System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a user input; means for analyzing the user input; means for identifying a motivation-lowering factor based on a result of the analysis; means for generating an additional question or advice based on the identified factor; and means for returning the generated question or advice 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] Many people today experience a decline in motivation in their work and personal lives, but are unable to accurately identify the cause and find it difficult to take appropriate measures. Existing tools to solve this problem are limited, and in many cases, expert assistance is required, making them difficult to access. In particular, with the increase in working from home and changes in lifestyles, the causes of decreased motivation are diversifying, and appropriate measures tailored to individual situations are required. [Means for solving the problem]

[0005] The present invention provides a system for identifying factors that decrease a user's motivation and providing appropriate countermeasures. The system includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, and means for returning the generated questions and advice to the user. The system may also include means for re-accepting additional information from the user and performing reanalysis based on the additional information. The system may further include means for generating a specific action plan to improve the user's motivation based on the information obtained by the reanalysis, and means for storing the dialogue history with the user and the generated action plan in a database. By using natural language processing for the analysis and identification, the meaning of the user's input can be accurately understood and appropriate countermeasures can be proposed. This allows for a consistent process from identifying factors that decrease motivation to proposing countermeasures, enabling the user to accurately understand their own situation and be supported to take appropriate action.

[0006] "User" refers to a person who uses this system, who identifies the cause of their own declining motivation, and seeks measures to improve it.

[0007] "User terminal" refers to a device that a user uses to access the system, such as a smartphone, tablet, or PC.

[0008] An "AI server" is a server that runs a program using artificial intelligence (AI) technology, analyzes user input, identifies factors that decrease motivation, and generates solutions.

[0009] The "database server" is a server for storing the user interaction history, analysis data, generated action plans, and the like.

[0010] "Input" refers to text information provided by the user to the system, including information regarding their own motivation decline.

[0011] "Analysis" refers to the process of evaluating the input provided by the user using natural language processing, understanding its meaning, and identifying the factors behind the decline in motivation.

[0012] "Factors that decrease motivation" are factors that cause a user to lose motivation, and specifically refer to overload of work, monotonous tasks, mental stress, etc.

[0013] A "question" is a question generated by the AI ​​server to make it easier for users to provide specific information.

[0014] "Advice" refers to content that suggests specific actions or improvements to help users improve their motivation.

[0015] An "action plan" is a plan that shows specific measures to address factors that lower motivation, and is intended to improve the user's motivation.

[0016] "Natural language processing" is a technology that allows computers to understand and analyze human language, and is used in this system to analyze user input.

[0017] "Dialogue history" refers to a record of the series of interactions between the user and the AI ​​server.

[0018] "Reanalysis" refers to the re-analysis process being carried out to obtain additional information and to identify the user's underlying problem. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. Each component and its processing are described in detail below in natural language.

[0041] User terminal

[0042] The user terminal functions as an interface for the user to interact with the system. The user inputs information about their motivation decline in text format and presses the send button. This input information can be multiple sentences at once.

[0043] AI Server

[0044] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[0045] 1. Text Analysis:

[0046] The AI ​​server analyzes user input using natural language processing (NLP) technology, which extracts important keywords and emotional characteristics from the input sentence.

[0047] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted.

[0048] 2. Identifying the factors that cause low motivation:

[0049] Based on the extracted keywords and emotional characteristics, the AI ​​server identifies the factors that are causing the user's motivation to decline. In this process, it compares past data and known patterns to infer the most likely factors.

[0050] For example, the keywords "work" and "lack of motivation" may lead to the identification of "overload of work" and "monotonous tasks" as contributing factors.

[0051] 3. Generate follow-up questions and advice:

[0052] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[0053] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[0054] 4. Dialogue Response:

[0055] The generated questions and advice are sent back to the user's terminal, making it easier for the user to input specific answers.

[0056] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[0057] Database Server

[0058] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0059] Specific examples

[0060] Here is an example of a specific dialogue:

[0061] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0062] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[0063] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0064] 4. AI server: Sends the generated questions back to the user device.

[0065] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0066] 6. User terminal: Send the input text to the AI ​​server again.

[0067] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0068] 8. AI server: Sends the question back to the user device.

[0069] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0070] 10. User terminal: Send the input text to the AI ​​server again.

[0071] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0072] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0073] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0074] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to those problems. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The user enters their concerns or problems related to their motivation into the text input field on the device and presses the send button.

[0078] Step 2:

[0079] The terminal acquires the input text data and sends it to the server together with the user ID and session information using an HTTP request.

[0080] Step 3:

[0081] The server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[0082] Step 4:

[0083] The server identifies factors that decrease motivation based on keywords and emotional characteristics output by the NLP module, using an internal database and known patterns. For example, from the keywords "work" and "unmotivated," "work overload" and "monotonous work" become candidates.

[0084] Step 5:

[0085] The server generates additional questions to obtain further information from the user based on the identified demotivation factors. For example, a question might be generated such as, "What tasks have you found particularly burdensome recently?"

[0086] Step 6:

[0087] The server returns the generated question to the user's terminal, where it is displayed in a format that allows the user to easily answer it.

[0088] Step 7:

[0089] The user enters specific answers to the questions displayed on the terminal, presses the send button again, and the process is repeated.

[0090] Step 8:

[0091] The device again sends the user's answers to the server, which analyzes this new information and again identifies the factors that lower motivation.

[0092] Step 9:

[0093] The server generates more specific questions and advice based on the results of the reanalysis. By repeating this process several times, the factors that decrease motivation can be identified in detail.

[0094] Step 10:

[0095] The server then generates a specific action plan based on the motivation-reducing factors, such as recommending "dividing tasks and taking short breaks."

[0096] Step 11:

[0097] The server sends the generated action plan to the user's terminal and displays it to the user. The action plan includes specific instructions and advice that the user can immediately implement.

[0098] Step 12:

[0099] The server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[0100] In this way, the user terminal, AI server, and database server work together to consistently identify factors that lower a user's motivation and provide specific measures for improvement.

[0101] Example 1

[0102] 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."

[0103] In modern society, many people suffer from a lack of motivation in their work and personal lives. However, the individual factors that cause this lack of motivation are diverse, making it difficult to find appropriate solutions. Furthermore, conventional systems often struggle to provide individualized solutions for each user, and can only provide general solutions. Therefore, there is a need for a system that can effectively identify the specific factors that cause a user to lose motivation and provide specific improvement measures tailored to each individual situation.

[0104] 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.

[0105] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for using a generative AI model for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for saving the analysis results and a dialogue history with the user in a database, and means for improving the quality of interaction with new users based on past data. This makes it possible to effectively identify specific factors that decrease a user's motivation and provide specific improvement measures tailored to individual situations.

[0106] The "means for accepting user input" refers to a means by which a user inputs information about a decrease in motivation to the system and transmits it to the system. Specifically, it includes interfaces such as a keyboard, a touch screen, and voice input.

[0107] "Natural language processing means" refers to means for analyzing text data entered by users and extracting important keywords and emotional characteristics. Specifically, it includes natural language processing libraries and algorithms.

[0108] A "generative AI model" is an artificial intelligence model that identifies factors that decrease motivation based on input data and analysis results, referring to specific patterns and past data. Specific examples include BERT and GPT.

[0109] The "means for generating additional questions and advice" is a means for generating questions to obtain further information from the user or initial measures for improvement based on the identified demotivation factors.

[0110] "Means for returning generated questions and advice to the user" refers to the means for sending questions and advice generated by the AI ​​server back to the user's terminal, and uses HTTPS or similar as a communication protocol.

[0111] "Means for saving analysis results and user interaction history in a database" refers to means for saving the analysis results performed by the AI ​​server and the content of user interaction in a database so that they can be referenced later. This includes database management systems and storage devices.

[0112] "Means for improving the quality of responses to new users based on past data" refers to a means for referring to saved past dialogue history and analysis results and using them to more effectively respond to new users. This makes it possible to more accurately identify factors that decrease motivation and provide improvement measures.

[0113] MODE FOR CARRYING OUT THE INVENTION

[0114] System Configuration

[0115] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. The detailed functions and processing flow of each component are explained below.

[0116] User terminal

[0117] The user terminal functions as an interface for the user to interact with the system. Using a dedicated application or a web interface, the user inputs information about their own lack of motivation in text format and presses the send button. This input information can include multiple sentences. For example, the user can input "I've been feeling unmotivated at work lately" and send it.

[0118] AI Server

[0119] Based on the information sent from the user device, the AI ​​server performs the following main processes:

[0120] 1. Text Analysis:

[0121] The AI ​​server analyzes the user's input using natural language processing (NLP) techniques, such as Python's NLTK or SpaCy libraries. This allows it to extract important keywords and emotional characteristics from the input sentence. For example, keywords such as "work" and "unmotivated" are extracted.

[0122] 2. Identifying the factors that cause low motivation:

[0123] Based on the extracted keywords and emotional characteristics, the AI ​​server uses generative AI models such as BERT and GPT to identify the factors behind the user's lack of motivation. During this process, it compares past data and known patterns to infer likely causes. For example, based on the keywords "work" and "lack of motivation," it can identify that "work overload" is the cause.

[0124] 3. Generate follow-up questions and advice:

[0125] Based on the identified demotivators, the AI ​​server generates follow-up questions to obtain further information from the user and initial improvement measures, such as, "Which tasks do you find particularly stressful?"

[0126] 4. Dialogue Response:

[0127] The generated questions and advice are sent back to the user's device using the HTTPS protocol to ensure security.

[0128] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[0129] Database Server

[0130] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0131] Specific examples

[0132] Here is an example of a specific dialogue:

[0133] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0134] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[0135] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0136] 4. AI server: Sends the generated questions back to the user device.

[0137] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0138] 6. User terminal: Send the input text to the AI ​​server again.

[0139] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0140] 8. AI server: Sends the question back to the user device.

[0141] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0142] 10. User terminal: Send the response text to the AI ​​server again.

[0143] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0144] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0145] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0146] In this way, by using the system of the present invention, the user can gain a deeper understanding of his or her own problems and take concrete measures to improve them.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1:

[0149] The user uses a dedicated application or web interface to enter text information about the decline in motivation and presses the send button.

[0150] Input: Text information from the user (e.g., "I've been feeling unmotivated at work lately.")

[0151] Output: The entered text information is sent from the user's device.

[0152] Step 2:

[0153] The user's device sends the input text information to the AI ​​server. The HTTPS protocol is used for communication to ensure data security.

[0154] Input: Text information entered by the user

[0155] Output: Text information arrives at the AI ​​server

[0156] Step 3:

[0157] The server analyzes the received text information using natural language processing (NLP) techniques, specifically using Python's NLTK and SpaCy libraries, to extract important keywords and sentiment features.

[0158] Input: Text information received by the server

[0159] Data processing / data calculation: Analyze text using NLP technology to extract keywords and sentiment features

[0160] Output: Extracted keywords and sentiment features (e.g., "work" and "unmotivated")

[0161] Step 4:

[0162] The server uses a generative AI model (such as BERT or GPT) to identify factors that cause demotivation based on the extracted keywords and emotional characteristics. The AI ​​model refers to past data and known patterns to infer likely factors.

[0163] Input: Extracted keywords and sentiment features

[0164] Data processing / data calculation: Identifying factors that decrease motivation using generative AI models

[0165] Output: Identified demotivators (e.g., "work overload")

[0166] Step 5:

[0167] The server generates additional questions to obtain further information from the user and initial remedial measures based on the identified demotivation factors.

[0168] Input: Identified demotivators

[0169] Data manipulation / data calculation: Generate additional questions and advice

[0170] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[0171] Step 6:

[0172] The server sends the generated questions and advice to the user's terminal, also using the HTTPS protocol.

[0173] Input: Generated questions and advice

[0174] Output: Questions and advice are sent to the user's device.

[0175] Step 7:

[0176] The user terminal displays the received question or advice, and the user inputs an answer. For example, the user inputs "Daily report work."

[0177] Input: Questions and advice sent by the server

[0178] Output: User's answer (e.g., "Daily report work")

[0179] Step 8:

[0180] The user's terminal sends the user's answer back to the AI ​​server.

[0181] Input: User's answer

[0182] Output: The answer arrives at the AI ​​server

[0183] Step 9:

[0184] The server then analyzes the newly received text data again. For example, it infers that the cause is "monotonous work" and generates a question such as, "Which part of the report work is particularly stressful for you?"

[0185] Input: User's answer submitted again

[0186] Data processing / data calculation: Reanalyze using NLP technology to generate the next question

[0187] Output: Generated follow-up questions (e.g., "What aspects of the report task are particularly stressful for you?")

[0188] Step 10:

[0189] The server transmits the generated follow-up question to the user terminal.

[0190] Input: Generated follow-up question

[0191] Output: The question arrives at the user's terminal.

[0192] Step 11:

[0193] The user terminal displays the question, and the user again inputs the answer. For example, the user inputs "It's monotonous and there is a lot of repetitive work."

[0194] Input: Additional question sent by the server

[0195] Output: User response (e.g., "It's repetitive and monotonous.")

[0196] Step 12:

[0197] The user's terminal sends the user's answer back to the AI ​​server.

[0198] Input: User's answer

[0199] Output: The answer arrives at the AI ​​server

[0200] Step 13:

[0201] The server generates a final action plan, for example recommending "break up tasks and take short breaks."

[0202] Input: User's answer submitted again

[0203] Data processing / data calculation: Generate a final action plan using a generative AI model

[0204] Output: Final action plan (e.g., "Break down tasks and take short breaks")

[0205] Step 14:

[0206] The server sends the proposed final action plan to the user terminal, which displays it.

[0207] Input: Final Action Plan

[0208] Output: The final action plan is displayed on the user's device.

[0209] Step 15:

[0210] The server stores the final dialogue history and action plan in the database server, which enables future responses based on the dialogue history.

[0211] Input: Final interaction history and action plan

[0212] Output: Dialogue history and action plans are saved in a database

[0213] (Application example 1)

[0214] 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."

[0215] Conventional motivation management systems typically identify factors that decrease motivation based on user input and then provide questions and advice. However, these systems do not necessarily adapt to the user's behavior or situation, and real-time dialogue and data updates are difficult, especially when used by field workers. As a result, the user experience is poor and motivation improvement effects are not fully achieved.

[0216] 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.

[0217] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating follow-up questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for accepting user input using a wearable device worn on the user's body, means for analyzing input from the wearable device using natural language analysis technology, means for generating follow-up questions and advice in a form that is displayed on the wearable device, means for referencing past data to identify factors that decrease the user's motivation, and a database for storing dialogue history. This enables users to engage in real-time dialogue, identify their own factors that decrease motivation, and quickly receive a specific and effective action plan for addressing those factors.

[0218] The "means for accepting user input" refers to a device that includes an interface or device that allows a user to provide input to the system.

[0219] The "means for analyzing the user input" refers to software and algorithms for analyzing input information received from a user and understanding its content.

[0220] The "means for identifying factors causing a decrease in motivation" is a system that has the function of extracting and identifying the causes of a decrease in motivation from the analyzed user input.

[0221] The "means for generating additional questions and advice" is a function that automatically generates questions to obtain further information from the user and advice on measures to be taken based on the identified motivation-reducing factors.

[0222] The "means for returning the generated question or advice to the user" is a system including a communication means and a display device for presenting the generated question or advice to the user.

[0223] A "wearable device" is a device that can be worn on the user's body and has functions such as input reception and information display.

[0224] "Natural language analysis technology" is a technology that analyzes input information such as text and voice and understands human language.

[0225] "Means for referencing past data" refers to a function that allows the system to refer to data collected in the past and improve the accuracy of analysis and identification.

[0226] The "database for storing dialogue history" refers to a database for storing the contents of dialogue with users and analysis results, and a system for managing such database.

[0227] The system of this invention is composed of a user terminal, an AI server, and a database server to identify factors that decrease a user's motivation and provide appropriate measures.

[0228] User terminal

[0229] The user terminal functions as an interface for the user to interact with the system. Specifically, the user wears a wearable device such as smart glasses and provides information to the system through voice or text input. The user inputs information about their own decline in motivation and presses a button to send it. This input information is then sent to the AI ​​server.

[0230] AI Server

[0231] The AI ​​server receives input information sent from the user device and performs the following main functions:

[0232] 1. Text Analysis:

[0233] The server analyzes the user's input using natural language processing technology, using software such as TextBlob and Transformers, to extract important keywords and emotional features and understand the user's state.

[0234] 2. Identifying the factors that cause low motivation:

[0235] Based on the extracted keywords and emotional characteristics, past data is referenced to identify factors that have reduced the user's motivation. Past data is stored on a database server, and the AI ​​server searches and compares this data to identify factors.

[0236] 3. Generate follow-up questions and advice:

[0237] Based on the identified demotivators, we generate follow-up questions to obtain more information from the user and initial improvement measures, such as "Which tasks do you find particularly burdensome?"

[0238] 4. Dialogue Response:

[0239] The generated questions and advice are sent back to the user's device, where the user can respond, and the information is then analyzed again by the AI ​​server.

[0240] Database Server

[0241] The AI ​​server's analysis results and user interaction history are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0242] Specific examples

[0243] Here is an example of a specific dialogue:

[0244] 1. User device: The user types "I haven't been motivated to work lately" through the smart glasses and presses the send button.

[0245] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[0246] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0247] 4. AI server: Sends the generated questions back to the user device.

[0248] 5. User terminal: The received question is displayed, and the user answers, "This is my daily report work."

[0249] 6. User terminal: Send the input text to the AI ​​server again.

[0250] 7. AI server: Reanalyzes the data and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0251] 8. AI server: Sends the question back to the user device.

[0252] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0253] 10. User terminal: Send the input text to the AI ​​server again.

[0254] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0255] 12. AI server: Sends the proposal to the user's device and presents it to the user.

[0256] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0257] Prompt Sentence Examples

[0258] Worker: I've been feeling unmotivated at work lately.

[0259] System: What parts of the job do you find particularly taxing?

[0260] Workers: There is a lot of monotonous work and it is hard.

[0261] System: Break up your tasks and take short breaks.

[0262] In this way, the system of the present invention identifies factors that decrease a user's motivation in real time and realizes a series of processes to provide solutions to those problems, allowing the user to gain a deeper understanding of their own problems and take concrete measures to improve them.

[0263] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0264] Step 1:

[0265] The user enters information about their motivation decline on their device and presses the send button. The entered information is sent in text format from the user device to the AI ​​server. The user device is a wearable device such as smart glasses.

[0266] Step 2:

[0267] The AI ​​server receives text information sent from the user's device. The received text information is analyzed using natural language analysis technology. Specifically, keywords and emotional features are extracted using TextBlob and Transformers. The input is text information related to the user's decreased motivation, and the output is the extracted keywords and emotional features.

[0268] Step 3:

[0269] The AI ​​server identifies factors that decrease motivation based on the extracted keywords and emotional characteristics. Specifically, it compares the extracted data with past data, which is stored in a database server. The input is keywords and emotional characteristics, and the output is the identified factors that decrease motivation.

[0270] Step 4:

[0271] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures. For example, if the identified factor is "work overload," it generates the question "Which tasks do you find particularly burdensome?" The input is the demotivation factors, and the output is the generated questions and advice.

[0272] Step 5:

[0273] The generated questions and advice are sent back from the AI ​​server to the user's device. The user's device displays these questions and advice to the user. The user then inputs an answer to the question. The input is the generated question or advice, and the output is the user's additional answer.

[0274] Step 6:

[0275] The user enters an additional answer and sends it again to the AI ​​server. The AI ​​server receives this additional information and performs text analysis again. The input is the additional answer from the user, and the output is the analyzed additional information.

[0276] Step 7:

[0277] Based on the reanalyzed information, the AI ​​server will dig deeper into further factors that lower motivation and generate further questions or advice as necessary. For example, if the user answers, "It's the daily report work," the next question generated will be, "Which part of that report work is particularly stressful for you?" The input is the reanalyzed additional information, and the output is further questions or advice.

[0278] Step 8:

[0279] The AI ​​server sends the final action plan to the user's device. The user's device displays this action plan to the user. For example, it may recommend "dividing tasks and taking short breaks." The input is the final action plan, and the output is the action plan displayed to the user.

[0280] Step 9:

[0281] The AI ​​server saves the final dialogue history and action plan in the database server. This is expected to improve the accuracy of identifying future declines in motivation and developing improvement measures. The input is the final dialogue history and action plan, and the output is the information saved in the database.

[0282] 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.

[0283] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and its accuracy is particularly enhanced by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine. Each component and its processing are described in detail below in natural language.

[0284] User terminal

[0285] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[0286] AI Server

[0287] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[0288] 1. Text analysis and emotion recognition:

[0289] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[0290] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[0291] 2. Identifying the factors that cause low motivation:

[0292] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[0293] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[0294] 3. Generate follow-up questions and advice:

[0295] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[0296] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[0297] 4. Dialogue Response:

[0298] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[0299] Emotion Engine

[0300] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[0301] Database Server

[0302] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0303] Specific examples

[0304] Here is an example of a specific dialogue:

[0305] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0306] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[0307] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0308] 4. AI server: Sends the generated questions back to the user device.

[0309] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0310] 6. User terminal: Send the input text to the AI ​​server again.

[0311] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0312] 8. AI server: Sends the question back to the user device.

[0313] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0314] 10. User terminal: Send the input text to the AI ​​server again.

[0315] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0316] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0317] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0318] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to address them. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them. By combining it with an emotion engine, highly accurate identification and solutions can be achieved, taking into account the user's emotional state.

[0319] The processing flow will be explained below.

[0320] Step 1:

[0321] The user enters their motivation-related worries or problems into a text input field on the device and presses the send button. For example, they might enter, "I haven't been feeling motivated at work lately."

[0322] Step 2:

[0323] The device acquires the entered text data and sends it to the AI ​​server using an HTTP request along with the user ID and session information.

[0324] Step 3:

[0325] The AI ​​server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[0326] Step 4:

[0327] The emotion engine recognizes emotions from text. For example, it recognizes "negative emotions" from the phrase "I'm not motivated."

[0328] Step 5:

[0329] Based on the output of the NLP module and emotion engine, the AI ​​server uses an internal database and known patterns to identify factors that decrease motivation, such as "work overload" and "monotonous work."

[0330] Step 6:

[0331] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user, such as, "What tasks have you found particularly burdensome recently?"

[0332] Step 7:

[0333] The AI ​​server returns the generated question to the user's terminal and displays it to the user.

[0334] Step 8:

[0335] The user inputs a specific answer to the question displayed on the terminal and presses the send button again. For example, the user might answer, "I'm working on a daily report."

[0336] Step 9:

[0337] The device again sends the user's answer to the AI ​​server, which again analyzes this new information with the NLP module and again recognizes emotions using the emotion engine.

[0338] Step 10:

[0339] Based on the results of the reanalysis, the AI ​​server generates more specific questions and advice, such as, "Which part of the report work is particularly stressful for you?"

[0340] Step 11:

[0341] The AI ​​server then sends the generated questions to the user's device, and the user enters the answers again. By repeating this process several times, the factors that decrease the user's motivation can be identified in detail.

[0342] Step 12:

[0343] Finally, the AI ​​server generates a specific action plan based on the factors that cause the decrease in motivation, such as recommending "dividing tasks and taking short breaks."

[0344] Step 13:

[0345] The AI ​​server sends the generated action plan to the user's device and displays it to the user. The action plan includes specific instructions and advice that are easy for the user to follow.

[0346] Step 14:

[0347] The AI ​​server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[0348] In this way, the user terminal, AI server, emotion engine, and database server work together to consistently identify factors that lower the user's motivation and provide specific measures for improvement.

[0349] Example 2

[0350] 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."

[0351] In modern society, many people suffer from a lack of motivation in their work or studies. It is particularly difficult to identify the individual causes of motivation loss and provide appropriate solutions, creating a demand for effective support systems. However, existing systems are unable to fully consider the user's emotions and specific circumstances, resulting in poor accuracy and effectiveness of the solutions they provide. Therefore, the present invention aims to recognize the user's emotions, more accurately identify the causes of motivation loss, and provide appropriate solutions.

[0352] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0353] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for recognizing the user's emotion using emotion recognition means, means for identifying factors that decrease motivation based on the analysis results and the recognized emotion, means for generating additional questions and advice based on the identified factors, and means for returning the generated questions and advice to the user. This makes it possible to accurately identify factors that decrease motivation according to individual circumstances, taking into account the user's emotional state, and to provide countermeasures against them.

[0354] The "means for accepting user input" refers to an interface and function that allows a user to input information about their own decline in motivation and transmit it to the system.

[0355] "Natural language processing means for analyzing said user input" refers to techniques and processes that analyze text data submitted by a user and extract important keywords and phrases.

[0356] "Emotion Recognition Method" refers to the technology and process for recognizing and determining emotions from user input text, using emotion engines and AI algorithms.

[0357] "Means for identifying factors that decrease motivation based on the analysis results and recognized emotions" refers to technology and functions that identify factors that decrease a user's motivation based on extracted keywords and recognized emotions.

[0358] "Means for generating additional questions and advice based on identified factors" refers to technology and functionality for generating questions and advice to gather further information and provide improvement measures in response to factors that reduce motivation.

[0359] The "means for returning the generated question or advice to the user" refers to the technology and functionality for transmitting and displaying the generated question or advice to the user.

[0360] "Means for reanalysis" refers to the technology and process of reanalyzing additional information and response data from users and extracting new keywords and emotions based on the newly obtained information.

[0361] The "means for generating a specific action plan" refers to a technology and function for creating a feasible plan or instructions for improving the user's motivation based on the reanalysis results.

[0362] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and in particular, improves accuracy by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine.

[0363] User terminal

[0364] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[0365] AI Server

[0366] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[0367] 1. Text analysis and emotion recognition:

[0368] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[0369] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[0370] 2. Identifying the factors that cause low motivation:

[0371] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[0372] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[0373] 3. Generate follow-up questions and advice:

[0374] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[0375] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[0376] 4. Dialogue Response:

[0377] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[0378] Emotion Engine

[0379] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[0380] Database Server

[0381] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0382] Specific examples

[0383] Here is an example of a specific dialogue:

[0384] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0385] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[0386] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0387] 4. AI server: Sends the generated questions back to the user device.

[0388] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0389] 6. User terminal: Send the input text to the AI ​​server again.

[0390] 7. AI server: Analyzes again and infers that the cause is "monotonous work," generating a question such as, "Which part of the report work do you find particularly stressful?"

[0391] 8. AI server: Sends the question back to the user device.

[0392] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0393] 10. User terminal: Send the input text to the AI ​​server again.

[0394] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0395] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0396] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0397] In general, the system of the present invention takes into account the user's emotional state, and is able to accurately identify factors that decrease motivation according to individual circumstances and provide countermeasures. Examples of prompts include "If you have been feeling unmotivated by your recent work, please tell us in detail why" and "Please feel free to write about your current feelings and the stress you are experiencing."

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1:

[0400] User Input Processing

[0401] The user uses the user terminal to input information about his / her own decreased motivation in text format and presses the send button.

[0402] Input: The user types "I've been feeling unmotivated at work lately" into the text box.

[0403] Output: The entered text data will be ready on the terminal after the send button is pressed.

[0404] Specific action: The user enters text using a keyboard or touch panel and clicks the send button.

[0405] Step 2:

[0406] Sending input data

[0407] The user terminal sends the input data to the AI ​​server.

[0408] Input: Text data entered by the user.

[0409] Output: Text data is sent to the AI ​​server via API.

[0410] Specific operation: When the user presses the send button, the device's communication module sends the data to the server.

[0411] Step 3:

[0412] Text Analysis and Emotion Recognition

[0413] The server analyzes the received data using natural language processing (NLP) technology to extract important keywords and phrases, while also using emotion recognition tools to recognize emotions.

[0414] Input: Sent text data: "I haven't been motivated to work lately."

[0415] Output: Keywords "work" and "unmotivated" and emotion "negative".

[0416] How it works: The NLP module on the server analyzes the text data and extracts keywords, while the emotion engine simultaneously identifies emotions.

[0417] Step 4:

[0418] Identifying factors that decrease motivation

[0419] The server identifies factors that decrease motivation based on the extracted keywords and recognized emotions.

[0420] Input: Keywords "work" and "unmotivated" and emotion "negative".

[0421] Output: "Work overload" and "monotonous work" are identified as factors that decrease motivation.

[0422] Specific operation: Based on the keywords and emotion data, the server compares it with an internal database and identifies the cause by referring to past data and cases.

[0423] Step 5:

[0424] Generate follow-up questions and advice

[0425] The server generates additional questions and advice based on the identified factors.

[0426] Input: Motivational factor "Work overload."

[0427] Output: Produces the question "What tasks have you found particularly taxing recently?"

[0428] Specific behavior: The server uses its internal logic and dialogue model to generate appropriate questions and advice based on the factors.

[0429] Step 6:

[0430] Submit a question or suggestion

[0431] The generated questions and advice are sent back to the user terminal.

[0432] Input: Generated additional questions or advice.

[0433] Output: Questions and advice displayed on the user's terminal.

[0434] Specific operation: The data generated by the server is sent to the user's terminal via API and presented to the user via a display interface.

[0435] Step 7:

[0436] User response processing

[0437] The user inputs and transmits an answer to the question displayed on the user terminal.

[0438] Input: The user enters "Daily report work" into the input field and presses the submit button.

[0439] Output: User response data is ready.

[0440] Specific behavior: The user again enters information using the keyboard or touch panel and clicks the send button.

[0441] Step 8:

[0442] Sending response data

[0443] The user terminal transmits the user's response data to the AI ​​server.

[0444] Input: User's answer data: "Daily reporting."

[0445] Output: The response data sent to the server.

[0446] Specific operation: The terminal's communication module sends the user's response data to the AI ​​server.

[0447] Step 9:

[0448] Reanalysis and countermeasure generation

[0449] The server analyzes the input data again, extracts new keywords and phrases, and generates the next questions and solutions.

[0450] Input: User's answer data: "Daily reporting."

[0451] Output: Keywords "report work" and "monotonous" and the following question: "Which part of the report work do you find particularly stressful?"

[0452] Specific operation: The server re-analyzes, extracts new keywords, and generates the next question.

[0453] Step 10:

[0454] Submit an action plan

[0455] The server generates a final action plan and proposes it to the user.

[0456] Input: Reanalysis result: "Monotonous work is a stressor."

[0457] Output: Action plan: "Divide tasks and take short breaks"

[0458] Specific operation: The server generates an action plan and sends it to the user's device via API.

[0459] Step 11:

[0460] Data storage

[0461] The server stores the dialogue history and the final action plan in a database server.

[0462] Input: Interaction history and action plan data.

[0463] Output: History and plans stored in a database.

[0464] Specific operation: The server connects to the database and saves the analysis results and countermeasure data.

[0465] Through the above processing steps, the system can identify factors that reduce a user's motivation and provide highly accurate countermeasures that take into account the user's emotional state.

[0466] (Application example 2)

[0467] 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."

[0468] In modern industrial environments, monotonous tasks and long working hours can lead to a decline in worker motivation. This can lead to a decline in work efficiency and quality, ultimately affecting productivity. There is a need for a system that can solve this problem and maintain and improve worker motivation.

[0469] 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.

[0470] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for being installed in the industrial machine, and means for analyzing the emotions of workers and managing their motivation. This makes it possible to quickly and accurately identify factors that decrease motivation in workers and provide appropriate advice and improvements.

[0471] The "means for accepting user input" refers to a device or interface that allows a user to input information in text format and that allows the system to receive that information.

[0472] "Means for analyzing user input" refers to a device or software that analyzes input text information using natural language processing techniques and extracts keywords and phrases.

[0473] The "means for identifying factors that decrease motivation" is a device or algorithm for identifying factors that decrease a user's motivation based on analyzed keywords and emotional data.

[0474] The "means for generating additional questions and advice" is a device or program for automatically generating additional questions and advice for the user in response to the identified demotivation factors.

[0475] The "means for returning questions and advice to the user" refers to a device or interface for transmitting the generated questions and advice to the user terminal and displaying them to the user.

[0476] "Means installed on industrial machines" refers to devices or software for incorporating and using the motivation management system on factory machines.

[0477] "Means for analyzing worker emotions" refers to a device or algorithm for analyzing text or voice data to recognize the worker's emotional state.

[0478] "Means for managing motivation" refers to a device or program that provides appropriate measures based on the worker's emotional data and factors that decrease motivation, thereby maintaining and improving their motivation to work.

[0479] This invention is a system for identifying factors that decrease the motivation of factory workers and providing countermeasures. This system consists of a user terminal, an AI server, a database server, and an emotion recognition engine. Each component and its processing are described in detail below.

[0480] User terminal

[0481] The user terminal functions as an interface for the worker to interact with the system. The user enters information about their emotional state and motivation in text format and presses the send button. The system is designed so that users can enter either a single sentence or multiple sentences. Smartphones, head-mounted displays, etc. are used as user terminals.

[0482] AI Server

[0483] The AI ​​server processes input information sent from the user terminal. The AI ​​server has the following main functions:

[0484] 1. Text analysis and emotion recognition:

[0485] The AI ​​server uses natural language processing (NLP) techniques to analyze user input and extract key keywords and phrases, and an emotion recognition engine to analyze emotional states.

[0486] The software used includes Python, NLTK (Natural Language Toolkit), SentimentIntensityAnalyzer, etc.

[0487] 2. Identifying the factors that cause low motivation:

[0488] Based on the results of text analysis and the user's emotional state, factors that decrease the user's motivation are identified, such as "monotonous work" and "long working hours."

[0489] 3. Generate follow-up questions and advice:

[0490] Based on the identified factors, the AI ​​server generates additional questions and advice for the user, and specific countermeasures are proposed and sent to the user.

[0491] Emotion Recognition Engine

[0492] The emotion recognition engine is a dedicated module for extracting emotions from user input text. It has the ability to distinguish between positive, negative, and neutral emotions, and is used in the analysis process of the AI ​​server.

[0493] Database Server

[0494] The results of the analysis performed by the AI ​​server and the history of user interactions are stored on a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of responses to new users based on past data. Examples of database management systems used include MySQL.

[0495] Specific examples

[0496] Here is an example of a specific dialogue:

[0497] 1. User terminal: The worker types in, "Recently, I've been doing monotonous work and I'm not motivated," and presses the send button.

[0498] 2. AI server: Analyzes the text and extracts keywords such as "monotonous work" and "unmotivated." An emotion recognition engine recognizes "negative" emotions.

[0499] 3. AI server: Based on the analysis results, it identifies that "monotonous work is the cause" and generates the next question: "Which part of the work is particularly burdensome?"

[0500] 4. AI server: Returns the generated questions to the user device.

[0501] 5. User terminal: The question is received and the worker enters "There is a lot of repetitive work."

[0502] 6. User terminal: Re-send the input text to the AI ​​server.

[0503] 7. AI server: Reanalyzes and infers that "diversification of work is necessary" and suggests "try combining other tasks."

[0504] 8. AI server: Sends suggestions to the user's device and displays them to the worker.

[0505] Prompt Sentence Examples

[0506] "Recently, I've been doing monotonous tasks that have been unmotivating me. For example, I have to assemble the same parts all day. Do you have any suggestions for solving this problem?"

[0507] As described above, by using this system, it is possible to quickly and accurately identify the factors that decrease worker motivation and provide appropriate countermeasures. Specific feedback and countermeasures are expected to improve the work environment and increase efficiency.

[0508] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0509] Step 1:

[0510] The user provides input

[0511] The user uses a smartphone or head-mounted display to input information about their emotional state and motivation in text format and presses the send button. This input becomes the data to be analyzed in the next step.

[0512] Input: User's text information (e.g., "Recently, I've been doing monotonous work and I'm not feeling motivated.")

[0513] Output: The text data sent

[0514] Step 2:

[0515] Sending data from the user device to the AI ​​server

[0516] The user terminal sends the input text data to the AI ​​server, which uses this data in the next analysis step.

[0517] Input: Text data entered into the user's terminal

[0518] Output: Text data sent to the AI ​​server

[0519] Step 3:

[0520] Text Analysis and Emotion Recognition

[0521] The AI ​​server analyzes the received text data using natural language processing (NLP) technology to extract important keywords and phrases. At the same time, it analyzes the emotional state using an emotion recognition engine. The software used is Python, NLTK, and SentimentIntensityAnalyzer.

[0522] Input: Text data sent to the AI ​​server

[0523] Output: Analyzed keywords, emotional state (e.g., "monotonous work," "unmotivated," emotion recognition result: negative)

[0524] Specific behavior:

[0525] 1. Tokenize the text data and extract important keywords and phrases.

[0526] 2. Analyze emotional states using SentimentIntensityAnalyzer.

[0527] 3. Obtain a positive, negative, or neutral score.

[0528] Step 4:

[0529] Identifying factors that decrease motivation

[0530] The AI ​​server identifies factors that decrease the user's motivation based on the results of text analysis and emotion recognition, such as "monotonous work" and "long working hours."

[0531] Input: Parsed keywords, emotional state

[0532] Output: Identified demotivators (e.g., "monotonous work")

[0533] Specific behavior:

[0534] 1. Analyzed keywords and sentiment data are compared with known factors in the database.

[0535] 2. Identify the most consistent demotivator.

[0536] Step 5:

[0537] Generate additional questions and advice

[0538] Based on the identified demotivation factors, the AI ​​server generates additional questions and advice for the user, such as "Which part of the work is particularly burdensome?", and suggests specific measures.

[0539] Input: Identified demotivators

[0540] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[0541] Specific behavior:

[0542] 1. Retrieve relevant questions and measures from the database.

[0543] 2. Generate questions and advice tailored to the user.

[0544] Step 6:

[0545] Sending additional questions or advice to the user's device

[0546] The generated questions and advice are sent to the user's terminal and displayed to the user, and this information serves as feedback to the user.

[0547] Input: Generated questions and advice

[0548] Output: Questions and advice sent to the user's terminal

[0549] Specific behavior:

[0550] 1. Convert the generated content into a format that can be easily viewed by the user.

[0551] 2. Send to the user's terminal and display.

[0552] Step 7:

[0553] Accepting additional information from the user

[0554] The user can then enter additional information in response to the submitted question or advice and submit it again, a process that yields more detailed information.

[0555] Input: Additional information about the user (e.g., "Daily report work")

[0556] Output: Data sent to the AI ​​server as additional information

[0557] Specific behavior:

[0558] 1. The user enters answers to questions and additional information and submits.

[0559] 2. Transfer additional information to the AI ​​server.

[0560] Step 8:

[0561] Reanalysis and updated measures

[0562] The AI ​​server receives the additional information and analyzes it again, proposing specific measures to improve the user's motivation as a final action plan.

[0563] Input: Additional information from the user

[0564] Output: An updated action plan (e.g., "Break up tasks and take short breaks")

[0565] Specific behavior:

[0566] 1. Reanalyze additional information to identify new factors and details.

[0567] 2. Generate and propose a specific action plan.

[0568] Step 9:

[0569] Sending the final action plan to the user's device

[0570] The generated action plan is sent to the user's terminal and displayed to the user, allowing the user to know specific improvement measures.

[0571] Input: Updated Action Plan

[0572] Output: Action plan sent to user device

[0573] Specific behavior:

[0574] 1. Convert the generated action plan into a format that is easy for users to execute.

[0575] 2. Send to the user's terminal and display.

[0576] Step 10:

[0577] Save conversation history and action plans

[0578] The AI ​​server stores all interaction history and generated action plans in a database server, allowing for future improvements and user progress tracking.

[0579] Input: Dialogue history, generated action plan

[0580] Output: Data stored on the database server

[0581] Specific behavior:

[0582] 1. Dialogue history and generated action plans are saved in a database.

[0583] 2. Retaining data for subsequent analysis and improvement.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] [Second embodiment]

[0588] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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."

[0600] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. Each component and its processing are described in detail below in natural language.

[0601] User terminal

[0602] The user terminal functions as an interface for the user to interact with the system. The user inputs information about their motivation decline in text format and presses the send button. This input information can be multiple sentences at once.

[0603] AI Server

[0604] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[0605] 1. Text Analysis:

[0606] The AI ​​server analyzes user input using natural language processing (NLP) technology, which extracts important keywords and emotional characteristics from the input sentence.

[0607] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted.

[0608] 2. Identifying the factors that cause low motivation:

[0609] Based on the extracted keywords and emotional characteristics, the AI ​​server identifies the factors that are causing the user's motivation to decline. In this process, it compares past data and known patterns to infer the most likely factors.

[0610] For example, the keywords "work" and "lack of motivation" may lead to the identification of "overload of work" and "monotonous tasks" as contributing factors.

[0611] 3. Generate follow-up questions and advice:

[0612] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[0613] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[0614] 4. Dialogue Response:

[0615] The generated questions and advice are sent back to the user's terminal, making it easier for the user to input specific answers.

[0616] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[0617] Database Server

[0618] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0619] Specific examples

[0620] Here is an example of a specific dialogue:

[0621] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0622] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[0623] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0624] 4. AI server: Sends the generated questions back to the user device.

[0625] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0626] 6. User terminal: Send the input text to the AI ​​server again.

[0627] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0628] 8. AI server: Sends the question back to the user device.

[0629] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0630] 10. User terminal: Send the input text to the AI ​​server again.

[0631] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0632] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0633] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0634] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to those problems. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them.

[0635] The processing flow will be explained below.

[0636] Step 1:

[0637] The user enters their concerns or problems related to their motivation into the text input field on the device and presses the send button.

[0638] Step 2:

[0639] The terminal acquires the input text data and sends it to the server together with the user ID and session information using an HTTP request.

[0640] Step 3:

[0641] The server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[0642] Step 4:

[0643] The server identifies factors that decrease motivation based on keywords and emotional characteristics output by the NLP module, using an internal database and known patterns. For example, from the keywords "work" and "unmotivated," "work overload" and "monotonous work" become candidates.

[0644] Step 5:

[0645] The server generates additional questions to obtain further information from the user based on the identified demotivation factors. For example, a question might be generated such as, "What tasks have you found particularly burdensome recently?"

[0646] Step 6:

[0647] The server returns the generated question to the user's terminal, where it is displayed in a format that allows the user to easily answer it.

[0648] Step 7:

[0649] The user enters specific answers to the questions displayed on the terminal, presses the send button again, and the process is repeated.

[0650] Step 8:

[0651] The device again sends the user's answers to the server, which analyzes this new information and again identifies the factors that lower motivation.

[0652] Step 9:

[0653] The server generates more specific questions and advice based on the results of the reanalysis. By repeating this process several times, the factors that decrease motivation can be identified in detail.

[0654] Step 10:

[0655] The server then generates a specific action plan based on the motivation-reducing factors, such as recommending "dividing tasks and taking short breaks."

[0656] Step 11:

[0657] The server sends the generated action plan to the user's terminal and displays it to the user. The action plan includes specific instructions and advice that the user can immediately implement.

[0658] Step 12:

[0659] The server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[0660] In this way, the user terminal, AI server, and database server work together to consistently identify factors that lower a user's motivation and provide specific measures for improvement.

[0661] Example 1

[0662] 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."

[0663] In modern society, many people suffer from a lack of motivation in their work and personal lives. However, the individual factors that cause this lack of motivation are diverse, making it difficult to find appropriate solutions. Furthermore, conventional systems often struggle to provide individualized solutions for each user, and can only provide general solutions. Therefore, there is a need for a system that can effectively identify the specific factors that cause a user to lose motivation and provide specific improvement measures tailored to each individual situation.

[0664] 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.

[0665] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for using a generative AI model for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for saving the analysis results and a dialogue history with the user in a database, and means for improving the quality of interaction with new users based on past data. This makes it possible to effectively identify specific factors that decrease a user's motivation and provide specific improvement measures tailored to individual situations.

[0666] The "means for accepting user input" refers to a means by which a user inputs information about a decrease in motivation to the system and transmits it to the system. Specifically, it includes interfaces such as a keyboard, a touch screen, and voice input.

[0667] "Natural language processing means" refers to means for analyzing text data entered by users and extracting important keywords and emotional characteristics. Specifically, it includes natural language processing libraries and algorithms.

[0668] A "generative AI model" is an artificial intelligence model that identifies factors that decrease motivation based on input data and analysis results, referring to specific patterns and past data. Specific examples include BERT and GPT.

[0669] The "means for generating additional questions and advice" is a means for generating questions to obtain further information from the user or initial measures for improvement based on the identified demotivation factors.

[0670] "Means for returning generated questions and advice to the user" refers to the means for sending questions and advice generated by the AI ​​server back to the user's terminal, and uses HTTPS or similar as a communication protocol.

[0671] "Means for saving analysis results and user interaction history in a database" refers to means for saving the analysis results performed by the AI ​​server and the content of user interaction in a database so that they can be referenced later. This includes database management systems and storage devices.

[0672] "Means for improving the quality of responses to new users based on past data" refers to a means for referring to saved past dialogue history and analysis results and using them to more effectively respond to new users. This makes it possible to more accurately identify factors that decrease motivation and provide improvement measures.

[0673] MODE FOR CARRYING OUT THE INVENTION

[0674] System Configuration

[0675] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. The detailed functions and processing flow of each component are explained below.

[0676] User terminal

[0677] The user terminal functions as an interface for the user to interact with the system. Using a dedicated application or a web interface, the user inputs information about their own lack of motivation in text format and presses the send button. This input information can include multiple sentences. For example, the user can input "I've been feeling unmotivated at work lately" and send it.

[0678] AI Server

[0679] Based on the information sent from the user device, the AI ​​server performs the following main processes:

[0680] 1. Text Analysis:

[0681] The AI ​​server analyzes the user's input using natural language processing (NLP) techniques, such as Python's NLTK or SpaCy libraries. This allows it to extract important keywords and emotional characteristics from the input sentence. For example, keywords such as "work" and "unmotivated" are extracted.

[0682] 2. Identifying the factors that cause low motivation:

[0683] Based on the extracted keywords and emotional characteristics, the AI ​​server uses generative AI models such as BERT and GPT to identify the factors behind the user's lack of motivation. During this process, it compares past data and known patterns to infer likely causes. For example, based on the keywords "work" and "lack of motivation," it can identify that "work overload" is the cause.

[0684] 3. Generate follow-up questions and advice:

[0685] Based on the identified demotivators, the AI ​​server generates follow-up questions to obtain further information from the user and initial improvement measures, such as, "Which tasks do you find particularly stressful?"

[0686] 4. Dialogue Response:

[0687] The generated questions and advice are sent back to the user's device using the HTTPS protocol to ensure security.

[0688] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[0689] Database Server

[0690] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0691] Specific examples

[0692] Here is an example of a specific dialogue:

[0693] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0694] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[0695] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0696] 4. AI server: Sends the generated questions back to the user device.

[0697] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0698] 6. User terminal: Send the input text to the AI ​​server again.

[0699] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0700] 8. AI server: Sends the question back to the user device.

[0701] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0702] 10. User terminal: Send the response text to the AI ​​server again.

[0703] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0704] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0705] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0706] In this way, by using the system of the present invention, the user can gain a deeper understanding of his or her own problems and take concrete measures to improve them.

[0707] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0708] Step 1:

[0709] The user uses a dedicated application or web interface to enter text information about the decline in motivation and presses the send button.

[0710] Input: Text information from the user (e.g., "I've been feeling unmotivated at work lately.")

[0711] Output: The entered text information is sent from the user's device.

[0712] Step 2:

[0713] The user's device sends the input text information to the AI ​​server. The HTTPS protocol is used for communication to ensure data security.

[0714] Input: Text information entered by the user

[0715] Output: Text information arrives at the AI ​​server

[0716] Step 3:

[0717] The server analyzes the received text information using natural language processing (NLP) techniques, specifically using Python's NLTK and SpaCy libraries, to extract important keywords and sentiment features.

[0718] Input: Text information received by the server

[0719] Data processing / data calculation: Analyze text using NLP technology to extract keywords and sentiment features

[0720] Output: Extracted keywords and sentiment features (e.g., "work" and "unmotivated")

[0721] Step 4:

[0722] The server uses a generative AI model (such as BERT or GPT) to identify factors that cause demotivation based on the extracted keywords and emotional characteristics. The AI ​​model refers to past data and known patterns to infer likely factors.

[0723] Input: Extracted keywords and sentiment features

[0724] Data processing / data calculation: Identifying factors that decrease motivation using generative AI models

[0725] Output: Identified demotivators (e.g., "work overload")

[0726] Step 5:

[0727] The server generates additional questions to obtain further information from the user and initial remedial measures based on the identified demotivation factors.

[0728] Input: Identified demotivators

[0729] Data manipulation / data calculation: Generate additional questions and advice

[0730] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[0731] Step 6:

[0732] The server sends the generated questions and advice to the user's terminal, also using the HTTPS protocol.

[0733] Input: Generated questions and advice

[0734] Output: Questions and advice are sent to the user's device.

[0735] Step 7:

[0736] The user terminal displays the received question or advice, and the user inputs an answer. For example, the user inputs "Daily report work."

[0737] Input: Questions and advice sent by the server

[0738] Output: User's answer (e.g., "Daily report work")

[0739] Step 8:

[0740] The user's terminal sends the user's answer back to the AI ​​server.

[0741] Input: User's answer

[0742] Output: The answer arrives at the AI ​​server

[0743] Step 9:

[0744] The server then analyzes the newly received text data again. For example, it infers that the cause is "monotonous work" and generates a question such as, "Which part of the report work is particularly stressful for you?"

[0745] Input: User's answer submitted again

[0746] Data processing / data calculation: Reanalyze using NLP technology to generate the next question

[0747] Output: Generated follow-up questions (e.g., "What aspects of the report task are particularly stressful for you?")

[0748] Step 10:

[0749] The server transmits the generated follow-up question to the user terminal.

[0750] Input: Generated follow-up question

[0751] Output: The question arrives at the user's terminal.

[0752] Step 11:

[0753] The user terminal displays the question, and the user again inputs the answer. For example, the user inputs "It's monotonous and there is a lot of repetitive work."

[0754] Input: Additional question sent by the server

[0755] Output: User response (e.g., "It's repetitive and monotonous.")

[0756] Step 12:

[0757] The user's terminal sends the user's answer back to the AI ​​server.

[0758] Input: User's answer

[0759] Output: The answer arrives at the AI ​​server

[0760] Step 13:

[0761] The server generates a final action plan, for example recommending "break up tasks and take short breaks."

[0762] Input: User's answer submitted again

[0763] Data processing / data calculation: Generate a final action plan using a generative AI model

[0764] Output: Final action plan (e.g., "Break down tasks and take short breaks")

[0765] Step 14:

[0766] The server sends the proposed final action plan to the user terminal, which displays it.

[0767] Input: Final Action Plan

[0768] Output: The final action plan is displayed on the user's device.

[0769] Step 15:

[0770] The server stores the final dialogue history and action plan in the database server, which enables future responses based on the dialogue history.

[0771] Input: Final interaction history and action plan

[0772] Output: Dialogue history and action plans are saved in a database

[0773] (Application example 1)

[0774] 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."

[0775] Conventional motivation management systems typically identify factors that decrease motivation based on user input and then provide questions and advice. However, these systems do not necessarily adapt to the user's behavior or situation, and real-time dialogue and data updates are difficult, especially when used by field workers. As a result, the user experience is poor and motivation improvement effects are not fully achieved.

[0776] 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.

[0777] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating follow-up questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for accepting user input using a wearable device worn on the user's body, means for analyzing input from the wearable device using natural language analysis technology, means for generating follow-up questions and advice in a form that is displayed on the wearable device, means for referencing past data to identify factors that decrease the user's motivation, and a database for storing dialogue history. This enables users to engage in real-time dialogue, identify their own factors that decrease motivation, and quickly receive a specific and effective action plan for addressing those factors.

[0778] The "means for accepting user input" refers to a device that includes an interface or device that allows a user to provide input to the system.

[0779] The "means for analyzing the user input" refers to software and algorithms for analyzing input information received from a user and understanding its content.

[0780] The "means for identifying factors causing a decrease in motivation" is a system that has the function of extracting and identifying the causes of a decrease in motivation from the analyzed user input.

[0781] The "means for generating additional questions and advice" is a function that automatically generates questions to obtain further information from the user and advice on measures to be taken based on the identified motivation-reducing factors.

[0782] The "means for returning the generated question or advice to the user" is a system including a communication means and a display device for presenting the generated question or advice to the user.

[0783] A "wearable device" is a device that can be worn on the user's body and has functions such as input reception and information display.

[0784] "Natural language analysis technology" is a technology that analyzes input information such as text and voice and understands human language.

[0785] "Means for referencing past data" refers to a function that allows the system to refer to data collected in the past and improve the accuracy of analysis and identification.

[0786] The "database for storing dialogue history" refers to a database for storing the contents of dialogue with users and analysis results, and a system for managing such database.

[0787] The system of this invention is composed of a user terminal, an AI server, and a database server to identify factors that decrease a user's motivation and provide appropriate measures.

[0788] User terminal

[0789] The user terminal functions as an interface for the user to interact with the system. Specifically, the user wears a wearable device such as smart glasses and provides information to the system through voice or text input. The user inputs information about their own decline in motivation and presses a button to send it. This input information is then sent to the AI ​​server.

[0790] AI Server

[0791] The AI ​​server receives input information sent from the user device and performs the following main functions:

[0792] 1. Text Analysis:

[0793] The server analyzes the user's input using natural language processing technology, using software such as TextBlob and Transformers, to extract important keywords and emotional features and understand the user's state.

[0794] 2. Identifying the factors that cause low motivation:

[0795] Based on the extracted keywords and emotional characteristics, past data is referenced to identify factors that have reduced the user's motivation. Past data is stored on a database server, and the AI ​​server searches and compares this data to identify factors.

[0796] 3. Generate follow-up questions and advice:

[0797] Based on the identified demotivators, we generate follow-up questions to obtain more information from the user and initial improvement measures, such as "Which tasks do you find particularly burdensome?"

[0798] 4. Dialogue Response:

[0799] The generated questions and advice are sent back to the user's device, where the user can respond, and the information is then analyzed again by the AI ​​server.

[0800] Database Server

[0801] The AI ​​server's analysis results and user interaction history are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0802] Specific examples

[0803] Here is an example of a specific dialogue:

[0804] 1. User device: The user types "I haven't been motivated to work lately" through the smart glasses and presses the send button.

[0805] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[0806] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0807] 4. AI server: Sends the generated questions back to the user device.

[0808] 5. User terminal: The received question is displayed, and the user answers, "This is my daily report work."

[0809] 6. User terminal: Send the input text to the AI ​​server again.

[0810] 7. AI server: Reanalyzes the data and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0811] 8. AI server: Sends the question back to the user device.

[0812] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0813] 10. User terminal: Send the input text to the AI ​​server again.

[0814] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0815] 12. AI server: Sends the proposal to the user's device and presents it to the user.

[0816] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0817] Prompt Sentence Examples

[0818] Worker: I've been feeling unmotivated at work lately.

[0819] System: What parts of the job do you find particularly taxing?

[0820] Workers: There is a lot of monotonous work and it is hard.

[0821] System: Break up your tasks and take short breaks.

[0822] In this way, the system of the present invention identifies factors that decrease a user's motivation in real time and realizes a series of processes to provide solutions to those problems, allowing the user to gain a deeper understanding of their own problems and take concrete measures to improve them.

[0823] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0824] Step 1:

[0825] The user enters information about their motivation decline on their device and presses the send button. The entered information is sent in text format from the user device to the AI ​​server. The user device is a wearable device such as smart glasses.

[0826] Step 2:

[0827] The AI ​​server receives text information sent from the user's device. The received text information is analyzed using natural language analysis technology. Specifically, keywords and emotional features are extracted using TextBlob and Transformers. The input is text information related to the user's decreased motivation, and the output is the extracted keywords and emotional features.

[0828] Step 3:

[0829] The AI ​​server identifies factors that decrease motivation based on the extracted keywords and emotional characteristics. Specifically, it compares the extracted data with past data, which is stored in a database server. The input is keywords and emotional characteristics, and the output is the identified factors that decrease motivation.

[0830] Step 4:

[0831] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures. For example, if the identified factor is "work overload," it generates the question "Which tasks do you find particularly burdensome?" The input is the demotivation factors, and the output is the generated questions and advice.

[0832] Step 5:

[0833] The generated questions and advice are sent back from the AI ​​server to the user's device. The user's device displays these questions and advice to the user. The user then inputs an answer to the question. The input is the generated question or advice, and the output is the user's additional answer.

[0834] Step 6:

[0835] The user enters an additional answer and sends it again to the AI ​​server. The AI ​​server receives this additional information and performs text analysis again. The input is the additional answer from the user, and the output is the analyzed additional information.

[0836] Step 7:

[0837] Based on the reanalyzed information, the AI ​​server will dig deeper into further factors that lower motivation and generate further questions or advice as necessary. For example, if the user answers, "It's the daily report work," the next question generated will be, "Which part of that report work is particularly stressful for you?" The input is the reanalyzed additional information, and the output is further questions or advice.

[0838] Step 8:

[0839] The AI ​​server sends the final action plan to the user's device. The user's device displays this action plan to the user. For example, it may recommend "dividing tasks and taking short breaks." The input is the final action plan, and the output is the action plan displayed to the user.

[0840] Step 9:

[0841] The AI ​​server saves the final dialogue history and action plan in the database server. This is expected to improve the accuracy of identifying future declines in motivation and developing improvement measures. The input is the final dialogue history and action plan, and the output is the information saved in the database.

[0842] 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.

[0843] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and its accuracy is particularly enhanced by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine. Each component and its processing are described in detail below in natural language.

[0844] User terminal

[0845] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[0846] AI Server

[0847] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[0848] 1. Text analysis and emotion recognition:

[0849] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[0850] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[0851] 2. Identifying the factors that cause low motivation:

[0852] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[0853] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[0854] 3. Generate follow-up questions and advice:

[0855] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[0856] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[0857] 4. Dialogue Response:

[0858] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[0859] Emotion Engine

[0860] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[0861] Database Server

[0862] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0863] Specific examples

[0864] Here is an example of a specific dialogue:

[0865] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0866] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[0867] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0868] 4. AI server: Sends the generated questions back to the user device.

[0869] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0870] 6. User terminal: Send the input text to the AI ​​server again.

[0871] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[0872] 8. AI server: Sends the question back to the user device.

[0873] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0874] 10. User terminal: Send the input text to the AI ​​server again.

[0875] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0876] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0877] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0878] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to address them. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them. By combining it with an emotion engine, highly accurate identification and solutions can be achieved, taking into account the user's emotional state.

[0879] The processing flow will be explained below.

[0880] Step 1:

[0881] The user enters their motivation-related worries or problems into a text input field on the device and presses the send button. For example, they might enter, "I haven't been feeling motivated at work lately."

[0882] Step 2:

[0883] The device acquires the entered text data and sends it to the AI ​​server using an HTTP request along with the user ID and session information.

[0884] Step 3:

[0885] The AI ​​server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[0886] Step 4:

[0887] The emotion engine recognizes emotions from text. For example, it recognizes "negative emotions" from the phrase "I'm not motivated."

[0888] Step 5:

[0889] Based on the output of the NLP module and emotion engine, the AI ​​server uses an internal database and known patterns to identify factors that decrease motivation, such as "work overload" and "monotonous work."

[0890] Step 6:

[0891] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user, such as, "What tasks have you found particularly burdensome recently?"

[0892] Step 7:

[0893] The AI ​​server returns the generated question to the user's terminal and displays it to the user.

[0894] Step 8:

[0895] The user inputs a specific answer to the question displayed on the terminal and presses the send button again. For example, the user might answer, "I'm working on a daily report."

[0896] Step 9:

[0897] The device again sends the user's answer to the AI ​​server, which again analyzes this new information with the NLP module and again recognizes emotions using the emotion engine.

[0898] Step 10:

[0899] Based on the results of the reanalysis, the AI ​​server generates more specific questions and advice, such as, "Which part of the report work is particularly stressful for you?"

[0900] Step 11:

[0901] The AI ​​server then sends the generated questions to the user's device, and the user enters the answers again. By repeating this process several times, the factors that decrease the user's motivation can be identified in detail.

[0902] Step 12:

[0903] Finally, the AI ​​server generates a specific action plan based on the factors that cause the decrease in motivation, such as recommending "dividing tasks and taking short breaks."

[0904] Step 13:

[0905] The AI ​​server sends the generated action plan to the user's device and displays it to the user. The action plan includes specific instructions and advice that are easy for the user to follow.

[0906] Step 14:

[0907] The AI ​​server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[0908] In this way, the user terminal, AI server, emotion engine, and database server work together to consistently identify factors that lower the user's motivation and provide specific measures for improvement.

[0909] Example 2

[0910] 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."

[0911] In modern society, many people suffer from a lack of motivation in their work or studies. It is particularly difficult to identify the individual causes of motivation loss and provide appropriate solutions, creating a demand for effective support systems. However, existing systems are unable to fully consider the user's emotions and specific circumstances, resulting in poor accuracy and effectiveness of the solutions they provide. Therefore, the present invention aims to recognize the user's emotions, more accurately identify the causes of motivation loss, and provide appropriate solutions.

[0912] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0913] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for recognizing the user's emotion using emotion recognition means, means for identifying factors that decrease motivation based on the analysis results and the recognized emotion, means for generating additional questions and advice based on the identified factors, and means for returning the generated questions and advice to the user. This makes it possible to accurately identify factors that decrease motivation according to individual circumstances, taking into account the user's emotional state, and to provide countermeasures against them.

[0914] The "means for accepting user input" refers to an interface and function that allows a user to input information about their own decline in motivation and transmit it to the system.

[0915] "Natural language processing means for analyzing said user input" refers to techniques and processes that analyze text data submitted by a user and extract important keywords and phrases.

[0916] "Emotion Recognition Method" refers to the technology and process for recognizing and determining emotions from user input text, using emotion engines and AI algorithms.

[0917] "Means for identifying factors that decrease motivation based on the analysis results and recognized emotions" refers to technology and functions that identify factors that decrease a user's motivation based on extracted keywords and recognized emotions.

[0918] "Means for generating additional questions and advice based on identified factors" refers to technology and functionality for generating questions and advice to gather further information and provide improvement measures in response to factors that reduce motivation.

[0919] The "means for returning the generated question or advice to the user" refers to the technology and functionality for transmitting and displaying the generated question or advice to the user.

[0920] "Means for reanalysis" refers to the technology and process of reanalyzing additional information and response data from users and extracting new keywords and emotions based on the newly obtained information.

[0921] The "means for generating a specific action plan" refers to a technology and function for creating a feasible plan or instructions for improving the user's motivation based on the reanalysis results.

[0922] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and in particular, improves accuracy by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine.

[0923] User terminal

[0924] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[0925] AI Server

[0926] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[0927] 1. Text analysis and emotion recognition:

[0928] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[0929] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[0930] 2. Identifying the factors that cause low motivation:

[0931] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[0932] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[0933] 3. Generate follow-up questions and advice:

[0934] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[0935] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[0936] 4. Dialogue Response:

[0937] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[0938] Emotion Engine

[0939] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[0940] Database Server

[0941] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[0942] Specific examples

[0943] Here is an example of a specific dialogue:

[0944] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[0945] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[0946] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[0947] 4. AI server: Sends the generated questions back to the user device.

[0948] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[0949] 6. User terminal: Send the input text to the AI ​​server again.

[0950] 7. AI server: Analyzes again and infers that the cause is "monotonous work," generating a question such as, "Which part of the report work do you find particularly stressful?"

[0951] 8. AI server: Sends the question back to the user device.

[0952] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[0953] 10. User terminal: Send the input text to the AI ​​server again.

[0954] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[0955] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[0956] 13. AI Server: Save the final dialogue history and action plan in the database server.

[0957] In general, the system of the present invention takes into account the user's emotional state, and is able to accurately identify factors that decrease motivation according to individual circumstances and provide countermeasures. Examples of prompts include "If you have been feeling unmotivated by your recent work, please tell us in detail why" and "Please feel free to write about your current feelings and the stress you are experiencing."

[0958] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] User Input Processing

[0961] The user uses the user terminal to input information about his / her own decreased motivation in text format and presses the send button.

[0962] Input: The user types "I've been feeling unmotivated at work lately" into the text box.

[0963] Output: The entered text data will be ready on the terminal after the send button is pressed.

[0964] Specific action: The user enters text using a keyboard or touch panel and clicks the send button.

[0965] Step 2:

[0966] Sending input data

[0967] The user terminal sends the input data to the AI ​​server.

[0968] Input: Text data entered by the user.

[0969] Output: Text data is sent to the AI ​​server via API.

[0970] Specific operation: When the user presses the send button, the device's communication module sends the data to the server.

[0971] Step 3:

[0972] Text Analysis and Emotion Recognition

[0973] The server analyzes the received data using natural language processing (NLP) technology to extract important keywords and phrases, while also using emotion recognition tools to recognize emotions.

[0974] Input: Sent text data: "I haven't been motivated to work lately."

[0975] Output: Keywords "work" and "unmotivated" and emotion "negative".

[0976] How it works: The NLP module on the server analyzes the text data and extracts keywords, while the emotion engine simultaneously identifies emotions.

[0977] Step 4:

[0978] Identifying factors that decrease motivation

[0979] The server identifies factors that decrease motivation based on the extracted keywords and recognized emotions.

[0980] Input: Keywords "work" and "unmotivated" and emotion "negative".

[0981] Output: "Work overload" and "monotonous work" are identified as factors that decrease motivation.

[0982] Specific operation: Based on the keywords and emotion data, the server compares it with an internal database and identifies the cause by referring to past data and cases.

[0983] Step 5:

[0984] Generate follow-up questions and advice

[0985] The server generates additional questions and advice based on the identified factors.

[0986] Input: Motivational factor "Work overload."

[0987] Output: Produces the question "What tasks have you found particularly taxing recently?"

[0988] Specific behavior: The server uses its internal logic and dialogue model to generate appropriate questions and advice based on the factors.

[0989] Step 6:

[0990] Submit a question or suggestion

[0991] The generated questions and advice are sent back to the user terminal.

[0992] Input: Generated additional questions or advice.

[0993] Output: Questions and advice displayed on the user's terminal.

[0994] Specific operation: The data generated by the server is sent to the user's terminal via API and presented to the user via a display interface.

[0995] Step 7:

[0996] User response processing

[0997] The user inputs and transmits an answer to the question displayed on the user terminal.

[0998] Input: The user enters "Daily report work" into the input field and presses the submit button.

[0999] Output: User response data is ready.

[1000] Specific behavior: The user again enters information using the keyboard or touch panel and clicks the send button.

[1001] Step 8:

[1002] Sending response data

[1003] The user terminal transmits the user's response data to the AI ​​server.

[1004] Input: User's answer data: "Daily reporting."

[1005] Output: The response data sent to the server.

[1006] Specific operation: The terminal's communication module sends the user's response data to the AI ​​server.

[1007] Step 9:

[1008] Reanalysis and countermeasure generation

[1009] The server analyzes the input data again, extracts new keywords and phrases, and generates the next questions and solutions.

[1010] Input: User's answer data: "Daily reporting."

[1011] Output: Keywords "report work" and "monotonous" and the following question: "Which part of the report work do you find particularly stressful?"

[1012] Specific operation: The server re-analyzes, extracts new keywords, and generates the next question.

[1013] Step 10:

[1014] Submit an action plan

[1015] The server generates a final action plan and proposes it to the user.

[1016] Input: Reanalysis result: "Monotonous work is a stressor."

[1017] Output: Action plan: "Divide tasks and take short breaks"

[1018] Specific operation: The server generates an action plan and sends it to the user's device via API.

[1019] Step 11:

[1020] Data storage

[1021] The server stores the dialogue history and the final action plan in a database server.

[1022] Input: Interaction history and action plan data.

[1023] Output: History and plans stored in a database.

[1024] Specific operation: The server connects to the database and saves the analysis results and countermeasure data.

[1025] Through the above processing steps, the system can identify factors that reduce a user's motivation and provide highly accurate countermeasures that take into account the user's emotional state.

[1026] (Application example 2)

[1027] 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."

[1028] In modern industrial environments, monotonous tasks and long working hours can lead to a decline in worker motivation. This can lead to a decline in work efficiency and quality, ultimately affecting productivity. There is a need for a system that can solve this problem and maintain and improve worker motivation.

[1029] 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.

[1030] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for being installed in the industrial machine, and means for analyzing the emotions of workers and managing their motivation. This makes it possible to quickly and accurately identify factors that decrease motivation in workers and provide appropriate advice and improvements.

[1031] The "means for accepting user input" refers to a device or interface that allows a user to input information in text format and that allows the system to receive that information.

[1032] "Means for analyzing user input" refers to a device or software that analyzes input text information using natural language processing techniques and extracts keywords and phrases.

[1033] The "means for identifying factors that decrease motivation" is a device or algorithm for identifying factors that decrease a user's motivation based on analyzed keywords and emotional data.

[1034] The "means for generating additional questions and advice" is a device or program for automatically generating additional questions and advice for the user in response to the identified demotivation factors.

[1035] The "means for returning questions and advice to the user" refers to a device or interface for transmitting the generated questions and advice to the user terminal and displaying them to the user.

[1036] "Means installed on industrial machines" refers to devices or software for incorporating and using the motivation management system on factory machines.

[1037] "Means for analyzing worker emotions" refers to a device or algorithm for analyzing text or voice data to recognize the worker's emotional state.

[1038] "Means for managing motivation" refers to a device or program that provides appropriate measures based on the worker's emotional data and factors that decrease motivation, thereby maintaining and improving their motivation to work.

[1039] This invention is a system for identifying factors that decrease the motivation of factory workers and providing countermeasures. This system consists of a user terminal, an AI server, a database server, and an emotion recognition engine. Each component and its processing are described in detail below.

[1040] User terminal

[1041] The user terminal functions as an interface for the worker to interact with the system. The user enters information about their emotional state and motivation in text format and presses the send button. The system is designed so that users can enter either a single sentence or multiple sentences. Smartphones, head-mounted displays, etc. are used as user terminals.

[1042] AI Server

[1043] The AI ​​server processes input information sent from the user terminal. The AI ​​server has the following main functions:

[1044] 1. Text analysis and emotion recognition:

[1045] The AI ​​server uses natural language processing (NLP) techniques to analyze user input and extract key keywords and phrases, and an emotion recognition engine to analyze emotional states.

[1046] The software used includes Python, NLTK (Natural Language Toolkit), SentimentIntensityAnalyzer, etc.

[1047] 2. Identifying the factors that cause low motivation:

[1048] Based on the results of text analysis and the user's emotional state, factors that decrease the user's motivation are identified, such as "monotonous work" and "long working hours."

[1049] 3. Generate follow-up questions and advice:

[1050] Based on the identified factors, the AI ​​server generates additional questions and advice for the user, and specific countermeasures are proposed and sent to the user.

[1051] Emotion Recognition Engine

[1052] The emotion recognition engine is a dedicated module for extracting emotions from user input text. It has the ability to distinguish between positive, negative, and neutral emotions, and is used in the analysis process of the AI ​​server.

[1053] Database Server

[1054] The results of the analysis performed by the AI ​​server and the history of user interactions are stored on a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of responses to new users based on past data. Examples of database management systems used include MySQL.

[1055] Specific examples

[1056] Here is an example of a specific dialogue:

[1057] 1. User terminal: The worker types in, "Recently, I've been doing monotonous work and I'm not motivated," and presses the send button.

[1058] 2. AI server: Analyzes the text and extracts keywords such as "monotonous work" and "unmotivated." An emotion recognition engine recognizes "negative" emotions.

[1059] 3. AI server: Based on the analysis results, it identifies that "monotonous work is the cause" and generates the next question: "Which part of the work is particularly burdensome?"

[1060] 4. AI server: Returns the generated questions to the user device.

[1061] 5. User terminal: The question is received and the worker enters "There is a lot of repetitive work."

[1062] 6. User terminal: Re-send the input text to the AI ​​server.

[1063] 7. AI server: Reanalyzes and infers that "diversification of work is necessary" and suggests "try combining other tasks."

[1064] 8. AI server: Sends suggestions to the user's device and displays them to the worker.

[1065] Prompt Sentence Examples

[1066] "Recently, I've been doing monotonous tasks that have been unmotivating me. For example, I have to assemble the same parts all day. Do you have any suggestions for solving this problem?"

[1067] As described above, by using this system, it is possible to quickly and accurately identify the factors that decrease worker motivation and provide appropriate countermeasures. Specific feedback and countermeasures are expected to improve the work environment and increase efficiency.

[1068] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1069] Step 1:

[1070] The user provides input

[1071] The user uses a smartphone or head-mounted display to input information about their emotional state and motivation in text format and presses the send button. This input becomes the data to be analyzed in the next step.

[1072] Input: User's text information (e.g., "Recently, I've been doing monotonous work and I'm not feeling motivated.")

[1073] Output: The text data sent

[1074] Step 2:

[1075] Sending data from the user device to the AI ​​server

[1076] The user terminal sends the input text data to the AI ​​server, which uses this data in the next analysis step.

[1077] Input: Text data entered into the user's terminal

[1078] Output: Text data sent to the AI ​​server

[1079] Step 3:

[1080] Text Analysis and Emotion Recognition

[1081] The AI ​​server analyzes the received text data using natural language processing (NLP) technology to extract important keywords and phrases. At the same time, it analyzes the emotional state using an emotion recognition engine. The software used is Python, NLTK, and SentimentIntensityAnalyzer.

[1082] Input: Text data sent to the AI ​​server

[1083] Output: Analyzed keywords, emotional state (e.g., "monotonous work," "unmotivated," emotion recognition result: negative)

[1084] Specific behavior:

[1085] 1. Tokenize the text data and extract important keywords and phrases.

[1086] 2. Analyze emotional states using SentimentIntensityAnalyzer.

[1087] 3. Obtain a positive, negative, or neutral score.

[1088] Step 4:

[1089] Identifying factors that decrease motivation

[1090] The AI ​​server identifies factors that decrease the user's motivation based on the results of text analysis and emotion recognition, such as "monotonous work" and "long working hours."

[1091] Input: Parsed keywords, emotional state

[1092] Output: Identified demotivators (e.g., "monotonous work")

[1093] Specific behavior:

[1094] 1. Analyzed keywords and sentiment data are compared with known factors in the database.

[1095] 2. Identify the most consistent demotivator.

[1096] Step 5:

[1097] Generate additional questions and advice

[1098] Based on the identified demotivation factors, the AI ​​server generates additional questions and advice for the user, such as "Which part of the work is particularly burdensome?", and suggests specific measures.

[1099] Input: Identified demotivators

[1100] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[1101] Specific behavior:

[1102] 1. Retrieve relevant questions and measures from the database.

[1103] 2. Generate questions and advice tailored to the user.

[1104] Step 6:

[1105] Sending additional questions or advice to the user's device

[1106] The generated questions and advice are sent to the user's terminal and displayed to the user, and this information serves as feedback to the user.

[1107] Input: Generated questions and advice

[1108] Output: Questions and advice sent to the user's terminal

[1109] Specific behavior:

[1110] 1. Convert the generated content into a format that can be easily viewed by the user.

[1111] 2. Send to the user's terminal and display.

[1112] Step 7:

[1113] Accepting additional information from the user

[1114] The user can then enter additional information in response to the submitted question or advice and submit it again, a process that yields more detailed information.

[1115] Input: Additional information about the user (e.g., "Daily report work")

[1116] Output: Data sent to the AI ​​server as additional information

[1117] Specific behavior:

[1118] 1. The user enters answers to questions and additional information and submits.

[1119] 2. Transfer additional information to the AI ​​server.

[1120] Step 8:

[1121] Reanalysis and updated measures

[1122] The AI ​​server receives the additional information and analyzes it again, proposing specific measures to improve the user's motivation as a final action plan.

[1123] Input: Additional information from the user

[1124] Output: An updated action plan (e.g., "Break up tasks and take short breaks")

[1125] Specific behavior:

[1126] 1. Reanalyze additional information to identify new factors and details.

[1127] 2. Generate and propose a specific action plan.

[1128] Step 9:

[1129] Sending the final action plan to the user's device

[1130] The generated action plan is sent to the user's terminal and displayed to the user, allowing the user to know specific improvement measures.

[1131] Input: Updated Action Plan

[1132] Output: Action plan sent to user device

[1133] Specific behavior:

[1134] 1. Convert the generated action plan into a format that is easy for users to execute.

[1135] 2. Send to the user's terminal and display.

[1136] Step 10:

[1137] Save conversation history and action plans

[1138] The AI ​​server stores all interaction history and generated action plans in a database server, allowing for future improvements and user progress tracking.

[1139] Input: Dialogue history, generated action plan

[1140] Output: Data stored on the database server

[1141] Specific behavior:

[1142] 1. Dialogue history and generated action plans are saved in a database.

[1143] 2. Retaining data for subsequent analysis and improvement.

[1144] 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.

[1145] 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.

[1146] 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.

[1147] [Third embodiment]

[1148] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1149] 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.

[1150] 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).

[1151] 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.

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] 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."

[1160] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. Each component and its processing are described in detail below in natural language.

[1161] User terminal

[1162] The user terminal functions as an interface for the user to interact with the system. The user inputs information about their motivation decline in text format and presses the send button. This input information can be multiple sentences at once.

[1163] AI Server

[1164] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[1165] 1. Text Analysis:

[1166] The AI ​​server analyzes user input using natural language processing (NLP) technology, which extracts important keywords and emotional characteristics from the input sentence.

[1167] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted.

[1168] 2. Identifying the factors that cause low motivation:

[1169] Based on the extracted keywords and emotional characteristics, the AI ​​server identifies the factors that are causing the user's motivation to decline. In this process, it compares past data and known patterns to infer the most likely factors.

[1170] For example, the keywords "work" and "lack of motivation" may lead to the identification of "overload of work" and "monotonous tasks" as contributing factors.

[1171] 3. Generate follow-up questions and advice:

[1172] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[1173] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[1174] 4. Dialogue Response:

[1175] The generated questions and advice are sent back to the user's terminal, making it easier for the user to input specific answers.

[1176] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[1177] Database Server

[1178] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1179] Specific examples

[1180] Here is an example of a specific dialogue:

[1181] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1182] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[1183] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1184] 4. AI server: Sends the generated questions back to the user device.

[1185] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1186] 6. User terminal: Send the input text to the AI ​​server again.

[1187] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1188] 8. AI server: Sends the question back to the user device.

[1189] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1190] 10. User terminal: Send the input text to the AI ​​server again.

[1191] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1192] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1193] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1194] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to those problems. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them.

[1195] The processing flow will be explained below.

[1196] Step 1:

[1197] The user enters their concerns or problems related to their motivation into the text input field on the device and presses the send button.

[1198] Step 2:

[1199] The terminal acquires the input text data and sends it to the server together with the user ID and session information using an HTTP request.

[1200] Step 3:

[1201] The server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[1202] Step 4:

[1203] The server identifies factors that decrease motivation based on keywords and emotional characteristics output by the NLP module, using an internal database and known patterns. For example, from the keywords "work" and "unmotivated," "work overload" and "monotonous work" become candidates.

[1204] Step 5:

[1205] The server generates additional questions to obtain further information from the user based on the identified demotivation factors. For example, a question might be generated such as, "What tasks have you found particularly burdensome recently?"

[1206] Step 6:

[1207] The server returns the generated question to the user's terminal, where it is displayed in a format that allows the user to easily answer it.

[1208] Step 7:

[1209] The user enters specific answers to the questions displayed on the terminal, presses the send button again, and the process is repeated.

[1210] Step 8:

[1211] The device again sends the user's answers to the server, which analyzes this new information and again identifies the factors that lower motivation.

[1212] Step 9:

[1213] The server generates more specific questions and advice based on the results of the reanalysis. By repeating this process several times, the factors that decrease motivation can be identified in detail.

[1214] Step 10:

[1215] The server then generates a specific action plan based on the motivation-reducing factors, such as recommending "dividing tasks and taking short breaks."

[1216] Step 11:

[1217] The server sends the generated action plan to the user's terminal and displays it to the user. The action plan includes specific instructions and advice that the user can immediately implement.

[1218] Step 12:

[1219] The server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[1220] In this way, the user terminal, AI server, and database server work together to consistently identify factors that lower a user's motivation and provide specific measures for improvement.

[1221] Example 1

[1222] 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."

[1223] In modern society, many people suffer from a lack of motivation in their work and personal lives. However, the individual factors that cause this lack of motivation are diverse, making it difficult to find appropriate solutions. Furthermore, conventional systems often struggle to provide individualized solutions for each user, and can only provide general solutions. Therefore, there is a need for a system that can effectively identify the specific factors that cause a user to lose motivation and provide specific improvement measures tailored to each individual situation.

[1224] 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.

[1225] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for using a generative AI model for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for saving the analysis results and a dialogue history with the user in a database, and means for improving the quality of interaction with new users based on past data. This makes it possible to effectively identify specific factors that decrease a user's motivation and provide specific improvement measures tailored to individual situations.

[1226] The "means for accepting user input" refers to a means by which a user inputs information about a decrease in motivation to the system and transmits it to the system. Specifically, it includes interfaces such as a keyboard, a touch screen, and voice input.

[1227] "Natural language processing means" refers to means for analyzing text data entered by users and extracting important keywords and emotional characteristics. Specifically, it includes natural language processing libraries and algorithms.

[1228] A "generative AI model" is an artificial intelligence model that identifies factors that decrease motivation based on input data and analysis results, referring to specific patterns and past data. Specific examples include BERT and GPT.

[1229] The "means for generating additional questions and advice" is a means for generating questions to obtain further information from the user or initial measures for improvement based on the identified demotivation factors.

[1230] "Means for returning generated questions and advice to the user" refers to the means for sending questions and advice generated by the AI ​​server back to the user's terminal, and uses HTTPS or similar as a communication protocol.

[1231] "Means for saving analysis results and user interaction history in a database" refers to means for saving the analysis results performed by the AI ​​server and the content of user interaction in a database so that they can be referenced later. This includes database management systems and storage devices.

[1232] "Means for improving the quality of responses to new users based on past data" refers to a means for referring to saved past dialogue history and analysis results and using them to more effectively respond to new users. This makes it possible to more accurately identify factors that decrease motivation and provide improvement measures.

[1233] MODE FOR CARRYING OUT THE INVENTION

[1234] System Configuration

[1235] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. The detailed functions and processing flow of each component are explained below.

[1236] User terminal

[1237] The user terminal functions as an interface for the user to interact with the system. Using a dedicated application or a web interface, the user inputs information about their own lack of motivation in text format and presses the send button. This input information can include multiple sentences. For example, the user can input "I've been feeling unmotivated at work lately" and send it.

[1238] AI Server

[1239] Based on the information sent from the user device, the AI ​​server performs the following main processes:

[1240] 1. Text Analysis:

[1241] The AI ​​server analyzes the user's input using natural language processing (NLP) techniques, such as Python's NLTK or SpaCy libraries. This allows it to extract important keywords and emotional characteristics from the input sentence. For example, keywords such as "work" and "unmotivated" are extracted.

[1242] 2. Identifying the factors that cause low motivation:

[1243] Based on the extracted keywords and emotional characteristics, the AI ​​server uses generative AI models such as BERT and GPT to identify the factors behind the user's lack of motivation. During this process, it compares past data and known patterns to infer likely causes. For example, based on the keywords "work" and "lack of motivation," it can identify that "work overload" is the cause.

[1244] 3. Generate follow-up questions and advice:

[1245] Based on the identified demotivators, the AI ​​server generates follow-up questions to obtain further information from the user and initial improvement measures, such as, "Which tasks do you find particularly stressful?"

[1246] 4. Dialogue Response:

[1247] The generated questions and advice are sent back to the user's device using the HTTPS protocol to ensure security.

[1248] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[1249] Database Server

[1250] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1251] Specific examples

[1252] Here is an example of a specific dialogue:

[1253] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1254] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[1255] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1256] 4. AI server: Sends the generated questions back to the user device.

[1257] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1258] 6. User terminal: Send the input text to the AI ​​server again.

[1259] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1260] 8. AI server: Sends the question back to the user device.

[1261] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1262] 10. User terminal: Send the response text to the AI ​​server again.

[1263] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1264] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1265] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1266] In this way, by using the system of the present invention, the user can gain a deeper understanding of his or her own problems and take concrete measures to improve them.

[1267] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1268] Step 1:

[1269] The user uses a dedicated application or web interface to enter text information about the decline in motivation and presses the send button.

[1270] Input: Text information from the user (e.g., "I've been feeling unmotivated at work lately.")

[1271] Output: The entered text information is sent from the user's device.

[1272] Step 2:

[1273] The user's device sends the input text information to the AI ​​server. The HTTPS protocol is used for communication to ensure data security.

[1274] Input: Text information entered by the user

[1275] Output: Text information arrives at the AI ​​server

[1276] Step 3:

[1277] The server analyzes the received text information using natural language processing (NLP) techniques, specifically using Python's NLTK and SpaCy libraries, to extract important keywords and sentiment features.

[1278] Input: Text information received by the server

[1279] Data processing / data calculation: Analyze text using NLP technology to extract keywords and sentiment features

[1280] Output: Extracted keywords and sentiment features (e.g., "work" and "unmotivated")

[1281] Step 4:

[1282] The server uses a generative AI model (such as BERT or GPT) to identify factors that cause demotivation based on the extracted keywords and emotional characteristics. The AI ​​model refers to past data and known patterns to infer likely factors.

[1283] Input: Extracted keywords and sentiment features

[1284] Data processing / data calculation: Identifying factors that decrease motivation using generative AI models

[1285] Output: Identified demotivators (e.g., "work overload")

[1286] Step 5:

[1287] The server generates additional questions to obtain further information from the user and initial remedial measures based on the identified demotivation factors.

[1288] Input: Identified demotivators

[1289] Data manipulation / data calculation: Generate additional questions and advice

[1290] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[1291] Step 6:

[1292] The server sends the generated questions and advice to the user's terminal, also using the HTTPS protocol.

[1293] Input: Generated questions and advice

[1294] Output: Questions and advice are sent to the user's device.

[1295] Step 7:

[1296] The user terminal displays the received question or advice, and the user inputs an answer. For example, the user inputs "Daily report work."

[1297] Input: Questions and advice sent by the server

[1298] Output: User's answer (e.g., "Daily report work")

[1299] Step 8:

[1300] The user's terminal sends the user's answer back to the AI ​​server.

[1301] Input: User's answer

[1302] Output: The answer arrives at the AI ​​server

[1303] Step 9:

[1304] The server then analyzes the newly received text data again. For example, it infers that the cause is "monotonous work" and generates a question such as, "Which part of the report work is particularly stressful for you?"

[1305] Input: User's answer submitted again

[1306] Data processing / data calculation: Reanalyze using NLP technology to generate the next question

[1307] Output: Generated follow-up questions (e.g., "What aspects of the report task are particularly stressful for you?")

[1308] Step 10:

[1309] The server transmits the generated follow-up question to the user terminal.

[1310] Input: Generated follow-up question

[1311] Output: The question arrives at the user's terminal.

[1312] Step 11:

[1313] The user terminal displays the question, and the user again inputs the answer. For example, the user inputs "It's monotonous and there is a lot of repetitive work."

[1314] Input: Additional question sent by the server

[1315] Output: User response (e.g., "It's repetitive and monotonous.")

[1316] Step 12:

[1317] The user's terminal sends the user's answer back to the AI ​​server.

[1318] Input: User's answer

[1319] Output: The answer arrives at the AI ​​server

[1320] Step 13:

[1321] The server generates a final action plan, for example recommending "break up tasks and take short breaks."

[1322] Input: User's answer submitted again

[1323] Data processing / data calculation: Generate a final action plan using a generative AI model

[1324] Output: Final action plan (e.g., "Break down tasks and take short breaks")

[1325] Step 14:

[1326] The server sends the proposed final action plan to the user terminal, which displays it.

[1327] Input: Final Action Plan

[1328] Output: The final action plan is displayed on the user's device.

[1329] Step 15:

[1330] The server stores the final dialogue history and action plan in the database server, which enables future responses based on the dialogue history.

[1331] Input: Final interaction history and action plan

[1332] Output: Dialogue history and action plans are saved in a database

[1333] (Application example 1)

[1334] 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."

[1335] Conventional motivation management systems typically identify factors that decrease motivation based on user input and then provide questions and advice. However, these systems do not necessarily adapt to the user's behavior or situation, and real-time dialogue and data updates are difficult, especially when used by field workers. As a result, the user experience is poor and motivation improvement effects are not fully achieved.

[1336] 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.

[1337] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating follow-up questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for accepting user input using a wearable device worn on the user's body, means for analyzing input from the wearable device using natural language analysis technology, means for generating follow-up questions and advice in a form that is displayed on the wearable device, means for referencing past data to identify factors that decrease the user's motivation, and a database for storing dialogue history. This enables users to engage in real-time dialogue, identify their own factors that decrease motivation, and quickly receive a specific and effective action plan for addressing those factors.

[1338] The "means for accepting user input" refers to a device that includes an interface or device that allows a user to provide input to the system.

[1339] The "means for analyzing the user input" refers to software and algorithms for analyzing input information received from a user and understanding its content.

[1340] The "means for identifying factors causing a decrease in motivation" is a system that has the function of extracting and identifying the causes of a decrease in motivation from the analyzed user input.

[1341] The "means for generating additional questions and advice" is a function that automatically generates questions to obtain further information from the user and advice on measures to be taken based on the identified motivation-reducing factors.

[1342] The "means for returning the generated question or advice to the user" is a system including a communication means and a display device for presenting the generated question or advice to the user.

[1343] A "wearable device" is a device that can be worn on the user's body and has functions such as input reception and information display.

[1344] "Natural language analysis technology" is a technology that analyzes input information such as text and voice and understands human language.

[1345] "Means for referencing past data" refers to a function that allows the system to refer to data collected in the past and improve the accuracy of analysis and identification.

[1346] The "database for storing dialogue history" refers to a database for storing the contents of dialogue with users and analysis results, and a system for managing such database.

[1347] The system of this invention is composed of a user terminal, an AI server, and a database server to identify factors that decrease a user's motivation and provide appropriate measures.

[1348] User terminal

[1349] The user terminal functions as an interface for the user to interact with the system. Specifically, the user wears a wearable device such as smart glasses and provides information to the system through voice or text input. The user inputs information about their own decline in motivation and presses a button to send it. This input information is then sent to the AI ​​server.

[1350] AI Server

[1351] The AI ​​server receives input information sent from the user device and performs the following main functions:

[1352] 1. Text Analysis:

[1353] The server analyzes the user's input using natural language processing technology, using software such as TextBlob and Transformers, to extract important keywords and emotional features and understand the user's state.

[1354] 2. Identifying the factors that cause low motivation:

[1355] Based on the extracted keywords and emotional characteristics, past data is referenced to identify factors that have reduced the user's motivation. Past data is stored on a database server, and the AI ​​server searches and compares this data to identify factors.

[1356] 3. Generate follow-up questions and advice:

[1357] Based on the identified demotivators, we generate follow-up questions to obtain more information from the user and initial improvement measures, such as "Which tasks do you find particularly burdensome?"

[1358] 4. Dialogue Response:

[1359] The generated questions and advice are sent back to the user's device, where the user can respond, and the information is then analyzed again by the AI ​​server.

[1360] Database Server

[1361] The AI ​​server's analysis results and user interaction history are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1362] Specific examples

[1363] Here is an example of a specific dialogue:

[1364] 1. User device: The user types "I haven't been motivated to work lately" through the smart glasses and presses the send button.

[1365] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[1366] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1367] 4. AI server: Sends the generated questions back to the user device.

[1368] 5. User terminal: The received question is displayed, and the user answers, "This is my daily report work."

[1369] 6. User terminal: Send the input text to the AI ​​server again.

[1370] 7. AI server: Reanalyzes the data and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1371] 8. AI server: Sends the question back to the user device.

[1372] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1373] 10. User terminal: Send the input text to the AI ​​server again.

[1374] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1375] 12. AI server: Sends the proposal to the user's device and presents it to the user.

[1376] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1377] Prompt Sentence Examples

[1378] Worker: I've been feeling unmotivated at work lately.

[1379] System: What parts of the job do you find particularly taxing?

[1380] Workers: There is a lot of monotonous work and it is hard.

[1381] System: Break up your tasks and take short breaks.

[1382] In this way, the system of the present invention identifies factors that decrease a user's motivation in real time and realizes a series of processes to provide solutions to those problems, allowing the user to gain a deeper understanding of their own problems and take concrete measures to improve them.

[1383] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1384] Step 1:

[1385] The user enters information about their motivation decline on their device and presses the send button. The entered information is sent in text format from the user device to the AI ​​server. The user device is a wearable device such as smart glasses.

[1386] Step 2:

[1387] The AI ​​server receives text information sent from the user's device. The received text information is analyzed using natural language analysis technology. Specifically, keywords and emotional features are extracted using TextBlob and Transformers. The input is text information related to the user's decreased motivation, and the output is the extracted keywords and emotional features.

[1388] Step 3:

[1389] The AI ​​server identifies factors that decrease motivation based on the extracted keywords and emotional characteristics. Specifically, it compares the extracted data with past data, which is stored in a database server. The input is keywords and emotional characteristics, and the output is the identified factors that decrease motivation.

[1390] Step 4:

[1391] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures. For example, if the identified factor is "work overload," it generates the question "Which tasks do you find particularly burdensome?" The input is the demotivation factors, and the output is the generated questions and advice.

[1392] Step 5:

[1393] The generated questions and advice are sent back from the AI ​​server to the user's device. The user's device displays these questions and advice to the user. The user then inputs an answer to the question. The input is the generated question or advice, and the output is the user's additional answer.

[1394] Step 6:

[1395] The user enters an additional answer and sends it again to the AI ​​server. The AI ​​server receives this additional information and performs text analysis again. The input is the additional answer from the user, and the output is the analyzed additional information.

[1396] Step 7:

[1397] Based on the reanalyzed information, the AI ​​server will dig deeper into further factors that lower motivation and generate further questions or advice as necessary. For example, if the user answers, "It's the daily report work," the next question generated will be, "Which part of that report work is particularly stressful for you?" The input is the reanalyzed additional information, and the output is further questions or advice.

[1398] Step 8:

[1399] The AI ​​server sends the final action plan to the user's device. The user's device displays this action plan to the user. For example, it may recommend "dividing tasks and taking short breaks." The input is the final action plan, and the output is the action plan displayed to the user.

[1400] Step 9:

[1401] The AI ​​server saves the final dialogue history and action plan in the database server. This is expected to improve the accuracy of identifying future declines in motivation and developing improvement measures. The input is the final dialogue history and action plan, and the output is the information saved in the database.

[1402] 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.

[1403] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and its accuracy is particularly enhanced by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine. Each component and its processing are described in detail below in natural language.

[1404] User terminal

[1405] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[1406] AI Server

[1407] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[1408] 1. Text analysis and emotion recognition:

[1409] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[1410] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[1411] 2. Identifying the factors that cause low motivation:

[1412] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[1413] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[1414] 3. Generate follow-up questions and advice:

[1415] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[1416] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[1417] 4. Dialogue Response:

[1418] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[1419] Emotion Engine

[1420] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[1421] Database Server

[1422] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1423] Specific examples

[1424] Here is an example of a specific dialogue:

[1425] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1426] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[1427] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1428] 4. AI server: Sends the generated questions back to the user device.

[1429] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1430] 6. User terminal: Send the input text to the AI ​​server again.

[1431] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1432] 8. AI server: Sends the question back to the user device.

[1433] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1434] 10. User terminal: Send the input text to the AI ​​server again.

[1435] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1436] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1437] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1438] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to address them. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them. By combining it with an emotion engine, highly accurate identification and solutions can be achieved, taking into account the user's emotional state.

[1439] The processing flow will be explained below.

[1440] Step 1:

[1441] The user enters their motivation-related worries or problems into a text input field on the device and presses the send button. For example, they might enter, "I haven't been feeling motivated at work lately."

[1442] Step 2:

[1443] The device acquires the entered text data and sends it to the AI ​​server using an HTTP request along with the user ID and session information.

[1444] Step 3:

[1445] The AI ​​server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[1446] Step 4:

[1447] The emotion engine recognizes emotions from text. For example, it recognizes "negative emotions" from the phrase "I'm not motivated."

[1448] Step 5:

[1449] Based on the output of the NLP module and emotion engine, the AI ​​server uses an internal database and known patterns to identify factors that decrease motivation, such as "work overload" and "monotonous work."

[1450] Step 6:

[1451] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user, such as, "What tasks have you found particularly burdensome recently?"

[1452] Step 7:

[1453] The AI ​​server returns the generated question to the user's terminal and displays it to the user.

[1454] Step 8:

[1455] The user inputs a specific answer to the question displayed on the terminal and presses the send button again. For example, the user might answer, "I'm working on a daily report."

[1456] Step 9:

[1457] The device again sends the user's answer to the AI ​​server, which again analyzes this new information with the NLP module and again recognizes emotions using the emotion engine.

[1458] Step 10:

[1459] Based on the results of the reanalysis, the AI ​​server generates more specific questions and advice, such as, "Which part of the report work is particularly stressful for you?"

[1460] Step 11:

[1461] The AI ​​server then sends the generated questions to the user's device, and the user enters the answers again. By repeating this process several times, the factors that decrease the user's motivation can be identified in detail.

[1462] Step 12:

[1463] Finally, the AI ​​server generates a specific action plan based on the factors that cause the decrease in motivation, such as recommending "dividing tasks and taking short breaks."

[1464] Step 13:

[1465] The AI ​​server sends the generated action plan to the user's device and displays it to the user. The action plan includes specific instructions and advice that are easy for the user to follow.

[1466] Step 14:

[1467] The AI ​​server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[1468] In this way, the user terminal, AI server, emotion engine, and database server work together to consistently identify factors that lower the user's motivation and provide specific measures for improvement.

[1469] Example 2

[1470] 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."

[1471] In modern society, many people suffer from a lack of motivation in their work or studies. It is particularly difficult to identify the individual causes of motivation loss and provide appropriate solutions, creating a demand for effective support systems. However, existing systems are unable to fully consider the user's emotions and specific circumstances, resulting in poor accuracy and effectiveness of the solutions they provide. Therefore, the present invention aims to recognize the user's emotions, more accurately identify the causes of motivation loss, and provide appropriate solutions.

[1472] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1473] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for recognizing the user's emotion using emotion recognition means, means for identifying factors that decrease motivation based on the analysis results and the recognized emotion, means for generating additional questions and advice based on the identified factors, and means for returning the generated questions and advice to the user. This makes it possible to accurately identify factors that decrease motivation according to individual circumstances, taking into account the user's emotional state, and to provide countermeasures against them.

[1474] The "means for accepting user input" refers to an interface and function that allows a user to input information about their own decline in motivation and transmit it to the system.

[1475] "Natural language processing means for analyzing said user input" refers to techniques and processes that analyze text data submitted by a user and extract important keywords and phrases.

[1476] "Emotion Recognition Method" refers to the technology and process for recognizing and determining emotions from user input text, using emotion engines and AI algorithms.

[1477] "Means for identifying factors that decrease motivation based on the analysis results and recognized emotions" refers to technology and functions that identify factors that decrease a user's motivation based on extracted keywords and recognized emotions.

[1478] "Means for generating additional questions and advice based on identified factors" refers to technology and functionality for generating questions and advice to gather further information and provide improvement measures in response to factors that reduce motivation.

[1479] The "means for returning the generated question or advice to the user" refers to the technology and functionality for transmitting and displaying the generated question or advice to the user.

[1480] "Means for reanalysis" refers to the technology and process of reanalyzing additional information and response data from users and extracting new keywords and emotions based on the newly obtained information.

[1481] The "means for generating a specific action plan" refers to a technology and function for creating a feasible plan or instructions for improving the user's motivation based on the reanalysis results.

[1482] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and in particular, improves accuracy by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine.

[1483] User terminal

[1484] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[1485] AI Server

[1486] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[1487] 1. Text analysis and emotion recognition:

[1488] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[1489] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[1490] 2. Identifying the factors that cause low motivation:

[1491] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[1492] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[1493] 3. Generate follow-up questions and advice:

[1494] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[1495] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[1496] 4. Dialogue Response:

[1497] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[1498] Emotion Engine

[1499] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[1500] Database Server

[1501] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1502] Specific examples

[1503] Here is an example of a specific dialogue:

[1504] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1505] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[1506] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1507] 4. AI server: Sends the generated questions back to the user device.

[1508] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1509] 6. User terminal: Send the input text to the AI ​​server again.

[1510] 7. AI server: Analyzes again and infers that the cause is "monotonous work," generating a question such as, "Which part of the report work do you find particularly stressful?"

[1511] 8. AI server: Sends the question back to the user device.

[1512] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1513] 10. User terminal: Send the input text to the AI ​​server again.

[1514] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1515] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1516] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1517] In general, the system of the present invention takes into account the user's emotional state, and is able to accurately identify factors that decrease motivation according to individual circumstances and provide countermeasures. Examples of prompts include "If you have been feeling unmotivated by your recent work, please tell us in detail why" and "Please feel free to write about your current feelings and the stress you are experiencing."

[1518] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1519] Step 1:

[1520] User Input Processing

[1521] The user uses the user terminal to input information about his / her own decreased motivation in text format and presses the send button.

[1522] Input: The user types "I've been feeling unmotivated at work lately" into the text box.

[1523] Output: The entered text data will be ready on the terminal after the send button is pressed.

[1524] Specific action: The user enters text using a keyboard or touch panel and clicks the send button.

[1525] Step 2:

[1526] Sending input data

[1527] The user terminal sends the input data to the AI ​​server.

[1528] Input: Text data entered by the user.

[1529] Output: Text data is sent to the AI ​​server via API.

[1530] Specific operation: When the user presses the send button, the device's communication module sends the data to the server.

[1531] Step 3:

[1532] Text Analysis and Emotion Recognition

[1533] The server analyzes the received data using natural language processing (NLP) technology to extract important keywords and phrases, while also using emotion recognition tools to recognize emotions.

[1534] Input: Sent text data: "I haven't been motivated to work lately."

[1535] Output: Keywords "work" and "unmotivated" and emotion "negative".

[1536] How it works: The NLP module on the server analyzes the text data and extracts keywords, while the emotion engine simultaneously identifies emotions.

[1537] Step 4:

[1538] Identifying factors that decrease motivation

[1539] The server identifies factors that decrease motivation based on the extracted keywords and recognized emotions.

[1540] Input: Keywords "work" and "unmotivated" and emotion "negative".

[1541] Output: "Work overload" and "monotonous work" are identified as factors that decrease motivation.

[1542] Specific operation: Based on the keywords and emotion data, the server compares it with an internal database and identifies the cause by referring to past data and cases.

[1543] Step 5:

[1544] Generate follow-up questions and advice

[1545] The server generates additional questions and advice based on the identified factors.

[1546] Input: Motivational factor "Work overload."

[1547] Output: Produces the question "What tasks have you found particularly taxing recently?"

[1548] Specific behavior: The server uses its internal logic and dialogue model to generate appropriate questions and advice based on the factors.

[1549] Step 6:

[1550] Submit a question or suggestion

[1551] The generated questions and advice are sent back to the user terminal.

[1552] Input: Generated additional questions or advice.

[1553] Output: Questions and advice displayed on the user's terminal.

[1554] Specific operation: The data generated by the server is sent to the user's terminal via API and presented to the user via a display interface.

[1555] Step 7:

[1556] User response processing

[1557] The user inputs and transmits an answer to the question displayed on the user terminal.

[1558] Input: The user enters "Daily report work" into the input field and presses the submit button.

[1559] Output: User response data is ready.

[1560] Specific behavior: The user again enters information using the keyboard or touch panel and clicks the send button.

[1561] Step 8:

[1562] Sending response data

[1563] The user terminal transmits the user's response data to the AI ​​server.

[1564] Input: User's answer data: "Daily reporting."

[1565] Output: The response data sent to the server.

[1566] Specific operation: The terminal's communication module sends the user's response data to the AI ​​server.

[1567] Step 9:

[1568] Reanalysis and countermeasure generation

[1569] The server analyzes the input data again, extracts new keywords and phrases, and generates the next questions and solutions.

[1570] Input: User's answer data: "Daily reporting."

[1571] Output: Keywords "report work" and "monotonous" and the following question: "Which part of the report work do you find particularly stressful?"

[1572] Specific operation: The server re-analyzes, extracts new keywords, and generates the next question.

[1573] Step 10:

[1574] Submit an action plan

[1575] The server generates a final action plan and proposes it to the user.

[1576] Input: Reanalysis result: "Monotonous work is a stressor."

[1577] Output: Action plan: "Divide tasks and take short breaks"

[1578] Specific operation: The server generates an action plan and sends it to the user's device via API.

[1579] Step 11:

[1580] Data storage

[1581] The server stores the dialogue history and the final action plan in a database server.

[1582] Input: Interaction history and action plan data.

[1583] Output: History and plans stored in a database.

[1584] Specific operation: The server connects to the database and saves the analysis results and countermeasure data.

[1585] Through the above processing steps, the system can identify factors that reduce a user's motivation and provide highly accurate countermeasures that take into account the user's emotional state.

[1586] (Application example 2)

[1587] 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."

[1588] In modern industrial environments, monotonous tasks and long working hours can lead to a decline in worker motivation. This can lead to a decline in work efficiency and quality, ultimately affecting productivity. There is a need for a system that can solve this problem and maintain and improve worker motivation.

[1589] 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.

[1590] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for being installed in the industrial machine, and means for analyzing the emotions of workers and managing their motivation. This makes it possible to quickly and accurately identify factors that decrease motivation in workers and provide appropriate advice and improvements.

[1591] The "means for accepting user input" refers to a device or interface that allows a user to input information in text format and that allows the system to receive that information.

[1592] "Means for analyzing user input" refers to a device or software that analyzes input text information using natural language processing techniques and extracts keywords and phrases.

[1593] The "means for identifying factors that decrease motivation" is a device or algorithm for identifying factors that decrease a user's motivation based on analyzed keywords and emotional data.

[1594] The "means for generating additional questions and advice" is a device or program for automatically generating additional questions and advice for the user in response to the identified demotivation factors.

[1595] The "means for returning questions and advice to the user" refers to a device or interface for transmitting the generated questions and advice to the user terminal and displaying them to the user.

[1596] "Means installed on industrial machines" refers to devices or software for incorporating and using the motivation management system on factory machines.

[1597] "Means for analyzing worker emotions" refers to a device or algorithm for analyzing text or voice data to recognize the worker's emotional state.

[1598] "Means for managing motivation" refers to a device or program that provides appropriate measures based on the worker's emotional data and factors that decrease motivation, thereby maintaining and improving their motivation to work.

[1599] This invention is a system for identifying factors that decrease the motivation of factory workers and providing countermeasures. This system consists of a user terminal, an AI server, a database server, and an emotion recognition engine. Each component and its processing are described in detail below.

[1600] User terminal

[1601] The user terminal functions as an interface for the worker to interact with the system. The user enters information about their emotional state and motivation in text format and presses the send button. The system is designed so that users can enter either a single sentence or multiple sentences. Smartphones, head-mounted displays, etc. are used as user terminals.

[1602] AI Server

[1603] The AI ​​server processes input information sent from the user terminal. The AI ​​server has the following main functions:

[1604] 1. Text analysis and emotion recognition:

[1605] The AI ​​server uses natural language processing (NLP) techniques to analyze user input and extract key keywords and phrases, and an emotion recognition engine to analyze emotional states.

[1606] The software used includes Python, NLTK (Natural Language Toolkit), SentimentIntensityAnalyzer, etc.

[1607] 2. Identifying the factors that cause low motivation:

[1608] Based on the results of text analysis and the user's emotional state, factors that decrease the user's motivation are identified, such as "monotonous work" and "long working hours."

[1609] 3. Generate follow-up questions and advice:

[1610] Based on the identified factors, the AI ​​server generates additional questions and advice for the user, and specific countermeasures are proposed and sent to the user.

[1611] Emotion Recognition Engine

[1612] The emotion recognition engine is a dedicated module for extracting emotions from user input text. It has the ability to distinguish between positive, negative, and neutral emotions, and is used in the analysis process of the AI ​​server.

[1613] Database Server

[1614] The results of the analysis performed by the AI ​​server and the history of user interactions are stored on a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of responses to new users based on past data. Examples of database management systems used include MySQL.

[1615] Specific examples

[1616] Here is an example of a specific dialogue:

[1617] 1. User terminal: The worker types in, "Recently, I've been doing monotonous work and I'm not motivated," and presses the send button.

[1618] 2. AI server: Analyzes the text and extracts keywords such as "monotonous work" and "unmotivated." An emotion recognition engine recognizes "negative" emotions.

[1619] 3. AI server: Based on the analysis results, it identifies that "monotonous work is the cause" and generates the next question: "Which part of the work is particularly burdensome?"

[1620] 4. AI server: Returns the generated questions to the user device.

[1621] 5. User terminal: The question is received and the worker enters "There is a lot of repetitive work."

[1622] 6. User terminal: Re-send the input text to the AI ​​server.

[1623] 7. AI server: Reanalyzes and infers that "diversification of work is necessary" and suggests "try combining other tasks."

[1624] 8. AI server: Sends suggestions to the user's device and displays them to the worker.

[1625] Prompt Sentence Examples

[1626] "Recently, I've been doing monotonous tasks that have been unmotivating me. For example, I have to assemble the same parts all day. Do you have any suggestions for solving this problem?"

[1627] As described above, by using this system, it is possible to quickly and accurately identify the factors that decrease worker motivation and provide appropriate countermeasures. Specific feedback and countermeasures are expected to improve the work environment and increase efficiency.

[1628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1629] Step 1:

[1630] The user provides input

[1631] The user uses a smartphone or head-mounted display to input information about their emotional state and motivation in text format and presses the send button. This input becomes the data to be analyzed in the next step.

[1632] Input: User's text information (e.g., "Recently, I've been doing monotonous work and I'm not feeling motivated.")

[1633] Output: The text data sent

[1634] Step 2:

[1635] Sending data from the user device to the AI ​​server

[1636] The user terminal sends the input text data to the AI ​​server, which uses this data in the next analysis step.

[1637] Input: Text data entered into the user's terminal

[1638] Output: Text data sent to the AI ​​server

[1639] Step 3:

[1640] Text Analysis and Emotion Recognition

[1641] The AI ​​server analyzes the received text data using natural language processing (NLP) technology to extract important keywords and phrases. At the same time, it analyzes the emotional state using an emotion recognition engine. The software used is Python, NLTK, and SentimentIntensityAnalyzer.

[1642] Input: Text data sent to the AI ​​server

[1643] Output: Analyzed keywords, emotional state (e.g., "monotonous work," "unmotivated," emotion recognition result: negative)

[1644] Specific behavior:

[1645] 1. Tokenize the text data and extract important keywords and phrases.

[1646] 2. Analyze emotional states using SentimentIntensityAnalyzer.

[1647] 3. Obtain a positive, negative, or neutral score.

[1648] Step 4:

[1649] Identifying factors that decrease motivation

[1650] The AI ​​server identifies factors that decrease the user's motivation based on the results of text analysis and emotion recognition, such as "monotonous work" and "long working hours."

[1651] Input: Parsed keywords, emotional state

[1652] Output: Identified demotivators (e.g., "monotonous work")

[1653] Specific behavior:

[1654] 1. Analyzed keywords and sentiment data are compared with known factors in the database.

[1655] 2. Identify the most consistent demotivator.

[1656] Step 5:

[1657] Generate additional questions and advice

[1658] Based on the identified demotivation factors, the AI ​​server generates additional questions and advice for the user, such as "Which part of the work is particularly burdensome?", and suggests specific measures.

[1659] Input: Identified demotivators

[1660] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[1661] Specific behavior:

[1662] 1. Retrieve relevant questions and measures from the database.

[1663] 2. Generate questions and advice tailored to the user.

[1664] Step 6:

[1665] Sending additional questions or advice to the user's device

[1666] The generated questions and advice are sent to the user's terminal and displayed to the user, and this information serves as feedback to the user.

[1667] Input: Generated questions and advice

[1668] Output: Questions and advice sent to the user's terminal

[1669] Specific behavior:

[1670] 1. Convert the generated content into a format that can be easily viewed by the user.

[1671] 2. Send to the user's terminal and display.

[1672] Step 7:

[1673] Accepting additional information from the user

[1674] The user can then enter additional information in response to the submitted question or advice and submit it again, a process that yields more detailed information.

[1675] Input: Additional information about the user (e.g., "Daily report work")

[1676] Output: Data sent to the AI ​​server as additional information

[1677] Specific behavior:

[1678] 1. The user enters answers to questions and additional information and submits.

[1679] 2. Transfer additional information to the AI ​​server.

[1680] Step 8:

[1681] Reanalysis and updated measures

[1682] The AI ​​server receives the additional information and analyzes it again, proposing specific measures to improve the user's motivation as a final action plan.

[1683] Input: Additional information from the user

[1684] Output: An updated action plan (e.g., "Break up tasks and take short breaks")

[1685] Specific behavior:

[1686] 1. Reanalyze additional information to identify new factors and details.

[1687] 2. Generate and propose a specific action plan.

[1688] Step 9:

[1689] Sending the final action plan to the user's device

[1690] The generated action plan is sent to the user's terminal and displayed to the user, allowing the user to know specific improvement measures.

[1691] Input: Updated Action Plan

[1692] Output: Action plan sent to user device

[1693] Specific behavior:

[1694] 1. Convert the generated action plan into a format that is easy for users to execute.

[1695] 2. Send to the user's terminal and display.

[1696] Step 10:

[1697] Save conversation history and action plans

[1698] The AI ​​server stores all interaction history and generated action plans in a database server, allowing for future improvements and user progress tracking.

[1699] Input: Dialogue history, generated action plan

[1700] Output: Data stored on the database server

[1701] Specific behavior:

[1702] 1. Dialogue history and generated action plans are saved in a database.

[1703] 2. Retaining data for subsequent analysis and improvement.

[1704] 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.

[1705] 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.

[1706] 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.

[1707] [Fourth embodiment]

[1708] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1709] 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.

[1710] 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).

[1711] 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.

[1712] 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.

[1713] 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).

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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."

[1721] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. Each component and its processing are described in detail below in natural language.

[1722] User terminal

[1723] The user terminal functions as an interface for the user to interact with the system. The user inputs information about their motivation decline in text format and presses the send button. This input information can be multiple sentences at once.

[1724] AI Server

[1725] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[1726] 1. Text Analysis:

[1727] The AI ​​server analyzes user input using natural language processing (NLP) technology, which extracts important keywords and emotional characteristics from the input sentence.

[1728] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted.

[1729] 2. Identifying the factors that cause low motivation:

[1730] Based on the extracted keywords and emotional characteristics, the AI ​​server identifies the factors that are causing the user's motivation to decline. In this process, it compares past data and known patterns to infer the most likely factors.

[1731] For example, the keywords "work" and "lack of motivation" may lead to the identification of "overload of work" and "monotonous tasks" as contributing factors.

[1732] 3. Generate follow-up questions and advice:

[1733] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[1734] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[1735] 4. Dialogue Response:

[1736] The generated questions and advice are sent back to the user's terminal, making it easier for the user to input specific answers.

[1737] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[1738] Database Server

[1739] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1740] Specific examples

[1741] Here is an example of a specific dialogue:

[1742] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1743] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[1744] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1745] 4. AI server: Sends the generated questions back to the user device.

[1746] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1747] 6. User terminal: Send the input text to the AI ​​server again.

[1748] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1749] 8. AI server: Sends the question back to the user device.

[1750] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1751] 10. User terminal: Send the input text to the AI ​​server again.

[1752] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1753] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1754] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1755] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to those problems. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them.

[1756] The processing flow will be explained below.

[1757] Step 1:

[1758] The user enters their concerns or problems related to their motivation into the text input field on the device and presses the send button.

[1759] Step 2:

[1760] The terminal acquires the input text data and sends it to the server together with the user ID and session information using an HTTP request.

[1761] Step 3:

[1762] The server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[1763] Step 4:

[1764] The server identifies factors that decrease motivation based on keywords and emotional characteristics output by the NLP module, using an internal database and known patterns. For example, from the keywords "work" and "unmotivated," "work overload" and "monotonous work" become candidates.

[1765] Step 5:

[1766] The server generates additional questions to obtain further information from the user based on the identified demotivation factors. For example, a question might be generated such as, "What tasks have you found particularly burdensome recently?"

[1767] Step 6:

[1768] The server returns the generated question to the user's terminal, where it is displayed in a format that allows the user to easily answer it.

[1769] Step 7:

[1770] The user enters specific answers to the questions displayed on the terminal, presses the send button again, and the process is repeated.

[1771] Step 8:

[1772] The device again sends the user's answers to the server, which analyzes this new information and again identifies the factors that lower motivation.

[1773] Step 9:

[1774] The server generates more specific questions and advice based on the results of the reanalysis. By repeating this process several times, the factors that decrease motivation can be identified in detail.

[1775] Step 10:

[1776] The server then generates a specific action plan based on the motivation-reducing factors, such as recommending "dividing tasks and taking short breaks."

[1777] Step 11:

[1778] The server sends the generated action plan to the user's terminal and displays it to the user. The action plan includes specific instructions and advice that the user can immediately implement.

[1779] Step 12:

[1780] The server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[1781] In this way, the user terminal, AI server, and database server work together to consistently identify factors that lower a user's motivation and provide specific measures for improvement.

[1782] Example 1

[1783] 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."

[1784] In modern society, many people suffer from a lack of motivation in their work and personal lives. However, the individual factors that cause this lack of motivation are diverse, making it difficult to find appropriate solutions. Furthermore, conventional systems often struggle to provide individualized solutions for each user, and can only provide general solutions. Therefore, there is a need for a system that can effectively identify the specific factors that cause a user to lose motivation and provide specific improvement measures tailored to each individual situation.

[1785] 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.

[1786] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for using a generative AI model for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for saving the analysis results and a dialogue history with the user in a database, and means for improving the quality of interaction with new users based on past data. This makes it possible to effectively identify specific factors that decrease a user's motivation and provide specific improvement measures tailored to individual situations.

[1787] The "means for accepting user input" refers to a means by which a user inputs information about a decrease in motivation to the system and transmits it to the system. Specifically, it includes interfaces such as a keyboard, a touch screen, and voice input.

[1788] "Natural language processing means" refers to means for analyzing text data entered by users and extracting important keywords and emotional characteristics. Specifically, it includes natural language processing libraries and algorithms.

[1789] A "generative AI model" is an artificial intelligence model that identifies factors that decrease motivation based on input data and analysis results, referring to specific patterns and past data. Specific examples include BERT and GPT.

[1790] The "means for generating additional questions and advice" is a means for generating questions to obtain further information from the user or initial measures for improvement based on the identified demotivation factors.

[1791] "Means for returning generated questions and advice to the user" refers to the means for sending questions and advice generated by the AI ​​server back to the user's terminal, and uses HTTPS or similar as a communication protocol.

[1792] "Means for saving analysis results and user interaction history in a database" refers to means for saving the analysis results performed by the AI ​​server and the content of user interaction in a database so that they can be referenced later. This includes database management systems and storage devices.

[1793] "Means for improving the quality of responses to new users based on past data" refers to a means for referring to saved past dialogue history and analysis results and using them to more effectively respond to new users. This makes it possible to more accurately identify factors that decrease motivation and provide improvement measures.

[1794] MODE FOR CARRYING OUT THE INVENTION

[1795] System Configuration

[1796] This invention is a system for identifying the causes of a user's declining motivation and providing appropriate countermeasures. This system consists of a user terminal, an AI server, and a database server. The detailed functions and processing flow of each component are explained below.

[1797] User terminal

[1798] The user terminal functions as an interface for the user to interact with the system. Using a dedicated application or a web interface, the user inputs information about their own lack of motivation in text format and presses the send button. This input information can include multiple sentences. For example, the user can input "I've been feeling unmotivated at work lately" and send it.

[1799] AI Server

[1800] Based on the information sent from the user device, the AI ​​server performs the following main processes:

[1801] 1. Text Analysis:

[1802] The AI ​​server analyzes the user's input using natural language processing (NLP) techniques, such as Python's NLTK or SpaCy libraries. This allows it to extract important keywords and emotional characteristics from the input sentence. For example, keywords such as "work" and "unmotivated" are extracted.

[1803] 2. Identifying the factors that cause low motivation:

[1804] Based on the extracted keywords and emotional characteristics, the AI ​​server uses generative AI models such as BERT and GPT to identify the factors behind the user's lack of motivation. During this process, it compares past data and known patterns to infer likely causes. For example, based on the keywords "work" and "lack of motivation," it can identify that "work overload" is the cause.

[1805] 3. Generate follow-up questions and advice:

[1806] Based on the identified demotivators, the AI ​​server generates follow-up questions to obtain further information from the user and initial improvement measures, such as, "Which tasks do you find particularly stressful?"

[1807] 4. Dialogue Response:

[1808] The generated questions and advice are sent back to the user's device using the HTTPS protocol to ensure security.

[1809] The AI ​​server repeats this process, digging deeper into the factors that are causing the user to lose motivation. When reanalyzing, it asks additional questions based on the previous answers. In this way, it helps the user to understand their problem more clearly and find an appropriate solution.

[1810] Database Server

[1811] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1812] Specific examples

[1813] Here is an example of a specific dialogue:

[1814] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1815] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[1816] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1817] 4. AI server: Sends the generated questions back to the user device.

[1818] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1819] 6. User terminal: Send the input text to the AI ​​server again.

[1820] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1821] 8. AI server: Sends the question back to the user device.

[1822] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1823] 10. User terminal: Send the response text to the AI ​​server again.

[1824] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1825] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1826] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1827] In this way, by using the system of the present invention, the user can gain a deeper understanding of his or her own problems and take concrete measures to improve them.

[1828] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1829] Step 1:

[1830] The user uses a dedicated application or web interface to enter text information about the decline in motivation and presses the send button.

[1831] Input: Text information from the user (e.g., "I've been feeling unmotivated at work lately.")

[1832] Output: The entered text information is sent from the user's device.

[1833] Step 2:

[1834] The user's device sends the input text information to the AI ​​server. The HTTPS protocol is used for communication to ensure data security.

[1835] Input: Text information entered by the user

[1836] Output: Text information arrives at the AI ​​server

[1837] Step 3:

[1838] The server analyzes the received text information using natural language processing (NLP) techniques, specifically using Python's NLTK and SpaCy libraries, to extract important keywords and sentiment features.

[1839] Input: Text information received by the server

[1840] Data processing / data calculation: Analyze text using NLP technology to extract keywords and sentiment features

[1841] Output: Extracted keywords and sentiment features (e.g., "work" and "unmotivated")

[1842] Step 4:

[1843] The server uses a generative AI model (such as BERT or GPT) to identify factors that cause demotivation based on the extracted keywords and emotional characteristics. The AI ​​model refers to past data and known patterns to infer likely factors.

[1844] Input: Extracted keywords and sentiment features

[1845] Data processing / data calculation: Identifying factors that decrease motivation using generative AI models

[1846] Output: Identified demotivators (e.g., "work overload")

[1847] Step 5:

[1848] The server generates additional questions to obtain further information from the user and initial remedial measures based on the identified demotivation factors.

[1849] Input: Identified demotivators

[1850] Data manipulation / data calculation: Generate additional questions and advice

[1851] Output: Generated questions and advice (e.g., "Which tasks do you find particularly stressful?")

[1852] Step 6:

[1853] The server sends the generated questions and advice to the user's terminal, also using the HTTPS protocol.

[1854] Input: Generated questions and advice

[1855] Output: Questions and advice are sent to the user's device.

[1856] Step 7:

[1857] The user terminal displays the received question or advice, and the user inputs an answer. For example, the user inputs "Daily report work."

[1858] Input: Questions and advice sent by the server

[1859] Output: User's answer (e.g., "Daily report work")

[1860] Step 8:

[1861] The user's terminal sends the user's answer back to the AI ​​server.

[1862] Input: User's answer

[1863] Output: The answer arrives at the AI ​​server

[1864] Step 9:

[1865] The server then analyzes the newly received text data again. For example, it infers that the cause is "monotonous work" and generates a question such as, "Which part of the report work is particularly stressful for you?"

[1866] Input: User's answer submitted again

[1867] Data processing / data calculation: Reanalyze using NLP technology to generate the next question

[1868] Output: Generated follow-up questions (e.g., "What aspects of the report task are particularly stressful for you?")

[1869] Step 10:

[1870] The server transmits the generated follow-up question to the user terminal.

[1871] Input: Generated follow-up question

[1872] Output: The question arrives at the user's terminal.

[1873] Step 11:

[1874] The user terminal displays the question, and the user again inputs the answer. For example, the user inputs "It's monotonous and there is a lot of repetitive work."

[1875] Input: Additional question sent by the server

[1876] Output: User response (e.g., "It's repetitive and monotonous.")

[1877] Step 12:

[1878] The user's terminal sends the user's answer back to the AI ​​server.

[1879] Input: User's answer

[1880] Output: The answer arrives at the AI ​​server

[1881] Step 13:

[1882] The server generates a final action plan, for example recommending "break up tasks and take short breaks."

[1883] Input: User's answer submitted again

[1884] Data processing / data calculation: Generate a final action plan using a generative AI model

[1885] Output: Final action plan (e.g., "Break down tasks and take short breaks")

[1886] Step 14:

[1887] The server sends the proposed final action plan to the user terminal, which displays it.

[1888] Input: Final Action Plan

[1889] Output: The final action plan is displayed on the user's device.

[1890] Step 15:

[1891] The server stores the final dialogue history and action plan in the database server, which enables future responses based on the dialogue history.

[1892] Input: Final interaction history and action plan

[1893] Output: Dialogue history and action plans are saved in a database

[1894] (Application example 1)

[1895] 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."

[1896] Conventional motivation management systems typically identify factors that decrease motivation based on user input and then provide questions and advice. However, these systems do not necessarily adapt to the user's behavior or situation, and real-time dialogue and data updates are difficult, especially when used by field workers. As a result, the user experience is poor and motivation improvement effects are not fully achieved.

[1897] 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.

[1898] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating follow-up questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for accepting user input using a wearable device worn on the user's body, means for analyzing input from the wearable device using natural language analysis technology, means for generating follow-up questions and advice in a form that is displayed on the wearable device, means for referencing past data to identify factors that decrease the user's motivation, and a database for storing dialogue history. This enables users to engage in real-time dialogue, identify their own factors that decrease motivation, and quickly receive a specific and effective action plan for addressing those factors.

[1899] The "means for accepting user input" refers to a device that includes an interface or device that allows a user to provide input to the system.

[1900] The "means for analyzing the user input" refers to software and algorithms for analyzing input information received from a user and understanding its content.

[1901] The "means for identifying factors causing a decrease in motivation" is a system that has the function of extracting and identifying the causes of a decrease in motivation from the analyzed user input.

[1902] The "means for generating additional questions and advice" is a function that automatically generates questions to obtain further information from the user and advice on measures to be taken based on the identified motivation-reducing factors.

[1903] The "means for returning the generated question or advice to the user" is a system including a communication means and a display device for presenting the generated question or advice to the user.

[1904] A "wearable device" is a device that can be worn on the user's body and has functions such as input reception and information display.

[1905] "Natural language analysis technology" is a technology that analyzes input information such as text and voice and understands human language.

[1906] "Means for referencing past data" refers to a function that allows the system to refer to data collected in the past and improve the accuracy of analysis and identification.

[1907] The "database for storing dialogue history" refers to a database for storing the contents of dialogue with users and analysis results, and a system for managing such database.

[1908] The system of this invention is composed of a user terminal, an AI server, and a database server to identify factors that decrease a user's motivation and provide appropriate measures.

[1909] User terminal

[1910] The user terminal functions as an interface for the user to interact with the system. Specifically, the user wears a wearable device such as smart glasses and provides information to the system through voice or text input. The user inputs information about their own decline in motivation and presses a button to send it. This input information is then sent to the AI ​​server.

[1911] AI Server

[1912] The AI ​​server receives input information sent from the user device and performs the following main functions:

[1913] 1. Text Analysis:

[1914] The server analyzes the user's input using natural language processing technology, using software such as TextBlob and Transformers, to extract important keywords and emotional features and understand the user's state.

[1915] 2. Identifying the factors that cause low motivation:

[1916] Based on the extracted keywords and emotional characteristics, past data is referenced to identify factors that have reduced the user's motivation. Past data is stored on a database server, and the AI ​​server searches and compares this data to identify factors.

[1917] 3. Generate follow-up questions and advice:

[1918] Based on the identified demotivators, we generate follow-up questions to obtain more information from the user and initial improvement measures, such as "Which tasks do you find particularly burdensome?"

[1919] 4. Dialogue Response:

[1920] The generated questions and advice are sent back to the user's device, where the user can respond, and the information is then analyzed again by the AI ​​server.

[1921] Database Server

[1922] The AI ​​server's analysis results and user interaction history are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1923] Specific examples

[1924] Here is an example of a specific dialogue:

[1925] 1. User device: The user types "I haven't been motivated to work lately" through the smart glasses and presses the send button.

[1926] 2. AI server: Analyzes the text and extracts the keywords "work" and "unmotivated."

[1927] 3. AI server: Based on the analysis results, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1928] 4. AI server: Sends the generated questions back to the user device.

[1929] 5. User terminal: The received question is displayed, and the user answers, "This is my daily report work."

[1930] 6. User terminal: Send the input text to the AI ​​server again.

[1931] 7. AI server: Reanalyzes the data and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1932] 8. AI server: Sends the question back to the user device.

[1933] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1934] 10. User terminal: Send the input text to the AI ​​server again.

[1935] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1936] 12. AI server: Sends the proposal to the user's device and presents it to the user.

[1937] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1938] Prompt Sentence Examples

[1939] Worker: I've been feeling unmotivated at work lately.

[1940] System: What parts of the job do you find particularly taxing?

[1941] Workers: There is a lot of monotonous work and it is hard.

[1942] System: Break up your tasks and take short breaks.

[1943] In this way, the system of the present invention identifies factors that decrease a user's motivation in real time and realizes a series of processes to provide solutions to those problems, allowing the user to gain a deeper understanding of their own problems and take concrete measures to improve them.

[1944] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1945] Step 1:

[1946] The user enters information about their motivation decline on their device and presses the send button. The entered information is sent in text format from the user device to the AI ​​server. The user device is a wearable device such as smart glasses.

[1947] Step 2:

[1948] The AI ​​server receives text information sent from the user's device. The received text information is analyzed using natural language analysis technology. Specifically, keywords and emotional features are extracted using TextBlob and Transformers. The input is text information related to the user's decreased motivation, and the output is the extracted keywords and emotional features.

[1949] Step 3:

[1950] The AI ​​server identifies factors that decrease motivation based on the extracted keywords and emotional characteristics. Specifically, it compares the extracted data with past data, which is stored in a database server. The input is keywords and emotional characteristics, and the output is the identified factors that decrease motivation.

[1951] Step 4:

[1952] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures. For example, if the identified factor is "work overload," it generates the question "Which tasks do you find particularly burdensome?" The input is the demotivation factors, and the output is the generated questions and advice.

[1953] Step 5:

[1954] The generated questions and advice are sent back from the AI ​​server to the user's device. The user's device displays these questions and advice to the user. The user then inputs an answer to the question. The input is the generated question or advice, and the output is the user's additional answer.

[1955] Step 6:

[1956] The user enters an additional answer and sends it again to the AI ​​server. The AI ​​server receives this additional information and performs text analysis again. The input is the additional answer from the user, and the output is the analyzed additional information.

[1957] Step 7:

[1958] Based on the reanalyzed information, the AI ​​server will dig deeper into further factors that lower motivation and generate further questions or advice as necessary. For example, if the user answers, "It's the daily report work," the next question generated will be, "Which part of that report work is particularly stressful for you?" The input is the reanalyzed additional information, and the output is further questions or advice.

[1959] Step 8:

[1960] The AI ​​server sends the final action plan to the user's device. The user's device displays this action plan to the user. For example, it may recommend "dividing tasks and taking short breaks." The input is the final action plan, and the output is the action plan displayed to the user.

[1961] Step 9:

[1962] The AI ​​server saves the final dialogue history and action plan in the database server. This is expected to improve the accuracy of identifying future declines in motivation and developing improvement measures. The input is the final dialogue history and action plan, and the output is the information saved in the database.

[1963] 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.

[1964] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and its accuracy is particularly enhanced by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine. Each component and its processing are described in detail below in natural language.

[1965] User terminal

[1966] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[1967] AI Server

[1968] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[1969] 1. Text analysis and emotion recognition:

[1970] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[1971] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[1972] 2. Identifying the factors that cause low motivation:

[1973] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[1974] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[1975] 3. Generate follow-up questions and advice:

[1976] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[1977] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[1978] 4. Dialogue Response:

[1979] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[1980] Emotion Engine

[1981] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[1982] Database Server

[1983] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[1984] Specific examples

[1985] Here is an example of a specific dialogue:

[1986] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[1987] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[1988] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[1989] 4. AI server: Sends the generated questions back to the user device.

[1990] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[1991] 6. User terminal: Send the input text to the AI ​​server again.

[1992] 7. AI server: Analyzes again and infers that the cause is "monotonous work," and generates a question: "Which part of the report work is particularly stressful for you?"

[1993] 8. AI server: Sends the question back to the user device.

[1994] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[1995] 10. User terminal: Send the input text to the AI ​​server again.

[1996] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[1997] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[1998] 13. AI Server: Save the final dialogue history and action plan in the database server.

[1999] In this way, the system of the present invention implements a series of processes to identify factors that decrease a user's motivation and provide solutions to address them. By using this system, users can gain a deeper understanding of their own problems and take concrete measures to improve them. By combining it with an emotion engine, highly accurate identification and solutions can be achieved, taking into account the user's emotional state.

[2000] The processing flow will be explained below.

[2001] Step 1:

[2002] The user enters their motivation-related worries or problems into a text input field on the device and presses the send button. For example, they might enter, "I haven't been feeling motivated at work lately."

[2003] Step 2:

[2004] The device acquires the entered text data and sends it to the AI ​​server using an HTTP request along with the user ID and session information.

[2005] Step 3:

[2006] The AI ​​server passes the received text data to an NLP (Natural Language Processing) module for analysis, which extracts keywords, key phrases, and sentiment features from the text.

[2007] Step 4:

[2008] The emotion engine recognizes emotions from text. For example, it recognizes "negative emotions" from the phrase "I'm not motivated."

[2009] Step 5:

[2010] Based on the output of the NLP module and emotion engine, the AI ​​server uses an internal database and known patterns to identify factors that decrease motivation, such as "work overload" and "monotonous work."

[2011] Step 6:

[2012] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user, such as, "What tasks have you found particularly burdensome recently?"

[2013] Step 7:

[2014] The AI ​​server returns the generated question to the user's terminal and displays it to the user.

[2015] Step 8:

[2016] The user inputs a specific answer to the question displayed on the terminal and presses the send button again. For example, the user might answer, "I'm working on a daily report."

[2017] Step 9:

[2018] The device again sends the user's answer to the AI ​​server, which again analyzes this new information with the NLP module and again recognizes emotions using the emotion engine.

[2019] Step 10:

[2020] Based on the results of the reanalysis, the AI ​​server generates more specific questions and advice, such as, "Which part of the report work is particularly stressful for you?"

[2021] Step 11:

[2022] The AI ​​server then sends the generated questions to the user's device, and the user enters the answers again. By repeating this process several times, the factors that decrease the user's motivation can be identified in detail.

[2023] Step 12:

[2024] Finally, the AI ​​server generates a specific action plan based on the factors that cause the decrease in motivation, such as recommending "dividing tasks and taking short breaks."

[2025] Step 13:

[2026] The AI ​​server sends the generated action plan to the user's device and displays it to the user. The action plan includes specific instructions and advice that are easy for the user to follow.

[2027] Step 14:

[2028] The AI ​​server stores all user interaction history and generated action plans in a database server. The stored data is used for future improvements and to monitor the user's progress.

[2029] In this way, the user terminal, AI server, emotion engine, and database server work together to consistently identify factors that lower the user's motivation and provide specific measures for improvement.

[2030] Example 2

[2031] 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."

[2032] In modern society, many people suffer from a lack of motivation in their work or studies. It is particularly difficult to identify the individual causes of motivation loss and provide appropriate solutions, creating a demand for effective support systems. However, existing systems are unable to fully consider the user's emotions and specific circumstances, resulting in poor accuracy and effectiveness of the solutions they provide. Therefore, the present invention aims to recognize the user's emotions, more accurately identify the causes of motivation loss, and provide appropriate solutions.

[2033] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2034] In this invention, the server includes means for accepting user input, natural language processing means for analyzing the user input, means for recognizing the user's emotion using emotion recognition means, means for identifying factors that decrease motivation based on the analysis results and the recognized emotion, means for generating additional questions and advice based on the identified factors, and means for returning the generated questions and advice to the user. This makes it possible to accurately identify factors that decrease motivation according to individual circumstances, taking into account the user's emotional state, and to provide countermeasures against them.

[2035] The "means for accepting user input" refers to an interface and function that allows a user to input information about their own decline in motivation and transmit it to the system.

[2036] "Natural language processing means for analyzing said user input" refers to techniques and processes that analyze text data submitted by a user and extract important keywords and phrases.

[2037] "Emotion Recognition Method" refers to the technology and process for recognizing and determining emotions from user input text, using emotion engines and AI algorithms.

[2038] "Means for identifying factors that decrease motivation based on the analysis results and recognized emotions" refers to technology and functions that identify factors that decrease a user's motivation based on extracted keywords and recognized emotions.

[2039] "Means for generating additional questions and advice based on identified factors" refers to technology and functionality for generating questions and advice to gather further information and provide improvement measures in response to factors that reduce motivation.

[2040] The "means for returning the generated question or advice to the user" refers to the technology and functionality for transmitting and displaying the generated question or advice to the user.

[2041] "Means for reanalysis" refers to the technology and process of reanalyzing additional information and response data from users and extracting new keywords and emotions based on the newly obtained information.

[2042] The "means for generating a specific action plan" refers to a technology and function for creating a feasible plan or instructions for improving the user's motivation based on the reanalysis results.

[2043] This invention is a system that identifies factors that decrease a user's motivation and provides appropriate countermeasures, and in particular, improves accuracy by combining it with an emotion engine that recognizes the user's emotions. This system consists of a user terminal, an AI server, a database server, and an emotion engine.

[2044] User terminal

[2045] The user terminal functions as an interface for the user to interact with the system. The user enters information about their motivation decline in text format and presses the send button. The system is designed so that users can enter multiple sentences at once.

[2046] AI Server

[2047] Input information sent from the user terminal reaches the AI ​​server, which has the following main functions:

[2048] 1. Text analysis and emotion recognition:

[2049] The AI ​​server first analyzes the user's input using natural language processing (NLP) techniques to extract important keywords and phrases from the text, and simultaneously uses an emotion engine to recognize the user's emotions from the input text.

[2050] For example, if the user inputs "I haven't been motivated to work lately," the keywords "work" and "lack of motivation" are extracted, and the "negative" emotion is recognized.

[2051] 2. Identifying the factors that cause low motivation:

[2052] Based on the extracted keywords and recognized emotions, the AI ​​server identifies factors that decrease the user's motivation. In this process, the type of emotion (positive / negative) can also be taken into consideration, enabling more accurate identification.

[2053] For example, the keywords "work" and "unmotivated" and the emotion "negative" may lead to the identification of "work overload" and "monotonous tasks" as contributing factors.

[2054] 3. Generate follow-up questions and advice:

[2055] Based on the identified demotivation factors, the AI ​​server generates additional questions to obtain further information from the user and initial improvement measures.

[2056] For example, a question might be generated: "What tasks have you found particularly burdensome recently?"

[2057] 4. Dialogue Response:

[2058] The generated questions and advice are sent back to the user's terminal and displayed so that the user can easily answer them.

[2059] Emotion Engine

[2060] The emotion engine is a dedicated module for extracting emotions from user input text. This emotion engine has the ability to distinguish between positive, negative, and neutral emotions, and is included in the process of identifying factors that decrease motivation in the AI ​​server.

[2061] Database Server

[2062] The results of the analysis performed by the AI ​​server and the history of user interactions are stored in a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of support for new users based on past data.

[2063] Specific examples

[2064] Here is an example of a specific dialogue:

[2065] 1. User terminal: The user types "I haven't been motivated to work lately" and presses the send button.

[2066] 2. AI server: Analyzes the text and extracts keywords such as "work" and "unmotivated." At the same time, it uses an emotion engine to recognize "negative" emotions.

[2067] 3. AI server: Based on the analysis results and emotion recognition, it identifies that "work overload is the cause" and generates the next question: "Which tasks do you find particularly burdensome?"

[2068] 4. AI server: Sends the generated questions back to the user device.

[2069] 5. User terminal: The received question is displayed and the user enters "Daily report work."

[2070] 6. User terminal: Send the input text to the AI ​​server again.

[2071] 7. AI server: Analyzes again and infers that the cause is "monotonous work," generating a question such as, "Which part of the report work do you find particularly stressful?"

[2072] 8. AI server: Sends the question back to the user device.

[2073] 9. User terminal: The question is displayed and the user types in "It's repetitive and monotonous."

[2074] 10. User terminal: Send the input text to the AI ​​server again.

[2075] 11. AI Server: As a final action plan, we recommend breaking up tasks and taking short breaks.

[2076] 12. AI server: Sends suggestions to the user's device and displays them to the user.

[2077] 13. AI Server: Save the final dialogue history and action plan in the database server.

[2078] In general, the system of the present invention takes into account the user's emotional state, and is able to accurately identify factors that decrease motivation according to individual circumstances and provide countermeasures. Examples of prompts include "If you have been feeling unmotivated by your recent work, please tell us in detail why" and "Please feel free to write about your current feelings and the stress you are experiencing."

[2079] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2080] Step 1:

[2081] User Input Processing

[2082] The user uses the user terminal to input information about his / her own decreased motivation in text format and presses the send button.

[2083] Input: The user types "I've been feeling unmotivated at work lately" into the text box.

[2084] Output: The entered text data will be ready on the terminal after the send button is pressed.

[2085] Specific action: The user enters text using a keyboard or touch panel and clicks the send button.

[2086] Step 2:

[2087] Sending input data

[2088] The user terminal sends the input data to the AI ​​server.

[2089] Input: Text data entered by the user.

[2090] Output: Text data is sent to the AI ​​server via API.

[2091] Specific operation: When the user presses the send button, the device's communication module sends the data to the server.

[2092] Step 3:

[2093] Text Analysis and Emotion Recognition

[2094] The server analyzes the received data using natural language processing (NLP) technology to extract important keywords and phrases, while also using emotion recognition tools to recognize emotions.

[2095] Input: Sent text data: "I haven't been motivated to work lately."

[2096] Output: Keywords "work" and "unmotivated" and emotion "negative".

[2097] How it works: The NLP module on the server analyzes the text data and extracts keywords, while the emotion engine simultaneously identifies emotions.

[2098] Step 4:

[2099] Identifying factors that decrease motivation

[2100] The server identifies factors that decrease motivation based on the extracted keywords and recognized emotions.

[2101] Input: Keywords "work" and "unmotivated" and emotion "negative".

[2102] Output: "Work overload" and "monotonous work" are identified as factors that decrease motivation.

[2103] Specific operation: Based on the keywords and emotion data, the server compares it with an internal database and identifies the cause by referring to past data and cases.

[2104] Step 5:

[2105] Generate follow-up questions and advice

[2106] The server generates additional questions and advice based on the identified factors.

[2107] Input: Motivational factor "Work overload."

[2108] Output: Produces the question "What tasks have you found particularly taxing recently?"

[2109] Specific behavior: The server uses its internal logic and dialogue model to generate appropriate questions and advice based on the factors.

[2110] Step 6:

[2111] Submit a question or suggestion

[2112] The generated questions and advice are sent back to the user terminal.

[2113] Input: Generated additional questions or advice.

[2114] Output: Questions and advice displayed on the user's terminal.

[2115] Specific operation: The data generated by the server is sent to the user's terminal via API and presented to the user via a display interface.

[2116] Step 7:

[2117] User response processing

[2118] The user inputs and transmits an answer to the question displayed on the user terminal.

[2119] Input: The user enters "Daily report work" into the input field and presses the submit button.

[2120] Output: User response data is ready.

[2121] Specific behavior: The user again enters information using the keyboard or touch panel and clicks the send button.

[2122] Step 8:

[2123] Sending response data

[2124] The user terminal transmits the user's response data to the AI ​​server.

[2125] Input: User's answer data: "Daily reporting."

[2126] Output: The response data sent to the server.

[2127] Specific operation: The terminal's communication module sends the user's response data to the AI ​​server.

[2128] Step 9:

[2129] Reanalysis and countermeasure generation

[2130] The server analyzes the input data again, extracts new keywords and phrases, and generates the next questions and solutions.

[2131] Input: User's answer data: "Daily reporting."

[2132] Output: Keywords "report work" and "monotonous" and the following question: "Which part of the report work do you find particularly stressful?"

[2133] Specific operation: The server re-analyzes, extracts new keywords, and generates the next question.

[2134] Step 10:

[2135] Submit an action plan

[2136] The server generates a final action plan and proposes it to the user.

[2137] Input: Reanalysis result: "Monotonous work is a stressor."

[2138] Output: Action plan: "Divide tasks and take short breaks"

[2139] Specific operation: The server generates an action plan and sends it to the user's device via API.

[2140] Step 11:

[2141] Data storage

[2142] The server stores the dialogue history and the final action plan in a database server.

[2143] Input: Interaction history and action plan data.

[2144] Output: History and plans stored in a database.

[2145] Specific operation: The server connects to the database and saves the analysis results and countermeasure data.

[2146] Through the above processing steps, the system can identify factors that reduce a user's motivation and provide highly accurate countermeasures that take into account the user's emotional state.

[2147] (Application example 2)

[2148] 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."

[2149] In modern industrial environments, monotonous tasks and long working hours can lead to a decline in worker motivation. This can lead to a decline in work efficiency and quality, ultimately affecting productivity. There is a need for a system that can solve this problem and maintain and improve worker motivation.

[2150] 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.

[2151] In this invention, the server includes means for accepting user input, means for analyzing the user input, means for identifying factors that decrease motivation based on the analysis results, means for generating additional questions and advice based on the identified factors, means for returning the generated questions and advice to the user, means for being installed in the industrial machine, and means for analyzing the emotions of workers and managing their motivation. This makes it possible to quickly and accurately identify factors that decrease motivation in workers and provide appropriate advice and improvements.

[2152] The "means for accepting user input" refers to a device or interface that allows a user to input information in text format and that allows the system to receive that information.

[2153] "Means for analyzing user input" refers to a device or software that analyzes input text information using natural language processing techniques and extracts keywords and phrases.

[2154] The "means for identifying factors that decrease motivation" is a device or algorithm for identifying factors that decrease a user's motivation based on analyzed keywords and emotional data.

[2155] The "means for generating additional questions and advice" is a device or program for automatically generating additional questions and advice for the user in response to the identified demotivation factors.

[2156] The "means for returning questions and advice to the user" refers to a device or interface for transmitting the generated questions and advice to the user terminal and displaying them to the user.

[2157] "Means installed on industrial machines" refers to devices or software for incorporating and using the motivation management system on factory machines.

[2158] "Means for analyzing worker emotions" refers to a device or algorithm for analyzing text or voice data to recognize the worker's emotional state.

[2159] "Means for managing motivation" refers to a device or program that provides appropriate measures based on the worker's emotional data and factors that decrease motivation, thereby maintaining and improving their motivation to work.

[2160] This invention is a system for identifying factors that decrease the motivation of factory workers and providing countermeasures. This system consists of a user terminal, an AI server, a database server, and an emotion recognition engine. Each component and its processing are described in detail below.

[2161] User terminal

[2162] The user terminal functions as an interface for the worker to interact with the system. The user enters information about their emotional state and motivation in text format and presses the send button. The system is designed so that users can enter either a single sentence or multiple sentences. Smartphones, head-mounted displays, etc. are used as user terminals.

[2163] AI Server

[2164] The AI ​​server processes input information sent from the user terminal. The AI ​​server has the following main functions:

[2165] 1. Text analysis and emotion recognition:

[2166] The AI ​​server uses natural language processing (NLP) techniques to analyze user input and extract key keywords and phrases, and an emotion recognition engine to analyze emotional states.

[2167] The software used includes Python, NLTK (Natural Language Toolkit), SentimentIntensityAnalyzer, etc.

[2168] 2. Identifying the factors that cause low motivation:

[2169] Based on the results of text analysis and the user's emotional state, factors that decrease the user's motivation are identified, such as "monotonous work" and "long working hours."

[2170] 3. Generate follow-up questions and advice:

[2171] Based on the identified factors, the AI ​​server generates additional questions and advice for the user, and specific countermeasures are proposed and sent to the user.

[2172] Emotion Recognition Engine

[2173] The emotion recognition engine is a dedicated module for extracting emotions from user input text. It has the ability to distinguish between positive, negative, and neutral emotions, and is used in the analysis process of the AI ​​server.

[2174] Database Server

[2175] The results of the analysis performed by the AI ​​server and the history of user interactions are stored on a database server. This allows for future improvements and checking the user's progress. It is also used to improve the quality of responses to new users based on past data. Examples of database management systems used include MySQL.

[2176] Specific examples

[2177] Here is an example of a specific dialogue:

[2178] 1. User terminal: The worker types in, "Recently, I've been doing monotonous work and I'm not motivated," and presses the send button.

[2179] 2. AI server: Analyzes the text and extracts keywords such as "monotonous work" and "unmotivated." An emotion recognition engine recognizes "negative" emotions.

[2180] 3. AI server: Based on the analysis results, it identifies that "monotonous work is the cause" and generates the next question: "Which part of the work is particularly burdensome?"

[2181] 4. AI server: Returns the generated questions to the user device.

[2182] 5. User terminal: The question is received and the worker enters "There is a lot of repetitive work."

[2183] 6. User terminal: Re-send the input text to the AI ​​server.

[2184] 7. AI server: Reanalyzes and infers that "diversification of work is necessary" and suggests "try combining other tasks."

[2185] 8. AI server: Sends suggestions to the user's device and displays them to the worker.

[2186] Prompt Sentence E...

Claims

1. means for accepting user input; means for analyzing said user input; A means for identifying factors that decrease motivation based on the analysis results; a means of generating additional questions and advice based on the identified factors; The system includes a means for returning the generated questions and advice to the user.

2. 2. The system according to claim 1, further comprising means for accepting additional information from the user again and performing reanalysis based on the additional information.

3. The system according to claim 1 , further comprising means for generating a specific action plan for improving the motivation of the user based on the information obtained by the reanalysis.

4. 2. The system of claim 1, further comprising means for storing the user interaction history and the generated action plan in a database.

5. The system of claim 1 further comprising means for using natural language processing for said analyzing and identifying.

6. 2. The system according to claim 1, wherein said system includes means for targeting work, lifestyle habits, and mental stress as factors that decrease motivation.

Images