System

Abstract

A system is provided.SOLUTION: A system comprising: means for storing past daily report data and comment data; means for receiving data of a daily report input by a user using a terminal; means for analyzing the input daily report using natural language processing; means for searching for a similar situation from the past daily report data and the comment data; means for generating feedback from an analysis result and the past data; and means for providing the generated feedback to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, with the emphasis on work style reform, the growth of new employees tends to depend primarily on the abilities of their assigned elders. As a result, there are often limitations on the scope of learning and awareness that new employees can receive. Furthermore, it is difficult for elders to accurately grasp the growth of new employees and to create an environment where new employees can easily consult with them, which increases the burden on both parties. The purpose of this invention is to solve these issues, promote the growth of new employees, and reduce the burden on elders. [Means for solving the problem]

[0005] The present invention provides a system including means for storing past daily report data and comment data, means for a user to input daily reports using a terminal and receive the data, means for analyzing the input daily reports using natural language processing, means for searching for similar situations from past daily report data and comment data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, and means for periodically analyzing the user's growth and visualizing the results.

[0006] This makes it possible to generate and provide appropriate feedback from saved past data in response to the daily reports entered by the user. Also, by periodically analyzing growth, it becomes easier for users to check their own growth, reducing the burden on elders. Furthermore, by using generative AI, it is possible to provide more accurate feedback from multiple perspectives. This has resulted in a system that effectively accelerates the growth of new employees.

[0007] "Past daily report data" refers to business records and reports previously entered and saved by the user.

[0008] "Comment data" refers to records of feedback and advice provided by elders and other leaders on past daily report data.

[0009] "Means of storage" refers to the function of using a database or cloud storage to accumulate past daily report data and comment data over a long period of time and make it accessible as needed.

[0010] "Means for receiving" refers to the communication interface or API for importing daily report data sent by users.

[0011] "Natural language processing" refers to the technology of analyzing input text data, extracting keywords, and understanding context.

[0012] "Means of analysis" refers to software modules and algorithms that use natural language processing to understand the content of daily report data and extract important information.

[0013] "Searching means" refers to the function of querying past daily report data and comment data based on analyzed keywords and context to find similar cases and related feedback.

[0014] "Generating means" refers to a software module that generates new feedback and advice based on analysis results and past data.

[0015] The "means for providing" refers to an interface that displays or notifies the user of the generated feedback.

[0016] "Means for analyzing growth" refers to a function that periodically analyzes a user's past daily report data and feedback, and visualizes growth trends and changes in performance.

[0017] "Visualization means" refers to the function of visually displaying analyzed growth data as graphs or charts, making it easy for users to understand.

[0018] "Device" refers to the device, such as a computer, tablet, or smartphone, that a user uses to enter their daily report and receive feedback.

[0019] "User" refers to the person, particularly new employees, who uses the system to input daily reports and receive feedback.

[0020] "AI" stands for artificial intelligence, and in this system in particular, it is responsible for providing feedback using natural language processing and generative models.

[0021] "Generative AI" refers to artificial intelligence technology that has the ability to generate new feedback and advice based on the results of text and data analysis. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[0044] Overall system overview

[0045] The system includes the following main components:

[0046] 1. Data storage means (server)

[0047] 2. Data receiving means (server)

[0048] 3. Natural language processing means (server)

[0049] 4. Data search method (server)

[0050] 5. Feedback Generation Means (Server)

[0051] 6. Feedback provision means (terminal)

[0052] 7. Growth analysis method (server)

[0053] System Operation

[0054] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis results and search results, feedback is generated and provided to the user.

[0055] Program processing explanation

[0056] Entering and sending daily reports

[0057] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "Today's work taught me new ways of dealing with customers. I received a lot of support from my senior colleagues."

[0058] Receiving and saving daily reports

[0059] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[0060] Analysis using natural language processing

[0061] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[0062] Searching for historical data

[0063] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches entries related to past customer interactions and extracts similar feedback.

[0064] Generate feedback

[0065] The server combines the search results and analysis results and uses generative AI to create new feedback, such as "To improve your customer service skills, try incorporating self-learning into your next customer service session based on your experience today."

[0066] Providing Feedback

[0067] The server sends the generated feedback to the user's device. The device then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[0068] Regular growth analysis and visualization

[0069] The server periodically analyzes the user's daily data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[0070] Specific examples

[0071] If a user enters on October 10th, "I learned new customer service skills during today's work. I received a lot of support from my seniors," the server will analyze this and search for similar past "customer service" data and feedback. As a result, feedback on "self-study methods to improve customer service skills" will be generated and provided to the user via their device. The server will also periodically analyze the user's daily report data, visualize the trend of "gradual improvement in customer service skills," and notify the device. This process makes it easier for users to understand their own growth and reduces the burden on seniors.

[0072] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user inputs and sends the daily report using the terminal.

[0076] Specifically, the user enters the contents of the daily report on the terminal, such as "I learned new skills in customer service. I received support from my senior colleagues," and presses the send button.

[0077] Step 2:

[0078] The terminal transmits the input daily report data to the server.

[0079] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[0080] Step 3:

[0081] The server receives the daily report data transmitted from the terminal.

[0082] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[0083] Step 4:

[0084] The server stores the received daily report data in a database.

[0085] Specifically, the server inserts the daily report data into the database using an INSERT command according to the appropriate schema.

[0086] Step 5:

[0087] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[0088] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text, extract keywords, and perform sentiment analysis.

[0089] Step 6:

[0090] The server searches for similar situations from past daily report data and comment data based on the extracted keywords and analysis results.

[0091] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries with similar keywords.

[0092] Step 7:

[0093] The server uses generative AI to generate feedback based on the data obtained from the search and the analysis results.

[0094] Specifically, the server inputs the analysis results into a generative AI model (e.g., GPT-4), which generates feedback such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[0095] Step 8:

[0096] The server generates feedback and sends it to the device.

[0097] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[0098] Step 9:

[0099] The terminal displays the received feedback to the user.

[0100] Specifically, the device displays the feedback it receives on the screen, providing the user with a visible message such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[0101] Step 10:

[0102] The server periodically analyzes the user's daily report data and feedback to visualize their growth.

[0103] Specifically, the server analyzes past data through scheduled execution, analyzes growth trends, and generates visualization data in the form of graphs and charts.

[0104] Step 11:

[0105] The server transmits the growth trend data to the terminal, which displays it to the user.

[0106] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[0107] The above is the specific processing flow in this system.

[0108] Example 1

[0109] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0110] With conventional human resource development systems, it was difficult to provide individual support for the growth of new employees, which increased the burden on elders. Furthermore, the system lacked the functionality to efficiently analyze new employees' daily report data and feedback, provide appropriate feedback, and visualize their long-term growth.

[0111] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0112] In this invention, the server includes means for storing past daily report data and comment data, means for users to input daily reports using a terminal and receive the data, means for analyzing the input daily reports using natural language processing, means for searching for similar situations from the past daily report data and comment data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for visualizing the user's growth trend based on the daily report data and feedback data and notifying the user's terminal. This makes it possible to efficiently support the growth of new employees and reduce the burden on elders.

[0113] "Past daily report data" is daily report data related to work that the user has input in the past.

[0114] "Comment data" refers to feedback and evaluation data provided in response to a daily report.

[0115] "Users" are individuals, including new employees, who use the system to enter daily reports and receive feedback.

[0116] "Terminal" refers to the device used by the user to enter daily reports and receive feedback, such as a smartphone, PC, or tablet.

[0117] A "server" is a computing device that receives, stores, analyzes, and generates feedback on daily report data sent by users.

[0118] "Natural language processing" is a technology that analyzes text data to understand, process, and generate human language.

[0119] The "analysis means" is a process or system that analyzes the stored daily report data using natural language processing technology.

[0120] A "search method" is a process or system that searches for similar situations from past daily report data and comment data.

[0121] A "generation means" is a process or system that combines search results and analysis results to generate new feedback.

[0122] A "generative AI model" is an artificial intelligence technology that automatically generates text and feedback based on input data.

[0123] "Feedback" is a response message that includes evaluation and advice regarding the daily report.

[0124] "Visualization" is the process of analyzing user growth and visually displaying the results in graphs, reports, etc.

[0125] "Growth trends" refer to trends or patterns that indicate an improvement in a user's skills or performance.

[0126] "Notification means" refers to a process or system that sends analysis results and feedback to the user's terminal and displays them.

[0127] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. It also periodically analyzes and visualizes the user's growth, making it easier for users to understand their own growth.

[0128] The system includes the following major components:

[0129] 1. Data storage means (server)

[0130] 2. Data receiving means (server)

[0131] 3. Natural language processing means (server)

[0132] 4. Data search method (server)

[0133] 5. Feedback Generation Means (Server)

[0134] 6. Feedback provision means (terminal)

[0135] 7. Growth analysis method (server)

[0136] 8. Trend notification method (server)

[0137] Hardware and Software Configuration

[0138] The server is a high-performance computing device that uses MySQL or PostgreSQL as the database system, Elasticsearch as the search engine, Google Cloud Natural Language or spaCy as the natural language processing (NLP) technology, and OpenAI's GPT-3 as the generative AI model.

[0139] A terminal is a device operated by a user, such as a smartphone, PC, or tablet, and has dedicated applications and a web browser installed.

[0140] Program processing

[0141] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis and search results, feedback is generated and provided to the user. The server also periodically analyzes the user's daily report data and feedback, visualizes the user's growth, and notifies the terminal.

[0142] Specific examples

[0143] If a user enters on October 10th, "I learned new customer service skills during work today. I received a lot of support from my seniors," the server analyzes this and searches for past similar "customer service" data and feedback. As a result, an AI model (such as GPT-3) is used to generate feedback on "self-study methods to improve customer service skills," which is provided to the user via their device. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in customer service skills," and notifies the device.

[0144] Prompt Sentence Examples

[0145] Examples of prompts to input to a generative AI model might include:

[0146] "Our new employees learned new customer service skills during today's work and received a lot of support from their seniors. Based on this experience, could you give us some advice on how to improve our customer service skills in the future?"

[0147] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[0148] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0149] Step 1:

[0150] A user inputs a daily report on work using a terminal and transmits it to the server.

[0151] Input: Daily report text entered by the user into the terminal (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my senior colleagues.")

[0152] Output: Daily report data is sent to the server as an HTTP request.

[0153] Specific operation: The user accesses the interface of a dedicated application or web browser, enters the daily report content into the text field, and clicks the send button.

[0154] Step 2:

[0155] The server receives the daily report data sent by the user and stores it in a database.

[0156] Input: User's daily report data received by the server (e.g., "I learned new ways to deal with customers during today's work. I received a lot of support from my senior colleagues.")

[0157] Output: Daily report data is stored in a database, along with metadata such as date and user ID.

[0158] Specific operation: When the server receives an HTTP request, it extracts the daily report data and stores it in a database system (e.g., MySQL or PostgreSQL).

[0159] Step 3:

[0160] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[0161] Input: Daily report data saved in the database (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my seniors.")

[0162] Output: Key phrases and entities extracted from daily report data (e.g., "customer service," "senior support")

[0163] Specific operation: The server uses Google Cloud Natural Language API and spaCy to tokenize the daily report text and extract important key phrases and entities.

[0164] Step 4:

[0165] The server searches past daily report data and comment data based on the extracted key phrases.

[0166] Input: Extracted key phrases (e.g., "customer service," "senpai support")

[0167] Output: Past similar daily report data and comment data (e.g., "Past customer correspondence entries")

[0168] Specific operation: The server uses the full-text search function of Elasticsearch or PostgreSQL to search for similar past daily report data and comment data within the database.

[0169] Step 5:

[0170] The server combines the search results and analysis results and creates new feedback using generative AI.

[0171] Input: Search results and analysis results (e.g., previous entries and key phrases related to customer service)

[0172] Output: Generated feedback (e.g., "To improve your customer service skills, try incorporating self-study into your next customer service experience based on this experience.")

[0173] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3), which generates a feedback sentence based on the prompt sentence. The generated feedback sentence is then formatted and saved in an appropriate format.

[0174] Step 6:

[0175] The server transmits the generated feedback to the user's terminal, which then displays the received feedback to the user.

[0176] Input: Generated feedback statement (e.g., "Based on this experience, I will incorporate self-study into my next customer interaction to improve my customer interaction skills.")

[0177] Output: Feedback message displayed on the user's device (e.g., "Today's customer service efforts should be better supported by your senior colleagues, but it would be good to incorporate self-study into your work.")

[0178] Specific operation: The server sends feedback data as an HTTP response, and the device analyzes the received data and displays it in the application or web interface.

[0179] Step 7:

[0180] The server periodically analyzes past daily report data and feedback data, visualizes the user's growth trends, and notifies the user's device.

[0181] Input: Daily report data and feedback data stored in the database (past 3 months, etc.)

[0182] Output: User growth trend report (e.g. "Customer service skills are gradually improving")

[0183] Specific operation: The server periodically retrieves past daily report data and feedback data from the database and analyzes growth trends using specific algorithms or analytical tools. The results are compiled in graph or report format and sent to the user's device as an HTTP response. The user can then check the results on their device and understand their growth.

[0184] (Application example 1)

[0185] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] When new employees operate robots in factories, there is a need for a method to efficiently manage their development while receiving appropriate training. Systematic support is also needed to reduce the burden on elders and supervisors and enable new employees to improve their skills independently. There is a need for a system that visualizes on-site learning progress and provides feedback to support new employees in improving their skills.

[0187] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0188] In this invention, the server includes means for storing past daily report data and comment data, means for a user to input a daily report using a terminal and receive the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from the past data and comment data, means for generating necessary feedback, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for storing and analyzing training data related to machine operation in the factory and providing the generated feedback to the user. This makes it possible to efficiently support the growth of new employees in the factory, visualize learning progress, and provide feedback while reducing the burden on elders and supervisors.

[0189] "Past daily report data" is report information relating to work that the user previously input.

[0190] "Comment data" refers to information about feedback and advice provided by elders or superiors regarding daily reports.

[0191] "Device" refers to the smartphone, tablet, or computer used by the user.

[0192] "Natural language processing" is a technology for understanding and analyzing human language, and a means of extracting useful information from text data.

[0193] "Analysis means" refers to a means for analyzing data stored on the server and extracting specific information.

[0194] "Search means" is a function for searching for similar data from past databases.

[0195] "Feedback" is advice or instructions provided based on daily reports and data entered by the user.

[0196] "Means for analyzing user growth" is a function for evaluating how much a user has grown based on past data.

[0197] "Visualization" is a method of visually displaying the analyzed user's growth status using graphs, charts, etc.

[0198] "Training data" refers to specific training content related to machine operation in a factory and data used for practice.

[0199] "Generative AI" is a type of artificial intelligence technology that is a system that automatically generates new data and feedback based on input data.

[0200] This invention provides a system that supports robot operation training in factories to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[0201] Overall system overview

[0202] The system includes the following main components:

[0203] 1. Data storage means (server)

[0204] 2. Data receiving means (server)

[0205] 3. Natural language processing means (server)

[0206] 4. Data search method (server)

[0207] 5. Feedback Generation Means (Server)

[0208] 6. Feedback provision means (terminal)

[0209] 7. Growth analysis method (server)

[0210] 8. Training data management means (server)

[0211] Program processing

[0212] 1. Enter and submit daily reports

[0213] Users can use their smartphones to input daily training reports. For example, they can write, "Today's training taught me precision robot assembly operations. Accuracy was more important than speed."

[0214] 2. Receiving and saving daily reports

[0215] The server receives the daily report data sent by the user and stores it in a database using a relational database such as PostgreSQL.

[0216] 3. Analysis using natural language processing

[0217] The server analyzes the saved daily report data using a natural language processing engine (such as SpaCy or BERT) to extract key phrases such as "precision assembly" and "accuracy."

[0218] 4. Searching for past data

[0219] The server searches past daily report data and comment data based on the extracted key phrases, searching for similar past training situations and feedback.

[0220] 5. Generate feedback

[0221] The server combines the search results and analysis results and generates new feedback using generative AI (such as OpenAI's GPT-3). For example, it can generate feedback such as, "Today's training taught you that accuracy is important in precision assembly. To improve this skill, it would be effective to incorporate repeated practice of the movement in your next training session."

[0222] 6. Providing Feedback

[0223] The server sends the generated feedback to the smartphone and notifies and displays it to the user, who can then use the feedback to improve their training.

[0224] 7. Regular growth analysis and visualization

[0225] The server periodically analyzes the user's daily data and visualizes growth trends. For example, it analyzes data from the past three months and identifies a trend that "precision assembly skills are gradually improving," and notifies the user's smartphone.

[0226] Specific examples

[0227] If a user inputs, "In today's training, I learned a new precision assembly operation. I learned that accuracy is more important than speed," the server analyzes this and searches for past similar "precision assembly" data and feedback. As a result, feedback such as, "In the next training, it would be good to incorporate repetitive practice of the operation," is generated and provided to the user via their smartphone. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in precision assembly skills," and notifies the user via their smartphone. This makes it easier for users to understand their own growth and reduces the burden on elders.

[0228] In this way, a mode for carrying out the invention is provided. This system enables efficient training within a factory, reduces the burden on elders and supervisors, and supports the improvement of the skills of new employees.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] The user inputs a daily report using a smartphone. For example, the user might input, "Today's training taught us precision robot assembly operations. Accuracy was more important than speed." This daily report is sent to the server via the smartphone app.

[0232] Step 2:

[0233] The server receives the daily report data sent from the smartphone and stores it in a database. A relational database such as PostgreSQL is used for storage. The entered daily report data is saved as an entry for, for example, "2023-10-10."

[0234] Step 3:

[0235] The server analyzes the saved daily report data using a natural language processing engine (e.g., SpaCy or BERT). Specifically, it extracts key phrases such as "precision assembly" and "accuracy" from the daily report text. The input is the daily report text, and the output is the extracted key phrases.

[0236] Step 4:

[0237] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches for past training data and feedback related to similar "precision assembly" tasks. The input is the extracted key phrase, and the output is similar daily report data and comment data.

[0238] Step 5:

[0239] The server combines the search results and analysis results and generates new feedback using generative AI (for example, OpenAI's GPT-3). The input is similar daily report data and feedback, and the output is the newly generated feedback. For example, the generated feedback might be, "To improve the precision assembly skills learned in this training, it would be effective to incorporate repeated practice of the movements in the next training session."

[0240] Step 6:

[0241] The server sends the generated feedback to the smartphone app, which notifies and displays it to the user. The smartphone app displays the feedback to the user and provides specific advice. The input is the generated feedback, and the output is the notification to the user.

[0242] Step 7:

[0243] The server periodically analyzes the user's daily report data and visualizes growth trends. It analyzes data from the past three months, identifies a trend that "precision assembly skills are gradually improving," and notifies the smartphone. The input is the past daily report data, and the output is the visualized growth trend.

[0244] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0245] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[0246] Overall system overview

[0247] The system includes the following main components:

[0248] 1. Data storage means (server)

[0249] 2. Data receiving means (server)

[0250] 3. Natural language processing means (server)

[0251] 4. Data search method (server)

[0252] 5. Feedback Generation Means (Server)

[0253] 6. Feedback provision means (terminal)

[0254] 7. Growth analysis method (server)

[0255] 8. Emotion Engine (Server)

[0256] System Operation

[0257] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and corresponding comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is promoted by regularly analyzing the user's growth and visualizing the results.

[0258] Program processing explanation

[0259] Entering and sending daily reports

[0260] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "I learned new skills about customer service. I received support from my senior colleague."

[0261] Receiving and saving daily reports

[0262] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[0263] Analysis using natural language processing

[0264] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[0265] Emotion analysis using an emotion engine

[0266] The server uses the emotion engine to analyze emotions from the user's daily report data, for example, to determine whether the user's daily report has positive emotions or negative emotions.

[0267] Searching for historical data

[0268] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis, for example, searching for entries and feedback about past customer interactions.

[0269] Generate feedback

[0270] The server combines the search results with the analysis results and uses generative AI to create new feedback. It also takes into account the results of sentiment analysis and provides feedback that helps users grow in a positive way. For example, it could generate feedback like, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[0271] Providing Feedback

[0272] The server sends the generated feedback to the user's device. The device then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[0273] Regular growth analysis and visualization

[0274] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[0275] Specific examples

[0276] If a user types in "I learned a new way of dealing with customers today at work. I received a lot of support from my seniors" on October 10th, the server will analyze this and use its emotion engine to determine that the emotion is positive. The server then searches for past data and feedback about "customer interactions." Based on this past feedback, the server generates feedback such as "To improve your customer interaction skills, daily review is effective in addition to support from your seniors," and provides this to the user via their device. The server also periodically analyzes the user's daily report data, visualizing the trend of "your customer interaction skills are gradually improving," and notifies the device. This process makes it easier for users to understand their own growth and reduces the burden on elders.

[0277] As described above, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[0278] The processing flow will be explained below.

[0279] Step 1:

[0280] The user inputs and sends the daily report using the terminal.

[0281] Specifically, the user enters the following into the terminal screen as a daily report: "I learned new skills in customer service. I received support from my senior colleague." and presses the send button.

[0282] Step 2:

[0283] The terminal transmits the input daily report data to the server.

[0284] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[0285] Step 3:

[0286] The server receives the daily report data transmitted from the terminal.

[0287] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[0288] Step 4:

[0289] The server stores the received daily report data in a database.

[0290] Specifically, the server uses an INSERT command to store the daily report data in a database according to an appropriate schema.

[0291] Step 5:

[0292] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[0293] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text and perform key phrase extraction and sentiment analysis.

[0294] Step 6:

[0295] The server uses an emotion engine to analyze emotions from the daily report data of the user.

[0296] Specifically, the server uses an emotion engine to detect positive emotions from the part "I learned new skills in customer service," and detect a sense of security from the part "I received support from my senior."

[0297] Step 7:

[0298] The server searches for similar situations from past daily report data and comment data based on the extracted key phrases and sentiment analysis results.

[0299] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries that include "customer service" or "senior support."

[0300] Step 8:

[0301] The server combines the search results and analysis results and generates feedback using generative AI.

[0302] Specifically, the server uses a generative AI model (e.g., GPT-4) to generate feedback such as, "To improve your customer service skills, daily review is effective in addition to support from senior employees." This feedback also takes into account the results of sentiment analysis and is adjusted to help the user approach their next task with a positive attitude.

[0303] Step 9:

[0304] The server generates feedback and sends it to the user's device.

[0305] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[0306] Step 10:

[0307] The terminal displays the received feedback to the user.

[0308] Specifically, the feedback received by the device is placed in a UI component and displayed as, "Today's customer service, it would be a good idea to incorporate self-study while making use of the support of your senior colleagues."

[0309] Step 11:

[0310] The server periodically analyzes users' daily data and feedback to visualize growth trends.

[0311] Specifically, the server analyzes past daily report data and feedback every month or quarter and converts the user's skills and growth trends into visualized data in the form of graphs and charts.

[0312] Step 12:

[0313] The server transmits the generated growth trend data to the terminal, which displays it to the user.

[0314] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[0315] The above is the specific processing flow in this system.

[0316] Example 2

[0317] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] Developing new employees is an important issue for companies, but it places a heavy burden on elder employees. In order for new employees to feel that they are growing and to reduce the burden on elder employees, efficient feedback and visualization of growth are necessary. Traditional methods require elder employees to manually provide feedback and manage the growth of new employees, which requires a great deal of effort. Furthermore, there is a risk of a decrease in motivation if the feedback is inappropriate or new employees do not feel that they are growing properly.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for saving past data, means for a user to input a daily report using an information processing device and receiving the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from past data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, means for analyzing emotions, and means for adjusting feedback based on the analyzed emotions. This makes it possible to provide appropriate and timely feedback to new employees and give them a sense of growth while reducing the burden on older employees.

[0320] "Past data" refers to daily report data and comment data that users have entered and saved in the past.

[0321] "User" refers to the person who uses the system to enter daily reports and receive feedback.

[0322] The term "information processing device" refers to a terminal or device that a user uses to input a daily report.

[0323] "Natural language processing" refers to the technology that analyzes input daily report data and extracts key phrases and important topics.

[0324] "Similar situations" refer to situations in which there is a commonality or relevance between past daily report data and comment data and current input data.

[0325] "Feedback" refers to information generated based on the analysis results, including evaluations, advice, and suggestions for improvement for users.

[0326] A "generative artificial intelligence model" refers to an artificial intelligence technology that learns from large amounts of data and generates new information and feedback.

[0327] "Analyzing emotions" refers to the process of identifying emotions contained in input text data and classifying them into emotional categories such as positive, negative, and neutral.

[0328] "Visualizing growth" refers to the process of analyzing a user's past data and visually representing their growth trends and progress.

[0329] "Adjusting feedback" refers to modifying or emphasizing the content of feedback based on the analyzed emotions to help the user develop most effectively.

[0330] This invention provides a human resource development system that utilizes artificial intelligence (AI) technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[0331] The system includes the following main components:

[0332] 1. Data storage means (server)

[0333] 2. Data receiving means (server)

[0334] 3. Natural language processing means (server)

[0335] 4. Data search method (server)

[0336] 5. Feedback Generation Means (Server)

[0337] 6. Feedback provision means (terminal)

[0338] 7. Growth analysis method (server)

[0339] 8. Emotion Engine (Server)

[0340] The server receives the daily report data input by the user using an information processing device, and stores the data in a database using a data storage means.

[0341] The server analyzes the saved daily report data using natural language processing (NLP) technology. This analysis extracts key phrases and themes from the daily report. For example, if a user enters, "I learned new skills in customer service. I received support from my senior colleague," "customer service" and "senior colleague's support" are extracted as key phrases.

[0342] The server uses an emotion engine to analyze emotions from the user's daily report data, and determines whether the user's daily report contains positive or negative emotions.

[0343] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis. This search identifies similar past situations. For example, past entries related to "customer service" are searched for.

[0344] The server uses a generative AI model (such as GPT-3) to generate new feedback. This generation utilizes search results and analysis results, as well as the results of user sentiment analysis. For example, the generated feedback might be, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[0345] The server sends the generated feedback to the user's terminal, which then displays the feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study into your work" is displayed on the terminal.

[0346] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes trends such as "improvement in customer service skills" in the form of graphs and charts, and notifies the device.

[0347] For example:

[0348] If a user enters on October 10th, "I learned new ways to deal with customers during today's work. I received a lot of support from my seniors," the server will analyze this and use its emotion engine to determine positive emotions. The server then searches for past data and feedback about "customer service," and generates the following feedback: "To improve your customer service skills, daily review is effective in addition to support from your seniors." This feedback is then provided to the user via their device. The server periodically analyzes the user's daily report data, visualizes the trend of "your customer service skills are gradually improving," and notifies the device.

[0349] In this way, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[0350] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0351] Specific processing steps of the program

[0352] Step 1: Enter and submit your daily report

[0353] The user inputs a daily report using the terminal. For example, the user inputs, "I learned a new way of dealing with customers during today's work. I received support from my senior colleagues."

[0354] Input: User's daily report text data.

[0355] Action: Formats input data and sends it to the server.

[0356] Output: Daily report text data sent to the server.

[0357] Step 2: Receive and save daily reports

[0358] The server receives the daily report data sent by the user and stores it in a database in a structured format.

[0359] Input: User's daily report text data.

[0360] How it works: Adds metadata such as date and user ID and saves it in a database.

[0361] Output: Daily report data stored in a database.

[0362] Step 3: Natural Language Processing Analysis

[0363] The server analyzes the stored daily report data using natural language processing (NLP) technology, specifically extracting key phrases and important topics from the sentences.

[0364] Input: Saved daily report text data.

[0365] How it works: It uses NLP techniques to tokenize text and extract key phrases.

[0366] Output: Extracted key phrases (e.g., "customer service," "senior support").

[0367] Step 4: Emotion analysis using the emotion engine

[0368] The server uses an emotion engine to analyze emotions from users' daily report data, which are then classified into positive, negative, neutral, etc.

[0369] Input: Saved daily report text data.

[0370] How it works: Uses the sentiment engine to calculate sentiment scores for text and classify it into categories.

[0371] Output: Parsed sentiment data (e.g. "positive").

[0372] Step 5: Search historical data

[0373] The server searches the database for past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis.

[0374] Input: Extracted key phrases, sentiment data.

[0375] What it does: Runs a database query to find relevant historical data.

[0376] Output: Relevant historical datasets as search results.

[0377] Step 6: Generate feedback

[0378] The server uses a generative AI model (such as GPT-3) to generate new feedback, using search results, analysis results, and sentiment analysis results.

[0379] Input: historical data as search results, analysis results, sentiment data.

[0380] How it works: Enter prompts into a generative AI model to generate new feedback.

[0381] Output: Generated feedback text (e.g., "To improve your customer service skills, daily review in addition to support from your seniors is effective.").

[0382] Step 7: Provide feedback

[0383] The server transmits the generated feedback to the user's terminal.

[0384] The terminal displays this feedback to the user.

[0385] Input: The generated feedback text.

[0386] Action: Sends the feedback text to the user's device and displays it.

[0387] Output: The feedback message displayed on the user's terminal.

[0388] Step 8: Regularly analyze and visualize growth

[0389] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth.

[0390] Input: All past daily report data, feedback data.

[0391] How it works: It uses analytical algorithms to calculate growth trends and produces results in the form of graphs and charts.

[0392] Output: Visualized growth trends (e.g., a chart showing "Customer-facing skills are improving").

[0393] The above are the specific processing steps of this system.

[0394] (Application example 2)

[0395] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0396] There is a need for an appropriate educational support system to enable new employees to efficiently learn how to operate robots used in factories. However, with conventional educational methods, it is often difficult for employees to grasp their own progress, resulting in insufficient feedback. This results in issues such as delayed growth of new employees and increased burden on elders. Furthermore, the content of the feedback does not take into account the emotional state of new employees, which can lead to a decrease in motivation to learn and stress. A system that solves these issues and supports the efficient growth of new employees is needed.

[0397] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0398] In this invention, the server includes: means for storing past daily report data and comment data; means for users to input daily reports using a terminal and receive the data; means for analyzing the input daily reports using natural language processing; means for searching for similar situations from past daily report data and comment data; means for generating feedback from the analysis results and past data; means for providing the generated feedback to the user; means for periodically analyzing the user's growth and visualizing the results; means including an emotion engine for analyzing emotions based on the user's daily report data; means for adjusting feedback taking into account the results of the emotion analysis; and means for enabling the use of a smart device as the user's terminal. This allows users to receive feedback that matches their emotional state and allows them to grow efficiently. Furthermore, visualizing one's own growth can increase motivation to learn and reduce the burden on elders.

[0399] "Past daily report data" is report data relating to work that the user has input in the past.

[0400] "Comment data" refers to feedback and opinions added by elders or staff members to past daily report data.

[0401] "Terminal" refers to a device used by a user to input and send daily reports, and includes PCs, smartphones, tablets, smart glasses, head-mounted displays (HMDs), etc.

[0402] "Natural language processing" is a technology that analyzes and understands text data and extracts or generates information.

[0403] The "emotion engine" is a system for analyzing and evaluating user emotions from text data.

[0404] "Generative AI" is artificial intelligence that has algorithms that generate new data and feedback based on input data.

[0405] "Feedback" refers to advice and suggestions created based on the analysis results of the user's daily report and past data.

[0406] "Growth analysis" is the process of evaluating and visualizing a user's level of growth based on the user's past daily report data and feedback history.

[0407] A "smart device" is a terminal that can connect to the Internet and install various applications, and includes smartphones, smart glasses, and head-mounted displays (HMDs).

[0408] "Visualization" means displaying data and analysis results in a form that is visually easy for users to understand.

[0409] A "daily report" is a report that allows a user to record the details of their daily work and learning.

[0410] This invention provides a human resource development system that utilizes AI technology, and in particular, shows its application to a smart device educational application that allows new employees to efficiently learn how to operate robots used in factories. The system configuration and operation are described in detail below.

[0411] Overall system configuration

[0412] The system includes the following major components:

[0413] 1. Data storage means (server)

[0414] 2. Data receiving means (server)

[0415] 3. Natural language processing means (server)

[0416] 4. Data search method (server)

[0417] 5. Feedback Generation Means (Server)

[0418] 6. Feedback Methods (Smart Devices)

[0419] 7. Growth analysis method (server)

[0420] 8. Emotion Engine (Server)

[0421] 9. Smart devices (smart glasses, head-mounted displays (HMD))

[0422] Hardware and Software

[0423] Smart glasses: Google Glass, Vuzix Blade

[0424] Head-mounted display (HMD): Microsoft HoloLens, Meta Quest

[0425] NLP technology: Google BERT, spaCy NLP

[0426] Sentiment analysis: VADER Sentiment Analysis, IBM Watson Natural Language Understanding

[0427] Generation AI: OpenAI GPT-4, GPT-3

[0428] Database: PostgreSQL, MongoDB

[0429] Data search engine: Elasticsearch

[0430] System Operation

[0431] New employees (users) use smart glasses or an HMD to input daily reports on robot operation. This daily report data is sent to a server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is regularly analyzed and visualized to promote it.

[0432] Specific examples

[0433] Data entry and submission

[0434] This example shows a user entering a daily report by voice or text using smart glasses or an HMD.

[0435] For example: "I was able to control the robot arm successfully, but I had difficulty with gripping."

[0436] Data reception and storage

[0437] The server receives the daily report data sent by the user and stores it in a database.

[0438] Natural Language Processing and Sentiment Analysis

[0439] The server analyzes the stored daily report data using natural language processing (NLP) technology and extracts key phrases.

[0440] For example, extract "robot arm", "gripping", etc.

[0441] The emotion engine then analyzes emotions from the user's daily report data.

[0442] Example: Determine that a daily report indicates "positive emotions."

[0443] Feedback generation and provision

[0444] The server searches past data and generates feedback based on the extracted key phrases and the results of sentiment analysis.

[0445] Example: The feedback generated is, "The angle and force of the arm are important for gripping operations. Let's continue experimenting."

[0446] The smart device receives the generated feedback and provides it to the user via voice or text.

[0447] Prompt Sentence Examples

[0448] Below is an example of a prompt sentence input to the generative AI model (GPT-4).

[0449] User: I performed gripping operations on the robot during today's work, but I still find it difficult.

[0450] Generative AI model (GPT-4) prompt:

[0451] Generate appropriate feedback based on the user's daily report. Sentiment analysis shows that the user has slightly negative sentiment.

[0452] Taking into account feedback about previous gripping actions.

[0453] Output: The angle and force of the arm are important for gripping operations. Let's continue with trial and error.

[0454] This invention helps new employees grow efficiently by receiving feedback that matches their emotional state. It also reduces the burden on elders and improves the skills of the entire workforce.

[0455] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0456] Step 1:

[0457] Users input daily reports using smart devices (smart glasses or HMDs), and then input and submit detailed information and impressions about their work using voice or text.

[0458] Input: "I performed a robot gripping operation today, but I'm still having difficulty."

[0459] Output: Data sent from smart device to server

[0460] Step 2:

[0461] The server receives the daily report data sent by the user and stores it in a database. This data becomes the basis for subsequent analysis processing.

[0462] Input: Daily report data sent from a smart device

[0463] Output: Daily data entries stored in the database

[0464] Step 3:

[0465] The server retrieves the daily report data stored in the database and analyzes it using natural language processing (NLP) techniques to extract key phrases and important information.

[0466] Input: Daily report data stored in the database

[0467] Output: Extracted key phrases (e.g., "gripping," "difficult")

[0468] Step 4:

[0469] The server uses a sentiment analysis engine to analyze the user's sentiment from the daily report data. The sentiment engine (e.g., VADER Sentiment Analysis) generates a positive or negative evaluation of the sentiment contained in the daily report.

[0470] Input: Daily report data, extracted key phrases

[0471] Output: Sentiment analysis result (e.g. "negative")

[0472] Step 5:

[0473] The server searches the database for similar past daily report data and comment data based on the extracted key phrases and sentiment analysis results, using a data search engine such as Elasticsearch.

[0474] Input: Key phrases, sentiment analysis results

[0475] Output: Past similar daily report data and comment data

[0476] Step 6:

[0477] The server uses a generative AI model (e.g., GPT-4) based on the search results and analysis results to generate appropriate feedback for the user. The generative AI model takes into account past data and sentiment analysis results to generate feedback that helps the user grow positively.

[0478] Input: Search results, sentiment analysis results

[0479] Output: Generated feedback (e.g., "The angle and force of the arm are important for gripping operations. Let's continue experimenting.")

[0480] Step 7:

[0481] The server sends the generated feedback to the user's smart device.

[0482] Input: Generated feedback

[0483] Output: Feedback sent to the user's smart device

[0484] Step 8:

[0485] The smart device provides the received feedback to the user via voice or text.

[0486] Input: Feedback sent by the server

[0487] Output: Feedback provided to the user, either visually or audibly (e.g., "The angle and force of the arm are important for gripping. Let's continue experimenting.")

[0488] Step 9:

[0489] The server periodically analyzes the user's daily report data and feedback, and visualizes the user's growth trend. This visualization helps the user visually confirm their own growth.

[0490] Input: Past daily report data, feedback data

[0491] Output: Visualization of user growth trends (e.g., "Gripping success rate improved by 25% over the course of one month.")

[0492] Through these steps, users can efficiently improve their robot operation skills while receiving specific and emotionally sensitive feedback, which can also contribute to reducing the burden on elders and improving the skills of the entire workforce.

[0493] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0494] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0495] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0496] [Second embodiment]

[0497] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0498] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0499] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0500] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0501] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0502] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0503] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0504] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0505] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0506] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0507] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0508] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0509] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[0510] Overall system overview

[0511] The system includes the following main components:

[0512] 1. Data storage means (server)

[0513] 2. Data receiving means (server)

[0514] 3. Natural language processing means (server)

[0515] 4. Data search method (server)

[0516] 5. Feedback Generation Means (Server)

[0517] 6. Feedback provision means (terminal)

[0518] 7. Growth analysis method (server)

[0519] System Operation

[0520] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis results and search results, feedback is generated and provided to the user.

[0521] Program processing explanation

[0522] Entering and sending daily reports

[0523] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "Today's work taught me new ways of dealing with customers. I received a lot of support from my senior colleagues."

[0524] Receiving and saving daily reports

[0525] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[0526] Analysis using natural language processing

[0527] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[0528] Searching for historical data

[0529] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches entries related to past customer interactions and extracts similar feedback.

[0530] Generate feedback

[0531] The server combines the search results and analysis results and uses generative AI to create new feedback, such as "To improve your customer service skills, try incorporating self-learning into your next customer service session based on your experience today."

[0532] Providing Feedback

[0533] The server sends the generated feedback to the user's device. The device then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[0534] Regular growth analysis and visualization

[0535] The server periodically analyzes the user's daily data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[0536] Specific examples

[0537] If a user enters on October 10th, "I learned new customer service skills during today's work. I received a lot of support from my seniors," the server will analyze this and search for similar past "customer service" data and feedback. As a result, feedback on "self-study methods to improve customer service skills" will be generated and provided to the user via their device. The server will also periodically analyze the user's daily report data, visualize the trend of "gradual improvement in customer service skills," and notify the device. This process makes it easier for users to understand their own growth and reduces the burden on seniors.

[0538] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[0539] The processing flow will be explained below.

[0540] Step 1:

[0541] The user inputs and sends the daily report using the terminal.

[0542] Specifically, the user enters the contents of the daily report on the terminal, such as "I learned new skills in customer service. I received support from my senior colleagues," and presses the send button.

[0543] Step 2:

[0544] The terminal transmits the input daily report data to the server.

[0545] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[0546] Step 3:

[0547] The server receives the daily report data transmitted from the terminal.

[0548] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[0549] Step 4:

[0550] The server stores the received daily report data in a database.

[0551] Specifically, the server inserts the daily report data into the database using an INSERT command according to the appropriate schema.

[0552] Step 5:

[0553] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[0554] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text, extract keywords, and perform sentiment analysis.

[0555] Step 6:

[0556] The server searches for similar situations from past daily report data and comment data based on the extracted keywords and analysis results.

[0557] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries with similar keywords.

[0558] Step 7:

[0559] The server uses generative AI to generate feedback based on the data obtained from the search and the analysis results.

[0560] Specifically, the server inputs the analysis results into a generative AI model (e.g., GPT-4), which generates feedback such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[0561] Step 8:

[0562] The server generates feedback and sends it to the device.

[0563] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[0564] Step 9:

[0565] The terminal displays the received feedback to the user.

[0566] Specifically, the device displays the feedback it receives on the screen, providing the user with a visible message such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[0567] Step 10:

[0568] The server periodically analyzes the user's daily report data and feedback to visualize their growth.

[0569] Specifically, the server analyzes past data through scheduled execution, analyzes growth trends, and generates visualization data in the form of graphs and charts.

[0570] Step 11:

[0571] The server transmits the growth trend data to the terminal, which displays it to the user.

[0572] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[0573] The above is the specific processing flow in this system.

[0574] Example 1

[0575] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0576] With conventional human resource development systems, it was difficult to provide individual support for the growth of new employees, which increased the burden on elders. Furthermore, the system lacked the functionality to efficiently analyze new employees' daily report data and feedback, provide appropriate feedback, and visualize their long-term growth.

[0577] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0578] In this invention, the server includes means for storing past daily report data and comment data, means for users to input daily reports using a terminal and receive the data, means for analyzing the input daily reports using natural language processing, means for searching for similar situations from the past daily report data and comment data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for visualizing the user's growth trend based on the daily report data and feedback data and notifying the user's terminal. This makes it possible to efficiently support the growth of new employees and reduce the burden on elders.

[0579] "Past daily report data" is daily report data related to work that the user has input in the past.

[0580] "Comment data" refers to feedback and evaluation data provided in response to a daily report.

[0581] "Users" are individuals, including new employees, who use the system to enter daily reports and receive feedback.

[0582] "Terminal" refers to the device used by the user to enter daily reports and receive feedback, such as a smartphone, PC, or tablet.

[0583] A "server" is a computing device that receives, stores, analyzes, and generates feedback on daily report data sent by users.

[0584] "Natural language processing" is a technology that analyzes text data to understand, process, and generate human language.

[0585] The "analysis means" is a process or system that analyzes the stored daily report data using natural language processing technology.

[0586] A "search method" is a process or system that searches for similar situations from past daily report data and comment data.

[0587] A "generation means" is a process or system that combines search results and analysis results to generate new feedback.

[0588] A "generative AI model" is an artificial intelligence technology that automatically generates text and feedback based on input data.

[0589] "Feedback" is a response message that includes evaluation and advice regarding the daily report.

[0590] "Visualization" is the process of analyzing user growth and visually displaying the results in graphs, reports, etc.

[0591] "Growth trends" refer to trends or patterns that indicate an improvement in a user's skills or performance.

[0592] "Notification means" refers to a process or system that sends analysis results and feedback to the user's terminal and displays them.

[0593] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. It also periodically analyzes and visualizes the user's growth, making it easier for users to understand their own growth.

[0594] The system includes the following major components:

[0595] 1. Data storage means (server)

[0596] 2. Data receiving means (server)

[0597] 3. Natural language processing means (server)

[0598] 4. Data search method (server)

[0599] 5. Feedback Generation Means (Server)

[0600] 6. Feedback provision means (terminal)

[0601] 7. Growth analysis method (server)

[0602] 8. Trend notification method (server)

[0603] Hardware and Software Configuration

[0604] The server is a high-performance computing device that uses MySQL or PostgreSQL as the database system, Elasticsearch as the search engine, Google Cloud Natural Language or spaCy as the natural language processing (NLP) technology, and OpenAI's GPT-3 as the generative AI model.

[0605] A terminal is a device operated by a user, such as a smartphone, PC, or tablet, and has dedicated applications and a web browser installed.

[0606] Program processing

[0607] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis and search results, feedback is generated and provided to the user. The server also periodically analyzes the user's daily report data and feedback, visualizes the user's growth, and notifies the terminal.

[0608] Specific examples

[0609] If a user enters on October 10th, "I learned new customer service skills during work today. I received a lot of support from my seniors," the server analyzes this and searches for past similar "customer service" data and feedback. As a result, an AI model (such as GPT-3) is used to generate feedback on "self-study methods to improve customer service skills," which is provided to the user via their device. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in customer service skills," and notifies the device.

[0610] Prompt Sentence Examples

[0611] Examples of prompts to input to a generative AI model might include:

[0612] "Our new employees learned new customer service skills during today's work and received a lot of support from their seniors. Based on this experience, could you give us some advice on how to improve our customer service skills in the future?"

[0613] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[0614] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0615] Step 1:

[0616] A user inputs a daily report on work using a terminal and transmits it to the server.

[0617] Input: Daily report text entered by the user into the terminal (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my senior colleagues.")

[0618] Output: Daily report data is sent to the server as an HTTP request.

[0619] Specific operation: The user accesses the interface of a dedicated application or web browser, enters the daily report content into the text field, and clicks the send button.

[0620] Step 2:

[0621] The server receives the daily report data sent by the user and stores it in a database.

[0622] Input: User's daily report data received by the server (e.g., "I learned new ways to deal with customers during today's work. I received a lot of support from my senior colleagues.")

[0623] Output: Daily report data is stored in a database, along with metadata such as date and user ID.

[0624] Specific operation: When the server receives an HTTP request, it extracts the daily report data and stores it in a database system (e.g., MySQL or PostgreSQL).

[0625] Step 3:

[0626] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[0627] Input: Daily report data saved in the database (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my seniors.")

[0628] Output: Key phrases and entities extracted from daily report data (e.g., "customer service," "senior support")

[0629] Specific operation: The server uses Google Cloud Natural Language API and spaCy to tokenize the daily report text and extract important key phrases and entities.

[0630] Step 4:

[0631] The server searches past daily report data and comment data based on the extracted key phrases.

[0632] Input: Extracted key phrases (e.g., "customer service," "senpai support")

[0633] Output: Past similar daily report data and comment data (e.g., "Past customer correspondence entries")

[0634] Specific operation: The server uses the full-text search function of Elasticsearch or PostgreSQL to search for similar past daily report data and comment data within the database.

[0635] Step 5:

[0636] The server combines the search results and analysis results and creates new feedback using generative AI.

[0637] Input: Search results and analysis results (e.g., previous entries and key phrases related to customer service)

[0638] Output: Generated feedback (e.g., "To improve your customer service skills, try incorporating self-study into your next customer service experience based on this experience.")

[0639] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3), which generates a feedback sentence based on the prompt sentence. The generated feedback sentence is then formatted and saved in an appropriate format.

[0640] Step 6:

[0641] The server transmits the generated feedback to the user's terminal, which then displays the received feedback to the user.

[0642] Input: Generated feedback statement (e.g., "Based on this experience, I will incorporate self-study into my next customer interaction to improve my customer interaction skills.")

[0643] Output: Feedback message displayed on the user's device (e.g., "Today's customer service efforts should be better supported by your senior colleagues, but it would be good to incorporate self-study into your work.")

[0644] Specific operation: The server sends feedback data as an HTTP response, and the device analyzes the received data and displays it in the application or web interface.

[0645] Step 7:

[0646] The server periodically analyzes past daily report data and feedback data, visualizes the user's growth trends, and notifies the user's device.

[0647] Input: Daily report data and feedback data stored in the database (past 3 months, etc.)

[0648] Output: User growth trend report (e.g. "Customer service skills are gradually improving")

[0649] Specific operation: The server periodically retrieves past daily report data and feedback data from the database and analyzes growth trends using specific algorithms or analytical tools. The results are compiled in graph or report format and sent to the user's device as an HTTP response. The user can then check the results on their device and understand their growth.

[0650] (Application example 1)

[0651] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0652] When new employees operate robots in factories, there is a need for a method to efficiently manage their development while receiving appropriate training. Systematic support is also needed to reduce the burden on elders and supervisors and enable new employees to improve their skills independently. There is a need for a system that visualizes on-site learning progress and provides feedback to support new employees in improving their skills.

[0653] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0654] In this invention, the server includes means for storing past daily report data and comment data, means for a user to input a daily report using a terminal and receive the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from the past data and comment data, means for generating necessary feedback, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for storing and analyzing training data related to machine operation in the factory and providing the generated feedback to the user. This makes it possible to efficiently support the growth of new employees in the factory, visualize learning progress, and provide feedback while reducing the burden on elders and supervisors.

[0655] "Past daily report data" is report information relating to work that the user previously input.

[0656] "Comment data" refers to information about feedback and advice provided by elders or superiors regarding daily reports.

[0657] "Device" refers to the smartphone, tablet, or computer used by the user.

[0658] "Natural language processing" is a technology for understanding and analyzing human language, and a means of extracting useful information from text data.

[0659] "Analysis means" refers to a means for analyzing data stored on the server and extracting specific information.

[0660] "Search means" is a function for searching for similar data from past databases.

[0661] "Feedback" is advice or instructions provided based on daily reports and data entered by the user.

[0662] "Means for analyzing user growth" is a function for evaluating how much a user has grown based on past data.

[0663] "Visualization" is a method of visually displaying the analyzed user's growth status using graphs, charts, etc.

[0664] "Training data" refers to specific training content related to machine operation in a factory and data used for practice.

[0665] "Generative AI" is a type of artificial intelligence technology that is a system that automatically generates new data and feedback based on input data.

[0666] This invention provides a system that supports robot operation training in factories to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[0667] Overall system overview

[0668] The system includes the following main components:

[0669] 1. Data storage means (server)

[0670] 2. Data receiving means (server)

[0671] 3. Natural language processing means (server)

[0672] 4. Data search method (server)

[0673] 5. Feedback Generation Means (Server)

[0674] 6. Feedback provision means (terminal)

[0675] 7. Growth analysis method (server)

[0676] 8. Training data management means (server)

[0677] Program processing

[0678] 1. Enter and submit daily reports

[0679] Users can use their smartphones to input daily training reports. For example, they can write, "Today's training taught me precision robot assembly operations. Accuracy was more important than speed."

[0680] 2. Receiving and saving daily reports

[0681] The server receives the daily report data sent by the user and stores it in a database using a relational database such as PostgreSQL.

[0682] 3. Analysis using natural language processing

[0683] The server analyzes the saved daily report data using a natural language processing engine (such as SpaCy or BERT) to extract key phrases such as "precision assembly" and "accuracy."

[0684] 4. Searching for past data

[0685] The server searches past daily report data and comment data based on the extracted key phrases, searching for similar past training situations and feedback.

[0686] 5. Generate feedback

[0687] The server combines the search results and analysis results and generates new feedback using generative AI (such as OpenAI's GPT-3). For example, it can generate feedback such as, "Today's training taught you that accuracy is important in precision assembly. To improve this skill, it would be effective to incorporate repeated practice of the movement in your next training session."

[0688] 6. Providing Feedback

[0689] The server sends the generated feedback to the smartphone and notifies and displays it to the user, who can then use the feedback to improve their training.

[0690] 7. Regular growth analysis and visualization

[0691] The server periodically analyzes the user's daily data and visualizes growth trends. For example, it analyzes data from the past three months and identifies a trend that "precision assembly skills are gradually improving," and notifies the user's smartphone.

[0692] Specific examples

[0693] If a user inputs, "In today's training, I learned a new precision assembly operation. I learned that accuracy is more important than speed," the server analyzes this and searches for past similar "precision assembly" data and feedback. As a result, feedback such as, "In the next training, it would be good to incorporate repetitive practice of the operation," is generated and provided to the user via their smartphone. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in precision assembly skills," and notifies the user via their smartphone. This makes it easier for users to understand their own growth and reduces the burden on elders.

[0694] In this way, a mode for carrying out the invention is provided. This system enables efficient training within a factory, reduces the burden on elders and supervisors, and supports the improvement of the skills of new employees.

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] The user inputs a daily report using a smartphone. For example, the user might input, "Today's training taught us precision robot assembly operations. Accuracy was more important than speed." This daily report is sent to the server via the smartphone app.

[0698] Step 2:

[0699] The server receives the daily report data sent from the smartphone and stores it in a database. A relational database such as PostgreSQL is used for storage. The entered daily report data is saved as an entry for, for example, "2023-10-10."

[0700] Step 3:

[0701] The server analyzes the saved daily report data using a natural language processing engine (e.g., SpaCy or BERT). Specifically, it extracts key phrases such as "precision assembly" and "accuracy" from the daily report text. The input is the daily report text, and the output is the extracted key phrases.

[0702] Step 4:

[0703] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches for past training data and feedback related to similar "precision assembly" tasks. The input is the extracted key phrase, and the output is similar daily report data and comment data.

[0704] Step 5:

[0705] The server combines the search results and analysis results and generates new feedback using generative AI (for example, OpenAI's GPT-3). The input is similar daily report data and feedback, and the output is the newly generated feedback. For example, the generated feedback might be, "To improve the precision assembly skills learned in this training, it would be effective to incorporate repeated practice of the movements in the next training session."

[0706] Step 6:

[0707] The server sends the generated feedback to the smartphone app, which notifies and displays it to the user. The smartphone app displays the feedback to the user and provides specific advice. The input is the generated feedback, and the output is the notification to the user.

[0708] Step 7:

[0709] The server periodically analyzes the user's daily report data and visualizes growth trends. It analyzes data from the past three months, identifies a trend that "precision assembly skills are gradually improving," and notifies the smartphone. The input is the past daily report data, and the output is the visualized growth trend.

[0710] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0711] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[0712] Overall system overview

[0713] The system includes the following main components:

[0714] 1. Data storage means (server)

[0715] 2. Data receiving means (server)

[0716] 3. Natural language processing means (server)

[0717] 4. Data search method (server)

[0718] 5. Feedback Generation Means (Server)

[0719] 6. Feedback provision means (terminal)

[0720] 7. Growth analysis method (server)

[0721] 8. Emotion Engine (Server)

[0722] System Operation

[0723] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and corresponding comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is promoted by regularly analyzing the user's growth and visualizing the results.

[0724] Program processing explanation

[0725] Entering and sending daily reports

[0726] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "I learned new skills about customer service. I received support from my senior colleague."

[0727] Receiving and saving daily reports

[0728] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[0729] Analysis using natural language processing

[0730] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[0731] Emotion analysis using an emotion engine

[0732] The server uses the emotion engine to analyze emotions from the user's daily report data, for example, to determine whether the user's daily report has positive emotions or negative emotions.

[0733] Searching for historical data

[0734] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis, for example, searching for entries and feedback about past customer interactions.

[0735] Generate feedback

[0736] The server combines the search results with the analysis results and uses generative AI to create new feedback. It also takes into account the results of sentiment analysis and provides feedback that helps users grow in a positive way. For example, it could generate feedback like, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[0737] Providing Feedback

[0738] The server sends the generated feedback to the user's device. The device then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[0739] Regular growth analysis and visualization

[0740] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[0741] Specific examples

[0742] If a user types in "I learned a new way of dealing with customers today at work. I received a lot of support from my seniors" on October 10th, the server will analyze this and use its emotion engine to determine that the emotion is positive. The server then searches for past data and feedback about "customer interactions." Based on this past feedback, the server generates feedback such as "To improve your customer interaction skills, daily review is effective in addition to support from your seniors," and provides this to the user via their device. The server also periodically analyzes the user's daily report data, visualizing the trend of "your customer interaction skills are gradually improving," and notifies the device. This process makes it easier for users to understand their own growth and reduces the burden on elders.

[0743] As described above, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[0744] The processing flow will be explained below.

[0745] Step 1:

[0746] The user inputs and sends the daily report using the terminal.

[0747] Specifically, the user enters the following into the terminal screen as a daily report: "I learned new skills in customer service. I received support from my senior colleague." and presses the send button.

[0748] Step 2:

[0749] The terminal transmits the input daily report data to the server.

[0750] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[0751] Step 3:

[0752] The server receives the daily report data transmitted from the terminal.

[0753] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[0754] Step 4:

[0755] The server stores the received daily report data in a database.

[0756] Specifically, the server uses an INSERT command to store the daily report data in a database according to an appropriate schema.

[0757] Step 5:

[0758] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[0759] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text and perform key phrase extraction and sentiment analysis.

[0760] Step 6:

[0761] The server uses an emotion engine to analyze emotions from the daily report data of the user.

[0762] Specifically, the server uses an emotion engine to detect positive emotions from the part "I learned new skills in customer service," and detect a sense of security from the part "I received support from my senior."

[0763] Step 7:

[0764] The server searches for similar situations from past daily report data and comment data based on the extracted key phrases and sentiment analysis results.

[0765] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries that include "customer service" or "senior support."

[0766] Step 8:

[0767] The server combines the search results and analysis results and generates feedback using generative AI.

[0768] Specifically, the server uses a generative AI model (e.g., GPT-4) to generate feedback such as, "To improve your customer service skills, daily review is effective in addition to support from senior employees." This feedback also takes into account the results of sentiment analysis and is adjusted to help the user approach their next task with a positive attitude.

[0769] Step 9:

[0770] The server generates feedback and sends it to the user's device.

[0771] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[0772] Step 10:

[0773] The terminal displays the received feedback to the user.

[0774] Specifically, the feedback received by the device is placed in a UI component and displayed as, "Today's customer service, it would be a good idea to incorporate self-study while making use of the support of your senior colleagues."

[0775] Step 11:

[0776] The server periodically analyzes users' daily data and feedback to visualize growth trends.

[0777] Specifically, the server analyzes past daily report data and feedback every month or quarter and converts the user's skills and growth trends into visualized data in the form of graphs and charts.

[0778] Step 12:

[0779] The server transmits the generated growth trend data to the terminal, which displays it to the user.

[0780] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[0781] The above is the specific processing flow in this system.

[0782] Example 2

[0783] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0784] Developing new employees is an important issue for companies, but it places a heavy burden on elder employees. In order for new employees to feel that they are growing and to reduce the burden on elder employees, efficient feedback and visualization of growth are necessary. Traditional methods require elder employees to manually provide feedback and manage the growth of new employees, which requires a great deal of effort. Furthermore, there is a risk of a decrease in motivation if the feedback is inappropriate or new employees do not feel that they are growing properly.

[0785] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for saving past data, means for a user to input a daily report using an information processing device and receiving the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from past data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, means for analyzing emotions, and means for adjusting feedback based on the analyzed emotions. This makes it possible to provide appropriate and timely feedback to new employees and give them a sense of growth while reducing the burden on older employees.

[0786] "Past data" refers to daily report data and comment data that users have entered and saved in the past.

[0787] "User" refers to the person who uses the system to enter daily reports and receive feedback.

[0788] The term "information processing device" refers to a terminal or device that a user uses to input a daily report.

[0789] "Natural language processing" refers to the technology that analyzes input daily report data and extracts key phrases and important topics.

[0790] "Similar situations" refer to situations in which there is a commonality or relevance between past daily report data and comment data and current input data.

[0791] "Feedback" refers to information generated based on the analysis results, including evaluations, advice, and suggestions for improvement for users.

[0792] A "generative artificial intelligence model" refers to an artificial intelligence technology that learns from large amounts of data and generates new information and feedback.

[0793] "Analyzing emotions" refers to the process of identifying emotions contained in input text data and classifying them into emotional categories such as positive, negative, and neutral.

[0794] "Visualizing growth" refers to the process of analyzing a user's past data and visually representing their growth trends and progress.

[0795] "Adjusting feedback" refers to modifying or emphasizing the content of feedback based on the analyzed emotions to help the user develop most effectively.

[0796] This invention provides a human resource development system that utilizes artificial intelligence (AI) technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[0797] The system includes the following main components:

[0798] 1. Data storage means (server)

[0799] 2. Data receiving means (server)

[0800] 3. Natural language processing means (server)

[0801] 4. Data search method (server)

[0802] 5. Feedback Generation Means (Server)

[0803] 6. Feedback provision means (terminal)

[0804] 7. Growth analysis method (server)

[0805] 8. Emotion Engine (Server)

[0806] The server receives the daily report data input by the user using an information processing device, and stores the data in a database using a data storage means.

[0807] The server analyzes the saved daily report data using natural language processing (NLP) technology. This analysis extracts key phrases and themes from the daily report. For example, if a user enters, "I learned new skills in customer service. I received support from my senior colleague," "customer service" and "senior colleague's support" are extracted as key phrases.

[0808] The server uses an emotion engine to analyze emotions from the user's daily report data, and determines whether the user's daily report contains positive or negative emotions.

[0809] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis. This search identifies similar past situations. For example, past entries related to "customer service" are searched for.

[0810] The server uses a generative AI model (such as GPT-3) to generate new feedback. This generation utilizes search results and analysis results, as well as the results of user sentiment analysis. For example, the generated feedback might be, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[0811] The server sends the generated feedback to the user's terminal, which then displays the feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study into your work" is displayed on the terminal.

[0812] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes trends such as "improvement in customer service skills" in the form of graphs and charts, and notifies the device.

[0813] For example:

[0814] If a user enters on October 10th, "I learned new ways to deal with customers during today's work. I received a lot of support from my seniors," the server will analyze this and use its emotion engine to determine positive emotions. The server then searches for past data and feedback about "customer service," and generates the following feedback: "To improve your customer service skills, daily review is effective in addition to support from your seniors." This feedback is then provided to the user via their device. The server periodically analyzes the user's daily report data, visualizes the trend of "your customer service skills are gradually improving," and notifies the device.

[0815] In this way, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[0816] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0817] Specific processing steps of the program

[0818] Step 1: Enter and submit your daily report

[0819] The user inputs a daily report using the terminal. For example, the user inputs, "I learned a new way of dealing with customers during today's work. I received support from my senior colleagues."

[0820] Input: User's daily report text data.

[0821] Action: Formats input data and sends it to the server.

[0822] Output: Daily report text data sent to the server.

[0823] Step 2: Receive and save daily reports

[0824] The server receives the daily report data sent by the user and stores it in a database in a structured format.

[0825] Input: User's daily report text data.

[0826] How it works: Adds metadata such as date and user ID and saves it in a database.

[0827] Output: Daily report data stored in a database.

[0828] Step 3: Natural Language Processing Analysis

[0829] The server analyzes the stored daily report data using natural language processing (NLP) technology, specifically extracting key phrases and important topics from the sentences.

[0830] Input: Saved daily report text data.

[0831] How it works: It uses NLP techniques to tokenize text and extract key phrases.

[0832] Output: Extracted key phrases (e.g., "customer service," "senior support").

[0833] Step 4: Emotion analysis using the emotion engine

[0834] The server uses an emotion engine to analyze emotions from users' daily report data, which are then classified into positive, negative, neutral, etc.

[0835] Input: Saved daily report text data.

[0836] How it works: Uses the sentiment engine to calculate sentiment scores for text and classify it into categories.

[0837] Output: Parsed sentiment data (e.g. "positive").

[0838] Step 5: Search historical data

[0839] The server searches the database for past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis.

[0840] Input: Extracted key phrases, sentiment data.

[0841] What it does: Runs a database query to find relevant historical data.

[0842] Output: Relevant historical datasets as search results.

[0843] Step 6: Generate feedback

[0844] The server uses a generative AI model (such as GPT-3) to generate new feedback, using search results, analysis results, and sentiment analysis results.

[0845] Input: historical data as search results, analysis results, sentiment data.

[0846] How it works: Enter prompts into a generative AI model to generate new feedback.

[0847] Output: Generated feedback text (e.g., "To improve your customer service skills, daily review in addition to support from your seniors is effective.").

[0848] Step 7: Provide feedback

[0849] The server transmits the generated feedback to the user's terminal.

[0850] The terminal displays this feedback to the user.

[0851] Input: The generated feedback text.

[0852] Action: Sends the feedback text to the user's device and displays it.

[0853] Output: The feedback message displayed on the user's terminal.

[0854] Step 8: Regularly analyze and visualize growth

[0855] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth.

[0856] Input: All past daily report data, feedback data.

[0857] How it works: It uses analytical algorithms to calculate growth trends and produces results in the form of graphs and charts.

[0858] Output: Visualized growth trends (e.g., a chart showing "Customer-facing skills are improving").

[0859] The above are the specific processing steps of this system.

[0860] (Application example 2)

[0861] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0862] There is a need for an appropriate educational support system to enable new employees to efficiently learn how to operate robots used in factories. However, with conventional educational methods, it is often difficult for employees to grasp their own progress, resulting in insufficient feedback. This results in issues such as delayed growth of new employees and increased burden on elders. Furthermore, the content of the feedback does not take into account the emotional state of new employees, which can lead to a decrease in motivation to learn and stress. A system that solves these issues and supports the efficient growth of new employees is needed.

[0863] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0864] In this invention, the server includes: means for storing past daily report data and comment data; means for users to input daily reports using a terminal and receive the data; means for analyzing the input daily reports using natural language processing; means for searching for similar situations from past daily report data and comment data; means for generating feedback from the analysis results and past data; means for providing the generated feedback to the user; means for periodically analyzing the user's growth and visualizing the results; means including an emotion engine for analyzing emotions based on the user's daily report data; means for adjusting feedback taking into account the results of the emotion analysis; and means for enabling the use of a smart device as the user's terminal. This allows users to receive feedback that matches their emotional state and allows them to grow efficiently. Furthermore, visualizing one's own growth can increase motivation to learn and reduce the burden on elders.

[0865] "Past daily report data" is report data relating to work that the user has input in the past.

[0866] "Comment data" refers to feedback and opinions added by elders or staff members to past daily report data.

[0867] "Terminal" refers to a device used by a user to input and send daily reports, and includes PCs, smartphones, tablets, smart glasses, head-mounted displays (HMDs), etc.

[0868] "Natural language processing" is a technology that analyzes and understands text data and extracts or generates information.

[0869] The "emotion engine" is a system for analyzing and evaluating user emotions from text data.

[0870] "Generative AI" is artificial intelligence that has algorithms that generate new data and feedback based on input data.

[0871] "Feedback" refers to advice and suggestions created based on the analysis results of the user's daily report and past data.

[0872] "Growth analysis" is the process of evaluating and visualizing a user's level of growth based on the user's past daily report data and feedback history.

[0873] A "smart device" is a terminal that can connect to the Internet and install various applications, and includes smartphones, smart glasses, and head-mounted displays (HMDs).

[0874] "Visualization" means displaying data and analysis results in a form that is visually easy for users to understand.

[0875] A "daily report" is a report that allows a user to record the details of their daily work and learning.

[0876] This invention provides a human resource development system that utilizes AI technology, and in particular, shows its application to a smart device educational application that allows new employees to efficiently learn how to operate robots used in factories. The system configuration and operation are described in detail below.

[0877] Overall system configuration

[0878] The system includes the following major components:

[0879] 1. Data storage means (server)

[0880] 2. Data receiving means (server)

[0881] 3. Natural language processing means (server)

[0882] 4. Data search method (server)

[0883] 5. Feedback Generation Means (Server)

[0884] 6. Feedback Methods (Smart Devices)

[0885] 7. Growth analysis method (server)

[0886] 8. Emotion Engine (Server)

[0887] 9. Smart devices (smart glasses, head-mounted displays (HMD))

[0888] Hardware and Software

[0889] Smart glasses: Google Glass, Vuzix Blade

[0890] Head-mounted display (HMD): Microsoft HoloLens, Meta Quest

[0891] NLP technology: Google BERT, spaCy NLP

[0892] Sentiment analysis: VADER Sentiment Analysis, IBM Watson Natural Language Understanding

[0893] Generation AI: OpenAI GPT-4, GPT-3

[0894] Database: PostgreSQL, MongoDB

[0895] Data search engine: Elasticsearch

[0896] System Operation

[0897] New employees (users) use smart glasses or an HMD to input daily reports on robot operation. This daily report data is sent to a server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is regularly analyzed and visualized to promote it.

[0898] Specific examples

[0899] Data entry and submission

[0900] This example shows a user entering a daily report by voice or text using smart glasses or an HMD.

[0901] For example: "I was able to control the robot arm successfully, but I had difficulty with gripping."

[0902] Data reception and storage

[0903] The server receives the daily report data sent by the user and stores it in a database.

[0904] Natural Language Processing and Sentiment Analysis

[0905] The server analyzes the stored daily report data using natural language processing (NLP) technology and extracts key phrases.

[0906] For example, extract "robot arm", "gripping", etc.

[0907] The emotion engine then analyzes emotions from the user's daily report data.

[0908] Example: Determine that a daily report indicates "positive emotions."

[0909] Feedback generation and provision

[0910] The server searches past data and generates feedback based on the extracted key phrases and the results of sentiment analysis.

[0911] Example: The feedback generated is, "The angle and force of the arm are important for gripping operations. Let's continue experimenting."

[0912] The smart device receives the generated feedback and provides it to the user via voice or text.

[0913] Prompt Sentence Examples

[0914] Below is an example of a prompt sentence input to the generative AI model (GPT-4).

[0915] User: I performed gripping operations on the robot during today's work, but I still find it difficult.

[0916] Generative AI model (GPT-4) prompt:

[0917] Generate appropriate feedback based on the user's daily report. Sentiment analysis shows that the user has slightly negative sentiment.

[0918] Taking into account feedback about previous gripping actions.

[0919] Output: The angle and force of the arm are important for gripping operations. Let's continue with trial and error.

[0920] This invention helps new employees grow efficiently by receiving feedback that matches their emotional state. It also reduces the burden on elders and improves the skills of the entire workforce.

[0921] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0922] Step 1:

[0923] Users input daily reports using smart devices (smart glasses or HMDs), and then input and submit detailed information and impressions about their work using voice or text.

[0924] Input: "I performed a robot gripping operation today, but I'm still having difficulty."

[0925] Output: Data sent from smart device to server

[0926] Step 2:

[0927] The server receives the daily report data sent by the user and stores it in a database. This data becomes the basis for subsequent analysis processing.

[0928] Input: Daily report data sent from a smart device

[0929] Output: Daily data entries stored in the database

[0930] Step 3:

[0931] The server retrieves the daily report data stored in the database and analyzes it using natural language processing (NLP) techniques to extract key phrases and important information.

[0932] Input: Daily report data stored in the database

[0933] Output: Extracted key phrases (e.g., "gripping," "difficult")

[0934] Step 4:

[0935] The server uses a sentiment analysis engine to analyze the user's sentiment from the daily report data. The sentiment engine (e.g., VADER Sentiment Analysis) generates a positive or negative evaluation of the sentiment contained in the daily report.

[0936] Input: Daily report data, extracted key phrases

[0937] Output: Sentiment analysis result (e.g. "negative")

[0938] Step 5:

[0939] The server searches the database for similar past daily report data and comment data based on the extracted key phrases and sentiment analysis results, using a data search engine such as Elasticsearch.

[0940] Input: Key phrases, sentiment analysis results

[0941] Output: Past similar daily report data and comment data

[0942] Step 6:

[0943] The server uses a generative AI model (e.g., GPT-4) based on the search results and analysis results to generate appropriate feedback for the user. The generative AI model takes into account past data and sentiment analysis results to generate feedback that helps the user grow positively.

[0944] Input: Search results, sentiment analysis results

[0945] Output: Generated feedback (e.g., "The angle and force of the arm are important for gripping operations. Let's continue experimenting.")

[0946] Step 7:

[0947] The server sends the generated feedback to the user's smart device.

[0948] Input: Generated feedback

[0949] Output: Feedback sent to the user's smart device

[0950] Step 8:

[0951] The smart device provides the received feedback to the user via voice or text.

[0952] Input: Feedback sent by the server

[0953] Output: Feedback provided to the user, either visually or audibly (e.g., "The angle and force of the arm are important for gripping. Let's continue experimenting.")

[0954] Step 9:

[0955] The server periodically analyzes the user's daily report data and feedback, and visualizes the user's growth trend. This visualization helps the user visually confirm their own growth.

[0956] Input: Past daily report data, feedback data

[0957] Output: Visualization of user growth trends (e.g., "Gripping success rate improved by 25% over the course of one month.")

[0958] Through these steps, users can efficiently improve their robot operation skills while receiving specific and emotionally sensitive feedback, which can also contribute to reducing the burden on elders and improving the skills of the entire workforce.

[0959] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0960] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0961] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0962] [Third embodiment]

[0963] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0964] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0965] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0966] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0967] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0968] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0969] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0970] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0971] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0972] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0973] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0974] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0975] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[0976] Overall system overview

[0977] The system includes the following main components:

[0978] 1. Data storage means (server)

[0979] 2. Data receiving means (server)

[0980] 3. Natural language processing means (server)

[0981] 4. Data search method (server)

[0982] 5. Feedback Generation Means (Server)

[0983] 6. Feedback provision method (terminal)

[0984] 7. Growth analysis method (server)

[0985] System Operation

[0986] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis results and search results, feedback is generated and provided to the user.

[0987] Program processing explanation

[0988] Entering and sending daily reports

[0989] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "Today's work taught me new ways of dealing with customers. I received a lot of support from my senior colleagues."

[0990] Receiving and saving daily reports

[0991] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[0992] Analysis using natural language processing

[0993] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[0994] Searching for past data

[0995] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches entries related to past customer interactions and extracts similar feedback.

[0996] Generate feedback

[0997] The server combines the search results and analysis results and uses generative AI to create new feedback, such as "To improve your customer service skills, try incorporating self-learning into your next customer service session based on your experience today."

[0998] Providing feedback

[0999] The server sends the generated feedback to the user's device, which then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[1000] Regular growth analysis and visualization

[1001] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[1002] Specific examples

[1003] If a user enters on October 10th, "I learned new customer service skills during today's work. I received a lot of support from my seniors," the server will analyze this and search for similar past "customer service" data and feedback. As a result, feedback on "self-study methods to improve customer service skills" will be generated and provided to the user via their device. The server will also periodically analyze the user's daily report data, visualize the trend of "gradual improvement in customer service skills," and notify the device. This process makes it easier for users to understand their own growth and reduces the burden on seniors.

[1004] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user inputs and sends the daily report using the terminal.

[1008] Specifically, the user enters the contents of the daily report on the terminal, such as "I learned new skills in customer service. I received support from my senior colleagues," and presses the send button.

[1009] Step 2:

[1010] The terminal transmits the input daily report data to the server.

[1011] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[1012] Step 3:

[1013] The server receives the daily report data transmitted from the terminal.

[1014] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[1015] Step 4:

[1016] The server stores the received daily report data in a database.

[1017] Specifically, the server inserts the daily report data into the database using an INSERT command according to the appropriate schema.

[1018] Step 5:

[1019] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[1020] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text, extract keywords, and perform sentiment analysis.

[1021] Step 6:

[1022] The server searches for similar situations from past daily report data and comment data based on the extracted keywords and analysis results.

[1023] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries with similar keywords.

[1024] Step 7:

[1025] The server uses generative AI to generate feedback based on the data obtained from the search and the analysis results.

[1026] Specifically, the server inputs the analysis results into a generative AI model (e.g., GPT-4), which generates feedback such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[1027] Step 8:

[1028] The server generates feedback and sends it to the device.

[1029] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[1030] Step 9:

[1031] The terminal displays the received feedback to the user.

[1032] Specifically, the device displays the feedback it receives on the screen, providing the user with a visible message such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[1033] Step 10:

[1034] The server periodically analyzes the user's daily report data and feedback to visualize their growth.

[1035] Specifically, the server analyzes past data through scheduled execution, analyzes growth trends, and generates visualization data in the form of graphs and charts.

[1036] Step 11:

[1037] The server transmits the growth trend data to the terminal, which displays it to the user.

[1038] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[1039] The above is the specific processing flow in this system.

[1040] Example 1

[1041] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1042] With conventional human resource development systems, it was difficult to provide individual support for the growth of new employees, which increased the burden on elders. Furthermore, the system lacked the functionality to efficiently analyze new employees' daily report data and feedback, provide appropriate feedback, and visualize their long-term growth.

[1043] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1044] In this invention, the server includes means for storing past daily report data and comment data, means for users to input daily reports using a terminal and receive the data, means for analyzing the input daily reports using natural language processing, means for searching for similar situations from the past daily report data and comment data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for visualizing the user's growth trend based on the daily report data and feedback data and notifying the user's terminal. This makes it possible to efficiently support the growth of new employees and reduce the burden on elders.

[1045] "Past daily report data" is daily report data related to work that the user has input in the past.

[1046] "Comment data" refers to feedback and evaluation data provided in response to a daily report.

[1047] "Users" are individuals, including new employees, who use the system to enter daily reports and receive feedback.

[1048] "Terminal" refers to the device used by the user to enter daily reports and receive feedback, such as a smartphone, PC, or tablet.

[1049] A "server" is a computing device that receives, stores, analyzes, and generates feedback on daily report data sent by users.

[1050] "Natural language processing" is a technology that analyzes text data to understand, process, and generate human language.

[1051] The "analysis means" is a process or system that analyzes the stored daily report data using natural language processing technology.

[1052] A "search method" is a process or system that searches for similar situations from past daily report data and comment data.

[1053] A "generation means" is a process or system that combines search results and analysis results to generate new feedback.

[1054] A "generative AI model" is an artificial intelligence technology that automatically generates text and feedback based on input data.

[1055] "Feedback" is a response message that includes evaluation and advice regarding the daily report.

[1056] "Visualization" is the process of analyzing user growth and visually displaying the results in graphs, reports, etc.

[1057] "Growth trends" refer to trends or patterns that indicate an improvement in a user's skills or performance.

[1058] "Notification means" refers to a process or system that sends analysis results and feedback to the user's terminal and displays them.

[1059] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. It also periodically analyzes and visualizes the user's growth, making it easier for users to understand their own growth.

[1060] The system includes the following major components:

[1061] 1. Data storage means (server)

[1062] 2. Data receiving means (server)

[1063] 3. Natural language processing means (server)

[1064] 4. Data search method (server)

[1065] 5. Feedback Generation Means (Server)

[1066] 6. Feedback provision method (terminal)

[1067] 7. Growth analysis method (server)

[1068] 8. Trend notification method (server)

[1069] Hardware and Software Configuration

[1070] The server is a high-performance computing device that uses MySQL or PostgreSQL as the database system, Elasticsearch as the search engine, Google Cloud Natural Language or spaCy as the natural language processing (NLP) technology, and OpenAI's GPT-3 as the generative AI model.

[1071] A terminal is a device operated by a user, such as a smartphone, PC, or tablet, and has dedicated applications and a web browser installed.

[1072] Program processing

[1073] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis and search results, feedback is generated and provided to the user. The server also periodically analyzes the user's daily report data and feedback, visualizes the user's growth, and notifies the terminal.

[1074] Specific examples

[1075] If a user enters on October 10th, "I learned new customer service skills during work today. I received a lot of support from my seniors," the server analyzes this and searches for past similar "customer service" data and feedback. As a result, an AI model (such as GPT-3) is used to generate feedback on "self-study methods to improve customer service skills," which is provided to the user via their device. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in customer service skills," and notifies the device.

[1076] Prompt Sentence Examples

[1077] Examples of prompts to input to a generative AI model might include:

[1078] "Our new employees learned new customer service skills during today's work and received a lot of support from their seniors. Based on this experience, could you give us some advice on how to improve our customer service skills in the future?"

[1079] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[1080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1081] Step 1:

[1082] A user inputs a daily report on work using a terminal and transmits it to the server.

[1083] Input: Daily report text entered by the user into the terminal (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my senior colleagues.")

[1084] Output: Daily report data is sent to the server as an HTTP request.

[1085] Specific operation: The user accesses the interface of a dedicated application or web browser, enters the daily report content into the text field, and clicks the send button.

[1086] Step 2:

[1087] The server receives the daily report data sent by the user and stores it in a database.

[1088] Input: User's daily report data received by the server (e.g., "I learned new ways to deal with customers during today's work. I received a lot of support from my senior colleagues.")

[1089] Output: Daily report data is stored in a database, along with metadata such as date and user ID.

[1090] Specific operation: When the server receives an HTTP request, it extracts the daily report data and stores it in a database system (e.g., MySQL or PostgreSQL).

[1091] Step 3:

[1092] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[1093] Input: Daily report data saved in the database (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my seniors.")

[1094] Output: Key phrases and entities extracted from daily report data (e.g., "customer service," "senior support")

[1095] Specific operation: The server uses Google Cloud Natural Language API and spaCy to tokenize the daily report text and extract important key phrases and entities.

[1096] Step 4:

[1097] The server searches past daily report data and comment data based on the extracted key phrases.

[1098] Input: Extracted key phrases (e.g., "customer service," "senpai support")

[1099] Output: Past similar daily report data and comment data (e.g., "Past customer correspondence entries")

[1100] Specific operation: The server uses the full-text search function of Elasticsearch or PostgreSQL to search for similar past daily report data and comment data within the database.

[1101] Step 5:

[1102] The server combines the search results and analysis results and creates new feedback using generative AI.

[1103] Input: Search results and analysis results (e.g., previous entries and key phrases related to customer service)

[1104] Output: Generated feedback (e.g., "To improve your customer service skills, try incorporating self-study into your next customer service experience based on this experience.")

[1105] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3), which generates a feedback sentence based on the prompt sentence. The generated feedback sentence is then formatted and saved in an appropriate format.

[1106] Step 6:

[1107] The server transmits the generated feedback to the user's terminal, which then displays the received feedback to the user.

[1108] Input: Generated feedback statement (e.g., "Based on this experience, I will incorporate self-study into my next customer interaction to improve my customer interaction skills.")

[1109] Output: Feedback message displayed on the user's device (e.g., "Today's customer service efforts should be better supported by your senior colleagues, but it would be good to incorporate self-study into your work.")

[1110] Specific operation: The server sends feedback data as an HTTP response, and the device analyzes the received data and displays it in the application or web interface.

[1111] Step 7:

[1112] The server periodically analyzes past daily report data and feedback data, visualizes the user's growth trends, and notifies the user's device.

[1113] Input: Daily report data and feedback data stored in the database (past 3 months, etc.)

[1114] Output: User growth trend report (e.g. "Customer service skills are gradually improving")

[1115] Specific operation: The server periodically retrieves past daily report data and feedback data from the database and analyzes growth trends using specific algorithms or analytical tools. The results are compiled in graph or report format and sent to the user's device as an HTTP response. The user can then check the results on their device and understand their growth.

[1116] (Application example 1)

[1117] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1118] When new employees operate robots in factories, there is a need for a method to efficiently manage their development while receiving appropriate training. Systematic support is also needed to reduce the burden on elders and supervisors and enable new employees to improve their skills independently. There is a need for a system that visualizes on-site learning progress and provides feedback to support new employees in improving their skills.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1120] In this invention, the server includes means for storing past daily report data and comment data, means for a user to input a daily report using a terminal and receive the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from the past data and comment data, means for generating necessary feedback, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for storing and analyzing training data related to machine operation in the factory and providing the generated feedback to the user. This makes it possible to efficiently support the growth of new employees in the factory, visualize learning progress, and provide feedback while reducing the burden on elders and supervisors.

[1121] "Past daily report data" is report information relating to work that the user previously input.

[1122] "Comment data" refers to information about feedback and advice provided by elders or superiors regarding daily reports.

[1123] "Device" refers to the smartphone, tablet, or computer used by the user.

[1124] "Natural language processing" is a technology for understanding and analyzing human language, and a means of extracting useful information from text data.

[1125] "Analysis means" refers to a means for analyzing data stored on the server and extracting specific information.

[1126] "Search means" is a function for searching for similar data from past databases.

[1127] "Feedback" is advice or instructions provided based on daily reports and data entered by the user.

[1128] "Means for analyzing user growth" is a function for evaluating how much a user has grown based on past data.

[1129] "Visualization" is a method of visually displaying the analyzed user's growth status using graphs, charts, etc.

[1130] "Training data" refers to specific training content related to machine operation in a factory and data used for practice.

[1131] "Generative AI" is a type of artificial intelligence technology that is a system that automatically generates new data and feedback based on input data.

[1132] This invention provides a system that supports robot operation training in factories to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[1133] Overall system overview

[1134] The system includes the following main components:

[1135] 1. Data storage means (server)

[1136] 2. Data receiving means (server)

[1137] 3. Natural language processing means (server)

[1138] 4. Data search method (server)

[1139] 5. Feedback Generation Means (Server)

[1140] 6. Feedback provision means (terminal)

[1141] 7. Growth analysis method (server)

[1142] 8. Training data management means (server)

[1143] Program processing

[1144] 1. Enter and submit daily reports

[1145] Users can use their smartphones to input daily training reports. For example, they can write, "Today's training taught me precision robot assembly operations. Accuracy was more important than speed."

[1146] 2. Receiving and saving daily reports

[1147] The server receives the daily report data sent by the user and stores it in a database using a relational database such as PostgreSQL.

[1148] 3. Analysis using natural language processing

[1149] The server analyzes the saved daily report data using a natural language processing engine (such as SpaCy or BERT) to extract key phrases such as "precision assembly" and "accuracy."

[1150] 4. Searching for past data

[1151] The server searches past daily report data and comment data based on the extracted key phrases, searching for similar past training situations and feedback.

[1152] 5. Generate feedback

[1153] The server combines the search results and analysis results and generates new feedback using generative AI (such as OpenAI's GPT-3). For example, it can generate feedback such as, "Today's training taught you that accuracy is important in precision assembly. To improve this skill, it would be effective to incorporate repeated practice of the movement in your next training session."

[1154] 6. Providing Feedback

[1155] The server sends the generated feedback to the smartphone and notifies and displays it to the user, who can then use the feedback to improve their training.

[1156] 7. Regular growth analysis and visualization

[1157] The server periodically analyzes the user's daily data and visualizes growth trends. For example, it analyzes data from the past three months and identifies a trend that "precision assembly skills are gradually improving," and notifies the user's smartphone.

[1158] Specific examples

[1159] If a user inputs, "In today's training, I learned a new precision assembly operation. I learned that accuracy is more important than speed," the server analyzes this and searches for past similar "precision assembly" data and feedback. As a result, feedback such as, "In the next training, it would be good to incorporate repetitive practice of the operation," is generated and provided to the user via their smartphone. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in precision assembly skills," and notifies the user via their smartphone. This makes it easier for users to understand their own growth and reduces the burden on elders.

[1160] In this way, a mode for carrying out the invention is provided. This system enables efficient training within a factory, reduces the burden on elders and supervisors, and supports the improvement of the skills of new employees.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] The user inputs a daily report using a smartphone. For example, the user might input, "Today's training taught us precision robot assembly operations. Accuracy was more important than speed." This daily report is sent to the server via the smartphone app.

[1164] Step 2:

[1165] The server receives the daily report data sent from the smartphone and stores it in a database. A relational database such as PostgreSQL is used for storage. The entered daily report data is saved as an entry for, for example, "2023-10-10."

[1166] Step 3:

[1167] The server analyzes the saved daily report data using a natural language processing engine (e.g., SpaCy or BERT). Specifically, it extracts key phrases such as "precision assembly" and "accuracy" from the daily report text. The input is the daily report text, and the output is the extracted key phrases.

[1168] Step 4:

[1169] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches for past training data and feedback related to similar "precision assembly" tasks. The input is the extracted key phrase, and the output is similar daily report data and comment data.

[1170] Step 5:

[1171] The server combines the search results and analysis results and generates new feedback using generative AI (for example, OpenAI's GPT-3). The input is similar daily report data and feedback, and the output is the newly generated feedback. For example, the generated feedback might be, "To improve the precision assembly skills learned in this training, it would be effective to incorporate repeated practice of the movements in the next training session."

[1172] Step 6:

[1173] The server sends the generated feedback to the smartphone app, which notifies and displays it to the user. The smartphone app displays the feedback to the user and provides specific advice. The input is the generated feedback, and the output is the notification to the user.

[1174] Step 7:

[1175] The server periodically analyzes the user's daily report data and visualizes growth trends. It analyzes data from the past three months, identifies a trend that "precision assembly skills are gradually improving," and notifies the smartphone. The input is the past daily report data, and the output is the visualized growth trend.

[1176] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1177] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[1178] Overall system overview

[1179] The system includes the following main components:

[1180] 1. Data storage means (server)

[1181] 2. Data receiving means (server)

[1182] 3. Natural language processing means (server)

[1183] 4. Data search method (server)

[1184] 5. Feedback Generation Means (Server)

[1185] 6. Feedback provision means (terminal)

[1186] 7. Growth analysis method (server)

[1187] 8. Emotion Engine (Server)

[1188] System Operation

[1189] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and corresponding comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is promoted by regularly analyzing the user's growth and visualizing the results.

[1190] Program processing explanation

[1191] Entering and sending daily reports

[1192] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "I learned new skills about customer service. I received support from my senior colleague."

[1193] Receiving and saving daily reports

[1194] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[1195] Analysis using natural language processing

[1196] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[1197] Emotion analysis using an emotion engine

[1198] The server uses the emotion engine to analyze emotions from the user's daily report data, for example, to determine whether the user's daily report has positive emotions or negative emotions.

[1199] Searching for historical data

[1200] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis, for example, searching for entries and feedback about past customer interactions.

[1201] Generate feedback

[1202] The server combines the search results with the analysis results and uses generative AI to create new feedback. It also takes into account the results of sentiment analysis and provides feedback that helps users grow in a positive way. For example, it could generate feedback like, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[1203] Providing Feedback

[1204] The server sends the generated feedback to the user's device. The device then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[1205] Regular growth analysis and visualization

[1206] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[1207] Specific examples

[1208] If a user types in "I learned a new way of dealing with customers today at work. I received a lot of support from my seniors" on October 10th, the server will analyze this and use its emotion engine to determine that the emotion is positive. The server then searches for past data and feedback about "customer interactions." Based on this past feedback, the server generates feedback such as "To improve your customer interaction skills, daily review is effective in addition to support from your seniors," and provides this to the user via their device. The server also periodically analyzes the user's daily report data, visualizing the trend of "your customer interaction skills are gradually improving," and notifies the device. This process makes it easier for users to understand their own growth and reduces the burden on elders.

[1209] As described above, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[1210] The processing flow will be explained below.

[1211] Step 1:

[1212] The user inputs and sends the daily report using the terminal.

[1213] Specifically, the user enters the following into the terminal screen as a daily report: "I learned new skills in customer service. I received support from my senior colleague." and presses the send button.

[1214] Step 2:

[1215] The terminal transmits the input daily report data to the server.

[1216] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[1217] Step 3:

[1218] The server receives the daily report data transmitted from the terminal.

[1219] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[1220] Step 4:

[1221] The server stores the received daily report data in a database.

[1222] Specifically, the server uses an INSERT command to store the daily report data in a database according to an appropriate schema.

[1223] Step 5:

[1224] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[1225] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text and perform key phrase extraction and sentiment analysis.

[1226] Step 6:

[1227] The server uses an emotion engine to analyze emotions from the daily report data of the user.

[1228] Specifically, the server uses an emotion engine to detect positive emotions from the part "I learned new skills in customer service," and detect a sense of security from the part "I received support from my senior."

[1229] Step 7:

[1230] The server searches for similar situations from past daily report data and comment data based on the extracted key phrases and sentiment analysis results.

[1231] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries that include "customer service" or "senior support."

[1232] Step 8:

[1233] The server combines the search results and analysis results and generates feedback using generative AI.

[1234] Specifically, the server uses a generative AI model (e.g., GPT-4) to generate feedback such as, "To improve your customer service skills, daily review is effective in addition to support from senior employees." This feedback also takes into account the results of sentiment analysis and is adjusted to help the user approach their next task with a positive attitude.

[1235] Step 9:

[1236] The server generates feedback and sends it to the user's device.

[1237] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[1238] Step 10:

[1239] The terminal displays the received feedback to the user.

[1240] Specifically, the feedback received by the device is placed in a UI component and displayed as, "Today's customer service, it would be a good idea to incorporate self-study while making use of the support of your senior colleagues."

[1241] Step 11:

[1242] The server periodically analyzes users' daily data and feedback to visualize growth trends.

[1243] Specifically, the server analyzes past daily report data and feedback every month or quarter and converts the user's skills and growth trends into visualized data in the form of graphs and charts.

[1244] Step 12:

[1245] The server transmits the generated growth trend data to the terminal, which displays it to the user.

[1246] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[1247] The above is the specific processing flow in this system.

[1248] Example 2

[1249] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1250] Developing new employees is an important issue for companies, but it places a heavy burden on elder employees. In order for new employees to feel that they are growing and to reduce the burden on elder employees, efficient feedback and visualization of growth are necessary. Traditional methods require elder employees to manually provide feedback and manage the growth of new employees, which requires a great deal of effort. Furthermore, there is a risk of a decrease in motivation if the feedback is inappropriate or new employees do not feel that they are growing properly.

[1251] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for saving past data, means for a user to input a daily report using an information processing device and receiving the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from past data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, means for analyzing emotions, and means for adjusting feedback based on the analyzed emotions. This makes it possible to provide appropriate and timely feedback to new employees and give them a sense of growth while reducing the burden on older employees.

[1252] "Past data" refers to daily report data and comment data that users have entered and saved in the past.

[1253] "User" refers to the person who uses the system to enter daily reports and receive feedback.

[1254] The term "information processing device" refers to a terminal or device that a user uses to input a daily report.

[1255] "Natural language processing" refers to the technology that analyzes input daily report data and extracts key phrases and important topics.

[1256] "Similar situations" refer to situations in which there is a commonality or relevance between past daily report data and comment data and current input data.

[1257] "Feedback" refers to information generated based on the analysis results, including evaluations, advice, and suggestions for improvement for users.

[1258] A "generative artificial intelligence model" refers to an artificial intelligence technology that learns from large amounts of data and generates new information and feedback.

[1259] "Analyzing emotions" refers to the process of identifying emotions contained in input text data and classifying them into emotional categories such as positive, negative, and neutral.

[1260] "Visualizing growth" refers to the process of analyzing a user's past data and visually representing their growth trends and progress.

[1261] "Adjusting feedback" refers to modifying or emphasizing the content of feedback based on the analyzed emotions to help the user develop most effectively.

[1262] This invention provides a human resource development system that utilizes artificial intelligence (AI) technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[1263] The system includes the following main components:

[1264] 1. Data storage means (server)

[1265] 2. Data receiving means (server)

[1266] 3. Natural language processing means (server)

[1267] 4. Data search method (server)

[1268] 5. Feedback Generation Means (Server)

[1269] 6. Feedback provision means (terminal)

[1270] 7. Growth analysis method (server)

[1271] 8. Emotion Engine (Server)

[1272] The server receives the daily report data input by the user using an information processing device, and stores the data in a database using a data storage means.

[1273] The server analyzes the saved daily report data using natural language processing (NLP) technology. This analysis extracts key phrases and themes from the daily report. For example, if a user enters, "I learned new skills in customer service. I received support from my senior colleague," "customer service" and "senior colleague's support" are extracted as key phrases.

[1274] The server uses an emotion engine to analyze emotions from the user's daily report data, and determines whether the user's daily report contains positive or negative emotions.

[1275] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis. This search identifies similar past situations. For example, past entries related to "customer service" are searched for.

[1276] The server uses a generative AI model (such as GPT-3) to generate new feedback. This generation utilizes search results and analysis results, as well as the results of user sentiment analysis. For example, the generated feedback might be, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[1277] The server sends the generated feedback to the user's terminal, which then displays the feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study into your work" is displayed on the terminal.

[1278] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes trends such as "improvement in customer service skills" in the form of graphs and charts, and notifies the device.

[1279] For example:

[1280] If a user enters on October 10th, "I learned new ways to deal with customers during today's work. I received a lot of support from my seniors," the server will analyze this and use its emotion engine to determine positive emotions. The server then searches for past data and feedback about "customer service," and generates the following feedback: "To improve your customer service skills, daily review is effective in addition to support from your seniors." This feedback is then provided to the user via their device. The server periodically analyzes the user's daily report data, visualizes the trend of "your customer service skills are gradually improving," and notifies the device.

[1281] In this way, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[1282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1283] Specific processing steps of the program

[1284] Step 1: Enter and submit your daily report

[1285] The user inputs a daily report using the terminal. For example, the user inputs, "I learned a new way of dealing with customers during today's work. I received support from my senior colleagues."

[1286] Input: User's daily report text data.

[1287] Action: Formats input data and sends it to the server.

[1288] Output: Daily report text data sent to the server.

[1289] Step 2: Receive and save daily reports

[1290] The server receives the daily report data sent by the user and stores it in a database in a structured format.

[1291] Input: User's daily report text data.

[1292] How it works: Adds metadata such as date and user ID and saves it in a database.

[1293] Output: Daily report data stored in a database.

[1294] Step 3: Natural Language Processing Analysis

[1295] The server analyzes the stored daily report data using natural language processing (NLP) technology, specifically extracting key phrases and important topics from the sentences.

[1296] Input: Saved daily report text data.

[1297] How it works: It uses NLP techniques to tokenize text and extract key phrases.

[1298] Output: Extracted key phrases (e.g., "customer service," "senior support").

[1299] Step 4: Emotion analysis using the emotion engine

[1300] The server uses an emotion engine to analyze emotions from users' daily report data, which are then classified into positive, negative, neutral, etc.

[1301] Input: Saved daily report text data.

[1302] How it works: Uses the sentiment engine to calculate sentiment scores for text and classify it into categories.

[1303] Output: Parsed sentiment data (e.g. "positive").

[1304] Step 5: Search historical data

[1305] The server searches the database for past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis.

[1306] Input: Extracted key phrases, sentiment data.

[1307] What it does: Runs a database query to find relevant historical data.

[1308] Output: Relevant historical datasets as search results.

[1309] Step 6: Generate feedback

[1310] The server uses a generative AI model (such as GPT-3) to generate new feedback, using search results, analysis results, and sentiment analysis results.

[1311] Input: historical data as search results, analysis results, sentiment data.

[1312] How it works: Enter prompts into a generative AI model to generate new feedback.

[1313] Output: Generated feedback text (e.g., "To improve your customer service skills, daily review in addition to support from your seniors is effective.").

[1314] Step 7: Provide feedback

[1315] The server transmits the generated feedback to the user's terminal.

[1316] The terminal displays this feedback to the user.

[1317] Input: The generated feedback text.

[1318] Action: Sends the feedback text to the user's device and displays it.

[1319] Output: The feedback message displayed on the user's terminal.

[1320] Step 8: Regularly analyze and visualize growth

[1321] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth.

[1322] Input: All past daily report data, feedback data.

[1323] How it works: It uses analytical algorithms to calculate growth trends and produces results in the form of graphs and charts.

[1324] Output: Visualized growth trends (e.g., a chart showing "Customer-facing skills are improving").

[1325] The above are the specific processing steps of this system.

[1326] (Application example 2)

[1327] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1328] There is a need for an appropriate educational support system to enable new employees to efficiently learn how to operate robots used in factories. However, with conventional educational methods, it is often difficult for employees to grasp their own progress, resulting in insufficient feedback. This results in issues such as delayed growth of new employees and increased burden on elders. Furthermore, the content of the feedback does not take into account the emotional state of new employees, which can lead to a decrease in motivation to learn and stress. A system that solves these issues and supports the efficient growth of new employees is needed.

[1329] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1330] In this invention, the server includes: means for storing past daily report data and comment data; means for users to input daily reports using a terminal and receive the data; means for analyzing the input daily reports using natural language processing; means for searching for similar situations from past daily report data and comment data; means for generating feedback from the analysis results and past data; means for providing the generated feedback to the user; means for periodically analyzing the user's growth and visualizing the results; means including an emotion engine for analyzing emotions based on the user's daily report data; means for adjusting feedback taking into account the results of the emotion analysis; and means for enabling the use of a smart device as the user's terminal. This allows users to receive feedback that matches their emotional state and allows them to grow efficiently. Furthermore, visualizing one's own growth can increase motivation to learn and reduce the burden on elders.

[1331] "Past daily report data" is report data relating to work that the user has input in the past.

[1332] "Comment data" refers to feedback and opinions added by elders or staff members to past daily report data.

[1333] "Terminal" refers to a device used by a user to input and send daily reports, and includes PCs, smartphones, tablets, smart glasses, head-mounted displays (HMDs), etc.

[1334] "Natural language processing" is a technology that analyzes and understands text data and extracts or generates information.

[1335] The "emotion engine" is a system for analyzing and evaluating user emotions from text data.

[1336] "Generative AI" is artificial intelligence that has algorithms that generate new data and feedback based on input data.

[1337] "Feedback" refers to advice and suggestions created based on the analysis results of the user's daily report and past data.

[1338] "Growth analysis" is the process of evaluating and visualizing a user's level of growth based on the user's past daily report data and feedback history.

[1339] A "smart device" is a terminal that can connect to the Internet and install various applications, and includes smartphones, smart glasses, and head-mounted displays (HMDs).

[1340] "Visualization" means displaying data and analysis results in a form that is visually easy for users to understand.

[1341] A "daily report" is a report that allows a user to record the details of their daily work and learning.

[1342] This invention provides a human resource development system that utilizes AI technology, and in particular, shows its application to a smart device educational application that allows new employees to efficiently learn how to operate robots used in factories. The system configuration and operation are described in detail below.

[1343] Overall system configuration

[1344] The system includes the following major components:

[1345] 1. Data storage means (server)

[1346] 2. Data receiving means (server)

[1347] 3. Natural language processing means (server)

[1348] 4. Data search method (server)

[1349] 5. Feedback Generation Means (Server)

[1350] 6. Feedback Methods (Smart Devices)

[1351] 7. Growth analysis method (server)

[1352] 8. Emotion Engine (Server)

[1353] 9. Smart devices (smart glasses, head-mounted displays (HMD))

[1354] Hardware and Software

[1355] Smart glasses: Google Glass, Vuzix Blade

[1356] Head-mounted display (HMD): Microsoft HoloLens, Meta Quest

[1357] NLP technology: Google BERT, spaCy NLP

[1358] Sentiment analysis: VADER Sentiment Analysis, IBM Watson Natural Language Understanding

[1359] Generation AI: OpenAI GPT-4, GPT-3

[1360] Database: PostgreSQL, MongoDB

[1361] Data search engine: Elasticsearch

[1362] System Operation

[1363] New employees (users) use smart glasses or an HMD to input daily reports on robot operation. This daily report data is sent to a server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is regularly analyzed and visualized to promote it.

[1364] Specific examples

[1365] Data entry and submission

[1366] This example shows a user entering a daily report by voice or text using smart glasses or an HMD.

[1367] For example: "I was able to control the robot arm successfully, but I had difficulty with gripping."

[1368] Data reception and storage

[1369] The server receives the daily report data sent by the user and stores it in a database.

[1370] Natural Language Processing and Sentiment Analysis

[1371] The server analyzes the stored daily report data using natural language processing (NLP) technology and extracts key phrases.

[1372] For example, extract "robot arm", "gripping", etc.

[1373] The emotion engine then analyzes emotions from the user's daily report data.

[1374] Example: Determine that a daily report indicates "positive emotions."

[1375] Feedback generation and provision

[1376] The server searches past data and generates feedback based on the extracted key phrases and the results of sentiment analysis.

[1377] Example: The feedback generated is, "The angle and force of the arm are important for gripping operations. Let's continue experimenting."

[1378] The smart device receives the generated feedback and provides it to the user via voice or text.

[1379] Prompt Sentence Examples

[1380] Below is an example of a prompt sentence input to the generative AI model (GPT-4).

[1381] User: I performed gripping operations on the robot during today's work, but I still find it difficult.

[1382] Generative AI model (GPT-4) prompt:

[1383] Generate appropriate feedback based on the user's daily report. Sentiment analysis shows that the user has slightly negative sentiment.

[1384] Taking into account feedback about previous gripping actions.

[1385] Output: The angle and force of the arm are important for gripping operations. Let's continue with trial and error.

[1386] This invention helps new employees grow efficiently by receiving feedback that matches their emotional state. It also reduces the burden on elders and improves the skills of the entire workforce.

[1387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1388] Step 1:

[1389] Users input daily reports using smart devices (smart glasses or HMDs), and then input and submit detailed information and impressions about their work using voice or text.

[1390] Input: "I performed a robot gripping operation today, but I'm still having difficulty."

[1391] Output: Data sent from smart device to server

[1392] Step 2:

[1393] The server receives the daily report data sent by the user and stores it in a database. This data becomes the basis for subsequent analysis processing.

[1394] Input: Daily report data sent from a smart device

[1395] Output: Daily data entries stored in the database

[1396] Step 3:

[1397] The server retrieves the daily report data stored in the database and analyzes it using natural language processing (NLP) techniques to extract key phrases and important information.

[1398] Input: Daily report data stored in the database

[1399] Output: Extracted key phrases (e.g., "gripping," "difficult")

[1400] Step 4:

[1401] The server uses a sentiment analysis engine to analyze the user's sentiment from the daily report data. The sentiment engine (e.g., VADER Sentiment Analysis) generates a positive or negative evaluation of the sentiment contained in the daily report.

[1402] Input: Daily report data, extracted key phrases

[1403] Output: Sentiment analysis result (e.g. "negative")

[1404] Step 5:

[1405] The server searches the database for similar past daily report data and comment data based on the extracted key phrases and sentiment analysis results, using a data search engine such as Elasticsearch.

[1406] Input: Key phrases, sentiment analysis results

[1407] Output: Past similar daily report data and comment data

[1408] Step 6:

[1409] The server uses a generative AI model (e.g., GPT-4) based on the search results and analysis results to generate appropriate feedback for the user. The generative AI model takes into account past data and sentiment analysis results to generate feedback that helps the user grow positively.

[1410] Input: Search results, sentiment analysis results

[1411] Output: Generated feedback (e.g., "The angle and force of the arm are important for gripping operations. Let's continue experimenting.")

[1412] Step 7:

[1413] The server sends the generated feedback to the user's smart device.

[1414] Input: Generated feedback

[1415] Output: Feedback sent to the user's smart device

[1416] Step 8:

[1417] The smart device provides the received feedback to the user via voice or text.

[1418] Input: Feedback sent by the server

[1419] Output: Feedback provided to the user, either visually or audibly (e.g., "The angle and force of the arm are important for gripping. Let's continue experimenting.")

[1420] Step 9:

[1421] The server periodically analyzes the user's daily report data and feedback, and visualizes the user's growth trend. This visualization helps the user visually confirm their own growth.

[1422] Input: Past daily report data, feedback data

[1423] Output: Visualization of user growth trends (e.g., "Gripping success rate improved by 25% over the course of one month.")

[1424] Through these steps, users can efficiently improve their robot operation skills while receiving specific and emotionally sensitive feedback, which can also contribute to reducing the burden on elders and improving the skills of the entire workforce.

[1425] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1427] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1428] [Fourth embodiment]

[1429] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1430] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1431] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1432] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1433] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1436] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1437] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1438] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1439] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1440] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1441] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1442] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[1443] Overall system overview

[1444] The system includes the following main components:

[1445] 1. Data storage means (server)

[1446] 2. Data receiving means (server)

[1447] 3. Natural language processing means (server)

[1448] 4. Data search method (server)

[1449] 5. Feedback Generation Means (Server)

[1450] 6. Feedback provision method (terminal)

[1451] 7. Growth analysis method (server)

[1452] System Operation

[1453] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis results and search results, feedback is generated and provided to the user.

[1454] Program processing explanation

[1455] Entering and sending daily reports

[1456] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "Today's work taught me new ways of dealing with customers. I received a lot of support from my senior colleagues."

[1457] Receiving and saving daily reports

[1458] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[1459] Analysis using natural language processing

[1460] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[1461] Searching for past data

[1462] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches entries related to past customer interactions and extracts similar feedback.

[1463] Generate feedback

[1464] The server combines the search results and analysis results and uses generative AI to create new feedback, such as "To improve your customer service skills, try incorporating self-learning into your next customer service session based on your experience today."

[1465] Providing feedback

[1466] The server sends the generated feedback to the user's device, which then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[1467] Regular growth analysis and visualization

[1468] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[1469] Specific examples

[1470] If a user enters on October 10th, "I learned new customer service skills during today's work. I received a lot of support from my seniors," the server will analyze this and search for similar past "customer service" data and feedback. As a result, feedback on "self-study methods to improve customer service skills" will be generated and provided to the user via their device. The server will also periodically analyze the user's daily report data, visualize the trend of "gradual improvement in customer service skills," and notify the device. This process makes it easier for users to understand their own growth and reduces the burden on seniors.

[1471] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[1472] The processing flow will be explained below.

[1473] Step 1:

[1474] The user inputs and sends the daily report using the terminal.

[1475] Specifically, the user enters the contents of the daily report on the terminal, such as "I learned new skills in customer service. I received support from my senior colleagues," and presses the send button.

[1476] Step 2:

[1477] The terminal transmits the input daily report data to the server.

[1478] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[1479] Step 3:

[1480] The server receives the daily report data transmitted from the terminal.

[1481] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[1482] Step 4:

[1483] The server stores the received daily report data in a database.

[1484] Specifically, the server inserts the daily report data into the database using an INSERT command according to the appropriate schema.

[1485] Step 5:

[1486] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[1487] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text, extract keywords, and perform sentiment analysis.

[1488] Step 6:

[1489] The server searches for similar situations from past daily report data and comment data based on the extracted keywords and analysis results.

[1490] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries with similar keywords.

[1491] Step 7:

[1492] The server uses generative AI to generate feedback based on the data obtained from the search and the analysis results.

[1493] Specifically, the server inputs the analysis results into a generative AI model (e.g., GPT-4), which generates feedback such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[1494] Step 8:

[1495] The server generates feedback and sends it to the device.

[1496] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[1497] Step 9:

[1498] The terminal displays the received feedback to the user.

[1499] Specifically, the device displays the feedback it receives on the screen, providing the user with a visible message such as, "To improve your customer service skills, daily review in addition to support from your seniors is effective."

[1500] Step 10:

[1501] The server periodically analyzes the user's daily report data and feedback to visualize their growth.

[1502] Specifically, the server analyzes past data through scheduled execution, analyzes growth trends, and generates visualization data in the form of graphs and charts.

[1503] Step 11:

[1504] The server transmits the growth trend data to the terminal, which displays it to the user.

[1505] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[1506] The above is the specific processing flow in this system.

[1507] Example 1

[1508] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1509] With conventional human resource development systems, it was difficult to provide individual support for the growth of new employees, which increased the burden on elders. Furthermore, the system lacked the functionality to efficiently analyze new employees' daily report data and feedback, provide appropriate feedback, and visualize their long-term growth.

[1510] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1511] In this invention, the server includes means for storing past daily report data and comment data, means for users to input daily reports using a terminal and receive the data, means for analyzing the input daily reports using natural language processing, means for searching for similar situations from the past daily report data and comment data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for visualizing the user's growth trend based on the daily report data and feedback data and notifying the user's terminal. This makes it possible to efficiently support the growth of new employees and reduce the burden on elders.

[1512] "Past daily report data" is daily report data related to work that the user has input in the past.

[1513] "Comment data" refers to feedback and evaluation data provided in response to a daily report.

[1514] "Users" are individuals, including new employees, who use the system to enter daily reports and receive feedback.

[1515] "Terminal" refers to the device used by the user to enter daily reports and receive feedback, such as a smartphone, PC, or tablet.

[1516] A "server" is a computing device that receives, stores, analyzes, and generates feedback on daily report data sent by users.

[1517] "Natural language processing" is a technology that analyzes text data to understand, process, and generate human language.

[1518] The "analysis means" is a process or system that analyzes the stored daily report data using natural language processing technology.

[1519] A "search method" is a process or system that searches for similar situations from past daily report data and comment data.

[1520] A "generation means" is a process or system that combines search results and analysis results to generate new feedback.

[1521] A "generative AI model" is an artificial intelligence technology that automatically generates text and feedback based on input data.

[1522] "Feedback" is a response message that includes evaluation and advice regarding the daily report.

[1523] "Visualization" is the process of analyzing user growth and visually displaying the results in graphs, reports, etc.

[1524] "Growth trends" refer to trends or patterns that indicate an improvement in a user's skills or performance.

[1525] "Notification means" refers to a process or system that sends analysis results and feedback to the user's terminal and displays them.

[1526] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. It also periodically analyzes and visualizes the user's growth, making it easier for users to understand their own growth.

[1527] The system includes the following major components:

[1528] 1. Data storage means (server)

[1529] 2. Data receiving means (server)

[1530] 3. Natural language processing means (server)

[1531] 4. Data search method (server)

[1532] 5. Feedback Generation Means (Server)

[1533] 6. Feedback provision method (terminal)

[1534] 7. Growth analysis method (server)

[1535] 8. Trend notification method (server)

[1536] Hardware and Software Configuration

[1537] The server is a high-performance computing device that uses MySQL or PostgreSQL as the database system, Elasticsearch as the search engine, Google Cloud Natural Language or spaCy as the natural language processing (NLP) technology, and OpenAI's GPT-3 as the generative AI model.

[1538] A terminal is a device operated by a user, such as a smartphone, PC, or tablet, and has dedicated applications and a web browser installed.

[1539] Program processing

[1540] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily report and searches for similar past daily reports and corresponding comment data. Based on the analysis and search results, feedback is generated and provided to the user. The server also periodically analyzes the user's daily report data and feedback, visualizes the user's growth, and notifies the terminal.

[1541] Specific examples

[1542] If a user enters on October 10th, "I learned new customer service skills during work today. I received a lot of support from my seniors," the server analyzes this and searches for past similar "customer service" data and feedback. As a result, an AI model (such as GPT-3) is used to generate feedback on "self-study methods to improve customer service skills," which is provided to the user via their device. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in customer service skills," and notifies the device.

[1543] Prompt Sentence Examples

[1544] Examples of prompts to input to a generative AI model might include:

[1545] "Our new employees learned new customer service skills during today's work and received a lot of support from their seniors. Based on this experience, could you give us some advice on how to improve our customer service skills in the future?"

[1546] As described above, this invention utilizes AI technology to support the growth of new employees and reduce the burden on elders.

[1547] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1548] Step 1:

[1549] A user inputs a daily report on work using a terminal and transmits it to the server.

[1550] Input: Daily report text entered by the user into the terminal (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my senior colleagues.")

[1551] Output: Daily report data is sent to the server as an HTTP request.

[1552] Specific operation: The user accesses the interface of a dedicated application or web browser, enters the daily report content into the text field, and clicks the send button.

[1553] Step 2:

[1554] The server receives the daily report data sent by the user and stores it in a database.

[1555] Input: User's daily report data received by the server (e.g., "I learned new ways to deal with customers during today's work. I received a lot of support from my senior colleagues.")

[1556] Output: Daily report data is stored in a database, along with metadata such as date and user ID.

[1557] Specific operation: When the server receives an HTTP request, it extracts the daily report data and stores it in a database system (e.g., MySQL or PostgreSQL).

[1558] Step 3:

[1559] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[1560] Input: Daily report data saved in the database (e.g., "Today's work taught me new ways to deal with customers. I received a lot of support from my seniors.")

[1561] Output: Key phrases and entities extracted from daily report data (e.g., "customer service," "senior support")

[1562] Specific operation: The server uses Google Cloud Natural Language API and spaCy to tokenize the daily report text and extract important key phrases and entities.

[1563] Step 4:

[1564] The server searches past daily report data and comment data based on the extracted key phrases.

[1565] Input: Extracted key phrases (e.g., "customer service," "senpai support")

[1566] Output: Past similar daily report data and comment data (e.g., "Past customer correspondence entries")

[1567] Specific operation: The server uses the full-text search function of Elasticsearch or PostgreSQL to search for similar past daily report data and comment data within the database.

[1568] Step 5:

[1569] The server combines the search results and analysis results and creates new feedback using generative AI.

[1570] Input: Search results and analysis results (e.g., previous entries and key phrases related to customer service)

[1571] Output: Generated feedback (e.g., "To improve your customer service skills, try incorporating self-study into your next customer service experience based on this experience.")

[1572] Specific operation: The server inputs a prompt sentence into a generative AI model (e.g., OpenAI's GPT-3), which generates a feedback sentence based on the prompt sentence. The generated feedback sentence is then formatted and saved in an appropriate format.

[1573] Step 6:

[1574] The server transmits the generated feedback to the user's terminal, which then displays the received feedback to the user.

[1575] Input: Generated feedback statement (e.g., "Based on this experience, I will incorporate self-study into my next customer interaction to improve my customer interaction skills.")

[1576] Output: Feedback message displayed on the user's device (e.g., "Today's customer service efforts should be better supported by your senior colleagues, but it would be good to incorporate self-study into your work.")

[1577] Specific operation: The server sends feedback data as an HTTP response, and the device analyzes the received data and displays it in the application or web interface.

[1578] Step 7:

[1579] The server periodically analyzes past daily report data and feedback data, visualizes the user's growth trends, and notifies the user's device.

[1580] Input: Daily report data and feedback data stored in the database (past 3 months, etc.)

[1581] Output: User growth trend report (e.g. "Customer service skills are gradually improving")

[1582] Specific operation: The server periodically retrieves past daily report data and feedback data from the database and analyzes growth trends using specific algorithms or analytical tools. The results are compiled in graph or report format and sent to the user's device as an HTTP response. The user can then check the results on their device and understand their growth.

[1583] (Application example 1)

[1584] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1585] When new employees operate robots in factories, there is a need for a method to efficiently manage their development while receiving appropriate training. Systematic support is also needed to reduce the burden on elders and supervisors and enable new employees to improve their skills independently. There is a need for a system that visualizes on-site learning progress and provides feedback to support new employees in improving their skills.

[1586] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1587] In this invention, the server includes means for storing past daily report data and comment data, means for a user to input a daily report using a terminal and receive the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from the past data and comment data, means for generating necessary feedback, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, and means for storing and analyzing training data related to machine operation in the factory and providing the generated feedback to the user. This makes it possible to efficiently support the growth of new employees in the factory, visualize learning progress, and provide feedback while reducing the burden on elders and supervisors.

[1588] "Past daily report data" is report information relating to work that the user previously input.

[1589] "Comment data" refers to information about feedback and advice provided by elders or superiors regarding daily reports.

[1590] "Device" refers to the smartphone, tablet, or computer used by the user.

[1591] "Natural language processing" is a technology for understanding and analyzing human language, and a means of extracting useful information from text data.

[1592] "Analysis means" is a means for analyzing data stored on the server and extracting specific information.

[1593] "Search means" is a function for searching for similar data from past databases.

[1594] "Feedback" is advice or instructions provided based on daily reports and data entered by the user.

[1595] "Means for analyzing user growth" is a function for evaluating how much a user has grown based on past data.

[1596] "Visualization" is a method of visually displaying the analyzed user's growth status using graphs, charts, etc.

[1597] "Training data" refers to specific training content related to machine operation in a factory and data used for practice.

[1598] "Generative AI" is a type of artificial intelligence technology that is a system that automatically generates new data and feedback based on input data.

[1599] This invention provides a system that supports robot operation training in factories to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users.

[1600] Overall system overview

[1601] The system includes the following main components:

[1602] 1. Data storage means (server)

[1603] 2. Data receiving means (server)

[1604] 3. Natural language processing means (server)

[1605] 4. Data search method (server)

[1606] 5. Feedback Generation Means (Server)

[1607] 6. Feedback provision method (terminal)

[1608] 7. Growth analysis method (server)

[1609] 8. Training data management means (server)

[1610] Program processing

[1611] 1. Enter and submit daily reports

[1612] Users can use their smartphones to input daily training reports. For example, they can write, "Today's training taught me precision robot assembly operations. Accuracy was more important than speed."

[1613] 2. Receiving and saving daily reports

[1614] The server receives the daily report data sent by the user and stores it in a database using a relational database such as PostgreSQL.

[1615] 3. Analysis using natural language processing

[1616] The server analyzes the saved daily report data using a natural language processing engine (such as SpaCy or BERT) to extract key phrases such as "precision assembly" and "accuracy."

[1617] 4. Searching for past data

[1618] The server searches past daily report data and comment data based on the extracted key phrases, searching for similar past training situations and feedback.

[1619] 5. Generate feedback

[1620] The server combines the search results and analysis results and generates new feedback using generative AI (such as OpenAI's GPT-3). For example, it can generate feedback such as, "Today's training taught you that accuracy is important in precision assembly. To improve this skill, it would be effective to incorporate repeated practice of the movement in your next training session."

[1621] 6. Providing Feedback

[1622] The server sends the generated feedback to the smartphone and notifies and displays it to the user, who can then use the feedback to improve their training.

[1623] 7. Regular growth analysis and visualization

[1624] The server periodically analyzes the user's daily data and visualizes growth trends. For example, it analyzes data from the past three months and identifies a trend that "precision assembly skills are gradually improving," and notifies the user's smartphone.

[1625] Specific examples

[1626] If a user inputs, "In today's training, I learned a new precision assembly operation. I learned that accuracy is more important than speed," the server analyzes this and searches for past similar "precision assembly" data and feedback. As a result, feedback such as, "In the next training, it would be good to incorporate repetitive practice of the operation," is generated and provided to the user via their smartphone. The server also periodically analyzes the user's daily report data, visualizes the trend of "gradual improvement in precision assembly skills," and notifies the user via their smartphone. This makes it easier for users to understand their own growth and reduces the burden on elders.

[1627] In this way, a mode for carrying out the invention is provided. This system enables efficient training within a factory, reduces the burden on elders and supervisors, and supports the improvement of the skills of new employees.

[1628] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1629] Step 1:

[1630] The user inputs a daily report using a smartphone. For example, the user might input, "Today's training taught us precision robot assembly operations. Accuracy was more important than speed." This daily report is sent to the server via the smartphone app.

[1631] Step 2:

[1632] The server receives the daily report data sent from the smartphone and stores it in a database. A relational database such as PostgreSQL is used for storage. The entered daily report data is saved as an entry for, for example, "2023-10-10."

[1633] Step 3:

[1634] The server analyzes the saved daily report data using a natural language processing engine (e.g., SpaCy or BERT). Specifically, it extracts key phrases such as "precision assembly" and "accuracy" from the daily report text. The input is the daily report text, and the output is the extracted key phrases.

[1635] Step 4:

[1636] The server searches past daily report data and comment data based on the extracted key phrases. For example, it searches for past training data and feedback related to similar "precision assembly" tasks. The input is the extracted key phrase, and the output is similar daily report data and comment data.

[1637] Step 5:

[1638] The server combines the search results and analysis results and generates new feedback using generative AI (for example, OpenAI's GPT-3). The input is similar daily report data and feedback, and the output is the newly generated feedback. For example, the generated feedback might be, "To improve the precision assembly skills learned in this training, it would be effective to incorporate repeated practice of the movements in the next training session."

[1639] Step 6:

[1640] The server sends the generated feedback to the smartphone app, which notifies and displays it to the user. The smartphone app displays the feedback to the user and provides specific advice. The input is the generated feedback, and the output is the notification to the user.

[1641] Step 7:

[1642] The server periodically analyzes the user's daily report data and visualizes growth trends. It analyzes data from the past three months, identifies a trend that "precision assembly skills are gradually improving," and notifies the smartphone. The input is the past daily report data, and the output is the visualized growth trend.

[1643] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1644] This invention provides a human resource development system that utilizes AI technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on past daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[1645] Overall system overview

[1646] The system includes the following main components:

[1647] 1. Data storage means (server)

[1648] 2. Data receiving means (server)

[1649] 3. Natural language processing means (server)

[1650] 4. Data search method (server)

[1651] 5. Feedback Generation Means (Server)

[1652] 6. Feedback provision method (terminal)

[1653] 7. Growth analysis method (server)

[1654] 8. Emotion Engine (Server)

[1655] System Operation

[1656] New employees (users) use their terminals to input daily reports about their daily work. This daily report data is sent to the server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and corresponding comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is promoted by regularly analyzing the user's growth and visualizing the results.

[1657] Program processing explanation

[1658] Entering and sending daily reports

[1659] A user inputs a daily report about work using a terminal and transmits it to the server. For example, the user inputs, "I learned new skills about customer service. I received support from my senior colleague."

[1660] Receiving and saving daily reports

[1661] The server receives the daily report data sent by the user and stores it in the database. For example, the daily report data is stored as an entry for "2023-10-10."

[1662] Analysis using natural language processing

[1663] The server analyzes the saved daily report data using natural language processing (NLP) technology, extracting key phrases such as "customer service" and "senior support."

[1664] Emotion analysis using an emotion engine

[1665] The server uses the emotion engine to analyze emotions from the user's daily report data, for example, to determine whether the user's daily report has positive emotions or negative emotions.

[1666] Searching for past data

[1667] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis, for example, searching for entries and feedback about past customer interactions.

[1668] Generate feedback

[1669] The server combines the search results with the analysis results and uses generative AI to create new feedback. It also takes into account the results of sentiment analysis and provides feedback that helps users grow in a positive way. For example, it could generate feedback like, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[1670] Providing feedback

[1671] The server sends the generated feedback to the user's device, which then displays the received feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the device.

[1672] Regular growth analysis and visualization

[1673] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes a trend such as "improvement in customer service skills" and notifies the device.

[1674] Specific examples

[1675] If a user types in "I learned new customer service skills during today's work. I received a lot of support from my seniors" on October 10th, the server will analyze this and use its emotion engine to determine that the emotion is positive. The server then searches for past data and feedback about "customer service." Based on this past feedback, the server generates feedback such as "To improve your customer service skills, daily review is effective in addition to support from your seniors," and provides this to the user via their device. The server also periodically analyzes the user's daily report data, visualizing the trend of "your customer service skills are gradually improving" and notifying the device. This process makes it easier for users to understand their own growth and reduces the burden on elders.

[1676] As described above, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[1677] The processing flow will be explained below.

[1678] Step 1:

[1679] The user inputs and sends the daily report using the terminal.

[1680] Specifically, the user enters the following into the terminal screen as a daily report: "I learned new skills in customer service. I received support from my senior colleague." and presses the send button.

[1681] Step 2:

[1682] The terminal transmits the input daily report data to the server.

[1683] Specifically, the terminal sends a POST request containing daily report data to the server's API endpoint.

[1684] Step 3:

[1685] The server receives the daily report data transmitted from the terminal.

[1686] Specifically, the server receives the API request and temporarily stores the daily report data for analysis.

[1687] Step 4:

[1688] The server stores the received daily report data in a database.

[1689] Specifically, the server uses an INSERT command to store the daily report data in the database according to the appropriate schema.

[1690] Step 5:

[1691] The server analyzes the stored daily report data using natural language processing (NLP) technology.

[1692] Specifically, the server uses an NLP library (e.g., spaCy, BERT, etc.) to tokenize the daily report text and perform key phrase extraction and sentiment analysis.

[1693] Step 6:

[1694] The server uses an emotion engine to analyze emotions from the daily report data of the user.

[1695] Specifically, the server uses an emotion engine to detect positive emotions from the part "I learned new skills in customer service," and detect a sense of security from the part "I received support from my senior."

[1696] Step 7:

[1697] The server searches for similar situations from past daily report data and comment data based on the extracted key phrases and sentiment analysis results.

[1698] Specifically, the server uses SQL queries or a full-text search engine (e.g., Elasticsearch) to search for past daily report entries that include "customer service" or "senior support."

[1699] Step 8:

[1700] The server combines the search results and analysis results and generates feedback using generative AI.

[1701] Specifically, the server uses a generative AI model (e.g., GPT-4) to generate feedback such as, "To improve your customer service skills, daily review is effective in addition to support from your superiors." This feedback also takes into account the results of sentiment analysis and is adjusted to help the user approach their next task with a positive attitude.

[1702] Step 9:

[1703] The server generates feedback and sends it to the user's device.

[1704] Specifically, the server converts the generated feedback into JSON format and sends it to the terminal as an HTTP response.

[1705] Step 10:

[1706] The terminal displays the received feedback to the user.

[1707] Specifically, the feedback received by the device is placed in a UI component and displayed as, "Today's customer service, it would be a good idea to incorporate self-study while making use of the support of your senior colleagues."

[1708] Step 11:

[1709] The server periodically analyzes users' daily data and feedback to visualize growth trends.

[1710] Specifically, the server analyzes past daily report data and feedback every month or quarter and converts the user's skills and growth trends into visualized data in the form of graphs and charts.

[1711] Step 12:

[1712] The server transmits the generated growth trend data to the terminal, which displays it to the user.

[1713] Specifically, the server sends analysis results such as "Customer service skills have improved over the past three months" in JSON format to the device, which then displays them to the user as graphs or messages.

[1714] The above is the specific processing flow in this system.

[1715] Example 2

[1716] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1717] Developing new employees is an important issue for companies, but it places a heavy burden on elder employees. In order for new employees to feel that they are growing and to reduce the burden on elder employees, efficient feedback and visualization of growth are necessary. Traditional methods require elder employees to manually provide feedback and manage the growth of new employees, which requires a great deal of effort. Furthermore, there is a risk of decreased motivation if the feedback is inappropriate or new employees do not feel that they are growing properly.

[1718] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for saving past data, means for a user to input a daily report using an information processing device and receiving the data, means for analyzing the input daily report using natural language processing, means for searching for similar situations from past data, means for generating feedback from the analysis results and past data, means for providing the generated feedback to the user, means for periodically analyzing the user's growth and visualizing the results, means for analyzing emotions, and means for adjusting feedback based on the analyzed emotions. This makes it possible to provide appropriate and timely feedback to new employees and give them a sense of growth while reducing the burden on older employees.

[1719] "Past data" refers to daily report data and comment data that users have entered and saved in the past.

[1720] "User" refers to the person who uses the system to enter daily reports and receive feedback.

[1721] The term "information processing device" refers to a terminal or device that a user uses to input a daily report.

[1722] "Natural language processing" refers to the technology that analyzes input daily report data and extracts key phrases and important topics.

[1723] "Similar situations" refer to situations in which there is a commonality or relevance between past daily report data and comment data and current input data.

[1724] "Feedback" refers to information generated based on the analysis results, including evaluations, advice, and suggestions for improvement for users.

[1725] A "generative artificial intelligence model" refers to an artificial intelligence technology that learns from large amounts of data and generates new information and feedback.

[1726] "Analyzing emotions" refers to the process of identifying emotions contained in input text data and classifying them into emotional categories such as positive, negative, and neutral.

[1727] "Visualizing growth" refers to the process of analyzing a user's past data and visually representing their growth trends and progress.

[1728] "Adjusting feedback" refers to modifying or emphasizing the content of feedback based on the analyzed emotions to help the user develop most effectively.

[1729] This invention provides a human resource development system that utilizes artificial intelligence (AI) technology to support the growth of new employees and reduce the burden on elders. This system generates feedback based on daily report data and comment data and provides it to users. In addition, by combining it with an emotion engine, it analyzes emotions from the user's daily report data and adjusts the feedback more appropriately.

[1730] The system includes the following main components:

[1731] 1. Data storage means (server)

[1732] 2. Data receiving means (server)

[1733] 3. Natural language processing means (server)

[1734] 4. Data search method (server)

[1735] 5. Feedback Generation Means (Server)

[1736] 6. Feedback provision method (terminal)

[1737] 7. Growth analysis method (server)

[1738] 8. Emotion Engine (Server)

[1739] The server receives the daily report data input by the user using an information processing device, and stores the data in a database using a data storage means.

[1740] The server analyzes the saved daily report data using natural language processing (NLP) technology. This analysis extracts key phrases and themes from the daily report. For example, if a user enters, "I learned new skills in customer service. I received support from my senior colleague," "customer service" and "senior colleague's support" are extracted as key phrases.

[1741] The server uses an emotion engine to analyze emotions from the user's daily report data, and determines whether the user's daily report contains positive or negative emotions.

[1742] The server searches past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis. This search identifies similar past situations. For example, past entries related to "customer service" are searched for.

[1743] The server uses a generative AI model (such as GPT-3) to generate new feedback. This generation utilizes search results and analysis results, as well as the results of user sentiment analysis. For example, the generated feedback might be, "To improve your customer service skills, daily review is effective in addition to support from your superiors."

[1744] The server sends the generated feedback to the user's terminal, which then displays the feedback to the user. For example, a message such as "Today's customer service efforts would benefit from the support of your senior colleagues while incorporating self-study" is displayed on the terminal.

[1745] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth. For example, it analyzes data from the past three months and visualizes trends such as "improvement in customer service skills" in the form of graphs and charts, and notifies the device.

[1746] For example:

[1747] If a user enters on October 10th, "I learned new ways to deal with customers during today's work. I received a lot of support from my seniors," the server will analyze this and use its emotion engine to determine positive emotions. The server then searches for past data and feedback about "customer service," and generates the following feedback: "To improve your customer service skills, daily review is effective in addition to support from your seniors." This feedback is then provided to the user via their device. The server periodically analyzes the user's daily report data, visualizes the trend of "your customer service skills are gradually improving," and notifies the device.

[1748] In this way, the present invention utilizes AI and emotion analysis technology to support the growth of new employees and reduce the burden on elders.

[1749] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1750] Specific processing steps of the program

[1751] Step 1: Enter and submit your daily report

[1752] The user inputs a daily report using the terminal. For example, the user inputs, "I learned a new way of dealing with customers during today's work. I received support from my senior colleagues."

[1753] Input: User's daily report text data.

[1754] Action: Formats input data and sends it to the server.

[1755] Output: Daily report text data sent to the server.

[1756] Step 2: Receive and save daily reports

[1757] The server receives the daily report data sent by the user and stores it in a database in a structured format.

[1758] Input: User's daily report text data.

[1759] How it works: Adds metadata such as date and user ID and saves it in a database.

[1760] Output: Daily report data stored in a database.

[1761] Step 3: Natural Language Processing Analysis

[1762] The server analyzes the stored daily report data using natural language processing (NLP) technology, specifically extracting key phrases and important topics from the sentences.

[1763] Input: Saved daily report text data.

[1764] How it works: It uses NLP techniques to tokenize text and extract key phrases.

[1765] Output: Extracted key phrases (e.g., "customer service," "senpai support").

[1766] Step 4: Emotion analysis using the emotion engine

[1767] The server uses an emotion engine to analyze emotions from users' daily report data, which are classified as positive, negative, neutral, etc.

[1768] Input: Saved daily report text data.

[1769] How it works: Uses the sentiment engine to calculate sentiment scores for text and classify it into categories.

[1770] Output: Parsed sentiment data (e.g. "positive").

[1771] Step 5: Search historical data

[1772] The server searches the database for past daily report data and comment data based on the extracted key phrases and the results of sentiment analysis.

[1773] Input: Extracted key phrases, sentiment data.

[1774] What it does: Runs a database query to find relevant historical data.

[1775] Output: Relevant historical datasets as search results.

[1776] Step 6: Generate feedback

[1777] The server uses a generative AI model (such as GPT-3) to generate new feedback, using search results, analysis results, and sentiment analysis results.

[1778] Input: historical data as search results, analysis results, sentiment data.

[1779] How it works: Enter prompts into a generative AI model to generate new feedback.

[1780] Output: Generated feedback text (e.g., "To improve your customer service skills, daily review in addition to support from your seniors is effective.").

[1781] Step 7: Provide feedback

[1782] The server transmits the generated feedback to the user's terminal.

[1783] The terminal displays this feedback to the user.

[1784] Input: The generated feedback text.

[1785] Action: Sends the feedback text to the user's device and displays it.

[1786] Output: The feedback message displayed on the user's terminal.

[1787] Step 8: Regularly analyze and visualize growth

[1788] The server periodically analyzes the user's daily report data and feedback to visualize the user's growth.

[1789] Input: All past daily report data, feedback data.

[1790] How it works: It uses analytical algorithms to calculate growth trends and produces results in the form of graphs and charts.

[1791] Output: Visualized growth trends (e.g., a chart showing "Customer-facing skills are improving").

[1792] The above are the specific processing steps of this system.

[1793] (Application example 2)

[1794] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1795] There is a need for an appropriate educational support system to enable new employees to efficiently learn how to operate robots used in factories. However, with conventional educational methods, it is often difficult for employees to grasp their own progress, resulting in insufficient feedback. This results in issues such as delayed growth of new employees and increased burden on elders. Furthermore, the content of the feedback does not take into account the emotional state of new employees, which can lead to a decrease in motivation to learn and stress. A system that solves these issues and supports the efficient growth of new employees is needed.

[1796] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1797] In this invention, the server includes: means for storing past daily report data and comment data; means for users to input daily reports using a terminal and receive the data; means for analyzing the input daily reports using natural language processing; means for searching for similar situations from past daily report data and comment data; means for generating feedback from the analysis results and past data; means for providing the generated feedback to the user; means for periodically analyzing the user's growth and visualizing the results; means including an emotion engine for analyzing emotions based on the user's daily report data; means for adjusting feedback taking into account the results of the emotion analysis; and means for enabling the use of a smart device as the user's terminal. This allows users to receive feedback that matches their emotional state and allows them to grow efficiently. Furthermore, visualizing one's own growth can increase motivation to learn and reduce the burden on elders.

[1798] "Past daily report data" is report data relating to work that the user has input in the past.

[1799] "Comment data" refers to feedback and opinions added by elders or staff members to past daily report data.

[1800] "Terminal" refers to a device used by a user to input and send daily reports, and includes PCs, smartphones, tablets, smart glasses, head-mounted displays (HMDs), etc.

[1801] "Natural language processing" is a technology that analyzes and understands text data and extracts or generates information.

[1802] The "emotion engine" is a system for analyzing and evaluating user emotions from text data.

[1803] "Generative AI" is artificial intelligence that has algorithms that generate new data and feedback based on input data.

[1804] "Feedback" refers to advice and suggestions created based on the analysis results of the user's daily report and past data.

[1805] "Growth analysis" is the process of evaluating and visualizing a user's level of growth based on the user's past daily report data and feedback history.

[1806] A "smart device" is a terminal that can connect to the Internet and install various applications, and includes smartphones, smart glasses, and head-mounted displays (HMDs).

[1807] "Visualization" means displaying data and analysis results in a form that is visually easy for users to understand.

[1808] A "daily report" is a report that allows a user to record the details of their daily work and learning.

[1809] This invention provides a human resource development system that utilizes AI technology, and in particular, shows its application to a smart device educational application that allows new employees to efficiently learn how to operate robots used in factories. The system configuration and operation are described in detail below.

[1810] Overall system configuration

[1811] The system includes the following major components:

[1812] 1. Data storage means (server)

[1813] 2. Data receiving means (server)

[1814] 3. Natural language processing means (server)

[1815] 4. Data search method (server)

[1816] 5. Feedback Generation Means (Server)

[1817] 6. Feedback Methods (Smart Devices)

[1818] 7. Growth analysis method (server)

[1819] 8. Emotion Engine (Server)

[1820] 9. Smart devices (smart glasses, head-mounted displays (HMD))

[1821] Hardware and Software

[1822] Smart glasses: Google Glass, Vuzix Blade

[1823] Head-mounted display (HMD): Microsoft HoloLens, Meta Quest

[1824] NLP technology: Google BERT, spaCy NLP

[1825] Sentiment analysis: VADER Sentiment Analysis, IBM Watson Natural Language Understanding

[1826] Generation AI: OpenAI GPT-4, GPT-3

[1827] Database: PostgreSQL, MongoDB

[1828] Data search engine: Elasticsearch

[1829] System Operation

[1830] New employees (users) use smart glasses or an HMD to input daily reports on robot operation. This daily report data is sent to a server and stored in a database. The server analyzes the daily reports using natural language processing (NLP) technology and recognizes the user's emotions using an emotion engine. It also searches for similar past daily reports and comment data, and generates and provides feedback to the user based on the analysis and search results. User growth is regularly analyzed and visualized to promote it.

[1831] Specific examples

[1832] Data entry and submission

[1833] This example shows a user entering a daily report by voice or text using smart glasses or an HMD.

[1834] For example: "I was able to control the robot arm successfully, but I had difficulty with gripping."

[1835] Data reception and storage

[1836] The server receives the daily report data sent by the user and stores it in a database.

[1837] Natural Language Processing and Sentiment Analysis

[1838] The server analyzes the stored daily report data using natural language processing (NLP) technology and extracts key phrases.

[1839] For example, extract "robot arm", "gripping", etc.

[1840] The emotion engine then analyzes emotions from the user's daily report data.

[1841] Example: Determine that a daily report indicates "positive emotions."

[1842] Feedback generation and provision

[1843] The server searches past data and generates feedback based on the extracted key phrases and the results of sentiment analysis.

[1844] Example: The feedback generated is, "The angle and force of the arm are important for gripping operations. Let's continue experimenting."

[1845] The smart device receives the generated feedback and provides it to the user via voice or text.

[1846] Prompt Sentence Examples

[1847] Below is an example of a prompt sentence input to the generative AI model (GPT-4).

[1848] User: I performed gripping operations on the robot during today's work, but I still find it difficult.

[1849] Generative AI model (GPT-4) prompt:

[1850] Generate appropriate feedback based on the user's daily report. Sentiment analysis shows that the user has slightly negative sentiment.

[1851] Taking into account feedback about previous gripping actions.

[1852] Output: The angle and force of the arm are important for gripping operations. Let's continue with trial and error.

[1853] This invention helps new employees grow efficiently by receiving feedback that matches their emotional state. It also reduces the burden on elders and improves the skills of the entire workforce.

[1854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1855] Step 1:

[1856] Users input daily reports using smart devices (smart glasses or HMDs), and submit detailed information and impressions about their work by voice or text.

[1857] Input: "I performed a robot gripping operation today, but I'm still having difficulty."

[1858] Output: Data sent from smart device to server

[1859] Step 2:

[1860] The server receives the daily report data sent by the user and stores it in a database. This data becomes the basis for subsequent analysis processing.

[1861] Input: Daily report data sent from a smart device

[1862] Output: Daily data entries stored in the database

[1863] Step 3:

[1864] The server retrieves the daily report data stored in the database and analyzes it using natural language processing (NLP) techniques to extract key phrases and important information.

[1865] Input: Daily report data stored in the database

[1866] Output: Extracted key phrases (e.g., "gripping," "difficult")

[1867] Step 4:

[1868] The server uses a sentiment analysis engine to analyze the user's sentiment from the daily report data. The sentiment engine (e.g., VADER Sentiment Analysis) generates a positive or negative evaluation of the sentiment contained in the daily report.

[1869] Input: Daily report data, extracted key phrases

[1870] Output: Sentiment analysis result (e.g. "negative")

[1871] Step 5:

[1872] The server searches the database for similar past daily report data and comment data based on the extracted key phrases and sentiment analysis results, using a data search engine such as Elasticsearch.

[1873] Input: Key phrases, sentiment analysis results

[1874] Output: Past similar daily report data and comment data

[1875] Step 6:

[1876] The server uses a generative AI model (e.g., GPT-4) based on the search results and analysis results to generate appropriate feedback for the user. The generative AI model takes into account past data and sentiment analysis results to generate feedback that helps the user grow positively.

[1877] Input: Search results, sentiment analysis results

[1878] Output: Generated feedback (e.g., "The angle and force of the arm are important for gripping operations. Let's continue experimenting.")

[1879] Step 7:

[1880] The server sends the generated feedback to the user's smart device.

[1881] Input: Generated feedback

[1882] Output: Feedback sent to the user's smart device

[1883] Step 8:

[1884] The smart device provides the received feedback to the user via voice or text.

[1885] Input: Feedback sent by the server

[1886] Output: Feedback provided to the user, either visually or audibly (e.g., "The angle and force of the arm are important for gripping. Let's continue experimenting.")

[1887] Step 9:

[1888] The server periodically analyzes the user's daily report data and feedback, and visualizes the user's growth trend. This visualization helps the user visually confirm their own growth.

[1889] Input: Past daily report data, feedback data

[1890] Output: Visualization of user growth trends (e.g., "Gripping success rate improved by 25% over the course of one month.")

[1891] Through these steps, users can efficiently improve their robot operation skills while receiving specific and emotionally sensitive feedback, which can also contribute to reducing the burden on elders and improving the skills of the entire workforce.

[1892] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1893] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1894] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1895] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1896] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1897] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1898] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1899] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1900] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1901] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1902] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1903] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1904] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1905] 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.

[1906] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1907] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1908] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1909] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1910] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1911] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1912] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1913] The following is further disclosed regarding the above embodiment.

[1914] (Claim 1)

[1915] A means of storing past daily report data and comment data,

[1916] A means for a user to input a daily report using a terminal and receive the data;

[1917] A means for analyzing the input daily report using natural language processing;

[1918] A means for searching for similar situations from past daily report data and comment data;

[1919] a means of generating feedback from the analysis results and historical data;

[1920] means for providing the generated feedback to the user;

[1921] A method to regularly analyze user growth and visualize the results,

[1922] A system including:

[1923] (Claim 2)

[1924] 10. The system of claim 1, wherein the means for generating feedback uses generative AI.

[1925] (Claim 3)

[1926] 10. The system of claim 1, wherein the means for analyzing user growth compares historical data.

[1927] "Example 1"

[1928] (Claim 1)

[1929] A means of storing past daily report data and comment data,

[1930] A means for a user to input a daily report using a terminal and receive the data;

[1931] A means for analyzing the input daily report using natural language processing;

[1932] A means for searching for similar situations from past daily report data and comment data;

[1933] a means of generating feedback from the analysis results and historical data;

[1934] means for providing the generated feedback to the user;

[1935] A method to regularly analyze user growth and visualize the results,

[1936] A means for visualizing user growth trends based on daily report data and feedback data and notifying them to the user's device;

[1937] A system including:

[1938] (Claim 2)

[1939] 10. The system of claim 1, wherein the means for generating feedback uses a generative AI model.

[1940] (Claim 3)

[1941] 2. The system of claim 1, wherein the means for analyzing the user's growth compares past daily report data and feedback data.

[1942] "Application Example 1"

[1943] (Claim 1)

[1944] A means of storing past daily report data and comment data,

[1945] A means for a user to input a daily report using a terminal and receive the data;

[1946] A means for analyzing the input daily report using natural language processing;

[1947] A means for searching for similar situations from past daily report data and comment data;

[1948] a means of generating feedback from the analysis results and historical data;

[1949] means for providing the generated feedback to the user;

[1950] A method to regularly analyze user growth and visualize the results,

[1951] means for storing and analyzing training data relating to machine operation in the factory and providing generated feedback to users;

[1952] A system including:

[1953] (Claim 2)

[1954] The system according to claim 1, characterized in that a generative AI is used as a means for generating feedback.

[1955] (Claim 3)

[1956] 10. The system of claim 1, wherein the means for analyzing user growth compares historical data.

[1957] "Example 2: Combining Emotion Engines"

[1958] (Claim 1)

[1959] A means of storing historical data;

[1960] A means for a user to input a daily report using an information processing device and receive the data;

[1961] A means for analyzing the input daily report using natural language processing;

[1962] A means of searching for similar situations from past data;

[1963] a means of generating feedback from the analysis results and historical data;

[1964] a means for providing the generated feedback to the user;

[1965] A method to regularly analyze user growth and visualize the results,

[1966] A means of analyzing emotions,

[1967] a means for adjusting the feedback based on the analyzed emotions;

[1968] A system including:

[1969] (Claim 2)

[1970] 10. The system of claim 1, wherein the means for generating feedback uses a generative artificial intelligence model.

[1971] (Claim 3)

[1972] 2. The system of claim 1, wherein the means for analyzing the user's growth compares past data.

[1973] "Application example 2 when combining emotion engines"

[1974] (Claim 1)

[1975] A means of storing past daily report data and comment data,

[1976] A means for a user to input a daily report using a terminal and receive the data;

[1977] A means for analyzing the input daily report using natural language processing;

[1978] A means for searching for similar situations from past daily report data and comment data;

[1979] a means of generating feedback from the analysis results and historical data;

[1980] means for providing the generated feedback to the user;

[1981] A method to regularly analyze user growth and visualize the results,

[1982] means including an emotion engine for analyzing emotions based on daily report data of a user;

[1983] a means for adjusting the feedback taking into account the results of the sentiment analysis;

[1984] means for enabling the use of a smart device as a user's terminal;

[1985] A system including:

[1986] (Claim 2)

[1987] 10. The system of claim 1, wherein the means for generating feedback uses generative AI.

[1988] (Claim 3)

[1989] 10. The system of claim 1, wherein the means for analyzing user growth compares historical data. [Explanation of symbols]

[1990] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of storing past daily report data and comment data, A means for a user to input a daily report using a terminal and receive the data; A means for analyzing the input daily report using natural language processing; A means for searching for similar situations from past daily report data and comment data; a means of generating feedback from the analysis results and historical data; means for providing the generated feedback to the user; A method to regularly analyze user growth and visualize the results, A system including:

2. 10. The system of claim 1, wherein the means for generating feedback uses generative AI.

3. 2. The system of claim 1, wherein the means for analyzing the user's progress compares historical data.

Images