules and points to note regarding the progress of work.

[1543] (Claim 3)

[1544] The system according to claim 1, characterized in that knowledge is organized by case and can be searched based on case identification information.

[1545] "Application example 2 when combining with an emotional engine"

[1546] (Claim 1)

[1547] A means of storing knowledge acquired during the progress of a project in a database,

[1548] A means of generating advice for new project managers using knowledge,

[1549] A means of providing the generated advice to the user's terminal,

[1550] A means of adjusting the content and format of advice using an emotion engine that recognizes the user's emotions,

[1551] A system that includes this.

[1552] (Claim 2)

[1553] The system according to claim 1, characterized in that the acquired knowledge includes implicit rules and points to note regarding the progress of work.

[1554] (Claim 3)

[1555] The system according to claim 1, characterized in that knowledge is organized by project and searchable based on the project ID.

[1556] (Claim 4)

[1557] The system according to claim 1, characterized in that it includes means for storing knowledge gained during work in a database and for recognizing the emotions of workers to provide appropriate advice in order to optimize the efficiency of logistics operations in real time. [Explanation of Symbols]

[1558] 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 saving the knowledge acquired during the progress of a project to a database, A method for generating advice for new project managers using knowledge, A means of providing the generated advice to the user's terminal, A system that includes this.

2. The system according to claim 1, characterized in that the acquired knowledge includes implicit rules and points to note regarding the progress of business operations.

3. The system according to claim 1, characterized in that knowledge is organized by project and searchable based on the project ID.

Images